From 9807a54cd74149988f5d20088bf7a7957c205bfb Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Mon, 7 Jan 2013 09:54:31 -0800 Subject: linux/openvswitch.h: Make OVSP_LOCAL 32-bit. OVS ports are now 32-bit, so OVSP_LOCAL should be too. (Internally, kernel module still keeps port numbers 16-bit, though.) Signed-off-by: Jarno Rajahalme Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index d42e174bd0c8..99e6414a40d9 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -94,7 +94,7 @@ struct ovs_vport_stats { }; /* Fixed logical ports. */ -#define OVSP_LOCAL ((__u16)0) +#define OVSP_LOCAL ((__u32)0) /* Packet transfer. */ -- cgit v1.2.3 From 4490108b4a5ada14c7be712260829faecc814ae5 Mon Sep 17 00:00:00 2001 From: Ben Pfaff Date: Fri, 15 Feb 2013 17:29:22 -0800 Subject: openvswitch: Allow OVS_USERSPACE_ATTR_USERDATA to be variable length. Until now, the optional OVS_USERSPACE_ATTR_USERDATA attribute had to be exactly 64 bits long, if it was present. However, 64 bits is not enough space to associate as much information with a flow as would be convenient for some userspace features now under development. This commit generalizes the attribute, allowing it to be any length. This generalization is backward-compatible: if userspace only uses 64-bit attributes, then it will not see any change in behavior. CC: Romain Lenglet Signed-off-by: Ben Pfaff Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index 99e6414a40d9..67d6c7b03581 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -127,7 +127,8 @@ enum ovs_packet_cmd { * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes. * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an - * %OVS_USERSPACE_ATTR_USERDATA attribute. + * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content + * specified there. * * These attributes follow the &struct ovs_header within the Generic Netlink * payload for %OVS_PACKET_* commands. @@ -137,7 +138,7 @@ enum ovs_packet_attr { OVS_PACKET_ATTR_PACKET, /* Packet data. */ OVS_PACKET_ATTR_KEY, /* Nested OVS_KEY_ATTR_* attributes. */ OVS_PACKET_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - OVS_PACKET_ATTR_USERDATA, /* u64 OVS_ACTION_ATTR_USERSPACE arg. */ + OVS_PACKET_ATTR_USERDATA, /* OVS_ACTION_ATTR_USERSPACE arg. */ __OVS_PACKET_ATTR_MAX }; @@ -389,13 +390,13 @@ enum ovs_sample_attr { * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action. * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION * message should be sent. Required. - * @OVS_USERSPACE_ATTR_USERDATA: If present, its u64 argument is copied to the - * %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA, + * @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is + * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA. */ enum ovs_userspace_attr { OVS_USERSPACE_ATTR_UNSPEC, OVS_USERSPACE_ATTR_PID, /* u32 Netlink PID to receive upcalls. */ - OVS_USERSPACE_ATTR_USERDATA, /* u64 optional user-specified cookie. */ + OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */ __OVS_USERSPACE_ATTR_MAX }; -- cgit v1.2.3 From 82dc3c63c692b1e1d59378ecee948ac88e034aad Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Mar 2013 15:57:22 +0000 Subject: net: introduce NAPI_POLL_WEIGHT Some drivers use a too big NAPI poll weight. This patch adds a NAPI_POLL_WEIGHT default value and issues an error message if a driver attempts to use a bigger weight. Signed-off-by: Eric Dumazet Cc: Eilon Greenstein 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 b3d00fa4b314..896eb4985f97 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1475,6 +1475,11 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) +/* Default NAPI poll() weight + * Device drivers are strongly advised to not use bigger value + */ +#define NAPI_POLL_WEIGHT 64 + /** * netif_napi_add - initialize a napi context * @dev: network device -- cgit v1.2.3 From a947b0a93efa9a25c012aa88848f4cf8d9b41280 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 22 Feb 2013 10:54:54 +0100 Subject: xfrm: allow to avoid copying DSCP during encapsulation By default, DSCP is copying during encapsulation. Copying the DSCP in IPsec tunneling may be a bit dangerous because packets with different DSCP may get reordered relative to each other in the network and then dropped by the remote IPsec GW if the reordering becomes too big compared to the replay window. It is possible to avoid this copy with netfilter rules, but it's very convenient to be able to configure it for each SA directly. This patch adds a toogle for this purpose. By default, it's not set to maintain backward compatibility. Field flags in struct xfrm_usersa_info is full, hence I add a new attribute. Signed-off-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 + include/uapi/linux/xfrm.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 24c8886fd969..ae16531d0d35 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -162,6 +162,7 @@ struct xfrm_state { xfrm_address_t saddr; int header_len; int trailer_len; + u32 extra_flags; } props; struct xfrm_lifetime_cfg lft; diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 28e493b5b94c..a8cd6a4a2970 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -297,6 +297,7 @@ enum xfrm_attr_type_t { XFRMA_MARK, /* struct xfrm_mark */ XFRMA_TFCPAD, /* __u32 */ XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_esn */ + XFRMA_SA_EXTRA_FLAGS, /* __u32 */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) @@ -367,6 +368,8 @@ struct xfrm_usersa_info { #define XFRM_STATE_ESN 128 }; +#define XFRM_SA_XFLAG_DONT_ENCAP_DSCP 1 + struct xfrm_usersa_id { xfrm_address_t daddr; __be32 spi; -- cgit v1.2.3 From f8bacc210408f7a2a182f184a9fa1475b8a67440 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 14 Feb 2013 23:27:01 +0100 Subject: cfg80211: clean up mesh plink station change API Make the ability to leave the plink_state unchanged not use a magic -1 variable that isn't in the enum, but an explicit change flag; reject invalid plink states or actions and move the needed constants for plink actions to the right header file. Also reject plink_state changes for non-mesh interfaces. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 15 ++------------- include/uapi/linux/nl80211.h | 20 +++++++++++++++++++- 2 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d581c6de5d64..9b54574c3df9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -610,23 +610,11 @@ struct cfg80211_ap_settings { bool radar_required; }; -/** - * enum plink_action - actions to perform in mesh peers - * - * @PLINK_ACTION_INVALID: action 0 is reserved - * @PLINK_ACTION_OPEN: start mesh peer link establishment - * @PLINK_ACTION_BLOCK: block traffic from this mesh peer - */ -enum plink_actions { - PLINK_ACTION_INVALID, - PLINK_ACTION_OPEN, - PLINK_ACTION_BLOCK, -}; - /** * enum station_parameters_apply_mask - station parameter values to apply * @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp) * @STATION_PARAM_APPLY_CAPABILITY: apply new capability + * @STATION_PARAM_APPLY_PLINK_STATE: apply new plink state * * Not all station parameters have in-band "no change" signalling, * for those that don't these flags will are used. @@ -634,6 +622,7 @@ enum plink_actions { enum station_parameters_apply_mask { STATION_PARAM_APPLY_UAPSD = BIT(0), STATION_PARAM_APPLY_CAPABILITY = BIT(1), + STATION_PARAM_APPLY_PLINK_STATE = BIT(2), }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c46bb016f4e4..7dcc69f73d2c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -884,7 +884,8 @@ enum nl80211_commands { * consisting of a nested array. * * @NL80211_ATTR_MESH_ID: mesh id (1-32 bytes). - * @NL80211_ATTR_STA_PLINK_ACTION: action to perform on the mesh peer link. + * @NL80211_ATTR_STA_PLINK_ACTION: action to perform on the mesh peer link + * (see &enum nl80211_plink_action). * @NL80211_ATTR_MPATH_NEXT_HOP: MAC address of the next hop for a mesh path. * @NL80211_ATTR_MPATH_INFO: information about a mesh_path, part of mesh path * info given for %NL80211_CMD_GET_MPATH, nested attribute described at @@ -3307,6 +3308,23 @@ enum nl80211_plink_state { MAX_NL80211_PLINK_STATES = NUM_NL80211_PLINK_STATES - 1 }; +/** + * enum nl80211_plink_action - actions to perform in mesh peers + * + * @NL80211_PLINK_ACTION_NO_ACTION: perform no action + * @NL80211_PLINK_ACTION_OPEN: start mesh peer link establishment + * @NL80211_PLINK_ACTION_BLOCK: block traffic from this mesh peer + * @NUM_NL80211_PLINK_ACTIONS: number of possible actions + */ +enum plink_actions { + NL80211_PLINK_ACTION_NO_ACTION, + NL80211_PLINK_ACTION_OPEN, + NL80211_PLINK_ACTION_BLOCK, + + NUM_NL80211_PLINK_ACTIONS, +}; + + #define NL80211_KCK_LEN 16 #define NL80211_KEK_LEN 16 #define NL80211_REPLAY_CTR_LEN 8 -- cgit v1.2.3 From 2c1aabf33d1832befc5291a14c870cd09dc2182d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 14 Feb 2013 23:33:40 +0100 Subject: cfg80211: constify station parameter pointers All the pointers point right into the skb data and not to anything that would be useful to change, so make them const. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9b54574c3df9..7ca321d2b599 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -658,7 +658,7 @@ enum station_parameters_apply_mask { * @ext_capab_len: number of extended capabilities */ struct station_parameters { - u8 *supported_rates; + const u8 *supported_rates; struct net_device *vlan; u32 sta_flags_mask, sta_flags_set; u32 sta_modify_mask; @@ -667,13 +667,13 @@ struct station_parameters { u8 supported_rates_len; u8 plink_action; u8 plink_state; - struct ieee80211_ht_cap *ht_capa; - struct ieee80211_vht_cap *vht_capa; + const struct ieee80211_ht_cap *ht_capa; + const struct ieee80211_vht_cap *vht_capa; u8 uapsd_queues; u8 max_sp; enum nl80211_mesh_power_mode local_pm; u16 capability; - u8 *ext_capab; + const u8 *ext_capab; u8 ext_capab_len; }; -- cgit v1.2.3 From 77ee7c891a04c3d254711ddf1bde5d7381339fb3 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 15 Feb 2013 00:48:33 +0100 Subject: cfg80211: comprehensively check station changes The station change API isn't being checked properly before drivers are called, and as a result it is difficult to see what should be allowed and what not. In order to comprehensively check the API parameters parse everything first, and then have the driver call a function (cfg80211_check_station_change()) with the additionally information about the kind of station that is being changed; this allows the function to make better decisions than the old code could. While at it, also add a few checks, particularly in mesh and clarify the TDLS station lifetime in documentation. To be able to reduce a few checks, ignore any flag set bits when the mask isn't set, they shouldn't be applied then. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 48 +++++++++++++++++++++++++++++++++++++++++--- include/uapi/linux/nl80211.h | 16 ++++++++++++++- 2 files changed, 60 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7ca321d2b599..ed2b08da3b93 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -677,6 +677,49 @@ struct station_parameters { u8 ext_capab_len; }; +/** + * enum cfg80211_station_type - the type of station being modified + * @CFG80211_STA_AP_CLIENT: client of an AP interface + * @CFG80211_STA_AP_MLME_CLIENT: client of an AP interface that has + * the AP MLME in the device + * @CFG80211_STA_AP_STA: AP station on managed interface + * @CFG80211_STA_IBSS: IBSS station + * @CFG80211_STA_TDLS_PEER_SETUP: TDLS peer on managed interface (dummy entry + * while TDLS setup is in progress, it moves out of this state when + * being marked authorized; use this only if TDLS with external setup is + * supported/used) + * @CFG80211_STA_TDLS_PEER_ACTIVE: TDLS peer on managed interface (active + * entry that is operating, has been marked authorized by userspace) + * @CFG80211_STA_MESH_PEER_NONSEC: peer on mesh interface (non-secured) + * @CFG80211_STA_MESH_PEER_SECURE: peer on mesh interface (secured) + */ +enum cfg80211_station_type { + CFG80211_STA_AP_CLIENT, + CFG80211_STA_AP_MLME_CLIENT, + CFG80211_STA_AP_STA, + CFG80211_STA_IBSS, + CFG80211_STA_TDLS_PEER_SETUP, + CFG80211_STA_TDLS_PEER_ACTIVE, + CFG80211_STA_MESH_PEER_NONSEC, + CFG80211_STA_MESH_PEER_SECURE, +}; + +/** + * cfg80211_check_station_change - validate parameter changes + * @wiphy: the wiphy this operates on + * @params: the new parameters for a station + * @statype: the type of station being modified + * + * Utility function for the @change_station driver method. Call this function + * with the appropriate station type looking up the station (and checking that + * it exists). It will verify whether the station change is acceptable, and if + * not will return an error code. Note that it may modify the parameters for + * backward compatibility reasons, so don't use them before calling this. + */ +int cfg80211_check_station_change(struct wiphy *wiphy, + struct station_parameters *params, + enum cfg80211_station_type statype); + /** * enum station_info_flags - station information flags * @@ -1770,9 +1813,8 @@ struct cfg80211_gtk_rekey_data { * @change_station: Modify a given station. Note that flags changes are not much * validated in cfg80211, in particular the auth/assoc/authorized flags * might come to the driver in invalid combinations -- make sure to check - * them, also against the existing state! Also, supported_rates changes are - * not checked in station mode -- drivers need to reject (or ignore) them - * for anything but TDLS peers. + * them, also against the existing state! Drivers must call + * cfg80211_check_station_change() to validate the information. * @get_station: get station information for the station identified by @mac * @dump_station: dump station callback -- resume dump at index @idx * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 7dcc69f73d2c..523ed3d65b41 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -36,7 +36,21 @@ * The station is still assumed to belong to the AP interface it was added * to. * - * TODO: need more info? + * Station handling varies per interface type and depending on the driver's + * capabilities. + * + * For drivers supporting TDLS with external setup (WIPHY_FLAG_SUPPORTS_TDLS + * and WIPHY_FLAG_TDLS_EXTERNAL_SETUP), the station lifetime is as follows: + * - a setup station entry is added, not yet authorized, without any rate + * or capability information, this just exists to avoid race conditions + * - when the TDLS setup is done, a single NL80211_CMD_SET_STATION is valid + * to add rate and capability information to the station and at the same + * time mark it authorized. + * - %NL80211_TDLS_ENABLE_LINK is then used + * - after this, the only valid operation is to remove it by tearing down + * the TDLS link (%NL80211_TDLS_DISABLE_LINK) + * + * TODO: need more info for other interface types */ /** -- cgit v1.2.3 From 3713b4e364effef4b170c97d54528b1cdb16aa6b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 14 Feb 2013 16:19:38 +0100 Subject: nl80211: allow splitting wiphy information in dumps The per-wiphy information is getting large, to the point where with more than the typical number of channels it's too large and overflows, and userspace can't get any of the information at all. To address this (in a way that doesn't require making all messages bigger) allow userspace to specify that it can deal with wiphy information split across multiple parts of the dump, and if it can split up the data. This also splits up each channel separately so an arbitrary number of channels can be supported. Additionally, since GET_WIPHY has the same problem, add support for filtering the wiphy dump and get information for a single wiphy only, this allows userspace apps to use dump in this case to retrieve all data from a single device. As userspace needs to know if all this this is supported, add a global nl80211 feature set and include a bit for this behaviour in it. Cc: Dennis H Jensen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 523ed3d65b41..9844c10a2999 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -625,6 +625,10 @@ * %NL80211_ATTR_RADAR_EVENT is used to inform about the type of the * event. * + * @NL80211_CMD_GET_PROTOCOL_FEATURES: Get global nl80211 protocol features, + * i.e. features for the nl80211 protocol rather than device features. + * Returns the features in the %NL80211_ATTR_PROTOCOL_FEATURES bitmap. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -779,6 +783,8 @@ enum nl80211_commands { NL80211_CMD_RADAR_DETECT, + NL80211_CMD_GET_PROTOCOL_FEATURES, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1383,6 +1389,13 @@ enum nl80211_commands { * advertised to the driver, e.g., to enable TDLS off channel operations * and PU-APSD. * + * @NL80211_ATTR_PROTOCOL_FEATURES: global nl80211 feature flags, see + * &enum nl80211_protocol_features, the attribute is a u32. + * + * @NL80211_ATTR_SPLIT_WIPHY_DUMP: flag attribute, userspace supports + * receiving the data for a single wiphy split across multiple + * messages, given with wiphy dump message + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1669,6 +1682,9 @@ enum nl80211_attrs { NL80211_ATTR_STA_CAPABILITY, NL80211_ATTR_STA_EXT_CAPABILITY, + NL80211_ATTR_PROTOCOL_FEATURES, + NL80211_ATTR_SPLIT_WIPHY_DUMP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3619,4 +3635,16 @@ enum nl80211_dfs_state { NL80211_DFS_AVAILABLE, }; +/** + * enum enum nl80211_protocol_features - nl80211 protocol features + * @NL80211_PROTOCOL_FEATURE_SPLIT_WIPHY_DUMP: nl80211 supports splitting + * wiphy dumps (if requested by the application with the attribute + * %NL80211_ATTR_SPLIT_WIPHY_DUMP. Also supported is filtering the + * wiphy dump by %NL80211_ATTR_WIPHY, %NL80211_ATTR_IFINDEX or + * %NL80211_ATTR_WDEV. + */ +enum nl80211_protocol_features { + NL80211_PROTOCOL_FEATURE_SPLIT_WIPHY_DUMP = 1 << 0, +}; + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 9a886586c82aa02cb49f8c85e961595716884545 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 15 Feb 2013 19:25:00 +0100 Subject: wireless: move sequence number arithmetic to ieee80211.h Move the sequence number arithmetic code from mac80211 to ieee80211.h so others can use it. Also rename the functions from _seq to _sn, they operate on the sequence number, not the sequence_control field. Also move macros to convert the sequence control to/from the sequence number value from various drivers. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7e24fe0cfbcd..a0c550fb65a6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -113,6 +113,34 @@ #define IEEE80211_CTL_EXT_SSW_FBACK 0x9000 #define IEEE80211_CTL_EXT_SSW_ACK 0xa000 + +#define IEEE80211_SN_MASK ((IEEE80211_SCTL_SEQ) >> 4) +#define IEEE80211_MAX_SN IEEE80211_SN_MASK +#define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) + +static inline int ieee80211_sn_less(u16 sn1, u16 sn2) +{ + return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); +} + +static inline u16 ieee80211_sn_add(u16 sn1, u16 sn2) +{ + return (sn1 + sn2) & IEEE80211_SN_MASK; +} + +static inline u16 ieee80211_sn_inc(u16 sn) +{ + return ieee80211_sn_add(sn, 1); +} + +static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) +{ + return (sn1 - sn2) & IEEE80211_SN_MASK; +} + +#define IEEE80211_SEQ_TO_SN(seq) (((seq) & IEEE80211_SCTL_SEQ) >> 4) +#define IEEE80211_SN_TO_SEQ(ssn) (((ssn) << 4) & IEEE80211_SCTL_SEQ) + /* miscellaneous IEEE 802.11 constants */ #define IEEE80211_MAX_FRAG_THRESHOLD 2352 #define IEEE80211_MAX_RTS_THRESHOLD 2353 -- cgit v1.2.3 From b8a31c9a5afff257cc5dd637cda5fef03e12d67b Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 22 Feb 2013 17:28:49 +0100 Subject: ieee80211: mark 802.11 related structs as being 2-byte aligned Regardless of what header features they use, or if they align the IP header or not, 802.11 packets from all drivers guarantee a 2-byte alignment (and there's a debug WARN_ON in case they don't). Annotate packet structs with __aligned(2) to allow the compiler to use 16-bit load/store operations on platforms with extremely inefficient unaligned access (e.g. MIPS). This reduces code size and improves performance on affected platforms and causes no binary code change on others. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a0c550fb65a6..6e352c31fee0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -213,7 +213,7 @@ struct ieee80211_hdr { u8 addr3[6]; __le16 seq_ctrl; u8 addr4[6]; -} __packed; +} __packed __aligned(2); struct ieee80211_hdr_3addr { __le16 frame_control; @@ -222,7 +222,7 @@ struct ieee80211_hdr_3addr { u8 addr2[6]; u8 addr3[6]; __le16 seq_ctrl; -} __packed; +} __packed __aligned(2); struct ieee80211_qos_hdr { __le16 frame_control; @@ -232,7 +232,7 @@ struct ieee80211_qos_hdr { u8 addr3[6]; __le16 seq_ctrl; __le16 qos_ctrl; -} __packed; +} __packed __aligned(2); /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set @@ -609,7 +609,7 @@ struct ieee80211s_hdr { __le32 seqnum; u8 eaddr1[6]; u8 eaddr2[6]; -} __packed; +} __packed __aligned(2); /* Mesh flags */ #define MESH_FLAGS_AE_A4 0x1 @@ -903,7 +903,7 @@ struct ieee80211_mgmt { } u; } __packed action; } u; -} __packed; +} __packed __aligned(2); /* Supported Rates value encodings in 802.11n-2009 7.3.2.2 */ #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 @@ -934,20 +934,20 @@ struct ieee80211_rts { __le16 duration; u8 ra[6]; u8 ta[6]; -} __packed; +} __packed __aligned(2); struct ieee80211_cts { __le16 frame_control; __le16 duration; u8 ra[6]; -} __packed; +} __packed __aligned(2); struct ieee80211_pspoll { __le16 frame_control; __le16 aid; u8 bssid[6]; u8 ta[6]; -} __packed; +} __packed __aligned(2); /* TDLS */ -- cgit v1.2.3 From c8bb93f5f5d478a01db66127844d1d2dd30abec7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Feb 2013 17:26:44 +0100 Subject: wireless: remove unused VHT MCS defines There's an enum with the same values (but slightly different names except for NOT_SUPPORTED) that is actually used, so remove the defines. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 6e352c31fee0..35c1f96d9365 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1318,11 +1318,6 @@ struct ieee80211_vht_operation { } __packed; -#define IEEE80211_VHT_MCS_ZERO_TO_SEVEN_SUPPORT 0 -#define IEEE80211_VHT_MCS_ZERO_TO_EIGHT_SUPPORT 1 -#define IEEE80211_VHT_MCS_ZERO_TO_NINE_SUPPORT 2 -#define IEEE80211_VHT_MCS_NOT_SUPPORTED 3 - /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 -- cgit v1.2.3 From ee2aca343c9aa64d277a75a5df043299dc84cfd9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Feb 2013 17:36:01 +0100 Subject: cfg80211: add ability to override VHT capabilities For testing it's sometimes useful to be able to override certain VHT capability advertisement, add the ability to do that in cfg80211. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 12 ++++++++++++ include/uapi/linux/nl80211.h | 3 +++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ed2b08da3b93..73a523901c73 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1430,9 +1430,11 @@ struct cfg80211_auth_request { * enum cfg80211_assoc_req_flags - Over-ride default behaviour in association. * * @ASSOC_REQ_DISABLE_HT: Disable HT (802.11n) + * @ASSOC_REQ_DISABLE_VHT: Disable VHT */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), + ASSOC_REQ_DISABLE_VHT = BIT(1), }; /** @@ -1454,6 +1456,8 @@ enum cfg80211_assoc_req_flags { * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. + * @vht_capa: VHT capability override + * @vht_capa_mask: VHT capability mask indicating which fields to use */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -1464,6 +1468,7 @@ struct cfg80211_assoc_request { u32 flags; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; + struct ieee80211_vht_cap vht_capa, vht_capa_mask; }; /** @@ -1574,6 +1579,8 @@ struct cfg80211_ibss_params { * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. + * @vht_capa: VHT Capability overrides + * @vht_capa_mask: The bits of vht_capa which are to be used. */ struct cfg80211_connect_params { struct ieee80211_channel *channel; @@ -1592,6 +1599,8 @@ struct cfg80211_connect_params { int bg_scan_period; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; + struct ieee80211_vht_cap vht_capa; + struct ieee80211_vht_cap vht_capa_mask; }; /** @@ -2516,6 +2525,8 @@ struct wiphy_wowlan_support { * @ap_sme_capa: AP SME capabilities, flags from &enum nl80211_ap_sme_features. * @ht_capa_mod_mask: Specify what ht_cap values can be over-ridden. * If null, then none can be over-ridden. + * @vht_capa_mod_mask: Specify what VHT capabilities can be over-ridden. + * If null, then none can be over-ridden. * * @max_acl_mac_addrs: Maximum number of MAC addresses that the device * supports for ACL. @@ -2624,6 +2635,7 @@ struct wiphy { struct dentry *debugfsdir; const struct ieee80211_ht_cap *ht_capa_mod_mask; + const struct ieee80211_vht_cap *vht_capa_mod_mask; #ifdef CONFIG_NET_NS /* the network namespace this phy lives in currently */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 9844c10a2999..2c3e88360037 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1685,6 +1685,9 @@ enum nl80211_attrs { NL80211_ATTR_PROTOCOL_FEATURES, NL80211_ATTR_SPLIT_WIPHY_DUMP, + NL80211_ATTR_DISABLE_VHT, + NL80211_ATTR_VHT_CAPABILITY_MASK, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From d339d5ca8eee34f3c70386cf2545edc53e546a13 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Tue, 12 Feb 2013 09:34:13 +0200 Subject: mac80211: Allow drivers to differentiate between ROC types Some devices can handle remain on channel requests differently based on the request type/priority. Add support to differentiate between different ROC types, i.e., indicate that the ROC is required for sending managment frames. Signed-off-by: Ilan Peer Reviewed-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f7eba1300d82..9b0d342c0675 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2134,6 +2134,24 @@ enum ieee80211_rate_control_changed { IEEE80211_RC_NSS_CHANGED = BIT(3), }; +/** + * enum ieee80211_roc_type - remain on channel type + * + * With the support for multi channel contexts and multi channel operations, + * remain on channel operations might be limited/deferred/aborted by other + * flows/operations which have higher priority (and vise versa). + * Specifying the ROC type can be used by devices to prioritize the ROC + * operations compared to other operations/flows. + * + * @IEEE80211_ROC_TYPE_NORMAL: There are no special requirements for this ROC. + * @IEEE80211_ROC_TYPE_MGMT_TX: The remain on channel request is required + * for sending managment frames offchannel. + */ +enum ieee80211_roc_type { + IEEE80211_ROC_TYPE_NORMAL = 0, + IEEE80211_ROC_TYPE_MGMT_TX, +}; + /** * struct ieee80211_ops - callbacks from mac80211 to the driver * @@ -2687,7 +2705,8 @@ struct ieee80211_ops { int (*remain_on_channel)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel *chan, - int duration); + int duration, + enum ieee80211_roc_type type); int (*cancel_remain_on_channel)(struct ieee80211_hw *hw); int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx); void (*get_ringparam)(struct ieee80211_hw *hw, -- cgit v1.2.3 From 355199e02b831fd4f652c34d6c7673d973da1369 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Wed, 27 Feb 2013 17:14:27 +0200 Subject: cfg80211: Extend support for IEEE 802.11r Fast BSS Transition Add NL80211_CMD_UPDATE_FT_IES to support update of FT IEs to the WLAN driver and NL80211_CMD_FT_EVENT to send FT events from the WLAN driver. This will carry the target AP's MAC address along with the relevant Information Elements. This event is used to report received FT IEs (MDIE, FTIE, RSN IE, TIE, RICIE). These changes allow FT to be supported with drivers that use an internal SME instead of user space option (like FT implementation in wpa_supplicant with mac80211-based drivers). Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 41 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/nl80211.h | 19 +++++++++++++++++++ 2 files changed, 60 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 73a523901c73..dfef0d5b5d3d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1762,6 +1762,21 @@ struct cfg80211_gtk_rekey_data { u8 replay_ctr[NL80211_REPLAY_CTR_LEN]; }; +/** + * struct cfg80211_update_ft_ies_params - FT IE Information + * + * This structure provides information needed to update the fast transition IE + * + * @md: The Mobility Domain ID, 2 Octet value + * @ie: Fast Transition IEs + * @ie_len: Length of ft_ie in octets + */ +struct cfg80211_update_ft_ies_params { + u16 md; + const u8 *ie; + size_t ie_len; +}; + /** * struct cfg80211_ops - backend description for wireless configuration * @@ -2208,6 +2223,8 @@ struct cfg80211_ops { int (*start_radar_detection)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef); + int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_update_ft_ies_params *ftie); }; /* @@ -4044,6 +4061,30 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate); */ void cfg80211_unregister_wdev(struct wireless_dev *wdev); +/** + * struct cfg80211_ft_event - FT Information Elements + * @ies: FT IEs + * @ies_len: length of the FT IE in bytes + * @target_ap: target AP's MAC address + * @ric_ies: RIC IE + * @ric_ies_len: length of the RIC IE in bytes + */ +struct cfg80211_ft_event_params { + const u8 *ies; + size_t ies_len; + const u8 *target_ap; + const u8 *ric_ies; + size_t ric_ies_len; +}; + +/** + * cfg80211_ft_event - notify userspace about FT IE and RIC IE + * @netdev: network device + * @ft_event: IE information + */ +void cfg80211_ft_event(struct net_device *netdev, + struct cfg80211_ft_event_params *ft_event); + /** * cfg80211_get_p2p_attr - find and copy a P2P attribute from IE buffer * @ies: the input IE buffer diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 2c3e88360037..2d0cff57ff89 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -629,6 +629,14 @@ * i.e. features for the nl80211 protocol rather than device features. * Returns the features in the %NL80211_ATTR_PROTOCOL_FEATURES bitmap. * + * @NL80211_CMD_UPDATE_FT_IES: Pass down the most up-to-date Fast Transition + * Information Element to the WLAN driver + * + * @NL80211_CMD_FT_EVENT: Send a Fast transition event from the WLAN driver + * to the supplicant. This will carry the target AP's MAC address along + * with the relevant Information Elements. This event is used to report + * received FT IEs (MDIE, FTIE, RSN IE, TIE, RICIE). + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -785,6 +793,9 @@ enum nl80211_commands { NL80211_CMD_GET_PROTOCOL_FEATURES, + NL80211_CMD_UPDATE_FT_IES, + NL80211_CMD_FT_EVENT, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1396,6 +1407,11 @@ enum nl80211_commands { * receiving the data for a single wiphy split across multiple * messages, given with wiphy dump message * + * @NL80211_ATTR_MDID: Mobility Domain Identifier + * + * @NL80211_ATTR_IE_RIC: Resource Information Container Information + * Element + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1688,6 +1704,9 @@ enum nl80211_attrs { NL80211_ATTR_DISABLE_VHT, NL80211_ATTR_VHT_CAPABILITY_MASK, + NL80211_ATTR_MDID, + NL80211_ATTR_IE_RIC, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From a87121051ce80831a302c67286119013104f7a5a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 23 Feb 2013 00:22:44 +0100 Subject: mac80211: remove IEEE80211_KEY_FLAG_WMM_STA There's no driver using this flag, so it seems that all drivers support HW crypto with WMM or don't support it at all. Remove the flag and code setting it. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9b0d342c0675..421c3ac8c521 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1101,8 +1101,6 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) * These flags are used for communication about keys between the driver * and mac80211, with the @flags parameter of &struct ieee80211_key_conf. * - * @IEEE80211_KEY_FLAG_WMM_STA: Set by mac80211, this flag indicates - * that the STA this key will be used with could be using QoS. * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the * driver to indicate that it requires IV generation for this * particular key. @@ -1127,7 +1125,6 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) * %IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW. */ enum ieee80211_key_flags { - IEEE80211_KEY_FLAG_WMM_STA = 1<<0, IEEE80211_KEY_FLAG_GENERATE_IV = 1<<1, IEEE80211_KEY_FLAG_GENERATE_MMIC= 1<<2, IEEE80211_KEY_FLAG_PAIRWISE = 1<<3, -- cgit v1.2.3 From 55d942f4246c79a8f3f17f92c224e641c5c26125 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 1 Mar 2013 13:07:48 +0100 Subject: mac80211: restrict peer's VHT capabilities to own Implement restricting peer VHT capabilities to the device's own capabilities. This is useful when a single driver supports more than one device and the devices have different capabilities (often they will differ in the number of spatial streams), but in particular is also necessary for VHT capability overrides to work correctly -- otherwise it'd be possible to e.g. advertise, due to overrides, that TX-STBC is not supported, but then still use it to TX to the AP because it supports RX-STBC. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 ++- include/net/mac80211.h | 5 ++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 35c1f96d9365..4cf0c9e4dd99 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1333,10 +1333,11 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 #define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 #define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 +#define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 #define IEEE80211_VHT_CAP_BEAMFORMER_ANTENNAS_MAX 0x00006000 -#define IEEE80211_VHT_CAP_SOUNDING_DIMENTION_MAX 0x00030000 +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MAX 0x00030000 #define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 #define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 #define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 421c3ac8c521..cdd7cea1fd4c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1228,9 +1228,8 @@ enum ieee80211_sta_rx_bandwidth { * @addr: MAC address * @aid: AID we assigned to the station if we're an AP * @supp_rates: Bitmap of supported rates (per band) - * @ht_cap: HT capabilities of this STA; restricted to our own TX capabilities - * @vht_cap: VHT capabilities of this STA; Not restricting any capabilities - * of remote STA. Taking as is. + * @ht_cap: HT capabilities of this STA; restricted to our own capabilities + * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities * @wme: indicates whether the STA supports WME. Only valid during AP-mode. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *), size is determined in hw information. -- cgit v1.2.3 From bb2798d45fc0575f5d08c0bb7baf4d5d5e8cc0c3 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 4 Mar 2013 13:06:10 -0800 Subject: nl80211: explicit userspace MPM Secure mesh had the implicit requirement that the Mesh Peering Management entity be in userspace. However userspace might want to implement an open MPM as well, so specify a mesh setup parameter to indicate this. Signed-off-by: Thomas Pedersen Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 25 ++++++++++++++++++------- 2 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index dfef0d5b5d3d..69b2b2631b9a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1151,6 +1151,7 @@ struct mesh_config { * @ie_len: length of vendor information elements * @is_authenticated: this mesh requires authentication * @is_secure: this mesh uses security + * @user_mpm: userspace handles all MPM functions * @dtim_period: DTIM period to use * @beacon_interval: beacon interval to use * @mcast_rate: multicat rate for Mesh Node [6Mbps is the default for 802.11a] @@ -1168,6 +1169,7 @@ struct mesh_setup { u8 ie_len; bool is_authenticated; bool is_secure; + bool user_mpm; u8 dtim_period; u16 beacon_interval; int mcast_rate[IEEE80211_NUM_BANDS]; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 2d0cff57ff89..8134c6a96f57 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -513,9 +513,11 @@ * @NL80211_CMD_NEW_PEER_CANDIDATE: Notification on the reception of a * beacon or probe response from a compatible mesh peer. This is only * sent while no station information (sta_info) exists for the new peer - * candidate and when @NL80211_MESH_SETUP_USERSPACE_AUTH is set. On - * reception of this notification, userspace may decide to create a new - * station (@NL80211_CMD_NEW_STATION). To stop this notification from + * candidate and when @NL80211_MESH_SETUP_USERSPACE_AUTH, + * @NL80211_MESH_SETUP_USERSPACE_AMPE, or + * @NL80211_MESH_SETUP_USERSPACE_MPM is set. On reception of this + * notification, userspace may decide to create a new station + * (@NL80211_CMD_NEW_STATION). To stop this notification from * reoccurring, the userspace authentication daemon may want to create the * new station with the AUTHENTICATED flag unset and maybe change it later * depending on the authentication result. @@ -1199,10 +1201,10 @@ enum nl80211_commands { * @NL80211_ATTR_SUPPORT_MESH_AUTH: Currently, this means the underlying driver * allows auth frames in a mesh to be passed to userspace for processing via * the @NL80211_MESH_SETUP_USERSPACE_AUTH flag. - * @NL80211_ATTR_STA_PLINK_STATE: The state of a mesh peer link as - * defined in &enum nl80211_plink_state. Used when userspace is - * driving the peer link management state machine. - * @NL80211_MESH_SETUP_USERSPACE_AMPE must be enabled. + * @NL80211_ATTR_STA_PLINK_STATE: The state of a mesh peer link as defined in + * &enum nl80211_plink_state. Used when userspace is driving the peer link + * management state machine. @NL80211_MESH_SETUP_USERSPACE_AMPE or + * @NL80211_MESH_SETUP_USERSPACE_MPM must be enabled. * * @NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED: indicates, as part of the wiphy * capabilities, the supported WoWLAN triggers @@ -2612,6 +2614,9 @@ enum nl80211_meshconf_params { * vendor specific synchronization method or disable it to use the default * neighbor offset synchronization * + * @NL80211_MESH_SETUP_USERSPACE_MPM: Enable this option if userspace will + * implement an MPM which handles peer allocation and state. + * * @NL80211_MESH_SETUP_ATTR_MAX: highest possible mesh setup attribute number * * @__NL80211_MESH_SETUP_ATTR_AFTER_LAST: Internal use @@ -2624,6 +2629,7 @@ enum nl80211_mesh_setup_params { NL80211_MESH_SETUP_USERSPACE_AUTH, NL80211_MESH_SETUP_USERSPACE_AMPE, NL80211_MESH_SETUP_ENABLE_VENDOR_SYNC, + NL80211_MESH_SETUP_USERSPACE_MPM, /* keep last */ __NL80211_MESH_SETUP_ATTR_AFTER_LAST, @@ -3526,6 +3532,10 @@ enum nl80211_ap_sme_features { * stations the authenticated/associated bits have to be set in the mask. * @NL80211_FEATURE_ADVERTISE_CHAN_LIMITS: cfg80211 advertises channel limits * (HT40, VHT 80/160 MHz) if this flag is set + * @NL80211_FEATURE_USERSPACE_MPM: This driver supports a userspace Mesh + * Peering Management entity which may be implemented by registering for + * beacons or NL80211_CMD_NEW_PEER_CANDIDATE events. The mesh beacon is + * still generated by the driver. */ enum nl80211_feature_flags { NL80211_FEATURE_SK_TX_STATUS = 1 << 0, @@ -3544,6 +3554,7 @@ enum nl80211_feature_flags { /* bit 13 is reserved */ NL80211_FEATURE_ADVERTISE_CHAN_LIMITS = 1 << 14, NL80211_FEATURE_FULL_AP_CLIENT_STATE = 1 << 15, + NL80211_FEATURE_USERSPACE_MPM = 1 << 16, }; /** -- cgit v1.2.3 From eef941e6d6be8bce72b5c2963b69f948be4df7a7 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 4 Mar 2013 13:06:11 -0800 Subject: cfg80211: rename mesh station types The mesh station types used to refer to whether the station was secure or nonsecure. Really the salient information is whether it is managed by the kernel or userspace Signed-off-by: Thomas Pedersen Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 69b2b2631b9a..bdba9b619064 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -690,8 +690,8 @@ struct station_parameters { * supported/used) * @CFG80211_STA_TDLS_PEER_ACTIVE: TDLS peer on managed interface (active * entry that is operating, has been marked authorized by userspace) - * @CFG80211_STA_MESH_PEER_NONSEC: peer on mesh interface (non-secured) - * @CFG80211_STA_MESH_PEER_SECURE: peer on mesh interface (secured) + * @CFG80211_STA_MESH_PEER_KERNEL: peer on mesh interface (kernel managed) + * @CFG80211_STA_MESH_PEER_USER: peer on mesh interface (user managed) */ enum cfg80211_station_type { CFG80211_STA_AP_CLIENT, @@ -700,8 +700,8 @@ enum cfg80211_station_type { CFG80211_STA_IBSS, CFG80211_STA_TDLS_PEER_SETUP, CFG80211_STA_TDLS_PEER_ACTIVE, - CFG80211_STA_MESH_PEER_NONSEC, - CFG80211_STA_MESH_PEER_SECURE, + CFG80211_STA_MESH_PEER_KERNEL, + CFG80211_STA_MESH_PEER_USER, }; /** -- cgit v1.2.3 From d37bb18ae3a3fa7ef239aad533742a8b07eae15f Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 4 Mar 2013 13:06:13 -0800 Subject: nl80211: user_mpm overrides auto_open_plinks If the user requested a userspace MPM, automatically disable auto_open_plinks to fully disable the kernel MPM. Signed-off-by: Thomas Pedersen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8134c6a96f57..79da8710448e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2467,8 +2467,10 @@ enum nl80211_mesh_power_mode { * @NL80211_MESHCONF_TTL: specifies the value of TTL field set at a source mesh * point. * - * @NL80211_MESHCONF_AUTO_OPEN_PLINKS: whether we should automatically - * open peer links when we detect compatible mesh peers. + * @NL80211_MESHCONF_AUTO_OPEN_PLINKS: whether we should automatically open + * peer links when we detect compatible mesh peers. Disabled if + * @NL80211_MESH_SETUP_USERSPACE_MPM or @NL80211_MESH_SETUP_USERSPACE_AMPE are + * set. * * @NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES: the number of action frames * containing a PREQ that an MP can send to a particular destination (path -- cgit v1.2.3 From acbba0d0f88e2577b9d92b61b136d13f65831a52 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 6 Mar 2013 01:31:12 +0000 Subject: team: introduce two default team_modeop functions and use them in modes No need to duplicate code for this. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index cfd21e3d5506..3283def74483 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -112,6 +112,10 @@ struct team_mode_ops { void (*port_disabled)(struct team *team, struct team_port *port); }; +extern int team_modeop_port_enter(struct team *team, struct team_port *port); +extern void team_modeop_port_change_dev_addr(struct team *team, + struct team_port *port); + enum team_option_type { TEAM_OPTION_TYPE_U32, TEAM_OPTION_TYPE_STRING, @@ -236,7 +240,6 @@ static inline struct team_port *team_get_port_by_index_rcu(struct team *team, return NULL; } -extern int team_port_set_team_dev_addr(struct team_port *port); extern int team_options_register(struct team *team, const struct team_option *option, size_t option_count); -- cgit v1.2.3 From 753f993911b32e479b4fab5d228dc07c11d1e7e7 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 6 Mar 2013 01:31:13 +0000 Subject: team: introduce random mode As suggested by Eric Dumazet, allow user to select mode which chooses TX port randomly. Functionality should be more of less similar to round-robin mode with even lower overhead. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 3283def74483..4474557904f6 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -240,6 +240,26 @@ static inline struct team_port *team_get_port_by_index_rcu(struct team *team, return NULL; } +static inline struct team_port * +team_get_first_port_txable_rcu(struct team *team, struct team_port *port) +{ + struct team_port *cur; + + if (likely(team_port_txable(port))) + return port; + cur = port; + list_for_each_entry_continue_rcu(cur, &team->port_list, list) + if (team_port_txable(port)) + return cur; + list_for_each_entry_rcu(cur, &team->port_list, list) { + if (cur == port) + break; + if (team_port_txable(port)) + return cur; + } + return NULL; +} + extern int team_options_register(struct team *team, const struct team_option *option, size_t option_count); -- cgit v1.2.3 From 6906f4ed6f85b2d72fd944e15da6a905fdde8b40 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2013 06:49:21 +0000 Subject: htb: add HTB_DIRECT_QLEN attribute HTB uses an internal pfifo queue, which limit is not reported to userland tools (tc), and value inherited from device tx_queue_len at setup time. Introduce TCA_HTB_DIRECT_QLEN attribute to allow finer control. Remove two obsolete pr_err() calls as well. Signed-off-by: Eric Dumazet Cc: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 32aef0a439ef..dbd71b0c7d8c 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -348,6 +348,7 @@ enum { TCA_HTB_INIT, TCA_HTB_CTAB, TCA_HTB_RTAB, + TCA_HTB_DIRECT_QLEN, __TCA_HTB_MAX, }; -- cgit v1.2.3 From 8524982847ff00b66ffb89314c342c51f4138ee7 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Mon, 18 Feb 2013 21:47:45 +0100 Subject: ssb: fix unaligned access to mac address The mac address should be aligned to u16 to prevent an unaligned access in drivers/ssb/pci.c where it is casted to __be16. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 22958d68ecfe..8b1322296fed 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -26,9 +26,9 @@ struct ssb_sprom_core_pwr_info { struct ssb_sprom { u8 revision; - u8 il0mac[6]; /* MAC address for 802.11b/g */ - u8 et0mac[6]; /* MAC address for Ethernet */ - u8 et1mac[6]; /* MAC address for 802.11a */ + u8 il0mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11b/g */ + u8 et0mac[6] __aligned(sizeof(u16)); /* MAC address for Ethernet */ + u8 et1mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11a */ u8 et0phyaddr; /* MII address for enet0 */ u8 et1phyaddr; /* MII address for enet1 */ u8 et0mdcport; /* MDIO for enet0 */ -- cgit v1.2.3 From e943789edbb1f9de71b129d9992489eb79ed341f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 15 Feb 2013 21:38:08 +0100 Subject: mac80211: provide ieee80211_sta_eosp() The irqsafe version ieee80211_sta_eosp_irqsafe() exists, but drivers must not mix calls to any irqsafe/non-irqsafe function. Both ath9k and iwlwifi, the likely first users of this interface, use non-irqsafe RX/TX/TX status so must also use a non-irqsafe version of this function. Since no driver uses the _irqsafe() version, remove that. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index cdd7cea1fd4c..8c0ca11a39c4 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1946,14 +1946,14 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * filter those response frames except in the case of frames that * are buffered in the driver -- those must remain buffered to avoid * reordering. Because it is possible that no frames are released - * in this case, the driver must call ieee80211_sta_eosp_irqsafe() + * in this case, the driver must call ieee80211_sta_eosp() * to indicate to mac80211 that the service period ended anyway. * * Finally, if frames from multiple TIDs are released from mac80211 * but the driver might reorder them, it must clear & set the flags * appropriately (only the last frame may have %IEEE80211_TX_STATUS_EOSP) * and also take care of the EOSP and MORE_DATA bits in the frame. - * The driver may also use ieee80211_sta_eosp_irqsafe() in this case. + * The driver may also use ieee80211_sta_eosp() in this case. */ /** @@ -2506,7 +2506,7 @@ enum ieee80211_roc_type { * setting the EOSP flag in the QoS header of the frames. Also, when the * service period ends, the driver must set %IEEE80211_TX_STATUS_EOSP * on the last frame in the SP. Alternatively, it may call the function - * ieee80211_sta_eosp_irqsafe() to inform mac80211 of the end of the SP. + * ieee80211_sta_eosp() to inform mac80211 of the end of the SP. * This callback must be atomic. * @allow_buffered_frames: Prepare device to allow the given number of frames * to go out to the given station. The frames will be sent by mac80211 @@ -2517,7 +2517,7 @@ enum ieee80211_roc_type { * them between the TIDs, it must set the %IEEE80211_TX_STATUS_EOSP flag * on the last frame and clear it on all others and also handle the EOSP * bit in the QoS header correctly. Alternatively, it can also call the - * ieee80211_sta_eosp_irqsafe() function. + * ieee80211_sta_eosp() function. * The @tids parameter is a bitmap and tells the driver which TIDs the * frames will be on; it will at most have two bits set. * This callback must be atomic. @@ -3857,14 +3857,17 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, * %IEEE80211_TX_STATUS_EOSP bit and call this function instead. * This applies for PS-Poll as well as uAPSD. * - * Note that there is no non-_irqsafe version right now as - * it wasn't needed, but just like _tx_status() and _rx() - * must not be mixed in irqsafe/non-irqsafe versions, this - * function must not be mixed with those either. Use the - * all irqsafe, or all non-irqsafe, don't mix! If you need - * the non-irqsafe version of this, you need to add it. + * Note that just like with _tx_status() and _rx() drivers must + * not mix calls to irqsafe/non-irqsafe versions, this function + * must not be mixed with those either. Use the all irqsafe, or + * all non-irqsafe, don't mix! + * + * NB: the _irqsafe version of this function doesn't exist, no + * driver needs it right now. Don't call this function if + * you'd need the _irqsafe version, look at the git history + * and restore the _irqsafe version! */ -void ieee80211_sta_eosp_irqsafe(struct ieee80211_sta *pubsta); +void ieee80211_sta_eosp(struct ieee80211_sta *pubsta); /** * ieee80211_iter_keys - iterate keys programmed into the device -- cgit v1.2.3 From 090096bf3db1c281ddd034573260045888a68fea Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 6 Mar 2013 15:39:42 +0000 Subject: net: generic fdb support for drivers without ndo_fdb_ If the driver does not support the ndo_op use the generic handler for it. This should work in the majority of cases. Eventually the fdb_dflt_add call gets translated into a __dev_set_rx_mode() call which should handle hardware support for filtering via the IFF_UNICAST_FLT flag. Namely IFF_UNICAST_FLT indicates if the hardware can do unicast address filtering. If no support is available the device is put into promisc mode. Signed-off-by: Vlad Yasevich Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 489dd7bb28ec..f28544b2f9af 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -69,6 +69,15 @@ extern int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, int idx); +extern int ndo_dflt_fdb_add(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 flags); +extern int ndo_dflt_fdb_del(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr); extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode); -- cgit v1.2.3 From b2fb4f54ecd47c42413d54b4666b06cf93c05abf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Mar 2013 12:58:01 +0000 Subject: tcp: uninline tcp_prequeue() tcp_prequeue() became too big to be inlined. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 45 +-------------------------------------------- 1 file changed, 1 insertion(+), 44 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index cf0694d4ad60..a2baa5e4ba31 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1030,50 +1030,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp) #endif } -/* Packet is added to VJ-style prequeue for processing in process - * context, if a reader task is waiting. Apparently, this exciting - * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93) - * failed somewhere. Latency? Burstiness? Well, at least now we will - * see, why it failed. 8)8) --ANK - * - * NOTE: is this not too big to inline? - */ -static inline bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (sysctl_tcp_low_latency || !tp->ucopy.task) - return false; - - if (skb->len <= tcp_hdrlen(skb) && - skb_queue_len(&tp->ucopy.prequeue) == 0) - return false; - - __skb_queue_tail(&tp->ucopy.prequeue, skb); - tp->ucopy.memory += skb->truesize; - if (tp->ucopy.memory > sk->sk_rcvbuf) { - struct sk_buff *skb1; - - BUG_ON(sock_owned_by_user(sk)); - - while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) { - sk_backlog_rcv(sk, skb1); - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPPREQUEUEDROPPED); - } - - tp->ucopy.memory = 0; - } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) { - wake_up_interruptible_sync_poll(sk_sleep(sk), - POLLIN | POLLRDNORM | POLLRDBAND); - if (!inet_csk_ack_scheduled(sk)) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, - (3 * tcp_rto_min(sk)) / 4, - TCP_RTO_MAX); - } - return true; -} - +extern bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); #undef STATE_TRACE -- cgit v1.2.3 From 7f0e44ac9f7f12a2519bfed9ea4df3c1471bd8bb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Mar 2013 04:20:32 +0000 Subject: ipv6 flowlabel: add __rcu annotations Commit 18367681a10b (ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.) omitted proper __rcu annotations. Signed-off-by: Eric Dumazet Cc: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ipv6.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 64d12e77719a..988c9f28f0fc 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -217,7 +217,7 @@ struct ipv6_txoptions { }; struct ip6_flowlabel { - struct ip6_flowlabel *next; + struct ip6_flowlabel __rcu *next; __be32 label; atomic_t users; struct in6_addr dst; @@ -238,9 +238,9 @@ struct ip6_flowlabel { #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) struct ipv6_fl_socklist { - struct ipv6_fl_socklist *next; - struct ip6_flowlabel *fl; - struct rcu_head rcu; + struct ipv6_fl_socklist __rcu *next; + struct ip6_flowlabel *fl; + struct rcu_head rcu; }; extern struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label); -- cgit v1.2.3 From bed71748346ae0807c7f7a2913965508dbd61403 Mon Sep 17 00:00:00 2001 From: Andre Guedes Date: Wed, 30 Jan 2013 11:50:56 -0300 Subject: Bluetooth: Rename hci_acl_disconn As hci_acl_disconn function basically sends the HCI Disconnect Command and it is used to disconnect ACL, SCO and LE links, renaming it to hci_disconnect is more suitable. Signed-off-by: Andre Guedes Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 90cf75afcb02..787d3b9bbd58 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -574,7 +574,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, return NULL; } -void hci_acl_disconn(struct hci_conn *conn, __u8 reason); +void hci_disconnect(struct hci_conn *conn, __u8 reason); void hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); -- cgit v1.2.3 From be9f97f04565a6c438b7521ad679870d25645475 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sun, 24 Feb 2013 19:36:52 +0100 Subject: Bluetooth: change bt_sock_unregister() to return void There is no reason a caller ever wants to check the return type of this call. _Iff_ a user successfully called bt_sock_register(), they're allowed to call bt_sock_unregister(). All other calls in the kernel (device_del, device_unregister, kfree(), ..) that are logically equivalent return void. Lets not make callers think they have to check the return type of this call and instead simply return void. We guarantee that after bt_sock_unregister() is called, the socket type _is_ unregistered. If that is not what the caller wants, they're using the wrong function, anyway. Signed-off-by: David Herrmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/bluetooth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 9531beee09b5..5f51bef13e61 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -232,7 +232,7 @@ struct bt_sock_list { }; int bt_sock_register(int proto, const struct net_proto_family *ops); -int bt_sock_unregister(int proto); +void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, -- cgit v1.2.3 From 8ff52f7d04d9cc31f1e81dcf9a2ba6335ed34905 Mon Sep 17 00:00:00 2001 From: Dean Jenkins Date: Thu, 28 Feb 2013 14:21:55 +0000 Subject: Bluetooth: Return RFCOMM session ptrs to avoid freed session Unfortunately, the design retains local copies of the s RFCOMM session pointer in various code blocks and this invites the erroneous access to a freed RFCOMM session structure. Therefore, return the RFCOMM session pointer back up the call stack to avoid accessing a freed RFCOMM session structure. When the RFCOMM session is deleted, NULL is passed up the call stack. If active DLCs exist when the rfcomm session is terminating, avoid a memory leak of rfcomm_dlc structures by ensuring that rfcomm_session_close() is used instead of rfcomm_session_del(). Signed-off-by: Dean Jenkins Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/rfcomm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index e2e3ecad1008..a4e38ead2282 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -278,7 +278,8 @@ void rfcomm_session_getaddr(struct rfcomm_session *s, bdaddr_t *src, static inline void rfcomm_session_hold(struct rfcomm_session *s) { - atomic_inc(&s->refcnt); + if (s) + atomic_inc(&s->refcnt); } /* ---- RFCOMM sockets ---- */ -- cgit v1.2.3 From 08c30aca9e698faddebd34f81e1196295f9dc063 Mon Sep 17 00:00:00 2001 From: Dean Jenkins Date: Thu, 28 Feb 2013 14:21:56 +0000 Subject: Bluetooth: Remove RFCOMM session refcnt Previous commits have improved the handling of the RFCOMM session timer and the RFCOMM session pointers such that freed RFCOMM session structures should no longer be erroneously accessed. The RFCOMM session refcnt now has no purpose and will be deleted by this commit. Note that the RFCOMM session is now deleted as soon as the RFCOMM control channel link is no longer required. This makes the lifetime of the RFCOMM session deterministic and absolute. Previously with the refcnt, there was uncertainty about when the session structure would be deleted because the relative refcnt prevented the session structure from being deleted at will. It was noted that the refcnt could malfunction under very heavy real-time processor loading in embedded SMP environments. This could cause premature RFCOMM session deletion or double session deletion that could result in kernel crashes. Removal of the refcnt prevents this issue. There are 4 connection / disconnection RFCOMM session scenarios: host initiated control link ---> host disconnected control link host initiated ctrl link ---> remote device disconnected ctrl link remote device initiated ctrl link ---> host disconnected ctrl link remote device initiated ctrl link ---> remote device disc'ed ctrl link The control channel connection procedures are independent of the disconnection procedures. Strangely, the RFCOMM session refcnt was applying special treatment so erroneously combining connection and disconnection events. This commit fixes this issue by removing some session code that used the "initiator" member of the session structure that was intended for use with the data channels. Signed-off-by: Dean Jenkins Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/rfcomm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index a4e38ead2282..7afd4199d6b6 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -158,7 +158,6 @@ struct rfcomm_session { struct timer_list timer; unsigned long state; unsigned long flags; - atomic_t refcnt; int initiator; /* Default DLC parameters */ @@ -276,12 +275,6 @@ static inline void rfcomm_dlc_unthrottle(struct rfcomm_dlc *d) void rfcomm_session_getaddr(struct rfcomm_session *s, bdaddr_t *src, bdaddr_t *dst); -static inline void rfcomm_session_hold(struct rfcomm_session *s) -{ - if (s) - atomic_inc(&s->refcnt); -} - /* ---- RFCOMM sockets ---- */ struct sockaddr_rc { sa_family_t rc_family; -- cgit v1.2.3 From 3119ae9599e5cdc1b9838563905c500b582ab6a5 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 5 Mar 2013 20:37:44 +0200 Subject: Bluetooth: Add initial skeleton for asynchronous HCI requests This patch adds the initial definitions and functions for asynchronous HCI requests. Asynchronous requests are essentially a group of HCI commands together with an optional completion callback. The request is tracked through the already existing command queue by having the necessary context information as part of the control buffer of each skb. The only information needed in the skb control buffer is a flag for indicating that the skb is the start of a request as well as the optional complete callback that should be used when the request is complete (this will be found in the last skb of the request). Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/bluetooth.h | 10 ++++++++++ include/net/bluetooth/hci_core.h | 8 ++++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 5f51bef13e61..ed6e9552252e 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -260,12 +260,22 @@ struct l2cap_ctrl { __u8 retries; }; +struct hci_dev; + +typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status); + +struct hci_req_ctrl { + bool start; + hci_req_complete_t complete; +}; + struct bt_skb_cb { __u8 pkt_type; __u8 incoming; __u16 expect; __u8 force_active; struct l2cap_ctrl control; + struct hci_req_ctrl req; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 787d3b9bbd58..7191217c6bd1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1041,6 +1041,14 @@ static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, int hci_register_cb(struct hci_cb *hcb); int hci_unregister_cb(struct hci_cb *hcb); +struct hci_request { + struct hci_dev *hdev; + struct sk_buff_head cmd_q; +}; + +void hci_req_init(struct hci_request *req, struct hci_dev *hdev); +int hci_req_run(struct hci_request *req, hci_req_complete_t complete); + int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); -- cgit v1.2.3 From 71c76a170e979d60e01bd093c9b79e3adeb710cc Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 5 Mar 2013 20:37:46 +0200 Subject: Bluetooth: Introduce new hci_req_add function This function is analogous to hci_send_cmd() but instead of directly queuing the command to hdev->cmd_q it adds it to the local queue of the asynchronous HCI request being build (inside struct hci_request). This is the main function used for building asynchronous requests and there should be one or more calls to it between calls to hci_req_init and hci_req_run. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7191217c6bd1..67fe661259ba 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1048,6 +1048,7 @@ struct hci_request { void hci_req_init(struct hci_request *req, struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); +int hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); -- cgit v1.2.3 From 9238f36a5a5097018b90baa42c473d2f916a46f5 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 5 Mar 2013 20:37:48 +0200 Subject: Bluetooth: Add request cmd_complete and cmd_status functions This patch introduces functions to process the HCI request state when receiving HCI Command Status or Command Complete events. Some HCI commands, like Inquiry do not result in a Command complete event so special handling is needed for them. Inquiry is a particularly important one since it is the only forseeable "non-cmd_complete" command that will make good use of the request functionality, and its completion is either indicated by an Inquiry Complete event of a successful Command Complete for HCI_Inquiry_Cancel. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- 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 67fe661259ba..d732d6894adc 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1049,6 +1049,8 @@ struct hci_request { void hci_req_init(struct hci_request *req, struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); int hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); +void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); +void hci_req_cmd_status(struct hci_dev *hdev, u16 opcode, u8 status); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); -- cgit v1.2.3 From 42c6b129cd8c2aa5012a78ec39672e7052cc677a Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 5 Mar 2013 20:37:49 +0200 Subject: Bluetooth: Use async requests internally in hci_req_sync This patch converts the hci_req_sync() procedure to internaly use the asynchronous HCI requests. The hci_req_sync mechanism relies on hci_req_complete() calls from hci_event.c into hci_core.c whenever a HCI command completes. This is very similar to what asynchronous requests do and makes the conversion fairly straight forward by converting hci_req_complete into a request complete callback. By this change hci_req_complete (renamed to hci_req_sync_complete) becomes private to hci_core.c and all calls to it can be removed from hci_event.c. The commands in each hci_req_sync procedure are collected into their own request by passing the hci_request pointer to the request callback (instead of the hci_dev pointer). The one slight exception is the HCI init request which has the special handling of HCI driver specific initialization commands. These commands are run in their own request prior to the "main" init request. One other extra change that this patch must contain is the handling of spontaneous HCI reset complete events that some controllers exhibit. These were previously handled in the hci_req_complete function but the right place for them now becomes the hci_req_cmd_complete function. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d732d6894adc..3f124f43fcb1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1164,8 +1164,6 @@ struct hci_sec_filter { #define hci_req_lock(d) mutex_lock(&d->req_lock) #define hci_req_unlock(d) mutex_unlock(&d->req_lock) -void hci_req_complete(struct hci_dev *hdev, __u16 cmd, int result); - void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], -- cgit v1.2.3 From cecbb967b2f5c52e090978ff6afe7deddbfbeda5 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 5 Mar 2013 20:37:50 +0200 Subject: Bluetooth: Remove unused hdev->init_last_cmd This variable is no longer needed (due to async HCI request support and the conversion of hci_req_sync to use it), so it can be safely removed. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 3f124f43fcb1..3a9cbf2b55c0 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -248,8 +248,6 @@ struct hci_dev { __u32 req_status; __u32 req_result; - __u16 init_last_cmd; - struct list_head mgmt_pending; struct discovery_state discovery; -- cgit v1.2.3 From c031e234ee304b507b79f76a7677ea0a7a8890e8 Mon Sep 17 00:00:00 2001 From: Andy King Date: Thu, 7 Mar 2013 05:26:13 +0000 Subject: VSOCK: Split vm_sockets.h into kernel/uapi Split the vSockets header into kernel and UAPI parts. The former gets the bits that used to be in __KERNEL__ guards, while the latter gets everything that is user-visible. Tested by compiling vsock (+transport) and a simple user-mode vSockets application. Reported-by: David Howells Acked-by: Dmitry Torokhov Signed-off-by: Andy King Acked-by: David Howells Signed-off-by: David S. Miller --- include/linux/vm_sockets.h | 23 +++++++++++++++++++++++ include/uapi/linux/vm_sockets.h | 23 ++++++++--------------- 2 files changed, 31 insertions(+), 15 deletions(-) create mode 100644 include/linux/vm_sockets.h (limited to 'include') diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h new file mode 100644 index 000000000000..0805eecba8f7 --- /dev/null +++ b/include/linux/vm_sockets.h @@ -0,0 +1,23 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _VM_SOCKETS_H +#define _VM_SOCKETS_H + +#include + +int vm_sockets_get_local_cid(void); + +#endif /* _VM_SOCKETS_H */ diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index df91301847ec..b4ed5d895699 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -13,12 +13,10 @@ * more details. */ -#ifndef _VM_SOCKETS_H_ -#define _VM_SOCKETS_H_ +#ifndef _UAPI_VM_SOCKETS_H +#define _UAPI_VM_SOCKETS_H -#if !defined(__KERNEL__) -#include -#endif +#include /* Option name for STREAM socket buffer size. Use as the option name in * setsockopt(3) or getsockopt(3) to set or get an unsigned long long that @@ -137,14 +135,13 @@ #define VM_SOCKETS_VERSION_MINOR(_v) (((_v) & 0x0000FFFF)) /* Address structure for vSockets. The address family should be set to - * whatever vmci_sock_get_af_value_fd() returns. The structure members should - * all align on their natural boundaries without resorting to compiler packing - * directives. The total size of this structure should be exactly the same as - * that of struct sockaddr. + * AF_VSOCK. The structure members should all align on their natural + * boundaries without resorting to compiler packing directives. The total size + * of this structure should be exactly the same as that of struct sockaddr. */ struct sockaddr_vm { - sa_family_t svm_family; + __kernel_sa_family_t svm_family; unsigned short svm_reserved1; unsigned int svm_port; unsigned int svm_cid; @@ -156,8 +153,4 @@ struct sockaddr_vm { #define IOCTL_VM_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9) -#if defined(__KERNEL__) -int vm_sockets_get_local_cid(void); -#endif - -#endif +#endif /* _UAPI_VM_SOCKETS_H */ -- cgit v1.2.3 From b7ef213ef65256168df83ddfbb8131ed9adc10f9 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 8 Mar 2013 02:07:16 +0000 Subject: ipv6: introdcue __ipv6_addr_needs_scope_id and ipv6_iface_scope_id helper functions __ipv6_addr_needs_scope_id checks if an ipv6 address needs to supply a 'sin6_scope_id != 0'. 'sin6_scope_id != 0' was enforced in case of link-local addresses. To support interface-local multicast these checks had to be enhanced and are now consolidated into these new helper functions. v2: a) migrated to struct ipv6_addr_props v3: a) reverted changes for ipv6_addr_props b) test for address type instead of comparing scope v4: a) unchanged Suggested-by: YOSHIFUJI Hideaki Cc: YOSHIFUJI Hideaki Acked-by: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Acked-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ipv6.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 988c9f28f0fc..42ef6abf25c3 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -320,6 +320,18 @@ static inline int ipv6_addr_src_scope(const struct in6_addr *addr) return __ipv6_addr_src_scope(__ipv6_addr_type(addr)); } +static inline bool __ipv6_addr_needs_scope_id(int type) +{ + return type & IPV6_ADDR_LINKLOCAL || + (type & IPV6_ADDR_MULTICAST && + (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL))); +} + +static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface) +{ + return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0; +} + static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2) { return memcmp(a1, a2, sizeof(struct in6_addr)); -- cgit v1.2.3 From 5d73e0342fd9bf500583868906325d42c4d2bf6f Mon Sep 17 00:00:00 2001 From: Andre Guedes Date: Fri, 8 Mar 2013 11:20:16 -0300 Subject: Bluetooth: HCI request error handling When we are building a HCI request with more than one HCI command and one of the hci_req_add calls fail, we should have some cleanup routine so the HCI commands already queued on HCI request can be deleted. Otherwise, we will face some memory leaks issues. This patch implements the HCI request error handling which is the following: If a hci_req_add fails, we save the error code in hci_ request. Once hci_req_run is called, we verify the error field. If it is different from zero, we delete all HCI commands already queued and return the error code. Signed-off-by: Andre Guedes Acked-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 3a9cbf2b55c0..332ee5099a52 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1042,6 +1042,11 @@ int hci_unregister_cb(struct hci_cb *hcb); struct hci_request { struct hci_dev *hdev; struct sk_buff_head cmd_q; + + /* If something goes wrong when building the HCI request, the error + * value is stored in this field. + */ + int err; }; void hci_req_init(struct hci_request *req, struct hci_dev *hdev); -- cgit v1.2.3 From e348fe6bbab85c513816d2536ffabac4be016442 Mon Sep 17 00:00:00 2001 From: Andre Guedes Date: Fri, 8 Mar 2013 11:20:17 -0300 Subject: Bluetooth: Make hci_req_add returning void Since no one checks the returning value of hci_req_add and HCI request errors are now handled in hci_req_run, we can make hci_ req_add returning void. Signed-off-by: Andre Guedes Acked-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 332ee5099a52..d6c32561fc02 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1051,7 +1051,7 @@ struct hci_request { void hci_req_init(struct hci_request *req, struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); -int hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); +void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); void hci_req_cmd_status(struct hci_dev *hdev, u16 opcode, u8 status); -- cgit v1.2.3 From ec5f061564238892005257c83565a0b58ec79295 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 09:28:01 +0000 Subject: net: Kill link between CSUM and SG features. Earlier SG was unset if CSUM was not available for given device to force skb copy to avoid sending inconsistent csum. Commit c9af6db4c11c (net: Fix possible wrong checksum generation) added explicit flag to force copy to fix this issue. Therefore there is no need to link SG and CSUM, following patch kills this link between there two features. This patch is also required following patch in series. Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/netdevice.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 896eb4985f97..e1ebeffa6b35 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2683,6 +2683,19 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { return __skb_gso_segment(skb, features, true); } +__be16 skb_network_protocol(struct sk_buff *skb); + +static inline bool can_checksum_protocol(netdev_features_t features, + __be16 protocol) +{ + return ((features & NETIF_F_GEN_CSUM) || + ((features & NETIF_F_V4_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_V6_CSUM) && + protocol == htons(ETH_P_IPV6)) || + ((features & NETIF_F_FCOE_CRC) && + protocol == htons(ETH_P_FCOE))); +} #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); -- cgit v1.2.3 From aefbd2b3c2a9c657605e4337f9919d6c6273e8e6 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 13:21:46 +0000 Subject: tunneling: Capture inner mac header during encapsulation. This patch adds inner mac header. This will be used in next patch to find tunner header length. Header len is required to copy tunnel header to each gso segment. This patch does not change any functionality. Signed-off-by: Pravin B Shelar Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/skbuff.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 821c7f45d2a7..d7f96ff68f77 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -387,6 +387,7 @@ typedef unsigned char *sk_buff_data_t; * @vlan_tci: vlan tag control information * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) + * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header @@ -505,6 +506,7 @@ struct sk_buff { sk_buff_data_t inner_transport_header; sk_buff_data_t inner_network_header; + sk_buff_data_t inner_mac_header; sk_buff_data_t transport_header; sk_buff_data_t network_header; sk_buff_data_t mac_header; @@ -1466,6 +1468,7 @@ static inline void skb_reserve(struct sk_buff *skb, int len) static inline void skb_reset_inner_headers(struct sk_buff *skb) { + skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } @@ -1511,6 +1514,22 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header += offset; } +static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) +{ + return skb->head + skb->inner_mac_header; +} + +static inline void skb_reset_inner_mac_header(struct sk_buff *skb) +{ + skb->inner_mac_header = skb->data - skb->head; +} + +static inline void skb_set_inner_mac_header(struct sk_buff *skb, + const int offset) +{ + skb_reset_inner_mac_header(skb); + skb->inner_mac_header += offset; +} static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != ~0U; @@ -1604,6 +1623,21 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header = skb->data + offset; } +static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) +{ + return skb->inner_mac_header; +} + +static inline void skb_reset_inner_mac_header(struct sk_buff *skb) +{ + skb->inner_mac_header = skb->data; +} + +static inline void skb_set_inner_mac_header(struct sk_buff *skb, + const int offset) +{ + skb->inner_mac_header = skb->data + offset; +} static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != NULL; -- cgit v1.2.3 From 731362674580cb0c696cd1b1a03d8461a10cf90a Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 13:21:51 +0000 Subject: tunneling: Add generic Tunnel segmentation. Adds generic tunneling offloading support for IPv4-UDP based tunnels. GSO type is added to request this offload for a skb. netdev feature NETIF_F_UDP_TUNNEL is added for hardware offloaded udp-tunnel support. Currently no device supports this feature, software offload is used. This can be used by tunneling protocols like VXLAN. CC: Jesse Gross Signed-off-by: Pravin B Shelar Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 7 ++++--- include/linux/skbuff.h | 2 ++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 3dd39340430e..f5e797c0c2a4 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -42,9 +42,9 @@ enum { NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */ NETIF_F_FSO_BIT, /* ... FCoE segmentation */ NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ - /**/NETIF_F_GSO_LAST, /* [can't be last bit, see GSO_MASK] */ - NETIF_F_GSO_RESERVED2 /* ... free (fill GSO_MASK to 8 bits) */ - = NETIF_F_GSO_LAST, + NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */ + /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ + NETIF_F_GSO_UDP_TUNNEL_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CSUM_BIT, /* SCTP checksum offload */ @@ -103,6 +103,7 @@ enum { #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) #define NETIF_F_GRE_GSO __NETIF_F(GSO_GRE) +#define NETIF_F_UDP_TUNNEL __NETIF_F(UDP_TUNNEL) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d7f96ff68f77..eb2106fe3bb4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -316,6 +316,8 @@ enum { SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, + + SKB_GSO_UDP_TUNNEL = 1 << 7, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From 6aed0c8bf7d2f389b472834053eb6e3bd6926999 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 9 Mar 2013 16:38:39 +0000 Subject: tunnel: use iptunnel_xmit() again With recent patches from Pravin, most tunnels can't use iptunnel_xmit() any more, due to ip_select_ident() and skb->ip_summed. But we can just move these operations out of iptunnel_xmit(), so that tunnels can use it again. This by the way fixes a bug in vxlan (missing nf_reset()) for net-next. Cc: Pravin B Shelar Cc: Stephen Hemminger Cc: "David S. Miller" Signed-off-by: Cong Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipip.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/ipip.h b/include/net/ipip.h index fd19625ff99d..0c046e3bca05 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -51,13 +51,10 @@ struct ip_tunnel_prl_entry { static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev) { int err; - struct iphdr *iph = ip_hdr(skb); int pkt_len = skb->len - skb_transport_offset(skb); struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); nf_reset(skb); - skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(iph, skb_dst(skb), NULL); err = ip_local_out(skb); if (likely(net_xmit_eval(err) == 0)) { -- cgit v1.2.3 From e8f72ea4a1380eeca10a551bc8d678e7d4388d42 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 9 Mar 2013 23:00:39 +0000 Subject: ipv6: introduce ip6tunnel_xmit() helper Similar to iptunnel_xmit(), group these operations into a helper function. This by the way fixes the missing u64_stats_update_begin() and u64_stats_update_end() for 32 bit arch. Cc: Eric Dumazet Cc: Pravin B Shelar Cc: "David S. Miller" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index e03047f7090b..ebdef7f60862 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -68,4 +68,24 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw); __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); +static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct net_device_stats *stats = &dev->stats; + int pkt_len, err; + + nf_reset(skb); + pkt_len = skb->len; + err = ip6_local_out(skb); + + if (net_xmit_eval(err) == 0) { + struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; + } +} #endif -- cgit v1.2.3 From e61667af2f77d481411f2ccd307fed2247d785a8 Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Sun, 10 Mar 2013 05:18:39 +0000 Subject: tcp: Remove unused tw_cookie_values from tcp_timewait_sock tw_cookie_values is never used in the TCP-stack. It was added by 435cf559f (TCPCT part 1d: define TCP cookie option, extend existing struct's), but already at that time it was not used at all, nor mentioned in the commit-message. Signed-off-by: Christoph Paasch Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f28408c07dc2..515c3746b675 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -361,10 +361,6 @@ struct tcp_timewait_sock { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif - /* Few sockets in timewait have cookies; in that case, then this - * object holds a reference to them (tw_cookie_values->kref). - */ - struct tcp_cookie_values *tw_cookie_values; }; static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) -- cgit v1.2.3 From 26fd76cab2e61cedc5c25f7151fb31b57ddc53c7 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Fri, 22 Feb 2013 10:53:25 +0100 Subject: NFC: llcp: Implement socket options Some LLCP services (e.g. the validation ones) require some control over the LLCP link parameters like the receive window (RW) or the MIU extension (MIUX). This can only be done through socket options. Signed-off-by: Samuel Ortiz --- include/linux/socket.h | 1 + include/uapi/linux/nfc.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 2b9f74b0ffea..428c37a1f95c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -298,6 +298,7 @@ struct ucred { #define SOL_IUCV 277 #define SOL_CAIF 278 #define SOL_ALG 279 +#define SOL_NFC 280 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index 7969f46f1bb3..855630fe731d 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -220,4 +220,8 @@ struct sockaddr_nfc_llcp { #define NFC_LLCP_DIRECTION_RX 0x00 #define NFC_LLCP_DIRECTION_TX 0x01 +/* socket option names */ +#define NFC_LLCP_RW 0 +#define NFC_LLCP_MIUX 1 + #endif /*__LINUX_NFC_H */ -- cgit v1.2.3 From d9b8d8e19b073096d3609bbd60f82148d128b555 Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Fri, 15 Feb 2013 10:43:06 +0100 Subject: NFC: llcp: Service Name Lookup netlink interface This adds a netlink interface for service name lookup support. Multiple URIs can be passed nested into the NFC_ATTR_LLC_SDP attribute using the NFC_CMD_LLC_SDREQ netlink command. When the SNL reply is received, a NFC_EVENT_LLC_SDRES event is sent to the user space. URI and SAP tuples are passed back, nested into NFC_ATTR_LLC_SDP attribute. Signed-off-by: Thierry Escande Signed-off-by: Samuel Ortiz --- include/uapi/linux/nfc.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index 855630fe731d..7440bc81a04b 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -90,6 +90,8 @@ enum nfc_commands { NFC_CMD_LLC_SET_PARAMS, NFC_CMD_ENABLE_SE, NFC_CMD_DISABLE_SE, + NFC_CMD_LLC_SDREQ, + NFC_EVENT_LLC_SDRES, /* private: internal use only */ __NFC_CMD_AFTER_LAST }; @@ -140,11 +142,21 @@ enum nfc_attrs { NFC_ATTR_LLC_PARAM_RW, NFC_ATTR_LLC_PARAM_MIUX, NFC_ATTR_SE, + NFC_ATTR_LLC_SDP, /* private: internal use only */ __NFC_ATTR_AFTER_LAST }; #define NFC_ATTR_MAX (__NFC_ATTR_AFTER_LAST - 1) +enum nfc_sdp_attr { + NFC_SDP_ATTR_UNSPEC, + NFC_SDP_ATTR_URI, + NFC_SDP_ATTR_SAP, +/* private: internal use only */ + __NFC_SDP_ATTR_AFTER_LAST +}; +#define NFC_SDP_ATTR_MAX (__NFC_SDP_ATTR_AFTER_LAST - 1) + #define NFC_DEVICE_NAME_MAXSIZE 8 #define NFC_NFCID1_MAXSIZE 10 #define NFC_SENSB_RES_MAXSIZE 12 -- cgit v1.2.3 From 488b366a452934141959384c7a1b52b22d6154ef Mon Sep 17 00:00:00 2001 From: Alexander Bondar Date: Mon, 11 Feb 2013 14:56:29 +0200 Subject: mac80211: add driver callback for per-interface multicast filter Some devices have multicast filter capability for each individual virtual interface rather than just a global one. Add an interface specific driver callback allowing such drivers to configure this. Signed-off-by: Alexander Bondar Signed-off-by: Johannes Berg --- include/net/mac80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 8c0ca11a39c4..f5db5e970428 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2259,6 +2259,9 @@ enum ieee80211_roc_type { * See the section "Frame filtering" for more information. * This callback must be implemented and can sleep. * + * @set_multicast_list: Configure the device's interface specific RX multicast + * filter. This callback is optional. This callback must be atomic. + * * @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. * @@ -2605,6 +2608,10 @@ struct ieee80211_ops { unsigned int changed_flags, unsigned int *total_flags, u64 multicast); + void (*set_multicast_list)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, bool allmulti, + struct netdev_hw_addr_list *mc_list); + int (*set_tim)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set); int (*set_key)(struct ieee80211_hw *hw, enum set_key_cmd cmd, -- cgit v1.2.3 From b818d1a7f72575eef17e00dc4085512c9cc8897d Mon Sep 17 00:00:00 2001 From: Hector Palacios Date: Sun, 10 Mar 2013 22:50:02 +0000 Subject: phy/micrel: Add support for KSZ8031 Micrel PHY KSZ8031 is similar to KSZ8021 and also requires the special initialization of "Operation Mode Strap Override" in reg 0x16 introduced in 212ea99 (phy/micrel: Implement support for KSZ8021). Signed-off-by: Hector Palacios Reviewed-by: Marek Vasut Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 9dbb41a4e250..8752dbbc6135 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -19,6 +19,7 @@ #define PHY_ID_KSZ9021 0x00221610 #define PHY_ID_KS8737 0x00221720 #define PHY_ID_KSZ8021 0x00221555 +#define PHY_ID_KSZ8031 0x00221556 #define PHY_ID_KSZ8041 0x00221510 #define PHY_ID_KSZ8051 0x00221550 /* same id: ks8001 Rev. A/B, and ks8721 Rev 3. */ -- cgit v1.2.3 From 6ba8a3b19e764b6a65e4030ab0999be50c291e6c Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 11 Mar 2013 10:00:43 +0000 Subject: tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati Acked-by: Neal Cardwell Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - include/net/inet_connection_sock.h | 5 ++++- include/net/tcp.h | 6 ++++-- include/uapi/linux/snmp.h | 1 + 4 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 515c3746b675..01860d74555c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -201,7 +201,6 @@ struct tcp_sock { unused : 1; u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ - early_retrans_delayed:1, /* Delayed ER timer installed */ syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 183292722f6e..de2c78529afa 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -133,6 +133,8 @@ struct inet_connection_sock { #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ #define ICSK_TIME_DACK 2 /* Delayed ack timer */ #define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ +#define ICSK_TIME_EARLY_RETRANS 4 /* Early retransmit timer */ +#define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ static inline struct inet_connection_sock *inet_csk(const struct sock *sk) { @@ -222,7 +224,8 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, when = max_when; } - if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { + if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || + what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE) { icsk->icsk_pending = what; icsk->icsk_timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); diff --git a/include/net/tcp.h b/include/net/tcp.h index a2baa5e4ba31..ab9f947b118b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -543,6 +543,8 @@ extern bool tcp_syn_flood_action(struct sock *sk, extern void tcp_push_one(struct sock *, unsigned int mss_now); extern void tcp_send_ack(struct sock *sk); extern void tcp_send_delayed_ack(struct sock *sk); +extern void tcp_send_loss_probe(struct sock *sk); +extern bool tcp_schedule_loss_probe(struct sock *sk); /* tcp_input.c */ extern void tcp_cwnd_application_limited(struct sock *sk); @@ -873,8 +875,8 @@ static inline void tcp_enable_fack(struct tcp_sock *tp) static inline void tcp_enable_early_retrans(struct tcp_sock *tp) { tp->do_early_retrans = sysctl_tcp_early_retrans && - !sysctl_tcp_thin_dupack && sysctl_tcp_reordering == 3; - tp->early_retrans_delayed = 0; + sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack && + sysctl_tcp_reordering == 3; } static inline void tcp_disable_early_retrans(struct tcp_sock *tp) diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index b49eab89c9fd..290bed6b085f 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -202,6 +202,7 @@ enum LINUX_MIB_TCPFORWARDRETRANS, /* TCPForwardRetrans */ LINUX_MIB_TCPSLOWSTARTRETRANS, /* TCPSlowStartRetrans */ LINUX_MIB_TCPTIMEOUTS, /* TCPTimeouts */ + LINUX_MIB_TCPLOSSPROBES, /* TCPLossProbes */ LINUX_MIB_TCPRENORECOVERYFAIL, /* TCPRenoRecoveryFail */ LINUX_MIB_TCPSACKRECOVERYFAIL, /* TCPSackRecoveryFail */ LINUX_MIB_TCPSCHEDULERFAILED, /* TCPSchedulerFailed */ -- cgit v1.2.3 From 9b717a8d245075ffb8e95a2dfb4ee97ce4747457 Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 11 Mar 2013 10:00:44 +0000 Subject: tcp: TLP loss detection. This is the second of the TLP patch series; it augments the basic TLP algorithm with a loss detection scheme. This patch implements a mechanism for loss detection when a Tail loss probe retransmission plugs a hole thereby masking packet loss from the sender. The loss detection algorithm relies on counting TLP dupacks as outlined in Sec. 3 of: http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01 The basic idea is: Sender keeps track of TLP "episode" upon retransmission of a TLP packet. An episode ends when the sender receives an ACK above the SND.NXT (tracked by tlp_high_seq) at the time of the episode. We want to make sure that before the episode ends the sender receives a "TLP dupack", indicating that the TLP retransmission was unnecessary, so there was no loss/hole that needed plugging. If the sender gets no TLP dupack before the end of the episode, then it reduces ssthresh and the congestion window, because the TLP packet arriving at the receiver probably plugged a hole. Signed-off-by: Nandita Dukkipati Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + include/uapi/linux/snmp.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 01860d74555c..763c108ee03d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -204,6 +204,7 @@ struct tcp_sock { syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ + u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ u32 srtt; /* smoothed round trip time << 3 */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 290bed6b085f..e00013a1debc 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -203,6 +203,7 @@ enum LINUX_MIB_TCPSLOWSTARTRETRANS, /* TCPSlowStartRetrans */ LINUX_MIB_TCPTIMEOUTS, /* TCPTimeouts */ LINUX_MIB_TCPLOSSPROBES, /* TCPLossProbes */ + LINUX_MIB_TCPLOSSPROBERECOVERY, /* TCPLossProbeRecovery */ LINUX_MIB_TCPRENORECOVERYFAIL, /* TCPRenoRecoveryFail */ LINUX_MIB_TCPSACKRECOVERYFAIL, /* TCPSackRecoveryFail */ LINUX_MIB_TCPSCHEDULERFAILED, /* TCPSchedulerFailed */ -- cgit v1.2.3 From 42e836eb4527fb635cb799a701fe4c9fe741c03a Mon Sep 17 00:00:00 2001 From: Michael Stapelberg Date: Mon, 11 Mar 2013 13:56:44 +0000 Subject: phy: add set_wol/get_wol functions This allows ethernet drivers (such as the mv643xx_eth) to support Wake on LAN on platforms where PHY registers have to be configured for Wake on LAN (e.g. the Marvell Kirkwood based qnap TS-119P II). Signed-off-by: Michael Stapelberg Signed-off-by: David S. Miller --- include/linux/phy.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 33999adbf8c8..9e11039dd7a3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -455,6 +455,14 @@ struct phy_driver { */ void (*txtstamp)(struct phy_device *dev, struct sk_buff *skb, int type); + /* Some devices (e.g. qnap TS-119P II) require PHY register changes to + * enable Wake on LAN, so set_wol is provided to be called in the + * ethernet driver's set_wol function. */ + int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); + + /* See set_wol, but for checking whether Wake on LAN is enabled. */ + void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); + struct device_driver driver; }; #define to_phy_driver(d) container_of(d, struct phy_driver, driver) @@ -560,6 +568,8 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); +int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); +void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int __init mdio_bus_init(void); void mdio_bus_exit(void); -- cgit v1.2.3 From e86ac13b031cf71d8f40ff513e627aac80e6b765 Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 11 Mar 2013 23:16:35 +0000 Subject: drivers: net: ethernet: cpsw: change cpts_active_slave to active_slave Change cpts_active_slave to active_slave so that the same DT property can be used to ethtool and SIOCGMIIPHY. CC: Richard Cochran Signed-off-by: Mugunthan V N Signed-off-by: David S. Miller --- include/linux/platform_data/cpsw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/cpsw.h b/include/linux/platform_data/cpsw.h index 798fb80b024b..bb3cd58d71e3 100644 --- a/include/linux/platform_data/cpsw.h +++ b/include/linux/platform_data/cpsw.h @@ -30,7 +30,7 @@ struct cpsw_platform_data { u32 channels; /* number of cpdma channels (symmetric) */ u32 slaves; /* number of slave cpgmac ports */ struct cpsw_slave_data *slave_data; - u32 cpts_active_slave; /* time stamping slave */ + u32 active_slave; /* time stamping, ethtool and SIOCGMIIPHY slave */ u32 cpts_clock_mult; /* convert input clock ticks to nanoseconds */ u32 cpts_clock_shift; /* convert input clock ticks to nanoseconds */ u32 ale_entries; /* ale table size */ -- cgit v1.2.3 From 8a7fbfab4be39b8690543f3d29b26860d2f6c576 Mon Sep 17 00:00:00 2001 From: "nikolay@redhat.com" Date: Tue, 12 Mar 2013 02:49:01 +0000 Subject: netxen: write IP address to firmware when using bonding This patch allows LRO aggregation on bonded devices that contain an NX3031 device. It also adds a for_each_netdev_in_bond_rcu(bond, slave) macro which executes for each slave that has bond as master. V3: After testing and discussing this with Rajesh, I decided to keep the vlan ip cache and just rename it to ip_cache since it will store bond ip addresses too. A new master flag has been added to the ip cache to denote that the address has been added because of a master device. I've taken care of the enslave/release cases by checking for various combinations of events and flags (e.g. netxen has a master, it's a bond master and it's not marked as a slave means it is being enslaved and is dev_open()ed in bond_enslave). I've changed netxen_free_ip_list() to have a "master" parameter which causes all IP addresses marked as master to be deleted (used when a netxen is being released). I've made the patch use the new upper device API as well. The following cases were tested: - bond -> netxen - vlan -> netxen - vlan -> bond -> netxen V2: Remove local ip caching, retrieve addresses dynamically and restore them if necessary. Note: Tested with NX3031 adapter. Tested-by: Rajesh Borundia Signed-off-by: Andy Gospodarek Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e1ebeffa6b35..9fc1ab0c8914 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1617,6 +1617,9 @@ extern seqcount_t devnet_rename_seq; /* Device rename seq */ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) +#define for_each_netdev_in_bond_rcu(bond, slave) \ + for_each_netdev_rcu(&init_net, slave) \ + if (netdev_master_upper_dev_get_rcu(slave) == bond) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) static inline struct net_device *next_net_device(struct net_device *dev) @@ -2774,6 +2777,11 @@ static inline void netif_set_gso_max_size(struct net_device *dev, dev->gso_max_size = size; } +static inline bool netif_is_bond_master(struct net_device *dev) +{ + return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; +} + static inline bool netif_is_bond_slave(struct net_device *dev) { return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; -- cgit v1.2.3 From 764444f5a324ad5a272773f078192819084388ce Mon Sep 17 00:00:00 2001 From: Fernando Luis Vazquez Cao Date: Wed, 13 Mar 2013 16:57:25 +0000 Subject: net: clean leftover of COMPAT_NET_DEV_OPS removal COMPAT_NET_DEV_OPS was removed a while back and with it the definition of netdev_resync_ops() went away. Let's finish the clean-up. Signed-off-by: Fernando Luis Vazquez Cao 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 9fc1ab0c8914..56e3e0665272 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1692,7 +1692,6 @@ extern int netdev_refcnt_read(const struct net_device *dev); extern void free_netdev(struct net_device *dev); extern void synchronize_net(void); extern int init_dummy_netdev(struct net_device *dev); -extern void netdev_resync_ops(struct net_device *dev); extern struct net_device *dev_get_by_index(struct net *net, int ifindex); extern struct net_device *__dev_get_by_index(struct net *net, int ifindex); -- cgit v1.2.3 From 7a875903389f3492d4cb06faa1d55a1630e77c11 Mon Sep 17 00:00:00 2001 From: Erwan Yvin Date: Mon, 11 Mar 2013 03:13:03 +0000 Subject: caif: remove caif_shm caif_shm is an old implementation caif_shm will be replaced by caif_virtio [ As explained by Linus Walleij: "U5500 used this, but was cancelled and the silicon did not reach anyone outside ST-Ericsson. Then for the next platforms, we have gone for the leaner & cleaner approach of using virtio, rpmesg and rproc." ] Signed-off-by: Erwan Yvin Acked-by: Linus Walleij Acked-by: Sjur Brendeland Signed-off-by: David S. Miller --- include/net/caif/caif_shm.h | 26 -------------------------- 1 file changed, 26 deletions(-) delete mode 100644 include/net/caif/caif_shm.h (limited to 'include') diff --git a/include/net/caif/caif_shm.h b/include/net/caif/caif_shm.h deleted file mode 100644 index 5bcce55438cf..000000000000 --- a/include/net/caif/caif_shm.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * Copyright (C) ST-Ericsson AB 2010 - * Contact: Sjur Brendeland / sjur.brandeland@stericsson.com - * Author: Amarnath Revanna / amarnath.bangalore.revanna@stericsson.com - * License terms: GNU General Public License (GPL) version 2 - */ - -#ifndef CAIF_SHM_H_ -#define CAIF_SHM_H_ - -struct shmdev_layer { - u32 shm_base_addr; - u32 shm_total_sz; - u32 shm_id; - u32 shm_loopback; - void *hmbx; - int (*pshmdev_mbxsend) (u32 shm_id, u32 mbx_msg); - int (*pshmdev_mbxsetup) (void *pshmdrv_cb, - struct shmdev_layer *pshm_dev, void *pshm_drv); - struct net_device *pshm_netdev; -}; - -extern int caif_shmcore_probe(struct shmdev_layer *pshm_dev); -extern void caif_shmcore_remove(struct net_device *pshm_netdev); - -#endif -- cgit v1.2.3 From 6681712d67eef14c4ce793561c3231659153a320 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Fri, 15 Mar 2013 04:35:51 +0000 Subject: vxlan: generalize forwarding tables This patch generalizes VXLAN forwarding table entries allowing an administrator to: 1) specify multiple destinations for a given MAC 2) specify alternate vni's in the VXLAN header 3) specify alternate destination UDP ports 4) use multicast MAC addresses as fdb lookup keys 5) specify multicast destinations 6) specify the outgoing interface for forwarded packets The combination allows configuration of more complex topologies using VXLAN encapsulation. Changes since v1: rebase to 3.9.0-rc2 Signed-Off-By: David L Stevens Signed-off-by: David S. Miller --- include/uapi/linux/neighbour.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index adb068c53c4e..f175212420ab 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -21,6 +21,9 @@ enum { NDA_CACHEINFO, NDA_PROBES, NDA_VLAN, + NDA_PORT, + NDA_VNI, + NDA_IFINDEX, __NDA_MAX }; -- cgit v1.2.3 From a362db3d6c8a952cbde510b1fa35d0ee001b347e Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 16 Mar 2013 04:47:55 +0000 Subject: net: fix some typos in netif features Cc: Pravin B Shelar Cc: "David S. Miller" Signed-off-by: Cong Wang Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index f5e797c0c2a4..d6ee2d008ee4 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -102,8 +102,8 @@ enum { #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) -#define NETIF_F_GRE_GSO __NETIF_F(GSO_GRE) -#define NETIF_F_UDP_TUNNEL __NETIF_F(UDP_TUNNEL) +#define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE) +#define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -- cgit v1.2.3 From 1a2c6181c4a1922021b4d7df373bba612c3e5f04 Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Sun, 17 Mar 2013 08:23:34 +0000 Subject: tcp: Remove TCPCT TCPCT uses option-number 253, reserved for experimental use and should not be used in production environments. Further, TCPCT does not fully implement RFC 6013. As a nice side-effect, removing TCPCT increases TCP's performance for very short flows: Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests for files of 1KB size. before this patch: average (among 7 runs) of 20845.5 Requests/Second after: average (among 7 runs) of 21403.6 Requests/Second Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 10 ------ include/net/request_sock.h | 8 +---- include/net/tcp.h | 89 +--------------------------------------------- include/uapi/linux/tcp.h | 26 -------------- 4 files changed, 2 insertions(+), 131 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 763c108ee03d..ed6a7456eecd 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -90,9 +90,6 @@ struct tcp_options_received { sack_ok : 4, /* SACK seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ - u8 cookie_plus:6, /* bytes in authenticator/cookie option */ - cookie_out_never:1, - cookie_in_always:1; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ @@ -102,7 +99,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) { rx_opt->tstamp_ok = rx_opt->sack_ok = 0; rx_opt->wscale_ok = rx_opt->snd_wscale = 0; - rx_opt->cookie_plus = 0; } /* This is the max number of SACKS that we'll generate and process. It's safe @@ -320,12 +316,6 @@ struct tcp_sock { struct tcp_md5sig_info __rcu *md5sig_info; #endif - /* When the cookie options are generated and exchanged, then this - * object holds a reference to them (cookie_values->kref). Also - * contains related tcp_cookie_transactions fields. - */ - struct tcp_cookie_values *cookie_values; - /* TCP fastopen related information */ struct tcp_fastopen_request *fastopen_req; /* fastopen_rsk points to request_sock that resulted in this big diff --git a/include/net/request_sock.h b/include/net/request_sock.h index a51dbd17c2de..9069e65c1c56 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -27,19 +27,13 @@ struct sk_buff; struct dst_entry; struct proto; -/* empty to "strongly type" an otherwise void parameter. - */ -struct request_values { -}; - struct request_sock_ops { int family; int obj_size; struct kmem_cache *slab; char *slab_name; int (*rtx_syn_ack)(struct sock *sk, - struct request_sock *req, - struct request_values *rvp); + struct request_sock *req); void (*send_ack)(struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*send_reset)(struct sock *sk, diff --git a/include/net/tcp.h b/include/net/tcp.h index ab9f947b118b..7f2f17198d75 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -179,7 +179,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ -#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt @@ -454,7 +453,7 @@ 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, int flags, int *addr_len); extern void tcp_parse_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx, const u8 **hvpp, + struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); @@ -476,7 +475,6 @@ extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, extern int tcp_connect(struct sock *sk); extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct request_values *rvp, struct tcp_fastopen_cookie *foc); extern int tcp_disconnect(struct sock *sk, int flags); @@ -1589,91 +1587,6 @@ struct tcp_request_sock_ops { #endif }; -/* Using SHA1 for now, define some constants. - */ -#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS) -#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4) -#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS) - -extern int tcp_cookie_generator(u32 *bakery); - -/** - * struct tcp_cookie_values - each socket needs extra space for the - * cookies, together with (optional) space for any SYN data. - * - * A tcp_sock contains a pointer to the current value, and this is - * cloned to the tcp_timewait_sock. - * - * @cookie_pair: variable data from the option exchange. - * - * @cookie_desired: user specified tcpct_cookie_desired. Zero - * indicates default (sysctl_tcp_cookie_size). - * After cookie sent, remembers size of cookie. - * Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX. - * - * @s_data_desired: user specified tcpct_s_data_desired. When the - * constant payload is specified (@s_data_constant), - * holds its length instead. - * Range 0 to TCP_MSS_DESIRED. - * - * @s_data_payload: constant data that is to be included in the - * payload of SYN or SYNACK segments when the - * cookie option is present. - */ -struct tcp_cookie_values { - struct kref kref; - u8 cookie_pair[TCP_COOKIE_PAIR_SIZE]; - u8 cookie_pair_size; - u8 cookie_desired; - u16 s_data_desired:11, - s_data_constant:1, - s_data_in:1, - s_data_out:1, - s_data_unused:2; - u8 s_data_payload[0]; -}; - -static inline void tcp_cookie_values_release(struct kref *kref) -{ - kfree(container_of(kref, struct tcp_cookie_values, kref)); -} - -/* The length of constant payload data. Note that s_data_desired is - * overloaded, depending on s_data_constant: either the length of constant - * data (returned here) or the limit on variable data. - */ -static inline int tcp_s_data_size(const struct tcp_sock *tp) -{ - return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant) - ? tp->cookie_values->s_data_desired - : 0; -} - -/** - * struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace. - * - * As tcp_request_sock has already been extended in other places, the - * only remaining method is to pass stack values along as function - * parameters. These parameters are not needed after sending SYNACK. - * - * @cookie_bakery: cryptographic secret and message workspace. - * - * @cookie_plus: bytes in authenticator/cookie option, copied from - * struct tcp_options_received (above). - */ -struct tcp_extend_values { - struct request_values rv; - u32 cookie_bakery[COOKIE_WORKSPACE_WORDS]; - u8 cookie_plus:6, - cookie_out_never:1, - cookie_in_always:1; -}; - -static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp) -{ - return (struct tcp_extend_values *)rvp; -} - extern void tcp_v4_init(void); extern void tcp_init(void); diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 6b1ead0b0c9d..8d776ebc4829 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -102,7 +102,6 @@ enum { #define TCP_QUICKACK 12 /* Block/reenable quick acks */ #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*/ #define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ #define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ @@ -199,29 +198,4 @@ struct tcp_md5sig { __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */ }; -/* for TCP_COOKIE_TRANSACTIONS (TCPCT) socket option */ -#define TCP_COOKIE_MIN 8 /* 64-bits */ -#define TCP_COOKIE_MAX 16 /* 128-bits */ -#define TCP_COOKIE_PAIR_SIZE (2*TCP_COOKIE_MAX) - -/* Flags for both getsockopt and setsockopt */ -#define TCP_COOKIE_IN_ALWAYS (1 << 0) /* Discard SYN without cookie */ -#define TCP_COOKIE_OUT_NEVER (1 << 1) /* Prohibit outgoing cookies, - * supercedes everything. */ - -/* Flags for getsockopt */ -#define TCP_S_DATA_IN (1 << 2) /* Was data received? */ -#define TCP_S_DATA_OUT (1 << 3) /* Was data sent? */ - -/* TCP_COOKIE_TRANSACTIONS data */ -struct tcp_cookie_transactions { - __u16 tcpct_flags; /* see above */ - __u8 __tcpct_pad1; /* zero */ - __u8 tcpct_cookie_desired; /* bytes */ - __u16 tcpct_s_data_desired; /* bytes of variable data */ - __u16 tcpct_used; /* bytes in value */ - __u8 tcpct_value[TCP_MSS_DEFAULT]; -}; - - #endif /* _UAPI_LINUX_TCP_H */ -- cgit v1.2.3 From 2908fe31cf6b8d3a975efb567347f85e724f4e81 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 15 Mar 2013 17:06:56 -0500 Subject: Bluetooth: Remove useless HCI_PENDING_CLASS flag Now that class related operations are tracked through asynchronous HCI requests this flag is no longer needed. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 7f12c25f1fca..1e723c76a8f6 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -119,7 +119,6 @@ enum { HCI_CONNECTABLE, HCI_DISCOVERABLE, HCI_LINK_SECURITY, - HCI_PENDING_CLASS, HCI_PERIODIC_INQ, }; -- cgit v1.2.3 From 2cc6fb0049bc02ca7a020ba7b4f88b4c35976058 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 15 Mar 2013 17:06:57 -0500 Subject: Bluetooth: Add a define for the HCI persistent flags mask We'll need to use this mask also when powering off the HCI device so it's better to have this in a single and visible place. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 1e723c76a8f6..1e40222e9dd0 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -122,6 +122,11 @@ enum { HCI_PERIODIC_INQ, }; +/* A mask for the flags that are supposed to remain when a reset happens + * or the HCI device is closed. + */ +#define HCI_PERSISTENT_MASK (BIT(HCI_LE_SCAN) | BIT(HCI_PERIODIC_INQ)) + /* HCI ioctl defines */ #define HCIDEVUP _IOW('H', 201, int) #define HCIDEVDOWN _IOW('H', 202, int) -- cgit v1.2.3 From 04b4edcbc9049e100681c0149b572de439be42ab Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 15 Mar 2013 17:07:01 -0500 Subject: Bluetooth: Handle AD updating through an async request For proper control of the AD update and the related HCI commands it's best to run the AD update through an async request instead of a standalone HCI command. This patch changes the hci_update_ad() function to take a request pointer and updates its users appropriately. E.g. the function is no longer called after the init sequence but during stage 3 of the init sequence. The TX power is read during the init sequence, so we don't need an explicit update whenever it is read and the AD update based on the local name should be done through the local name mgmt handler. The only other user is the update based on enabling advertising. This part is still kept as there is no mgmt API to enable it. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d6c32561fc02..cb99193c7493 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -740,8 +740,6 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash, u8 *randomizer); int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr); -int hci_update_ad(struct hci_dev *hdev); - void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_frame(struct sk_buff *skb); @@ -1167,6 +1165,8 @@ struct hci_sec_filter { #define hci_req_lock(d) mutex_lock(&d->req_lock) #define hci_req_unlock(d) mutex_unlock(&d->req_lock) +void hci_update_ad(struct hci_request *req); + void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], -- cgit v1.2.3 From 1a4d3c4b3750885733641216756de4e4d9b2443a Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 15 Mar 2013 17:07:08 -0500 Subject: Bluetooth: Add proper flag for fast connectable mode In order to be able to represent fast connectable mode in the mgmt settings we need to have a HCI dev flag for it. This patch adds the flag and makes sure its value is changed whenever a mgmt_set_fast_connectable command completes. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 1e40222e9dd0..b854506c859c 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -120,12 +120,14 @@ enum { HCI_DISCOVERABLE, HCI_LINK_SECURITY, HCI_PERIODIC_INQ, + HCI_FAST_CONNECTABLE, }; /* A mask for the flags that are supposed to remain when a reset happens * or the HCI device is closed. */ -#define HCI_PERSISTENT_MASK (BIT(HCI_LE_SCAN) | BIT(HCI_PERIODIC_INQ)) +#define HCI_PERSISTENT_MASK (BIT(HCI_LE_SCAN) | BIT(HCI_PERIODIC_INQ) | \ + BIT(HCI_FAST_CONNECTABLE)) /* HCI ioctl defines */ #define HCIDEVUP _IOW('H', 201, int) -- cgit v1.2.3 From f332ec6699980e0563408c7bcf1a8a31b825fee1 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 15 Mar 2013 17:07:11 -0500 Subject: Bluetooth: Add reading of page scan parameters These parameters are related to the "fast connectable" mode that can be changed through the mgmt interface. Not all controllers properly reset these values with HCI_Reset so they need to be read in order to be able to verify whether the values are correct or not before enabling page scan. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci.h | 13 +++++++++++++ include/net/bluetooth/hci_core.h | 4 ++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index b854506c859c..b3308927a0a1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -887,12 +887,25 @@ struct hci_rp_read_data_block_size { __le16 num_blocks; } __packed; +#define HCI_OP_READ_PAGE_SCAN_ACTIVITY 0x0c1b +struct hci_rp_read_page_scan_activity { + __u8 status; + __le16 interval; + __le16 window; +} __packed; + #define HCI_OP_WRITE_PAGE_SCAN_ACTIVITY 0x0c1c struct hci_cp_write_page_scan_activity { __le16 interval; __le16 window; } __packed; +#define HCI_OP_READ_PAGE_SCAN_TYPE 0x0c46 +struct hci_rp_read_page_scan_type { + __u8 status; + __u8 type; +} __packed; + #define HCI_OP_WRITE_PAGE_SCAN_TYPE 0x0c47 #define PAGE_SCAN_TYPE_STANDARD 0x00 #define PAGE_SCAN_TYPE_INTERLACED 0x01 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index cb99193c7493..358a6983d3bb 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -165,6 +165,10 @@ struct hci_dev { __u16 voice_setting; __u8 io_capability; __s8 inq_tx_power; + __u16 page_scan_interval; + __u16 page_scan_window; + __u8 page_scan_type; + __u16 devid_source; __u16 devid_vendor; __u16 devid_product; -- cgit v1.2.3 From ddbfe860acc39d4856a86186eb8a292426ea6224 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Fri, 8 Mar 2013 14:46:14 +0100 Subject: mac80211: move sdata debugfs dir to vif There is need create driver own per interface debugfs files. This is currently done by drv_{add,remove}_interface_debugfs() callbacks. But it is possible that after we remove interface from the driver (i.e. on suspend) we call drv_remove_interface_debugfs() function. Fixing this problem will require to add call drv_{add,remove}_interface_debugfs() anytime we create and remove interface in mac80211. So it's better to add debugfs dir dentry to vif structure to allow to create/remove custom debugfs driver files on drv_{add,remove}_interface(). Signed-off-by: Stanislaw Gruszka Signed-off-by: Johannes Berg --- include/net/mac80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f5db5e970428..8b2c7506f5cb 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1067,6 +1067,9 @@ enum ieee80211_vif_flags { * path needing to access it; even though the netdev carrier will always * be off when it is %NULL there can still be races and packets could be * processed after it switches back to %NULL. + * @debugfs_dir: debugfs dentry, can be used by drivers to create own per + * interface debug files. Note that it will be NULL for the virtual + * monitor interface (if that is requested.) * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *). */ @@ -1083,6 +1086,10 @@ struct ieee80211_vif { u32 driver_flags; +#ifdef CONFIG_MAC80211_DEBUGFS + struct dentry *debugfs_dir; +#endif + /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); }; -- cgit v1.2.3 From d260ff12e7768444b4da7612b785cfd7cbc1d1c1 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Fri, 8 Mar 2013 14:46:15 +0100 Subject: mac80211: remove vif debugfs driver callbacks This basically reverts commit b207cdb07f3f01ec1adaac62e9d0cc918c60a81a. Now is possible to use drv_{add,remove}_interface() and vif->debugfs_dir to create/remove per interface debugfs files. Remove redundant callbacks. Signed-off-by: Stanislaw Gruszka Signed-off-by: Johannes Berg --- include/net/mac80211.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 8b2c7506f5cb..0b912d22f82d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2233,18 +2233,6 @@ enum ieee80211_roc_type { * MAC address of the device going away. * Hence, this callback must be implemented. It can sleep. * - * @add_interface_debugfs: Drivers can use this callback to add debugfs files - * when a vif is added to mac80211. This callback and - * @remove_interface_debugfs should be within a CONFIG_MAC80211_DEBUGFS - * conditional. @remove_interface_debugfs must be provided for cleanup. - * This callback can sleep. - * - * @remove_interface_debugfs: Remove the debugfs files which were added using - * @add_interface_debugfs. This callback must remove all debugfs entries - * that were added because mac80211 only removes interface debugfs when the - * interface is destroyed, not when it is removed from the driver. - * This callback 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 @@ -2665,12 +2653,6 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct dentry *dir); - void (*add_interface_debugfs)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct dentry *dir); - void (*remove_interface_debugfs)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct dentry *dir); #endif void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd, struct ieee80211_sta *sta); -- cgit v1.2.3 From 39ecc01d1bbe3de2cf5f01a81e176ea5160d3b95 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Feb 2013 12:11:00 +0100 Subject: mac80211: pass queue bitmap to flush operation There are a number of situations in which mac80211 only really needs to flush queues for one virtual interface, and in fact during this frames might be transmitted on other virtual interfaces. Calculate and pass a queue bitmap to the driver so it knows which queues to flush. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0b912d22f82d..4158da74e11b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2438,8 +2438,11 @@ enum ieee80211_roc_type { * @testmode_dump: Implement a cfg80211 test mode dump. 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. The callback can sleep. + * that the hardware queues are empty. The @queues parameter is a bitmap + * of queues to flush, which is useful if different virtual interfaces + * use different hardware queues; it may also indicate all queues. + * If the parameter @drop is set to %true, pending frames may be dropped. + * The callback can sleep. * * @channel_switch: Drivers that need (or want) to offload the channel * switch operation for CSAs received from the AP may implement this @@ -2687,7 +2690,7 @@ struct ieee80211_ops { struct netlink_callback *cb, void *data, int len); #endif - void (*flush)(struct ieee80211_hw *hw, bool drop); + void (*flush)(struct ieee80211_hw *hw, u32 queues, bool drop); void (*channel_switch)(struct ieee80211_hw *hw, struct ieee80211_channel_switch *ch_switch); int (*napi_poll)(struct ieee80211_hw *hw, int budget); -- cgit v1.2.3 From 445ea4e83ec50668cc9ad7e5cf96d242f19165e8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Feb 2013 12:25:28 +0100 Subject: mac80211: stop queues temporarily for flushing Sometimes queues are flushed in the middle of operation, which can lead to driver issues. Stop queues temporarily, while flushing, to avoid transmitting new packets while they are being flushed. Signed-off-by: Johannes Berg --- 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 4158da74e11b..dd73b8c6746b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -93,9 +93,11 @@ struct device; * enum ieee80211_max_queues - maximum number of queues * * @IEEE80211_MAX_QUEUES: Maximum number of regular device queues. + * @IEEE80211_MAX_QUEUE_MAP: bitmap with maximum queues set */ enum ieee80211_max_queues { IEEE80211_MAX_QUEUES = 16, + IEEE80211_MAX_QUEUE_MAP = BIT(IEEE80211_MAX_QUEUES) - 1, }; #define IEEE80211_INVAL_HW_QUEUE 0xff -- cgit v1.2.3 From b962abdc6531c8de837504ebc98139587162f223 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 9 Mar 2013 23:25:08 +0200 Subject: ipvs: fix some sparse warnings Add missing __percpu annotations and make ip_vs_net_id static. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 68c69d54d392..29bc05577560 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -459,7 +459,7 @@ struct ip_vs_estimator { struct ip_vs_stats { struct ip_vs_stats_user ustats; /* statistics */ struct ip_vs_estimator est; /* estimator */ - struct ip_vs_cpu_stats *cpustats; /* per cpu counters */ + struct ip_vs_cpu_stats __percpu *cpustats; /* per cpu counters */ spinlock_t lock; /* spin lock */ struct ip_vs_stats_user ustats0; /* reset values */ }; -- cgit v1.2.3 From dece40e848f6e022f960dc9de54be518928460c3 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 13 Mar 2013 23:40:14 +0000 Subject: netfilter: nf_conntrack: speed up module removal path if netns in use The patch introduces nf_conntrack_cleanup_net_list(), which cleanups nf_conntrack for a list of netns and calls synchronize_net() only once for them all. This should reduce netns destruction time. I've measured cleanup time for 1k dummy net ns. Here are the results: # modprobe nf_conntrack # time modprobe -r nf_conntrack real 0m10.337s user 0m0.000s sys 0m0.376s # modprobe nf_conntrack # time modprobe -r nf_conntrack real 0m5.661s user 0m0.000s sys 0m0.216s Signed-off-by: Vladimir Davydov Cc: Patrick McHardy Cc: "David S. Miller" Cc: "Eric W. Biederman" Acked-by: Gao feng Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 930275fa2ea6..fb2b6234e937 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -27,6 +27,7 @@ extern unsigned int nf_conntrack_in(struct net *net, extern int nf_conntrack_init_net(struct net *net); extern void nf_conntrack_cleanup_net(struct net *net); +extern void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); extern int nf_conntrack_proto_pernet_init(struct net *net); extern void nf_conntrack_proto_pernet_fini(struct net *net); -- cgit v1.2.3 From 77f65ebdca506870d99bfabe52bde222511022ec Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 19 Mar 2013 10:18:11 +0000 Subject: packet: packet fanout rollover during socket overload Changes: v3->v2: rebase (no other changes) passes selftest v2->v1: read f->num_members only once fix bug: test rollover mode + flag Minimize packet drop in a fanout group. If one socket is full, roll over packets to another from the group. Maintain flow affinity during normal load using an rxhash fanout policy, while dispersing unexpected traffic storms that hit a single cpu, such as spoofed-source DoS flows. Rollover breaks affinity for flows arriving at saturated sockets during those conditions. The patch adds a fanout policy ROLLOVER that rotates between sockets, filling each socket before moving to the next. It also adds a fanout flag ROLLOVER. If passed along with any other fanout policy, the primary policy is applied until the chosen socket is full. Then, rollover selects another socket, to delay packet drop until the entire system is saturated. Probing sockets is not free. Selecting the last used socket, as rollover does, is a greedy approach that maximizes chance of success, at the cost of extreme load imbalance. In practice, with sufficiently long queues to absorb bursts, sockets are drained in parallel and load balance looks uniform in `top`. To avoid contention, scales counters with number of sockets and accesses them lockfree. Values are bounds checked to ensure correctness. Tested using an application with 9 threads pinned to CPUs, one socket per thread and sufficient busywork per packet operation to limits each thread to handling 32 Kpps. When sent 500 Kpps single UDP stream packets, a FANOUT_CPU setup processes 32 Kpps in total without this patch, 270 Kpps with the patch. Tested with read() and with a packet ring (V1). Also, passes psock_fanout.c unit test added to selftests. Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/if_packet.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index f9a60375f0d0..8136658ea477 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -55,6 +55,8 @@ struct sockaddr_ll { #define PACKET_FANOUT_HASH 0 #define PACKET_FANOUT_LB 1 #define PACKET_FANOUT_CPU 2 +#define PACKET_FANOUT_ROLLOVER 3 +#define PACKET_FANOUT_FLAG_ROLLOVER 0x1000 #define PACKET_FANOUT_FLAG_DEFRAG 0x8000 struct tpacket_stats { -- cgit v1.2.3 From f77668dc25b27270fe589031b22c432c3462b1d8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 Mar 2013 06:39:30 +0000 Subject: net: flow_dissector: add __skb_get_poff to get a start offset to payload __skb_get_poff() returns the offset to the payload as far as it could be dissected. The main user is currently BPF, so that we can dynamically truncate packets without needing to push actual payload to the user space and instead can analyze headers only. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b66ecc6ef102..497412165b1c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2840,6 +2840,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); +u32 __skb_get_poff(const struct sk_buff *skb); + /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check -- cgit v1.2.3 From 3e5289d5e3f98b7b5b8cac32e9e5a7004c067436 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 Mar 2013 06:39:31 +0000 Subject: filter: add ANC_PAY_OFFSET instruction for loading payload start offset It is very useful to do dynamic truncation of packets. In particular, we're interested to push the necessary header bytes to the user space and cut off user payload that should probably not be transferred for some reasons (e.g. privacy, speed, or others). With the ancillary extension PAY_OFFSET, we can load it into the accumulator, and return it. E.g. in bpfc syntax ... ld #poff ; { 0x20, 0, 0, 0xfffff034 }, ret a ; { 0x16, 0, 0, 0x00000000 }, ... as a filter will accomplish this without having to do a big hackery in a BPF filter itself. Follow-up JIT implementations are welcome. Thanks to Eric Dumazet for suggesting and discussing this during the Netfilter Workshop in Copenhagen. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + include/uapi/linux/filter.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index c45eabc135e1..d2059cb4e465 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -126,6 +126,7 @@ enum { BPF_S_ANC_SECCOMP_LD_W, BPF_S_ANC_VLAN_TAG, BPF_S_ANC_VLAN_TAG_PRESENT, + BPF_S_ANC_PAY_OFFSET, }; #endif /* __LINUX_FILTER_H__ */ diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h index 9cfde6941099..8eb9ccaa5b48 100644 --- a/include/uapi/linux/filter.h +++ b/include/uapi/linux/filter.h @@ -129,7 +129,8 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define SKF_AD_ALU_XOR_X 40 #define SKF_AD_VLAN_TAG 44 #define SKF_AD_VLAN_TAG_PRESENT 48 -#define SKF_AD_MAX 52 +#define SKF_AD_PAY_OFFSET 52 +#define SKF_AD_MAX 56 #define SKF_NET_OFF (-0x100000) #define SKF_LL_OFF (-0x200000) -- cgit v1.2.3 From 2b5faa4c553f90ee2dde1d976b220b1ca9741ef0 Mon Sep 17 00:00:00 2001 From: Jesper Derehag Date: Tue, 19 Mar 2013 20:50:05 +0000 Subject: connector: Added coredumping event to the process connector Process connector can now also detect coredumping events. Main aim of patch is get notified at start of coredumping, instead of having to wait for it to finish and then being notified through EXIT event. Could be used for instance by process-managers that want to get notified as soon as possible about process failures, and not necessarily beeing notified after coredump, which could be in the order of minutes depending on size of coredump, piping and so on. Signed-off-by: Jesper Derehag Signed-off-by: David S. Miller --- include/linux/cn_proc.h | 4 ++++ include/uapi/linux/cn_proc.h | 10 +++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cn_proc.h b/include/linux/cn_proc.h index 2c1bc1ea04ee..1d5b02a96c46 100644 --- a/include/linux/cn_proc.h +++ b/include/linux/cn_proc.h @@ -26,6 +26,7 @@ void proc_id_connector(struct task_struct *task, int which_id); void proc_sid_connector(struct task_struct *task); void proc_ptrace_connector(struct task_struct *task, int which_id); void proc_comm_connector(struct task_struct *task); +void proc_coredump_connector(struct task_struct *task); void proc_exit_connector(struct task_struct *task); #else static inline void proc_fork_connector(struct task_struct *task) @@ -48,6 +49,9 @@ static inline void proc_ptrace_connector(struct task_struct *task, int ptrace_id) {} +static inline void proc_coredump_connector(struct task_struct *task) +{} + static inline void proc_exit_connector(struct task_struct *task) {} #endif /* CONFIG_PROC_EVENTS */ diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index 0d7b49973bb3..f6c271035bbd 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -56,7 +56,9 @@ struct proc_event { PROC_EVENT_PTRACE = 0x00000100, PROC_EVENT_COMM = 0x00000200, /* "next" should be 0x00000400 */ - /* "last" is the last process event: exit */ + /* "last" is the last process event: exit, + * while "next to last" is coredumping event */ + PROC_EVENT_COREDUMP = 0x40000000, PROC_EVENT_EXIT = 0x80000000 } what; __u32 cpu; @@ -110,11 +112,17 @@ struct proc_event { char comm[16]; } comm; + struct coredump_proc_event { + __kernel_pid_t process_pid; + __kernel_pid_t process_tgid; + } coredump; + struct exit_proc_event { __kernel_pid_t process_pid; __kernel_pid_t process_tgid; __u32 exit_code, exit_signal; } exit; + } event_data; }; -- cgit v1.2.3 From 9b44190dc114c1720b34975b5bfc65aece112ced Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 20 Mar 2013 13:32:58 +0000 Subject: tcp: refactor F-RTO The patch series refactor the F-RTO feature (RFC4138/5682). This is to simplify the loss recovery processing. Existing F-RTO was developed during the experimental stage (RFC4138) and has many experimental features. It takes a separate code path from the traditional timeout processing by overloading CA_Disorder instead of using CA_Loss state. This complicates CA_Disorder state handling because it's also used for handling dubious ACKs and undos. While the algorithm in the RFC does not change the congestion control, the implementation intercepts congestion control in various places (e.g., frto_cwnd in tcp_ack()). The new code implements newer F-RTO RFC5682 using CA_Loss processing path. F-RTO becomes a small extension in the timeout processing and interfaces with congestion control and Eifel undo modules. It lets congestion control (module) determines how many to send independently. F-RTO only chooses what to send in order to detect spurious retranmission. If timeout is found spurious it invokes existing Eifel undo algorithms like DSACK or TCP timestamp based detection. The first patch removes all F-RTO code except the sysctl_tcp_frto is left for the new implementation. Since CA_EVENT_FRTO is removed, TCP westwood now computes ssthresh on regular timeout CA_EVENT_LOSS event. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++---- include/net/tcp.h | 4 ---- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ed6a7456eecd..f5f203b36379 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -187,14 +187,12 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ - u32 frto_highmark; /* snd_nxt when RTO occurred */ u16 advmss; /* Advertised MSS */ - u8 frto_counter; /* Number of new acks after RTO */ + u8 unused; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ - repair : 1, - unused : 1; + repair : 1; u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ syn_data:1, /* SYN includes data */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 7f2f17198d75..d1dcb596230e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -272,7 +272,6 @@ extern int sysctl_tcp_app_win; extern int sysctl_tcp_adv_win_scale; extern int sysctl_tcp_tw_reuse; extern int sysctl_tcp_frto; -extern int sysctl_tcp_frto_response; extern int sysctl_tcp_low_latency; extern int sysctl_tcp_dma_copybreak; extern int sysctl_tcp_nometrics_save; @@ -424,8 +423,6 @@ extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb, bool fastopen); extern int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); -extern bool tcp_use_frto(struct sock *sk); -extern void tcp_enter_frto(struct sock *sk); extern void tcp_enter_loss(struct sock *sk, int how); extern void tcp_clear_retrans(struct tcp_sock *tp); extern void tcp_update_metrics(struct sock *sk); @@ -756,7 +753,6 @@ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ CA_EVENT_CWND_RESTART, /* congestion window restart */ CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */ - CA_EVENT_FRTO, /* fast recovery timeout */ CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_FAST_ACK, /* in sequence ack */ CA_EVENT_SLOW_ACK, /* other ack */ -- cgit v1.2.3 From e33099f96d99c391b3325caa9c44258de04aae86 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 20 Mar 2013 13:33:00 +0000 Subject: tcp: implement RFC5682 F-RTO This patch implements F-RTO (foward RTO recovery): When the first retransmission after timeout is acknowledged, F-RTO sends new data instead of old data. If the next ACK acknowledges some never-retransmitted data, then the timeout was spurious and the congestion state is reverted. Otherwise if the next ACK selectively acknowledges the new data, then the timeout was genuine and the loss recovery continues. This idea applies to recurring timeouts as well. While F-RTO sends different data during timeout recovery, it does not (and should not) change the congestion control. The implementaion follows the three steps of SACK enhanced algorithm (section 3) in RFC5682. Step 1 is in tcp_enter_loss(). Step 2 and 3 are in tcp_process_loss(). The basic version is not supported because SACK enhanced version also works for non-SACK connections. The new implementation is functionally in parity with the old F-RTO implementation except the one case where it increases undo events: In addition to the RFC algorithm, a spurious timeout may be detected without sending data in step 2, as long as the SACK confirms not all the original data are dropped. When this happens, the sender will undo the cwnd and perhaps enter fast recovery instead. This additional check increases the F-RTO undo events by 5x compared to the prior implementation on Google Web servers, since the sender often does not have new data to send for HTTP. Note F-RTO may detect spurious timeout before Eifel with timestamps does so. Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f5f203b36379..5adbc33d1ab3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -192,7 +192,8 @@ struct tcp_sock { u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ - repair : 1; + repair : 1, + frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ syn_data:1, /* SYN includes data */ -- cgit v1.2.3 From eaaa31392690c7609f7afeec5ba38a79d009842d Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Thu, 21 Mar 2013 20:33:48 +0400 Subject: netlink: Diag core and basic socket info dumping (v2) The netlink_diag can be built as a module, just like it's done in unix sockets. The core dumping message carries the basic info about netlink sockets: family, type and protocol, portis, dst_group, dst_portid, state. Groups can be received as an optional parameter NETLINK_DIAG_GROUPS. Netlink sockets cab be filtered by protocols. The socket inode number and cookie is reserved for future per-socket info retrieving. The per-protocol filtering is also reserved for future by requiring the sdiag_protocol to be zero. The file /proc/net/netlink doesn't provide enough information for dumping netlink sockets. It doesn't provide dst_group, dst_portid, groups above 32. v2: fix NETLINK_DIAG_MAX. Now it's equal to the last constant. Acked-by: Pavel Emelyanov Cc: "David S. Miller" Cc: Eric Dumazet Cc: Pablo Neira Ayuso Cc: "Eric W. Biederman" Cc: Gao feng Cc: Thomas Graf Signed-off-by: Andrey Vagin Signed-off-by: David S. Miller --- include/uapi/linux/netlink_diag.h | 42 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 include/uapi/linux/netlink_diag.h (limited to 'include') diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h new file mode 100644 index 000000000000..88009a31cd06 --- /dev/null +++ b/include/uapi/linux/netlink_diag.h @@ -0,0 +1,42 @@ +#ifndef __NETLINK_DIAG_H__ +#define __NETLINK_DIAG_H__ + +#include + +struct netlink_diag_req { + __u8 sdiag_family; + __u8 sdiag_protocol; + __u16 pad; + __u32 ndiag_ino; + __u32 ndiag_show; + __u32 ndiag_cookie[2]; +}; + +struct netlink_diag_msg { + __u8 ndiag_family; + __u8 ndiag_type; + __u8 ndiag_protocol; + __u8 ndiag_state; + + __u32 ndiag_portid; + __u32 ndiag_dst_portid; + __u32 ndiag_dst_group; + __u32 ndiag_ino; + __u32 ndiag_cookie[2]; +}; + +enum { + NETLINK_DIAG_MEMINFO, + NETLINK_DIAG_GROUPS, + + __NETLINK_DIAG_MAX, +}; + +#define NETLINK_DIAG_MAX (__NETLINK_DIAG_MAX - 1) + +#define NDIAG_PROTO_ALL ((__u8) ~0) + +#define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */ +#define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */ + +#endif -- cgit v1.2.3 From 79617801ea0c0e6664cb497d4c1892c2ff407364 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 21 Mar 2013 22:22:03 +0100 Subject: filter: bpf_jit_comp: refactor and unify BPF JIT image dump output If bpf_jit_enable > 1, then we dump the emitted JIT compiled image after creation. Currently, only SPARC and PowerPC has similar output as in the reference implementation on x86_64. Make a small helper function in order to reduce duplicated code and make the dump output uniform across architectures x86_64, SPARC, PPC, ARM (e.g. on ARM flen, pass and proglen are currently not shown, but would be interesting to know as well), also for future BPF JIT implementations on other archs. Cc: Mircea Gherzan Cc: Matt Evans Cc: Eric Dumazet Cc: David S. Miller Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index d2059cb4e465..d7d25083130b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -50,6 +50,16 @@ extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, uns #ifdef CONFIG_BPF_JIT extern void bpf_jit_compile(struct sk_filter *fp); extern void bpf_jit_free(struct sk_filter *fp); + +static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, + u32 pass, void *image) +{ + pr_err("flen=%u proglen=%u pass=%u image=%p\n", + flen, proglen, pass, image); + if (image) + print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_ADDRESS, + 16, 1, image, proglen, false); +} #define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns) #else static inline void bpf_jit_compile(struct sk_filter *fp) -- cgit v1.2.3 From 19dde0bd71e3dffb03ddc509019e22250f4e20c0 Mon Sep 17 00:00:00 2001 From: Janusz Dziedzic Date: Thu, 21 Mar 2013 15:47:54 +0100 Subject: cfg80211: add P2P Notice of Absence attribute Add P2P Notice of Absence attribute structure. Signed-off-by: Janusz Dziedzic Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 4cf0c9e4dd99..d10b5bba3268 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1027,6 +1027,26 @@ enum ieee80211_p2p_attr_id { IEEE80211_P2P_ATTR_MAX }; +/* Notice of Absence attribute - described in P2P spec 4.1.14 */ +/* Typical max value used here */ +#define IEEE80211_P2P_NOA_DESC_MAX 4 + +struct ieee80211_p2p_noa_desc { + u8 count; + __le32 duration; + __le32 interval; + __le32 start_time; +} __packed; + +struct ieee80211_p2p_noa_attr { + u8 index; + u8 oppps_ctwindow; + struct ieee80211_p2p_noa_desc desc[IEEE80211_P2P_NOA_DESC_MAX]; +} __packed; + +#define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) +#define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F + /** * struct ieee80211_bar - HT Block Ack Request * -- cgit v1.2.3 From 67baf66339f82b5ddef5731caedb1e6db496818d Mon Sep 17 00:00:00 2001 From: Janusz Dziedzic Date: Thu, 21 Mar 2013 15:47:56 +0100 Subject: mac80211: add P2P NoA settings Add P2P NoA settings for STA mode. Signed-off-by: Janusz Dziedzic [fix docs] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dd73b8c6746b..9b536172e27e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -330,8 +330,7 @@ enum ieee80211_rssi_event { * @ssid_len: Length of SSID given in @ssid. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. * @txpower: TX power in dBm - * @p2p_ctwindow: P2P CTWindow, only for P2P client interfaces - * @p2p_oppps: P2P opportunistic PS is enabled + * @p2p_noa_attr: P2P NoA attribute for P2P powersave */ struct ieee80211_bss_conf { const u8 *bssid; @@ -365,8 +364,7 @@ struct ieee80211_bss_conf { size_t ssid_len; bool hidden_ssid; int txpower; - u8 p2p_ctwindow; - bool p2p_oppps; + struct ieee80211_p2p_noa_attr p2p_noa_attr; }; /** -- cgit v1.2.3 From 9d0ca6ed6f2f12eb488f450d5d38d047aa402a53 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 21 Mar 2013 14:17:34 +0000 Subject: virtio: remove obsolete virtqueue_get_queue_index() You can access it directly now, since 3.8: v3.7-rc1-13-g06ca287 'virtio: move queue_index and num_free fields into core struct virtqueue.' Cc: Cornelia Huck Signed-off-by: Rusty Russell Acked-by: Cornelia Huck Signed-off-by: David S. Miller --- include/linux/virtio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index ff6714e6d0f5..2d7a5e045908 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -58,12 +58,6 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq); unsigned int virtqueue_get_vring_size(struct virtqueue *vq); -/* FIXME: Obsolete accessor, but required for virtio_net merge. */ -static inline unsigned int virtqueue_get_queue_index(struct virtqueue *vq) -{ - return vq->index; -} - /** * virtio_device - representation of a device using virtio * @index: unique position on the virtio bus -- cgit v1.2.3 From c3a07134e6aa5b93a37f72ffa3d11fadf72bf757 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 22 Mar 2013 03:39:28 +0000 Subject: mv643xx_eth: convert to use the Marvell Orion MDIO driver This patch converts the Marvell MV643XX ethernet driver to use the Marvell Orion MDIO driver. As a result, PowerPC and ARM platforms registering the Marvell MV643XX ethernet driver are also updated to register a Marvell Orion MDIO driver. This driver voluntarily overlaps with the Marvell Ethernet shared registers because it will use a subset of this shared register (shared_base + 0x4 to shared_base + 0x84). The Ethernet driver is also updated to look up for a PHY device using the Orion MDIO bus driver. For ARM and PowerPC we register a single instance of the "mvmdio" driver in the system like it used to be done with the use of the "shared_smi" platform_data cookie on ARM. Note that it is safe to register the mvmdio driver only for the "ge00" instance of the driver because this "ge00" interface is guaranteed to always be explicitely registered by consumers of arch/arm/plat-orion/common.c and other instances (ge01, ge10 and ge11) were all pointing their shared_smi to ge00. For PowerPC the in-tree Device Tree Source files mention only one MV643XX ethernet MAC instance so the MDIO bus driver is registered only when id == 0. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mv643xx_eth.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index 49258e0ed1c6..141d395bbb5f 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -19,7 +19,6 @@ struct mv643xx_eth_shared_platform_data { struct mbus_dram_target_info *dram; - struct platform_device *shared_smi; /* * Max packet size for Tx IP/Layer 4 checksum, when set to 0, default * limit of 9KiB will be used. -- cgit v1.2.3 From 58d7d8f9b20ee6f883532b952f246e4289fe06eb Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 21 Mar 2013 07:45:28 +0000 Subject: decnet: Parse netlink attributes on our own decnet is the only subsystem left that is relying on the global netlink attribute buffer rta_buf. It's horrible design and we want to get rid of it. This converts all of decnet to do implicit attribute parsing. It also gets rid of the error prone struct dn_kern_rta. Yes, the fib_magic() stuff is not pretty. It's compiled tested but I need someone with appropriate hardware to test the patch since I don't have access to it. Cc: linux-decnet-user@lists.sourceforge.net Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/dn_fib.h | 28 ++++++---------------------- 1 file changed, 6 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index 1ee9d4bda30d..74004af31c48 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -1,24 +1,9 @@ #ifndef _NET_DN_FIB_H #define _NET_DN_FIB_H -/* WARNING: The ordering of these elements must match ordering - * of RTA_* rtnetlink attribute numbers. - */ -struct dn_kern_rta { - void *rta_dst; - void *rta_src; - int *rta_iif; - int *rta_oif; - void *rta_gw; - u32 *rta_priority; - void *rta_prefsrc; - struct rtattr *rta_mx; - struct rtattr *rta_mp; - unsigned char *rta_protoinfo; - u32 *rta_flow; - struct rta_cacheinfo *rta_ci; - struct rta_session *rta_sess; -}; +#include + +extern const struct nla_policy rtm_dn_policy[]; struct dn_fib_res { struct fib_rule *r; @@ -93,10 +78,10 @@ struct dn_fib_table { u32 n; int (*insert)(struct dn_fib_table *t, struct rtmsg *r, - struct dn_kern_rta *rta, struct nlmsghdr *n, + struct nlattr *attrs[], struct nlmsghdr *n, struct netlink_skb_parms *req); int (*delete)(struct dn_fib_table *t, struct rtmsg *r, - struct dn_kern_rta *rta, struct nlmsghdr *n, + struct nlattr *attrs[], struct nlmsghdr *n, struct netlink_skb_parms *req); int (*lookup)(struct dn_fib_table *t, const struct flowidn *fld, struct dn_fib_res *res); @@ -116,13 +101,12 @@ extern void dn_fib_cleanup(void); extern int dn_fib_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); extern struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, - struct dn_kern_rta *rta, + struct nlattr *attrs[], const struct nlmsghdr *nlh, int *errp); extern int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn *fld, struct dn_fib_res *res); extern void dn_fib_release_info(struct dn_fib_info *fi); -extern __le16 dn_fib_get_attr16(struct rtattr *attr, int attrlen, int type); extern void dn_fib_flush(void); extern void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res); -- cgit v1.2.3 From 661d2967b3f1b34eeaa7e212e7b9bbe8ee072b59 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 21 Mar 2013 07:45:29 +0000 Subject: rtnetlink: Remove passing of attributes into rtnl_doit functions With decnet converted, we can finally get rid of rta_buf and its computations around it. It also gets rid of the minimal header length verification since all message handlers do that explicitly anyway. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 5a15fabd6a75..702664833a53 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -4,7 +4,7 @@ #include #include -typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, void *); +typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *); typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); typedef u16 (*rtnl_calcit_func)(struct sk_buff *, struct nlmsghdr *); -- cgit v1.2.3 From 63998ac24f8370caf99e433483532bab8368eb7e Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 22 Mar 2013 06:28:43 +0000 Subject: ipv6: provide addr and netconf dump consistency info This patch adds a dev_addr_genid for IPv6. The goal is to use it, combined with dev_base_seq to check if a change occurs during a netlink dump. If a change is detected, the flag NLM_F_DUMP_INTR is set in the first message after the dump was interrupted. Note that only dump of unicast addresses is checked (multicast and anycast are not checked). Reported-by: Junwei Zhang Reported-by: Hongjun Li Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/netns/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 1242f371718b..005e2c2e39a9 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -71,6 +71,7 @@ struct netns_ipv6 { struct fib_rules_ops *mr6_rules_ops; #endif #endif + atomic_t dev_addr_genid; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) -- cgit v1.2.3 From be991971d53e0f5b6d13e3940192054216590072 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 22 Mar 2013 08:24:37 +0000 Subject: inet: generalize ipv4-only RFC3168 5.3 ecn fragmentation handling for future use by ipv6 This patch just moves some code arround to make the ip4_frag_ecn_table and IPFRAG_ECN_* constants accessible from the other reassembly engines. I also renamed ip4_frag_ecn_table to ip_frag_ecn_table. Cc: Eric Dumazet Cc: Jesper Dangaard Brouer Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Acked-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/inet_frag.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 0a1dcc2fa2f5..64b4e7d23b8a 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -153,4 +153,16 @@ static inline void inet_frag_lru_add(struct netns_frags *nf, list_add_tail(&q->lru_list, &nf->lru_list); spin_unlock(&nf->lru_lock); } + +/* RFC 3168 support : + * We want to check ECN values of all fragments, do detect invalid combinations. + * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value. + */ +#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */ +#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */ +#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */ +#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */ + +extern const u8 ip_frag_ecn_table[16]; + #endif -- cgit v1.2.3 From eec2e6185ff6eab18c2cae9b01a9fbc5c33248fc Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 22 Mar 2013 08:24:44 +0000 Subject: ipv6: implement RFC3168 5.3 (ecn protection) for ipv6 fragmentation handling Hello! After patch 1 got accepted to net-next I will also send a patch to netfilter-devel to make the corresponding changes to the netfilter reassembly logic. Thanks, Hannes -- >8 -- [PATCH 2/2] ipv6: implement RFC3168 5.3 (ecn protection) for ipv6 fragmentation handling This patch also ensures that INET_ECN_CE is propagated if one fragment had the codepoint set. Cc: Eric Dumazet Cc: Jesper Dangaard Brouer Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Acked-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- 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 42ef6abf25c3..0810aa57c780 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -478,6 +478,7 @@ struct ip6_create_arg { u32 user; const struct in6_addr *src; const struct in6_addr *dst; + u8 ecn; }; void ip6_frag_init(struct inet_frag_queue *q, void *a); @@ -497,6 +498,7 @@ struct frag_queue { int iif; unsigned int csum; __u16 nhoffset; + u8 ecn; }; void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, -- cgit v1.2.3 From 8bf24293453a10a696bcd00abb1248e6365f66c2 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Mon, 25 Mar 2013 11:15:59 +0200 Subject: cfg80211: Document update_ft_ies() cfg80211_ops This was forgotten from the commit that added support for FT operations with drivers that implement SME. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index bdba9b619064..57870b646974 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1998,6 +1998,10 @@ struct cfg80211_update_ft_ies_params { * advertise the support for MAC based ACL have to implement this callback. * * @start_radar_detection: Start radar detection in the driver. + * + * @update_ft_ies: Provide updated Fast BSS Transition information to the + * driver. If the SME is in the driver/firmware, this information can be + * used in building Authentication and Reassociation Request frames. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); -- cgit v1.2.3 From 219c38674c262378ec411dd8318ebfd199fbce8d Mon Sep 17 00:00:00 2001 From: Alexander Bondar Date: Tue, 22 Jan 2013 16:52:23 +0200 Subject: mac80211: allow drivers to set default uAPSD parameters mac80211 currently sets uAPSD parameters to have VO AC trigger- and delivery-enabled, with maximum service period length. Allow drivers to change these default settings since different uAPSD client implementations may handle errors differently and be able to recover from some errors. Note: some APs may not function correctly if one or all ACs are trigger- and delivery-enabled, see http://thread.gmane.org/gmane.linux.kernel.wireless.general/93577. We retested with this AP and later firmware doesn't have this bug any more. Signed-off-by: Alexander Bondar Signed-off-by: Johannes Berg --- include/net/mac80211.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9b536172e27e..23a275a9a3b2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1534,6 +1534,17 @@ enum ieee80211_hw_flags { * @netdev_features: netdev features to be set in each netdev created * from this HW. Note only HW checksum features are currently * compatible with mac80211. Other feature bits will be rejected. + * + * @uapsd_queues: This bitmap is included in (re)association frame to indicate + * for each access category if it is uAPSD trigger-enabled and delivery- + * enabled. Use IEEE80211_WMM_IE_STA_QOSINFO_AC_* to set this bitmap. + * Each bit corresponds to different AC. Value '1' in specific bit means + * that corresponding AC is both trigger- and delivery-enabled. '0' means + * neither enabled. + * + * @uapsd_max_sp_len: maximum number of total buffered frames the WMM AP may + * deliver to a WMM STA during any Service Period triggered by the WMM STA. + * Use IEEE80211_WMM_IE_STA_QOSINFO_SP_* for correct values. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -1559,6 +1570,8 @@ struct ieee80211_hw { u8 radiotap_mcs_details; u16 radiotap_vht_details; netdev_features_t netdev_features; + u8 uapsd_queues; + u8 uapsd_max_sp_len; }; /** -- cgit v1.2.3 From 25c7704d8bdcf6746dab4397953df51759924b37 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sun, 24 Mar 2013 17:36:29 +0000 Subject: ipv4: Fix ip-header identification for gso packets. ip-header id needs to be incremented even if IP_DF flag is set. This behaviour was changed in commit 490ab08127cebc25e3a26 (IP_GRE: Fix IP-Identification). Following patch fixes it so that identification is always incremented. Reported-by: Cong Wang Acked-by: Cong Wang Signed-off-by: Pravin B Shelar --- include/net/ipip.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ipip.h b/include/net/ipip.h index 0c046e3bca05..483b91a10bb2 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -74,15 +74,11 @@ static inline void tunnel_ip_select_ident(struct sk_buff *skb, { struct iphdr *iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_DF)) - iph->id = 0; - else { - /* Use inner packet iph-id if possible. */ - if (skb->protocol == htons(ETH_P_IP) && old_iph->id) - iph->id = old_iph->id; - else - __ip_select_ident(iph, dst, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); - } + /* Use inner packet iph-id if possible. */ + if (skb->protocol == htons(ETH_P_IP) && old_iph->id) + iph->id = old_iph->id; + else + __ip_select_ident(iph, dst, + (skb_shinfo(skb)->gso_segs ?: 1) - 1); } #endif -- cgit v1.2.3 From 675a0b049abf6edf30f8dd84c5610b6edc2296c8 Mon Sep 17 00:00:00 2001 From: Karl Beldan Date: Mon, 25 Mar 2013 16:26:57 +0100 Subject: mac80211: Use a cfg80211_chan_def in ieee80211_hw_conf_chan Drivers that don't use chanctxes cannot perform VHT association because they still use a "backward compatibility" pair of {ieee80211_channel, nl80211_channel_type} in ieee80211_conf and ieee80211_local. Signed-off-by: Karl Beldan [fix kernel-doc] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 23a275a9a3b2..64faf015dd1e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -974,8 +974,7 @@ enum ieee80211_smps_mode { * @power_level: requested transmit power (in dBm), backward compatibility * value only that is set to the minimum of all interfaces * - * @channel: the channel to tune to - * @channel_type: the channel (HT) type + * @chandef: the channel definition to tune to * @radar_enabled: whether radar detection is enabled * * @long_frame_max_tx_count: Maximum number of transmissions for a "long" frame @@ -1001,8 +1000,7 @@ struct ieee80211_conf { u8 long_frame_max_tx_count, short_frame_max_tx_count; - struct ieee80211_channel *channel; - enum nl80211_channel_type channel_type; + struct cfg80211_chan_def chandef; bool radar_enabled; enum ieee80211_smps_mode smps_mode; }; @@ -4216,31 +4214,33 @@ void ieee80211_rate_control_unregister(struct rate_control_ops *ops); static inline bool conf_is_ht20(struct ieee80211_conf *conf) { - return conf->channel_type == NL80211_CHAN_HT20; + return conf->chandef.width == NL80211_CHAN_WIDTH_20; } static inline bool conf_is_ht40_minus(struct ieee80211_conf *conf) { - return conf->channel_type == NL80211_CHAN_HT40MINUS; + return conf->chandef.width == NL80211_CHAN_WIDTH_40 && + conf->chandef.center_freq1 < conf->chandef.chan->center_freq; } static inline bool conf_is_ht40_plus(struct ieee80211_conf *conf) { - return conf->channel_type == NL80211_CHAN_HT40PLUS; + return conf->chandef.width == NL80211_CHAN_WIDTH_40 && + conf->chandef.center_freq1 > conf->chandef.chan->center_freq; } static inline bool conf_is_ht40(struct ieee80211_conf *conf) { - return conf_is_ht40_minus(conf) || conf_is_ht40_plus(conf); + return conf->chandef.width == NL80211_CHAN_WIDTH_40; } static inline bool conf_is_ht(struct ieee80211_conf *conf) { - return conf->channel_type != NL80211_CHAN_NO_HT; + return conf->chandef.width != NL80211_CHAN_WIDTH_20_NOHT; } static inline enum nl80211_iftype -- cgit v1.2.3 From c5116e9d8d2de324f13a91fe5afc308cd6b0ca93 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 19 Mar 2013 16:58:58 +0100 Subject: ssb: define more board types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 51 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 8b1322296fed..c64999fd1660 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -340,13 +340,61 @@ enum ssb_bustype { #define SSB_BOARDVENDOR_DELL 0x1028 /* Dell */ #define SSB_BOARDVENDOR_HP 0x0E11 /* HP */ /* board_type */ +#define SSB_BOARD_BCM94301CB 0x0406 +#define SSB_BOARD_BCM94301MP 0x0407 +#define SSB_BOARD_BU4309 0x040A +#define SSB_BOARD_BCM94309CB 0x040B +#define SSB_BOARD_BCM4309MP 0x040C +#define SSB_BOARD_BU4306 0x0416 #define SSB_BOARD_BCM94306MP 0x0418 #define SSB_BOARD_BCM4309G 0x0421 #define SSB_BOARD_BCM4306CB 0x0417 -#define SSB_BOARD_BCM4309MP 0x040C +#define SSB_BOARD_BCM94306PC 0x0425 /* pcmcia 3.3v 4306 card */ +#define SSB_BOARD_BCM94306CBSG 0x042B /* with SiGe PA */ +#define SSB_BOARD_PCSG94306 0x042D /* with SiGe PA */ +#define SSB_BOARD_BU4704SD 0x042E /* with sdram */ +#define SSB_BOARD_BCM94704AGR 0x042F /* dual 11a/11g Router */ +#define SSB_BOARD_BCM94308MP 0x0430 /* 11a-only minipci */ +#define SSB_BOARD_BU4318 0x0447 +#define SSB_BOARD_CB4318 0x0448 +#define SSB_BOARD_MPG4318 0x0449 #define SSB_BOARD_MP4318 0x044A -#define SSB_BOARD_BU4306 0x0416 -#define SSB_BOARD_BU4309 0x040A +#define SSB_BOARD_SD4318 0x044B +#define SSB_BOARD_BCM94306P 0x044C /* with SiGe */ +#define SSB_BOARD_BCM94303MP 0x044E +#define SSB_BOARD_BCM94306MPM 0x0450 +#define SSB_BOARD_BCM94306MPL 0x0453 +#define SSB_BOARD_PC4303 0x0454 /* pcmcia */ +#define SSB_BOARD_BCM94306MPLNA 0x0457 +#define SSB_BOARD_BCM94306MPH 0x045B +#define SSB_BOARD_BCM94306PCIV 0x045C +#define SSB_BOARD_BCM94318MPGH 0x0463 +#define SSB_BOARD_BU4311 0x0464 +#define SSB_BOARD_BCM94311MC 0x0465 +#define SSB_BOARD_BCM94311MCAG 0x0466 +/* 4321 boards */ +#define SSB_BOARD_BU4321 0x046B +#define SSB_BOARD_BU4321E 0x047C +#define SSB_BOARD_MP4321 0x046C +#define SSB_BOARD_CB2_4321 0x046D +#define SSB_BOARD_CB2_4321_AG 0x0066 +#define SSB_BOARD_MC4321 0x046E +/* 4325 boards */ +#define SSB_BOARD_BCM94325DEVBU 0x0490 +#define SSB_BOARD_BCM94325BGABU 0x0491 +#define SSB_BOARD_BCM94325SDGWB 0x0492 +#define SSB_BOARD_BCM94325SDGMDL 0x04AA +#define SSB_BOARD_BCM94325SDGMDL2 0x04C6 +#define SSB_BOARD_BCM94325SDGMDL3 0x04C9 +#define SSB_BOARD_BCM94325SDABGWBA 0x04E1 +/* 4322 boards */ +#define SSB_BOARD_BCM94322MC 0x04A4 +#define SSB_BOARD_BCM94322USB 0x04A8 /* dualband */ +#define SSB_BOARD_BCM94322HM 0x04B0 +#define SSB_BOARD_BCM94322USB2D 0x04Bf /* single band discrete front end */ +/* 4312 boards */ +#define SSB_BOARD_BU4312 0x048A +#define SSB_BOARD_BCM4312MCGSG 0x04B5 /* chip_package */ #define SSB_CHIPPACK_BCM4712S 1 /* Small 200pin 4712 */ #define SSB_CHIPPACK_BCM4712M 2 /* Medium 225pin 4712 */ -- cgit v1.2.3 From 3e6998574fde0ab7a3329c9229394dd80462ead2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 19 Mar 2013 16:58:59 +0100 Subject: bcma: define board types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using that IDs we can write workarounds for various cards Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index e0ce311011c0..0ab6712fd76b 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -173,6 +173,60 @@ struct bcma_host_ops { #define BCMA_CHIP_ID_BCM53572 53572 #define BCMA_PKG_ID_BCM47188 9 +/* Board types (on PCI usually equals to the subsystem dev id) */ +/* BCM4313 */ +#define BCMA_BOARD_TYPE_BCM94313BU 0X050F +#define BCMA_BOARD_TYPE_BCM94313HM 0X0510 +#define BCMA_BOARD_TYPE_BCM94313EPA 0X0511 +#define BCMA_BOARD_TYPE_BCM94313HMG 0X051C +/* BCM4716 */ +#define BCMA_BOARD_TYPE_BCM94716NR2 0X04CD +/* BCM43224 */ +#define BCMA_BOARD_TYPE_BCM943224X21 0X056E +#define BCMA_BOARD_TYPE_BCM943224X21_FCC 0X00D1 +#define BCMA_BOARD_TYPE_BCM943224X21B 0X00E9 +#define BCMA_BOARD_TYPE_BCM943224M93 0X008B +#define BCMA_BOARD_TYPE_BCM943224M93A 0X0090 +#define BCMA_BOARD_TYPE_BCM943224X16 0X0093 +#define BCMA_BOARD_TYPE_BCM94322X9 0X008D +#define BCMA_BOARD_TYPE_BCM94322M35E 0X008E +/* BCM43228 */ +#define BCMA_BOARD_TYPE_BCM943228BU8 0X0540 +#define BCMA_BOARD_TYPE_BCM943228BU9 0X0541 +#define BCMA_BOARD_TYPE_BCM943228BU 0X0542 +#define BCMA_BOARD_TYPE_BCM943227HM4L 0X0543 +#define BCMA_BOARD_TYPE_BCM943227HMB 0X0544 +#define BCMA_BOARD_TYPE_BCM943228HM4L 0X0545 +#define BCMA_BOARD_TYPE_BCM943228SD 0X0573 +/* BCM4331 */ +#define BCMA_BOARD_TYPE_BCM94331X19 0X00D6 +#define BCMA_BOARD_TYPE_BCM94331X28 0X00E4 +#define BCMA_BOARD_TYPE_BCM94331X28B 0X010E +#define BCMA_BOARD_TYPE_BCM94331PCIEBT3AX 0X00E4 +#define BCMA_BOARD_TYPE_BCM94331X12_2G 0X00EC +#define BCMA_BOARD_TYPE_BCM94331X12_5G 0X00ED +#define BCMA_BOARD_TYPE_BCM94331X29B 0X00EF +#define BCMA_BOARD_TYPE_BCM94331CSAX 0X00EF +#define BCMA_BOARD_TYPE_BCM94331X19C 0X00F5 +#define BCMA_BOARD_TYPE_BCM94331X33 0X00F4 +#define BCMA_BOARD_TYPE_BCM94331BU 0X0523 +#define BCMA_BOARD_TYPE_BCM94331S9BU 0X0524 +#define BCMA_BOARD_TYPE_BCM94331MC 0X0525 +#define BCMA_BOARD_TYPE_BCM94331MCI 0X0526 +#define BCMA_BOARD_TYPE_BCM94331PCIEBT4 0X0527 +#define BCMA_BOARD_TYPE_BCM94331HM 0X0574 +#define BCMA_BOARD_TYPE_BCM94331PCIEDUAL 0X059B +#define BCMA_BOARD_TYPE_BCM94331MCH5 0X05A9 +#define BCMA_BOARD_TYPE_BCM94331CS 0X05C6 +#define BCMA_BOARD_TYPE_BCM94331CD 0X05DA +/* BCM53572 */ +#define BCMA_BOARD_TYPE_BCM953572BU 0X058D +#define BCMA_BOARD_TYPE_BCM953572NR2 0X058E +#define BCMA_BOARD_TYPE_BCM947188NR2 0X058F +#define BCMA_BOARD_TYPE_BCM953572SDRNR2 0X0590 +/* BCM43142 */ +#define BCMA_BOARD_TYPE_BCM943142HM 0X05E0 + struct bcma_device { struct bcma_bus *bus; struct bcma_device_id id; -- cgit v1.2.3 From 12bef78f0a806639daef58b1770be6ea19b2e94d Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Thu, 21 Mar 2013 16:26:19 +0100 Subject: ssb: fix sprom constant for ant_available_{bg,a} This was done accordingly to new specs. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/ssb/ssb_regs.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 6ecfa02ddbac..3a7256955b10 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -289,11 +289,11 @@ #define SSB_SPROM4_ETHPHY_ET1A_SHIFT 5 #define SSB_SPROM4_ETHPHY_ET0M (1<<14) /* MDIO for enet0 */ #define SSB_SPROM4_ETHPHY_ET1M (1<<15) /* MDIO for enet1 */ -#define SSB_SPROM4_ANTAVAIL 0x005D /* Antenna available bitfields */ -#define SSB_SPROM4_ANTAVAIL_A 0x00FF /* A-PHY bitfield */ -#define SSB_SPROM4_ANTAVAIL_A_SHIFT 0 -#define SSB_SPROM4_ANTAVAIL_BG 0xFF00 /* B-PHY and G-PHY bitfield */ -#define SSB_SPROM4_ANTAVAIL_BG_SHIFT 8 +#define SSB_SPROM4_ANTAVAIL 0x005C /* Antenna available bitfields */ +#define SSB_SPROM4_ANTAVAIL_BG 0x00FF /* B-PHY and G-PHY bitfield */ +#define SSB_SPROM4_ANTAVAIL_BG_SHIFT 0 +#define SSB_SPROM4_ANTAVAIL_A 0xFF00 /* A-PHY bitfield */ +#define SSB_SPROM4_ANTAVAIL_A_SHIFT 8 #define SSB_SPROM4_AGAIN01 0x005E /* Antenna Gain (in dBm Q5.2) */ #define SSB_SPROM4_AGAIN0 0x00FF /* Antenna 0 */ #define SSB_SPROM4_AGAIN0_SHIFT 0 -- cgit v1.2.3 From c54419321455631079c7d6e60bc732dd0c5914c5 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Mon, 25 Mar 2013 14:49:35 +0000 Subject: GRE: Refactor GRE tunneling code. Following patch refactors GRE code into ip tunneling code and GRE specific code. Common tunneling code is moved to ip_tunnel module. ip_tunnel module is written as generic library which can be used by different tunneling implementations. ip_tunnel module contains following components: - packet xmit and rcv generic code. xmit flow looks like (gre_xmit/ipip_xmit)->ip_tunnel_xmit->ip_local_out. - hash table of all devices. - lookup for tunnel devices. - control plane operations like device create, destroy, ioctl, netlink operations code. - registration for tunneling modules, like gre, ipip etc. - define single pcpu_tstats dev->tstats. - struct tnl_ptk_info added to pass parsed tunnel packet parameters. ipip.h header is renamed to ip_tunnel.h Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/net/gre.h | 51 ++++++++++++++ include/net/ip6_tunnel.h | 1 + include/net/ip_tunnels.h | 177 +++++++++++++++++++++++++++++++++++++++++++++++ include/net/ipip.h | 84 ---------------------- 4 files changed, 229 insertions(+), 84 deletions(-) create mode 100644 include/net/ip_tunnels.h delete mode 100644 include/net/ipip.h (limited to 'include') diff --git a/include/net/gre.h b/include/net/gre.h index 82665474bcb7..9f03a390c826 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -2,6 +2,7 @@ #define __LINUX_GRE_H #include +#include #define GREPROTO_CISCO 0 #define GREPROTO_PPTP 1 @@ -12,7 +13,57 @@ struct gre_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); }; +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +}; +#define GRE_HEADER_SECTION 4 + int gre_add_protocol(const struct gre_protocol *proto, u8 version); int gre_del_protocol(const struct gre_protocol *proto, u8 version); +static inline __be16 gre_flags_to_tnl_flags(__be16 flags) +{ + __be16 tflags = 0; + + if (flags & GRE_CSUM) + tflags |= TUNNEL_CSUM; + if (flags & GRE_ROUTING) + tflags |= TUNNEL_ROUTING; + if (flags & GRE_KEY) + tflags |= TUNNEL_KEY; + if (flags & GRE_SEQ) + tflags |= TUNNEL_SEQ; + if (flags & GRE_STRICT) + tflags |= TUNNEL_STRICT; + if (flags & GRE_REC) + tflags |= TUNNEL_REC; + if (flags & GRE_VERSION) + tflags |= TUNNEL_VERSION; + + return tflags; +} + +static inline __be16 tnl_flags_to_gre_flags(__be16 tflags) +{ + __be16 flags = 0; + + if (tflags & TUNNEL_CSUM) + flags |= GRE_CSUM; + if (tflags & TUNNEL_ROUTING) + flags |= GRE_ROUTING; + if (tflags & TUNNEL_KEY) + flags |= GRE_KEY; + if (tflags & TUNNEL_SEQ) + flags |= GRE_SEQ; + if (tflags & TUNNEL_STRICT) + flags |= GRE_STRICT; + if (tflags & TUNNEL_REC) + flags |= GRE_REC; + if (tflags & TUNNEL_VERSION) + flags |= GRE_VERSION; + + return flags; +} + #endif diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index ebdef7f60862..4da5de10d1d4 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -3,6 +3,7 @@ #include #include +#include #include #define IP6TUNNEL_ERR_TIMEO (30*HZ) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h new file mode 100644 index 000000000000..4b6f0b28f41f --- /dev/null +++ b/include/net/ip_tunnels.h @@ -0,0 +1,177 @@ +#ifndef __NET_IP_TUNNELS_H +#define __NET_IP_TUNNELS_H 1 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_IPV6) +#include +#include +#include +#endif + +/* Keep error state on tunnel for 30 sec */ +#define IPTUNNEL_ERR_TIMEO (30*HZ) + +/* 6rd prefix/relay information */ +#ifdef CONFIG_IPV6_SIT_6RD +struct ip_tunnel_6rd_parm { + struct in6_addr prefix; + __be32 relay_prefix; + u16 prefixlen; + u16 relay_prefixlen; +}; +#endif + +struct ip_tunnel_prl_entry { + struct ip_tunnel_prl_entry __rcu *next; + __be32 addr; + u16 flags; + struct rcu_head rcu_head; +}; + +struct ip_tunnel { + struct ip_tunnel __rcu *next; + struct hlist_node hash_node; + struct net_device *dev; + + int err_count; /* Number of arrived ICMP errors */ + unsigned long err_time; /* Time when the last ICMP error + * arrived */ + + /* These four fields used only by GRE */ + __u32 i_seqno; /* The last seen seqno */ + __u32 o_seqno; /* The last output seqno */ + int hlen; /* Precalculated header length */ + int mlink; + + struct ip_tunnel_parm parms; + + /* for SIT */ +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd_parm ip6rd; +#endif + struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ + unsigned int prl_count; /* # of entries in PRL */ + int ip_tnl_net_id; + struct gro_cells gro_cells; +}; + +#define TUNNEL_CSUM __cpu_to_be16(0x01) +#define TUNNEL_ROUTING __cpu_to_be16(0x02) +#define TUNNEL_KEY __cpu_to_be16(0x04) +#define TUNNEL_SEQ __cpu_to_be16(0x08) +#define TUNNEL_STRICT __cpu_to_be16(0x10) +#define TUNNEL_REC __cpu_to_be16(0x20) +#define TUNNEL_VERSION __cpu_to_be16(0x40) +#define TUNNEL_NO_KEY __cpu_to_be16(0x80) + +struct tnl_ptk_info { + __be16 flags; + __be16 proto; + __be32 key; + __be32 seq; +}; + +#define PACKET_RCVD 0 +#define PACKET_REJECT 1 + +#define IP_TNL_HASH_BITS 10 +#define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS) + +struct ip_tunnel_net { + struct hlist_head *tunnels; + struct net_device *fb_tunnel_dev; +}; + +int ip_tunnel_init(struct net_device *dev); +void ip_tunnel_uninit(struct net_device *dev); +void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); +int __net_init ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, + struct rtnl_link_ops *ops, char *devname); + +void __net_exit ip_tunnel_delete_net(struct ip_tunnel_net *itn); + +void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + const struct iphdr *tnl_params); +int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); + +struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot); +struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, + int link, __be16 flags, + __be32 remote, __be32 local, + __be32 key); + +int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, + const struct tnl_ptk_info *tpi, bool log_ecn_error); +int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], + struct ip_tunnel_parm *p); +int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], + struct ip_tunnel_parm *p); +void ip_tunnel_setup(struct net_device *dev, int net_id); + +/* Extract dsfield from inner protocol */ +static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, + const struct sk_buff *skb) +{ + if (skb->protocol == htons(ETH_P_IP)) + return iph->tos; + else if (skb->protocol == htons(ETH_P_IPV6)) + return ipv6_get_dsfield((const struct ipv6hdr *)iph); + else + return 0; +} + +/* Propogate ECN bits out */ +static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, + const struct sk_buff *skb) +{ + u8 inner = ip_tunnel_get_dsfield(iph, skb); + + return INET_ECN_encapsulate(tos, inner); +} + +static inline void tunnel_ip_select_ident(struct sk_buff *skb, + const struct iphdr *old_iph, + struct dst_entry *dst) +{ + struct iphdr *iph = ip_hdr(skb); + + /* Use inner packet iph-id if possible. */ + if (skb->protocol == htons(ETH_P_IP) && old_iph->id) + iph->id = old_iph->id; + else + __ip_select_ident(iph, dst, + (skb_shinfo(skb)->gso_segs ?: 1) - 1); +} + +static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + int err; + int pkt_len = skb->len - skb_transport_offset(skb); + struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); + + nf_reset(skb); + + err = ip_local_out(skb); + if (likely(net_xmit_eval(err) == 0)) { + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; + } +} +#endif /* __NET_IP_TUNNELS_H */ diff --git a/include/net/ipip.h b/include/net/ipip.h deleted file mode 100644 index 483b91a10bb2..000000000000 --- a/include/net/ipip.h +++ /dev/null @@ -1,84 +0,0 @@ -#ifndef __NET_IPIP_H -#define __NET_IPIP_H 1 - -#include -#include -#include - -/* Keep error state on tunnel for 30 sec */ -#define IPTUNNEL_ERR_TIMEO (30*HZ) - -/* 6rd prefix/relay information */ -struct ip_tunnel_6rd_parm { - struct in6_addr prefix; - __be32 relay_prefix; - u16 prefixlen; - u16 relay_prefixlen; -}; - -struct ip_tunnel { - struct ip_tunnel __rcu *next; - struct net_device *dev; - - int err_count; /* Number of arrived ICMP errors */ - unsigned long err_time; /* Time when the last ICMP error arrived */ - - /* These four fields used only by GRE */ - __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ - int hlen; /* Precalculated GRE header length */ - int mlink; - - struct ip_tunnel_parm parms; - - /* for SIT */ -#ifdef CONFIG_IPV6_SIT_6RD - struct ip_tunnel_6rd_parm ip6rd; -#endif - struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ - unsigned int prl_count; /* # of entries in PRL */ - - struct gro_cells gro_cells; -}; - -struct ip_tunnel_prl_entry { - struct ip_tunnel_prl_entry __rcu *next; - __be32 addr; - u16 flags; - struct rcu_head rcu_head; -}; - -static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev) -{ - int err; - int pkt_len = skb->len - skb_transport_offset(skb); - struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); - - nf_reset(skb); - - err = ip_local_out(skb); - if (likely(net_xmit_eval(err) == 0)) { - u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; - u64_stats_update_end(&tstats->syncp); - } else { - dev->stats.tx_errors++; - dev->stats.tx_aborted_errors++; - } -} - -static inline void tunnel_ip_select_ident(struct sk_buff *skb, - const struct iphdr *old_iph, - struct dst_entry *dst) -{ - struct iphdr *iph = ip_hdr(skb); - - /* Use inner packet iph-id if possible. */ - if (skb->protocol == htons(ETH_P_IP) && old_iph->id) - iph->id = old_iph->id; - else - __ip_select_ident(iph, dst, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); -} -#endif -- cgit v1.2.3 From 6752c8db8e0cfedb44ba62806dd15b383ed64000 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?YOSHIFUJI=20Hideaki=20/=20=E5=90=89=E8=97=A4=E8=8B=B1?= =?UTF-8?q?=E6=98=8E?= Date: Mon, 25 Mar 2013 08:26:16 +0000 Subject: firewire net, ipv4 arp: Extend hardware address and remove driver-level packet inspection. Inspection of upper layer protocol is considered harmful, especially if it is about ARP or other stateful upper layer protocol; driver cannot (and should not) have full state of them. IPv4 over Firewire module used to inspect ARP (both in sending path and in receiving path), and record peer's GUID, max packet size, max speed and fifo address. This patch removes such inspection by extending our "hardware address" definition to include other information as well: max packet size, max speed and fifo. By doing this, The neighbour module in networking subsystem can cache them. Note: As we have started ignoring sspd and max_rec in ARP/NDP, those information will not be used in the driver when sending. When a packet is being sent, the IP layer fills our pseudo header with the extended "hardware address", including GUID and fifo. The driver can look-up node-id (the real but rather volatile low-level address) by GUID, and then the module can send the packet to the wire using parameters provided in the extendedn hardware address. This approach is realistic because IP over IEEE1394 (RFC2734) and IPv6 over IEEE1394 (RFC3146) share same "hardware address" format in their address resolution protocols. Here, extended "hardware address" is defined as follows: union fwnet_hwaddr { u8 u[16]; struct { __be64 uniq_id; /* EUI-64 */ u8 max_rec; /* max packet size */ u8 sspd; /* max speed */ __be16 fifo_hi; /* hi 16bits of FIFO addr */ __be32 fifo_lo; /* lo 32bits of FIFO addr */ } __packed uc; }; Note that Hardware address is declared as union, so that we can map full IP address into this, when implementing MCAP (Multicast Cannel Allocation Protocol) for IPv6, but IP and ARP subsystem do not need to know this format in detail. One difference between original ARP (RFC826) and 1394 ARP (RFC2734) is that 1394 ARP Request/Reply do not contain the target hardware address field (aka ar$tha). This difference is handled in the ARP subsystem. CC: Stephan Gatzka Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/if_arp.h | 12 ++++++++++-- include/net/firewire.h | 25 +++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 2 deletions(-) create mode 100644 include/net/firewire.h (limited to 'include') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 89b4614a4722..f563907ed776 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -33,7 +33,15 @@ static inline struct arphdr *arp_hdr(const struct sk_buff *skb) static inline int arp_hdr_len(struct net_device *dev) { - /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ - return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; + switch (dev->type) { +#if IS_ENABLED(CONFIG_FIREWIRE_NET) + case ARPHRD_IEEE1394: + /* ARP header, device address and 2 IP addresses */ + return sizeof(struct arphdr) + dev->addr_len + sizeof(u32) * 2; +#endif + default: + /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ + return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; + } } #endif /* _LINUX_IF_ARP_H */ diff --git a/include/net/firewire.h b/include/net/firewire.h new file mode 100644 index 000000000000..31bcbfe7a220 --- /dev/null +++ b/include/net/firewire.h @@ -0,0 +1,25 @@ +#ifndef _NET_FIREWIRE_H +#define _NET_FIREWIRE_H + +/* Pseudo L2 address */ +#define FWNET_ALEN 16 +union fwnet_hwaddr { + u8 u[FWNET_ALEN]; + /* "Hardware address" defined in RFC2734/RF3146 */ + struct { + __be64 uniq_id; /* EUI-64 */ + u8 max_rec; /* max packet size */ + u8 sspd; /* max speed */ + __be16 fifo_hi; /* hi 16bits of FIFO addr */ + __be32 fifo_lo; /* lo 32bits of FIFO addr */ + } __packed uc; +}; + +/* Pseudo L2 Header */ +#define FWNET_HLEN 18 +struct fwnet_header { + u8 h_dest[FWNET_ALEN]; /* destination address */ + __be16 h_proto; /* packet type ID field */ +} __packed; + +#endif -- cgit v1.2.3 From a88b9ce5ad4fc633b159b37d3ed8af60a4008fbc Mon Sep 17 00:00:00 2001 From: Hong zhi guo Date: Mon, 25 Mar 2013 19:04:05 +0000 Subject: netlink: remove duplicated NLMSG_ALIGN NLMSG_HDRLEN is already aligned value. It's for directly reference without extra alignment. The redundant alignment here may confuse the API users. Signed-off-by: Hong Zhiguo Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 78d5b8a546d6..32a354f67ba4 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -78,7 +78,7 @@ struct nlmsghdr { #define NLMSG_ALIGNTO 4U #define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) #define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) -#define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(NLMSG_HDRLEN)) +#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) #define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) #define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) #define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ -- cgit v1.2.3 From 5203cd28db6dc05c3618a602cf4cf81203d00257 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 26 Mar 2013 23:11:21 +0000 Subject: net: core: introduce skb_probe_transport_header() Sometimes, we need probe and set the transport header for packets (e.g from untrusted source). This patch introduces a new helper skb_probe_transport_header() which tries to probe and set the l4 header through skb_flow_dissect(), if not just set the transport header to the hint passed by caller. Cc: Eric Dumazet Signed-off-by: Jason Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 497412165b1c..fa88b966cb8e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,6 +32,7 @@ #include #include #include +#include /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 @@ -1559,6 +1560,19 @@ static inline void skb_set_transport_header(struct sk_buff *skb, skb->transport_header += offset; } +static inline void skb_probe_transport_header(struct sk_buff *skb, + const int offset_hint) +{ + struct flow_keys keys; + + if (skb_transport_header_was_set(skb)) + return; + else if (skb_flow_dissect(skb, &keys)) + skb_set_transport_header(skb, keys.thoff); + else + skb_set_transport_header(skb, offset_hint); +} + static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; -- cgit v1.2.3 From 1b5ab0def4f6e42e8b8097c3b11d2e8d96baafec Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 27 Mar 2013 05:55:56 +0000 Subject: net: use the frag lru_lock to protect netns_frags.nqueues update Move the protection of netns_frags.nqueues updates under the LRU_lock, instead of the write lock. As they are located on the same cacheline, and this is also needed when transitioning to use per hash bucket locking. Signed-off-by: Jesper Dangaard Brouer Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 64b4e7d23b8a..7cac9c5789b5 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -143,6 +143,7 @@ static inline void inet_frag_lru_del(struct inet_frag_queue *q) { spin_lock(&q->net->lru_lock); list_del(&q->lru_list); + q->net->nqueues--; spin_unlock(&q->net->lru_lock); } @@ -151,6 +152,7 @@ static inline void inet_frag_lru_add(struct netns_frags *nf, { spin_lock(&nf->lru_lock); list_add_tail(&q->lru_list, &nf->lru_list); + q->net->nqueues++; spin_unlock(&nf->lru_lock); } -- cgit v1.2.3 From d6b688cf2f7ca3e168acc73597f4d7102ae663fa Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Wed, 27 Mar 2013 17:23:10 +0100 Subject: bcma: handle more devices in bcma_pmu_get_alp_clock() Add some more chip IDs to bcma_pmu_get_alp_clock() Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 8390c474f69a..1db4c6de372e 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -104,6 +104,7 @@ #define BCMA_CC_CHIPST_4706_MIPS_BENDIAN BIT(3) /* 0: little, 1: big endian */ #define BCMA_CC_CHIPST_4706_PCIE1_DISABLE BIT(5) /* PCIE1 enable strap pin */ #define BCMA_CC_CHIPST_5357_NAND_BOOT BIT(4) /* NAND boot, valid for CC rev 38 and/or BCM5357 */ +#define BCMA_CC_CHIPST_4360_XTAL_40MZ 0x00000001 #define BCMA_CC_JCMD 0x0030 /* Rev >= 10 only */ #define BCMA_CC_JCMD_START 0x80000000 #define BCMA_CC_JCMD_BUSY 0x80000000 -- cgit v1.2.3 From 6951618b4b0bb022429ab17d49f2fa3650f21cb4 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Wed, 27 Mar 2013 17:23:11 +0100 Subject: bcma: export bcma_chipco_get_alp_clock() This function will be used by brcmsmac. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 1db4c6de372e..453fcc914683 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -608,6 +608,8 @@ void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable); extern u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks); +extern u32 bcma_chipco_get_alp_clock(struct bcma_drv_cc *cc); + void bcma_chipco_irq_mask(struct bcma_drv_cc *cc, u32 mask, u32 value); u32 bcma_chipco_irq_status(struct bcma_drv_cc *cc, u32 mask); -- cgit v1.2.3 From fbbdb8f096e0e5d8244e1ffa46e364146ab9a440 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 27 Mar 2013 16:46:06 +0000 Subject: net: fix compile error of implicit declaration of skb_probe_transport_header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit 40893fd(net: switch to use skb_probe_transport_header()) involes a new error accidently. When NET_SKBUFF_DATA_USES_OFFSE is not enabled, below compile error happens: CC net/packet/af_packet.o net/packet/af_packet.c: In function ‘packet_sendmsg_spkt’: net/packet/af_packet.c:1516:2: error: implicit declaration of function ‘skb_probe_transport_header’ [-Werror=implicit-function-declaration] cc1: some warnings being treated as errors make[2]: *** [net/packet/af_packet.o] Error 1 make[1]: *** [net/packet] Error 2 make: *** [net] Error 2 As it seems skb_probe_transport_header() is not related to NET_SKBUFF_DATA_USES_OFFSE, we should move the definition of skb_probe_transport_header() out of scope of NET_SKBUFF_DATA_USES_OFFSE macro. Cc: Jason Wang Cc: Eric Dumazet Signed-off-by: Ying Xue Acked-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fa88b966cb8e..878e0ee81068 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1560,19 +1560,6 @@ static inline void skb_set_transport_header(struct sk_buff *skb, skb->transport_header += offset; } -static inline void skb_probe_transport_header(struct sk_buff *skb, - const int offset_hint) -{ - struct flow_keys keys; - - if (skb_transport_header_was_set(skb)) - return; - else if (skb_flow_dissect(skb, &keys)) - skb_set_transport_header(skb, keys.thoff); - else - skb_set_transport_header(skb, offset_hint); -} - static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; @@ -1716,6 +1703,19 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline void skb_probe_transport_header(struct sk_buff *skb, + const int offset_hint) +{ + struct flow_keys keys; + + if (skb_transport_header_was_set(skb)) + return; + else if (skb_flow_dissect(skb, &keys)) + skb_set_transport_header(skb, keys.thoff); + else + skb_set_transport_header(skb, offset_hint); +} + static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { -- cgit v1.2.3 From f3d4039242af92a9d93dee2fd9ae47066b20ca29 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Wed, 27 Mar 2013 10:52:28 +0000 Subject: tokenring: delete last holdout of CONFIG_TR Tokenring support was deleted in v3.5. One last holdout of the macro CONFIG_TR escaped that fate. Until now. Signed-off-by: Paul Bolle Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 56e3e0665272..1dbb02c98946 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -144,8 +144,6 @@ static inline bool dev_xmit_complete(int rc) # else # define LL_MAX_HEADER 96 # endif -#elif IS_ENABLED(CONFIG_TR) -# define LL_MAX_HEADER 48 #else # define LL_MAX_HEADER 32 #endif -- cgit v1.2.3 From e5c5d22e8dcf7c2d430336cbf8e180bd38e8daf1 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 28 Mar 2013 13:38:25 +0900 Subject: net: add ETH_P_802_3_MIN Add a new constant ETH_P_802_3_MIN, the minimum ethernet type for an 802.3 frame. Frames with a lower value in the ethernet type field are Ethernet II. Also update all the users of this value that David Miller and I could find to use the new constant. Also correct a bug in util.c. The comparison with ETH_P_802_3_MIN should be >= not >. As suggested by Jesse Gross. Compile tested only. Cc: David Miller Cc: Jesse Gross Cc: Karsten Keil Cc: John W. Linville Cc: Johannes Berg Cc: Bart De Schuymer Cc: Stephen Hemminger Cc: Patrick McHardy Cc: Marcel Holtmann Cc: Gustavo Padovan Cc: Johan Hedberg Cc: linux-bluetooth@vger.kernel.org Cc: netfilter-devel@vger.kernel.org Cc: bridge@lists.linux-foundation.org Cc: linux-wireless@vger.kernel.org Cc: linux1394-devel@lists.sourceforge.net Cc: linux-media@vger.kernel.org Cc: netdev@vger.kernel.org Cc: dev@openvswitch.org Acked-by: Mauro Carvalho Chehab Acked-by: Stefan Richter Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 +- include/uapi/linux/if_ether.h | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 218a3b686d90..70962f3fdb79 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -339,7 +339,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, */ proto = vhdr->h_vlan_encapsulated_proto; - if (ntohs(proto) >= 1536) { + if (ntohs(proto) >= ETH_P_802_3_MIN) { skb->protocol = proto; return; } diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 798032d01112..ade07f1c491a 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -94,6 +94,9 @@ #define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is less than this value + * then the frame is Ethernet II. Else it is 802.3 */ + /* * Non DIX types. Won't clash for 1500 types. */ -- cgit v1.2.3 From a3f109bd793dfe5c611220ca5ab6c72f1aed479e Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Thu, 28 Mar 2013 11:51:31 +0000 Subject: sh_eth: add R-Car support for real Commit d0418bb7123f44b23d69ac349eec7daf9103472f (net: sh_eth: Add eth support for R8A7779 device) was a failed attempt to add support for one of members of the R-Car SoC family. That's for three reasons: it treated R8A7779 the same as SH7724 except including quite dirty hack adding ECMR_ELB bit to the mask in sh_eth_set_rate() while not removing ECMR_RTM bit (despite it's reserved in R-Car Ether), and it didn't add a new register offset array despite the closest SH_ETH_REG_FAST_SH4 mapping differs by 0x200 to the offsets all the R-Car Ether registers have, and also some of the registers in this old mapping don't exist on R-Car Ether (due to this, SH7724's 'sh_eth_my_cpu_data' structure is not adequeate for R-Car too). Fix all these shortcomings, restoring the SH7724 related section to its pristine state... Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- include/linux/sh_eth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index b17d765ded84..fc305713fc6d 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -6,6 +6,7 @@ enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; enum { SH_ETH_REG_GIGABIT, + SH_ETH_REG_FAST_RCAR, SH_ETH_REG_FAST_SH4, SH_ETH_REG_FAST_SH3_SH2 }; -- cgit v1.2.3 From 14b57a10553b5b768f77b247e6dd285c65816064 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 29 Mar 2013 14:46:51 +0100 Subject: openvswitch: Use ETH_ALEN to define ethernet addresses Signed-off-by: Thomas Graf Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index 67d6c7b03581..8b9d7217eddc 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -20,6 +20,7 @@ #define _LINUX_OPENVSWITCH_H 1 #include +#include /** * struct ovs_header - header for OVS Generic Netlink messages. @@ -269,8 +270,8 @@ enum ovs_frag_type { #define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1) struct ovs_key_ethernet { - __u8 eth_src[6]; - __u8 eth_dst[6]; + __u8 eth_src[ETH_ALEN]; + __u8 eth_dst[ETH_ALEN]; }; struct ovs_key_ipv4 { @@ -316,14 +317,14 @@ struct ovs_key_arp { __be32 arp_sip; __be32 arp_tip; __be16 arp_op; - __u8 arp_sha[6]; - __u8 arp_tha[6]; + __u8 arp_sha[ETH_ALEN]; + __u8 arp_tha[ETH_ALEN]; }; struct ovs_key_nd { __u32 nd_target[4]; - __u8 nd_sll[6]; - __u8 nd_tll[6]; + __u8 nd_sll[ETH_ALEN]; + __u8 nd_tll[ETH_ALEN]; }; /** -- cgit v1.2.3 From 22e3880a76bb9a0c4fa5c8fefdc8697a36a4dae1 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 29 Mar 2013 14:46:52 +0100 Subject: openvswitch: Expose to userspace It contains the public netlink interface bits required by userspace to make use of the interface. Signed-off-by: Thomas Graf Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 433 +------------------------------------ include/uapi/linux/Kbuild | 1 + include/uapi/linux/openvswitch.h | 456 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 458 insertions(+), 432 deletions(-) create mode 100644 include/uapi/linux/openvswitch.h (limited to 'include') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index 8b9d7217eddc..e6b240b6196c 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -19,437 +19,6 @@ #ifndef _LINUX_OPENVSWITCH_H #define _LINUX_OPENVSWITCH_H 1 -#include -#include - -/** - * struct ovs_header - header for OVS Generic Netlink messages. - * @dp_ifindex: ifindex of local port for datapath (0 to make a request not - * specific to a datapath). - * - * Attributes following the header are specific to a particular OVS Generic - * Netlink family, but all of the OVS families use this header. - */ - -struct ovs_header { - int dp_ifindex; -}; - -/* Datapaths. */ - -#define OVS_DATAPATH_FAMILY "ovs_datapath" -#define OVS_DATAPATH_MCGROUP "ovs_datapath" -#define OVS_DATAPATH_VERSION 0x1 - -enum ovs_datapath_cmd { - OVS_DP_CMD_UNSPEC, - OVS_DP_CMD_NEW, - OVS_DP_CMD_DEL, - OVS_DP_CMD_GET, - OVS_DP_CMD_SET -}; - -/** - * enum ovs_datapath_attr - attributes for %OVS_DP_* commands. - * @OVS_DP_ATTR_NAME: Name of the network device that serves as the "local - * port". This is the name of the network device whose dp_ifindex is given in - * the &struct ovs_header. Always present in notifications. Required in - * %OVS_DP_NEW requests. May be used as an alternative to specifying - * dp_ifindex in other requests (with a dp_ifindex of 0). - * @OVS_DP_ATTR_UPCALL_PID: The Netlink socket in userspace that is initially - * set on the datapath port (for OVS_ACTION_ATTR_MISS). Only valid on - * %OVS_DP_CMD_NEW requests. A value of zero indicates that upcalls should - * not be sent. - * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the - * datapath. Always present in notifications. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_DP_* commands. - */ -enum ovs_datapath_attr { - OVS_DP_ATTR_UNSPEC, - OVS_DP_ATTR_NAME, /* name of dp_ifindex netdev */ - OVS_DP_ATTR_UPCALL_PID, /* Netlink PID to receive upcalls */ - OVS_DP_ATTR_STATS, /* struct ovs_dp_stats */ - __OVS_DP_ATTR_MAX -}; - -#define OVS_DP_ATTR_MAX (__OVS_DP_ATTR_MAX - 1) - -struct ovs_dp_stats { - __u64 n_hit; /* Number of flow table matches. */ - __u64 n_missed; /* Number of flow table misses. */ - __u64 n_lost; /* Number of misses not sent to userspace. */ - __u64 n_flows; /* Number of flows present */ -}; - -struct ovs_vport_stats { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ -}; - -/* Fixed logical ports. */ -#define OVSP_LOCAL ((__u32)0) - -/* Packet transfer. */ - -#define OVS_PACKET_FAMILY "ovs_packet" -#define OVS_PACKET_VERSION 0x1 - -enum ovs_packet_cmd { - OVS_PACKET_CMD_UNSPEC, - - /* Kernel-to-user notifications. */ - OVS_PACKET_CMD_MISS, /* Flow table miss. */ - OVS_PACKET_CMD_ACTION, /* OVS_ACTION_ATTR_USERSPACE action. */ - - /* Userspace commands. */ - OVS_PACKET_CMD_EXECUTE /* Apply actions to a packet. */ -}; - -/** - * enum ovs_packet_attr - attributes for %OVS_PACKET_* commands. - * @OVS_PACKET_ATTR_PACKET: Present for all notifications. Contains the entire - * packet as received, from the start of the Ethernet header onward. For - * %OVS_PACKET_CMD_ACTION, %OVS_PACKET_ATTR_PACKET reflects changes made by - * actions preceding %OVS_ACTION_ATTR_USERSPACE, but %OVS_PACKET_ATTR_KEY is - * the flow key extracted from the packet as originally received. - * @OVS_PACKET_ATTR_KEY: Present for all notifications. Contains the flow key - * extracted from the packet as nested %OVS_KEY_ATTR_* attributes. This allows - * userspace to adapt its flow setup strategy by comparing its notion of the - * flow key against the kernel's. - * @OVS_PACKET_ATTR_ACTIONS: Contains actions for the packet. Used - * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes. - * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION - * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an - * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content - * specified there. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_PACKET_* commands. - */ -enum ovs_packet_attr { - OVS_PACKET_ATTR_UNSPEC, - OVS_PACKET_ATTR_PACKET, /* Packet data. */ - OVS_PACKET_ATTR_KEY, /* Nested OVS_KEY_ATTR_* attributes. */ - OVS_PACKET_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - OVS_PACKET_ATTR_USERDATA, /* OVS_ACTION_ATTR_USERSPACE arg. */ - __OVS_PACKET_ATTR_MAX -}; - -#define OVS_PACKET_ATTR_MAX (__OVS_PACKET_ATTR_MAX - 1) - -/* Virtual ports. */ - -#define OVS_VPORT_FAMILY "ovs_vport" -#define OVS_VPORT_MCGROUP "ovs_vport" -#define OVS_VPORT_VERSION 0x1 - -enum ovs_vport_cmd { - OVS_VPORT_CMD_UNSPEC, - OVS_VPORT_CMD_NEW, - OVS_VPORT_CMD_DEL, - OVS_VPORT_CMD_GET, - OVS_VPORT_CMD_SET -}; - -enum ovs_vport_type { - OVS_VPORT_TYPE_UNSPEC, - OVS_VPORT_TYPE_NETDEV, /* network device */ - OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */ - __OVS_VPORT_TYPE_MAX -}; - -#define OVS_VPORT_TYPE_MAX (__OVS_VPORT_TYPE_MAX - 1) - -/** - * enum ovs_vport_attr - attributes for %OVS_VPORT_* commands. - * @OVS_VPORT_ATTR_PORT_NO: 32-bit port number within datapath. - * @OVS_VPORT_ATTR_TYPE: 32-bit %OVS_VPORT_TYPE_* constant describing the type - * of vport. - * @OVS_VPORT_ATTR_NAME: Name of vport. For a vport based on a network device - * this is the name of the network device. Maximum length %IFNAMSIZ-1 bytes - * plus a null terminator. - * @OVS_VPORT_ATTR_OPTIONS: Vport-specific configuration information. - * @OVS_VPORT_ATTR_UPCALL_PID: The Netlink socket in userspace that - * OVS_PACKET_CMD_MISS upcalls will be directed to for packets received on - * this port. A value of zero indicates that upcalls should not be sent. - * @OVS_VPORT_ATTR_STATS: A &struct ovs_vport_stats giving statistics for - * packets sent or received through the vport. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_VPORT_* commands. - * - * For %OVS_VPORT_CMD_NEW requests, the %OVS_VPORT_ATTR_TYPE and - * %OVS_VPORT_ATTR_NAME attributes are required. %OVS_VPORT_ATTR_PORT_NO is - * optional; if not specified a free port number is automatically selected. - * Whether %OVS_VPORT_ATTR_OPTIONS is required or optional depends on the type - * of vport. - * and other attributes are ignored. - * - * For other requests, if %OVS_VPORT_ATTR_NAME is specified then it is used to - * look up the vport to operate on; otherwise dp_idx from the &struct - * ovs_header plus %OVS_VPORT_ATTR_PORT_NO determine the vport. - */ -enum ovs_vport_attr { - OVS_VPORT_ATTR_UNSPEC, - OVS_VPORT_ATTR_PORT_NO, /* u32 port number within datapath */ - OVS_VPORT_ATTR_TYPE, /* u32 OVS_VPORT_TYPE_* constant. */ - OVS_VPORT_ATTR_NAME, /* string name, up to IFNAMSIZ bytes long */ - OVS_VPORT_ATTR_OPTIONS, /* nested attributes, varies by vport type */ - OVS_VPORT_ATTR_UPCALL_PID, /* u32 Netlink PID to receive upcalls */ - OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */ - __OVS_VPORT_ATTR_MAX -}; - -#define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1) - -/* Flows. */ - -#define OVS_FLOW_FAMILY "ovs_flow" -#define OVS_FLOW_MCGROUP "ovs_flow" -#define OVS_FLOW_VERSION 0x1 - -enum ovs_flow_cmd { - OVS_FLOW_CMD_UNSPEC, - OVS_FLOW_CMD_NEW, - OVS_FLOW_CMD_DEL, - OVS_FLOW_CMD_GET, - OVS_FLOW_CMD_SET -}; - -struct ovs_flow_stats { - __u64 n_packets; /* Number of matched packets. */ - __u64 n_bytes; /* Number of matched bytes. */ -}; - -enum ovs_key_attr { - OVS_KEY_ATTR_UNSPEC, - OVS_KEY_ATTR_ENCAP, /* Nested set of encapsulated attributes. */ - OVS_KEY_ATTR_PRIORITY, /* u32 skb->priority */ - OVS_KEY_ATTR_IN_PORT, /* u32 OVS dp port number */ - OVS_KEY_ATTR_ETHERNET, /* struct ovs_key_ethernet */ - OVS_KEY_ATTR_VLAN, /* be16 VLAN TCI */ - OVS_KEY_ATTR_ETHERTYPE, /* be16 Ethernet type */ - OVS_KEY_ATTR_IPV4, /* struct ovs_key_ipv4 */ - OVS_KEY_ATTR_IPV6, /* struct ovs_key_ipv6 */ - OVS_KEY_ATTR_TCP, /* struct ovs_key_tcp */ - OVS_KEY_ATTR_UDP, /* struct ovs_key_udp */ - OVS_KEY_ATTR_ICMP, /* struct ovs_key_icmp */ - OVS_KEY_ATTR_ICMPV6, /* struct ovs_key_icmpv6 */ - OVS_KEY_ATTR_ARP, /* struct ovs_key_arp */ - OVS_KEY_ATTR_ND, /* struct ovs_key_nd */ - OVS_KEY_ATTR_SKB_MARK, /* u32 skb mark */ - __OVS_KEY_ATTR_MAX -}; - -#define OVS_KEY_ATTR_MAX (__OVS_KEY_ATTR_MAX - 1) - -/** - * enum ovs_frag_type - IPv4 and IPv6 fragment type - * @OVS_FRAG_TYPE_NONE: Packet is not a fragment. - * @OVS_FRAG_TYPE_FIRST: Packet is a fragment with offset 0. - * @OVS_FRAG_TYPE_LATER: Packet is a fragment with nonzero offset. - * - * Used as the @ipv4_frag in &struct ovs_key_ipv4 and as @ipv6_frag &struct - * ovs_key_ipv6. - */ -enum ovs_frag_type { - OVS_FRAG_TYPE_NONE, - OVS_FRAG_TYPE_FIRST, - OVS_FRAG_TYPE_LATER, - __OVS_FRAG_TYPE_MAX -}; - -#define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1) - -struct ovs_key_ethernet { - __u8 eth_src[ETH_ALEN]; - __u8 eth_dst[ETH_ALEN]; -}; - -struct ovs_key_ipv4 { - __be32 ipv4_src; - __be32 ipv4_dst; - __u8 ipv4_proto; - __u8 ipv4_tos; - __u8 ipv4_ttl; - __u8 ipv4_frag; /* One of OVS_FRAG_TYPE_*. */ -}; - -struct ovs_key_ipv6 { - __be32 ipv6_src[4]; - __be32 ipv6_dst[4]; - __be32 ipv6_label; /* 20-bits in least-significant bits. */ - __u8 ipv6_proto; - __u8 ipv6_tclass; - __u8 ipv6_hlimit; - __u8 ipv6_frag; /* One of OVS_FRAG_TYPE_*. */ -}; - -struct ovs_key_tcp { - __be16 tcp_src; - __be16 tcp_dst; -}; - -struct ovs_key_udp { - __be16 udp_src; - __be16 udp_dst; -}; - -struct ovs_key_icmp { - __u8 icmp_type; - __u8 icmp_code; -}; - -struct ovs_key_icmpv6 { - __u8 icmpv6_type; - __u8 icmpv6_code; -}; - -struct ovs_key_arp { - __be32 arp_sip; - __be32 arp_tip; - __be16 arp_op; - __u8 arp_sha[ETH_ALEN]; - __u8 arp_tha[ETH_ALEN]; -}; - -struct ovs_key_nd { - __u32 nd_target[4]; - __u8 nd_sll[ETH_ALEN]; - __u8 nd_tll[ETH_ALEN]; -}; - -/** - * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. - * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow - * key. Always present in notifications. Required for all requests (except - * dumps). - * @OVS_FLOW_ATTR_ACTIONS: Nested %OVS_ACTION_ATTR_* attributes specifying - * the actions to take for packets that match the key. Always present in - * notifications. Required for %OVS_FLOW_CMD_NEW requests, optional for - * %OVS_FLOW_CMD_SET requests. - * @OVS_FLOW_ATTR_STATS: &struct ovs_flow_stats giving statistics for this - * flow. Present in notifications if the stats would be nonzero. Ignored in - * requests. - * @OVS_FLOW_ATTR_TCP_FLAGS: An 8-bit value giving the OR'd value of all of the - * TCP flags seen on packets in this flow. Only present in notifications for - * TCP flows, and only if it would be nonzero. Ignored in requests. - * @OVS_FLOW_ATTR_USED: A 64-bit integer giving the time, in milliseconds on - * the system monotonic clock, at which a packet was last processed for this - * flow. Only present in notifications if a packet has been processed for this - * flow. Ignored in requests. - * @OVS_FLOW_ATTR_CLEAR: If present in a %OVS_FLOW_CMD_SET request, clears the - * last-used time, accumulated TCP flags, and statistics for this flow. - * Otherwise ignored in requests. Never present in notifications. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_FLOW_* commands. - */ -enum ovs_flow_attr { - OVS_FLOW_ATTR_UNSPEC, - OVS_FLOW_ATTR_KEY, /* Sequence of OVS_KEY_ATTR_* attributes. */ - OVS_FLOW_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - OVS_FLOW_ATTR_STATS, /* struct ovs_flow_stats. */ - OVS_FLOW_ATTR_TCP_FLAGS, /* 8-bit OR'd TCP flags. */ - OVS_FLOW_ATTR_USED, /* u64 msecs last used in monotonic time. */ - OVS_FLOW_ATTR_CLEAR, /* Flag to clear stats, tcp_flags, used. */ - __OVS_FLOW_ATTR_MAX -}; - -#define OVS_FLOW_ATTR_MAX (__OVS_FLOW_ATTR_MAX - 1) - -/** - * enum ovs_sample_attr - Attributes for %OVS_ACTION_ATTR_SAMPLE action. - * @OVS_SAMPLE_ATTR_PROBABILITY: 32-bit fraction of packets to sample with - * @OVS_ACTION_ATTR_SAMPLE. A value of 0 samples no packets, a value of - * %UINT32_MAX samples all packets and intermediate values sample intermediate - * fractions of packets. - * @OVS_SAMPLE_ATTR_ACTIONS: Set of actions to execute in sampling event. - * Actions are passed as nested attributes. - * - * Executes the specified actions with the given probability on a per-packet - * basis. - */ -enum ovs_sample_attr { - OVS_SAMPLE_ATTR_UNSPEC, - OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */ - OVS_SAMPLE_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - __OVS_SAMPLE_ATTR_MAX, -}; - -#define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1) - -/** - * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action. - * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION - * message should be sent. Required. - * @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is - * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA. - */ -enum ovs_userspace_attr { - OVS_USERSPACE_ATTR_UNSPEC, - OVS_USERSPACE_ATTR_PID, /* u32 Netlink PID to receive upcalls. */ - OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */ - __OVS_USERSPACE_ATTR_MAX -}; - -#define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1) - -/** - * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument. - * @vlan_tpid: Tag protocol identifier (TPID) to push. - * @vlan_tci: Tag control identifier (TCI) to push. The CFI bit must be set - * (but it will not be set in the 802.1Q header that is pushed). - * - * The @vlan_tpid value is typically %ETH_P_8021Q. The only acceptable TPID - * values are those that the kernel module also parses as 802.1Q headers, to - * prevent %OVS_ACTION_ATTR_PUSH_VLAN followed by %OVS_ACTION_ATTR_POP_VLAN - * from having surprising results. - */ -struct ovs_action_push_vlan { - __be16 vlan_tpid; /* 802.1Q TPID. */ - __be16 vlan_tci; /* 802.1Q TCI (VLAN ID and priority). */ -}; - -/** - * enum ovs_action_attr - Action types. - * - * @OVS_ACTION_ATTR_OUTPUT: Output packet to port. - * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested - * %OVS_USERSPACE_ATTR_* attributes. - * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header. The - * single nested %OVS_KEY_ATTR_* attribute specifies a header to modify and its - * value. - * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q header onto the - * packet. - * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet. - * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in - * the nested %OVS_SAMPLE_ATTR_* attributes. - * - * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all - * fields within a header are modifiable, e.g. the IPv4 protocol and fragment - * type may not be changed. - */ - -enum ovs_action_attr { - OVS_ACTION_ATTR_UNSPEC, - OVS_ACTION_ATTR_OUTPUT, /* u32 port number. */ - OVS_ACTION_ATTR_USERSPACE, /* Nested OVS_USERSPACE_ATTR_*. */ - OVS_ACTION_ATTR_SET, /* One nested OVS_KEY_ATTR_*. */ - OVS_ACTION_ATTR_PUSH_VLAN, /* struct ovs_action_push_vlan. */ - OVS_ACTION_ATTR_POP_VLAN, /* No argument. */ - OVS_ACTION_ATTR_SAMPLE, /* Nested OVS_SAMPLE_ATTR_*. */ - __OVS_ACTION_ATTR_MAX -}; - -#define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1) +#include #endif /* _LINUX_OPENVSWITCH_H */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 5c8a1d25e21c..d8fbc6aeac86 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -285,6 +285,7 @@ header-y += nvram.h header-y += omap3isp.h header-y += omapfb.h header-y += oom.h +header-y += openvswitch.h header-y += packet_diag.h header-y += param.h header-y += parport.h diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h new file mode 100644 index 000000000000..405918dd7b3f --- /dev/null +++ b/include/uapi/linux/openvswitch.h @@ -0,0 +1,456 @@ + +/* + * Copyright (c) 2007-2011 Nicira Networks. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * 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 Street, Fifth Floor, Boston, MA + * 02110-1301, USA + */ + +#ifndef _UAPI__LINUX_OPENVSWITCH_H +#define _UAPI__LINUX_OPENVSWITCH_H 1 + +#include +#include + +/** + * struct ovs_header - header for OVS Generic Netlink messages. + * @dp_ifindex: ifindex of local port for datapath (0 to make a request not + * specific to a datapath). + * + * Attributes following the header are specific to a particular OVS Generic + * Netlink family, but all of the OVS families use this header. + */ + +struct ovs_header { + int dp_ifindex; +}; + +/* Datapaths. */ + +#define OVS_DATAPATH_FAMILY "ovs_datapath" +#define OVS_DATAPATH_MCGROUP "ovs_datapath" +#define OVS_DATAPATH_VERSION 0x1 + +enum ovs_datapath_cmd { + OVS_DP_CMD_UNSPEC, + OVS_DP_CMD_NEW, + OVS_DP_CMD_DEL, + OVS_DP_CMD_GET, + OVS_DP_CMD_SET +}; + +/** + * enum ovs_datapath_attr - attributes for %OVS_DP_* commands. + * @OVS_DP_ATTR_NAME: Name of the network device that serves as the "local + * port". This is the name of the network device whose dp_ifindex is given in + * the &struct ovs_header. Always present in notifications. Required in + * %OVS_DP_NEW requests. May be used as an alternative to specifying + * dp_ifindex in other requests (with a dp_ifindex of 0). + * @OVS_DP_ATTR_UPCALL_PID: The Netlink socket in userspace that is initially + * set on the datapath port (for OVS_ACTION_ATTR_MISS). Only valid on + * %OVS_DP_CMD_NEW requests. A value of zero indicates that upcalls should + * not be sent. + * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the + * datapath. Always present in notifications. + * + * These attributes follow the &struct ovs_header within the Generic Netlink + * payload for %OVS_DP_* commands. + */ +enum ovs_datapath_attr { + OVS_DP_ATTR_UNSPEC, + OVS_DP_ATTR_NAME, /* name of dp_ifindex netdev */ + OVS_DP_ATTR_UPCALL_PID, /* Netlink PID to receive upcalls */ + OVS_DP_ATTR_STATS, /* struct ovs_dp_stats */ + __OVS_DP_ATTR_MAX +}; + +#define OVS_DP_ATTR_MAX (__OVS_DP_ATTR_MAX - 1) + +struct ovs_dp_stats { + __u64 n_hit; /* Number of flow table matches. */ + __u64 n_missed; /* Number of flow table misses. */ + __u64 n_lost; /* Number of misses not sent to userspace. */ + __u64 n_flows; /* Number of flows present */ +}; + +struct ovs_vport_stats { + __u64 rx_packets; /* total packets received */ + __u64 tx_packets; /* total packets transmitted */ + __u64 rx_bytes; /* total bytes received */ + __u64 tx_bytes; /* total bytes transmitted */ + __u64 rx_errors; /* bad packets received */ + __u64 tx_errors; /* packet transmit problems */ + __u64 rx_dropped; /* no space in linux buffers */ + __u64 tx_dropped; /* no space available in linux */ +}; + +/* Fixed logical ports. */ +#define OVSP_LOCAL ((__u32)0) + +/* Packet transfer. */ + +#define OVS_PACKET_FAMILY "ovs_packet" +#define OVS_PACKET_VERSION 0x1 + +enum ovs_packet_cmd { + OVS_PACKET_CMD_UNSPEC, + + /* Kernel-to-user notifications. */ + OVS_PACKET_CMD_MISS, /* Flow table miss. */ + OVS_PACKET_CMD_ACTION, /* OVS_ACTION_ATTR_USERSPACE action. */ + + /* Userspace commands. */ + OVS_PACKET_CMD_EXECUTE /* Apply actions to a packet. */ +}; + +/** + * enum ovs_packet_attr - attributes for %OVS_PACKET_* commands. + * @OVS_PACKET_ATTR_PACKET: Present for all notifications. Contains the entire + * packet as received, from the start of the Ethernet header onward. For + * %OVS_PACKET_CMD_ACTION, %OVS_PACKET_ATTR_PACKET reflects changes made by + * actions preceding %OVS_ACTION_ATTR_USERSPACE, but %OVS_PACKET_ATTR_KEY is + * the flow key extracted from the packet as originally received. + * @OVS_PACKET_ATTR_KEY: Present for all notifications. Contains the flow key + * extracted from the packet as nested %OVS_KEY_ATTR_* attributes. This allows + * userspace to adapt its flow setup strategy by comparing its notion of the + * flow key against the kernel's. + * @OVS_PACKET_ATTR_ACTIONS: Contains actions for the packet. Used + * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes. + * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION + * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an + * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content + * specified there. + * + * These attributes follow the &struct ovs_header within the Generic Netlink + * payload for %OVS_PACKET_* commands. + */ +enum ovs_packet_attr { + OVS_PACKET_ATTR_UNSPEC, + OVS_PACKET_ATTR_PACKET, /* Packet data. */ + OVS_PACKET_ATTR_KEY, /* Nested OVS_KEY_ATTR_* attributes. */ + OVS_PACKET_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ + OVS_PACKET_ATTR_USERDATA, /* OVS_ACTION_ATTR_USERSPACE arg. */ + __OVS_PACKET_ATTR_MAX +}; + +#define OVS_PACKET_ATTR_MAX (__OVS_PACKET_ATTR_MAX - 1) + +/* Virtual ports. */ + +#define OVS_VPORT_FAMILY "ovs_vport" +#define OVS_VPORT_MCGROUP "ovs_vport" +#define OVS_VPORT_VERSION 0x1 + +enum ovs_vport_cmd { + OVS_VPORT_CMD_UNSPEC, + OVS_VPORT_CMD_NEW, + OVS_VPORT_CMD_DEL, + OVS_VPORT_CMD_GET, + OVS_VPORT_CMD_SET +}; + +enum ovs_vport_type { + OVS_VPORT_TYPE_UNSPEC, + OVS_VPORT_TYPE_NETDEV, /* network device */ + OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */ + __OVS_VPORT_TYPE_MAX +}; + +#define OVS_VPORT_TYPE_MAX (__OVS_VPORT_TYPE_MAX - 1) + +/** + * enum ovs_vport_attr - attributes for %OVS_VPORT_* commands. + * @OVS_VPORT_ATTR_PORT_NO: 32-bit port number within datapath. + * @OVS_VPORT_ATTR_TYPE: 32-bit %OVS_VPORT_TYPE_* constant describing the type + * of vport. + * @OVS_VPORT_ATTR_NAME: Name of vport. For a vport based on a network device + * this is the name of the network device. Maximum length %IFNAMSIZ-1 bytes + * plus a null terminator. + * @OVS_VPORT_ATTR_OPTIONS: Vport-specific configuration information. + * @OVS_VPORT_ATTR_UPCALL_PID: The Netlink socket in userspace that + * OVS_PACKET_CMD_MISS upcalls will be directed to for packets received on + * this port. A value of zero indicates that upcalls should not be sent. + * @OVS_VPORT_ATTR_STATS: A &struct ovs_vport_stats giving statistics for + * packets sent or received through the vport. + * + * These attributes follow the &struct ovs_header within the Generic Netlink + * payload for %OVS_VPORT_* commands. + * + * For %OVS_VPORT_CMD_NEW requests, the %OVS_VPORT_ATTR_TYPE and + * %OVS_VPORT_ATTR_NAME attributes are required. %OVS_VPORT_ATTR_PORT_NO is + * optional; if not specified a free port number is automatically selected. + * Whether %OVS_VPORT_ATTR_OPTIONS is required or optional depends on the type + * of vport. + * and other attributes are ignored. + * + * For other requests, if %OVS_VPORT_ATTR_NAME is specified then it is used to + * look up the vport to operate on; otherwise dp_idx from the &struct + * ovs_header plus %OVS_VPORT_ATTR_PORT_NO determine the vport. + */ +enum ovs_vport_attr { + OVS_VPORT_ATTR_UNSPEC, + OVS_VPORT_ATTR_PORT_NO, /* u32 port number within datapath */ + OVS_VPORT_ATTR_TYPE, /* u32 OVS_VPORT_TYPE_* constant. */ + OVS_VPORT_ATTR_NAME, /* string name, up to IFNAMSIZ bytes long */ + OVS_VPORT_ATTR_OPTIONS, /* nested attributes, varies by vport type */ + OVS_VPORT_ATTR_UPCALL_PID, /* u32 Netlink PID to receive upcalls */ + OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */ + __OVS_VPORT_ATTR_MAX +}; + +#define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1) + +/* Flows. */ + +#define OVS_FLOW_FAMILY "ovs_flow" +#define OVS_FLOW_MCGROUP "ovs_flow" +#define OVS_FLOW_VERSION 0x1 + +enum ovs_flow_cmd { + OVS_FLOW_CMD_UNSPEC, + OVS_FLOW_CMD_NEW, + OVS_FLOW_CMD_DEL, + OVS_FLOW_CMD_GET, + OVS_FLOW_CMD_SET +}; + +struct ovs_flow_stats { + __u64 n_packets; /* Number of matched packets. */ + __u64 n_bytes; /* Number of matched bytes. */ +}; + +enum ovs_key_attr { + OVS_KEY_ATTR_UNSPEC, + OVS_KEY_ATTR_ENCAP, /* Nested set of encapsulated attributes. */ + OVS_KEY_ATTR_PRIORITY, /* u32 skb->priority */ + OVS_KEY_ATTR_IN_PORT, /* u32 OVS dp port number */ + OVS_KEY_ATTR_ETHERNET, /* struct ovs_key_ethernet */ + OVS_KEY_ATTR_VLAN, /* be16 VLAN TCI */ + OVS_KEY_ATTR_ETHERTYPE, /* be16 Ethernet type */ + OVS_KEY_ATTR_IPV4, /* struct ovs_key_ipv4 */ + OVS_KEY_ATTR_IPV6, /* struct ovs_key_ipv6 */ + OVS_KEY_ATTR_TCP, /* struct ovs_key_tcp */ + OVS_KEY_ATTR_UDP, /* struct ovs_key_udp */ + OVS_KEY_ATTR_ICMP, /* struct ovs_key_icmp */ + OVS_KEY_ATTR_ICMPV6, /* struct ovs_key_icmpv6 */ + OVS_KEY_ATTR_ARP, /* struct ovs_key_arp */ + OVS_KEY_ATTR_ND, /* struct ovs_key_nd */ + OVS_KEY_ATTR_SKB_MARK, /* u32 skb mark */ + __OVS_KEY_ATTR_MAX +}; + +#define OVS_KEY_ATTR_MAX (__OVS_KEY_ATTR_MAX - 1) + +/** + * enum ovs_frag_type - IPv4 and IPv6 fragment type + * @OVS_FRAG_TYPE_NONE: Packet is not a fragment. + * @OVS_FRAG_TYPE_FIRST: Packet is a fragment with offset 0. + * @OVS_FRAG_TYPE_LATER: Packet is a fragment with nonzero offset. + * + * Used as the @ipv4_frag in &struct ovs_key_ipv4 and as @ipv6_frag &struct + * ovs_key_ipv6. + */ +enum ovs_frag_type { + OVS_FRAG_TYPE_NONE, + OVS_FRAG_TYPE_FIRST, + OVS_FRAG_TYPE_LATER, + __OVS_FRAG_TYPE_MAX +}; + +#define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1) + +struct ovs_key_ethernet { + __u8 eth_src[ETH_ALEN]; + __u8 eth_dst[ETH_ALEN]; +}; + +struct ovs_key_ipv4 { + __be32 ipv4_src; + __be32 ipv4_dst; + __u8 ipv4_proto; + __u8 ipv4_tos; + __u8 ipv4_ttl; + __u8 ipv4_frag; /* One of OVS_FRAG_TYPE_*. */ +}; + +struct ovs_key_ipv6 { + __be32 ipv6_src[4]; + __be32 ipv6_dst[4]; + __be32 ipv6_label; /* 20-bits in least-significant bits. */ + __u8 ipv6_proto; + __u8 ipv6_tclass; + __u8 ipv6_hlimit; + __u8 ipv6_frag; /* One of OVS_FRAG_TYPE_*. */ +}; + +struct ovs_key_tcp { + __be16 tcp_src; + __be16 tcp_dst; +}; + +struct ovs_key_udp { + __be16 udp_src; + __be16 udp_dst; +}; + +struct ovs_key_icmp { + __u8 icmp_type; + __u8 icmp_code; +}; + +struct ovs_key_icmpv6 { + __u8 icmpv6_type; + __u8 icmpv6_code; +}; + +struct ovs_key_arp { + __be32 arp_sip; + __be32 arp_tip; + __be16 arp_op; + __u8 arp_sha[ETH_ALEN]; + __u8 arp_tha[ETH_ALEN]; +}; + +struct ovs_key_nd { + __u32 nd_target[4]; + __u8 nd_sll[ETH_ALEN]; + __u8 nd_tll[ETH_ALEN]; +}; + +/** + * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. + * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow + * key. Always present in notifications. Required for all requests (except + * dumps). + * @OVS_FLOW_ATTR_ACTIONS: Nested %OVS_ACTION_ATTR_* attributes specifying + * the actions to take for packets that match the key. Always present in + * notifications. Required for %OVS_FLOW_CMD_NEW requests, optional for + * %OVS_FLOW_CMD_SET requests. + * @OVS_FLOW_ATTR_STATS: &struct ovs_flow_stats giving statistics for this + * flow. Present in notifications if the stats would be nonzero. Ignored in + * requests. + * @OVS_FLOW_ATTR_TCP_FLAGS: An 8-bit value giving the OR'd value of all of the + * TCP flags seen on packets in this flow. Only present in notifications for + * TCP flows, and only if it would be nonzero. Ignored in requests. + * @OVS_FLOW_ATTR_USED: A 64-bit integer giving the time, in milliseconds on + * the system monotonic clock, at which a packet was last processed for this + * flow. Only present in notifications if a packet has been processed for this + * flow. Ignored in requests. + * @OVS_FLOW_ATTR_CLEAR: If present in a %OVS_FLOW_CMD_SET request, clears the + * last-used time, accumulated TCP flags, and statistics for this flow. + * Otherwise ignored in requests. Never present in notifications. + * + * These attributes follow the &struct ovs_header within the Generic Netlink + * payload for %OVS_FLOW_* commands. + */ +enum ovs_flow_attr { + OVS_FLOW_ATTR_UNSPEC, + OVS_FLOW_ATTR_KEY, /* Sequence of OVS_KEY_ATTR_* attributes. */ + OVS_FLOW_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ + OVS_FLOW_ATTR_STATS, /* struct ovs_flow_stats. */ + OVS_FLOW_ATTR_TCP_FLAGS, /* 8-bit OR'd TCP flags. */ + OVS_FLOW_ATTR_USED, /* u64 msecs last used in monotonic time. */ + OVS_FLOW_ATTR_CLEAR, /* Flag to clear stats, tcp_flags, used. */ + __OVS_FLOW_ATTR_MAX +}; + +#define OVS_FLOW_ATTR_MAX (__OVS_FLOW_ATTR_MAX - 1) + +/** + * enum ovs_sample_attr - Attributes for %OVS_ACTION_ATTR_SAMPLE action. + * @OVS_SAMPLE_ATTR_PROBABILITY: 32-bit fraction of packets to sample with + * @OVS_ACTION_ATTR_SAMPLE. A value of 0 samples no packets, a value of + * %UINT32_MAX samples all packets and intermediate values sample intermediate + * fractions of packets. + * @OVS_SAMPLE_ATTR_ACTIONS: Set of actions to execute in sampling event. + * Actions are passed as nested attributes. + * + * Executes the specified actions with the given probability on a per-packet + * basis. + */ +enum ovs_sample_attr { + OVS_SAMPLE_ATTR_UNSPEC, + OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */ + OVS_SAMPLE_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ + __OVS_SAMPLE_ATTR_MAX, +}; + +#define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1) + +/** + * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action. + * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION + * message should be sent. Required. + * @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is + * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA. + */ +enum ovs_userspace_attr { + OVS_USERSPACE_ATTR_UNSPEC, + OVS_USERSPACE_ATTR_PID, /* u32 Netlink PID to receive upcalls. */ + OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */ + __OVS_USERSPACE_ATTR_MAX +}; + +#define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1) + +/** + * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument. + * @vlan_tpid: Tag protocol identifier (TPID) to push. + * @vlan_tci: Tag control identifier (TCI) to push. The CFI bit must be set + * (but it will not be set in the 802.1Q header that is pushed). + * + * The @vlan_tpid value is typically %ETH_P_8021Q. The only acceptable TPID + * values are those that the kernel module also parses as 802.1Q headers, to + * prevent %OVS_ACTION_ATTR_PUSH_VLAN followed by %OVS_ACTION_ATTR_POP_VLAN + * from having surprising results. + */ +struct ovs_action_push_vlan { + __be16 vlan_tpid; /* 802.1Q TPID. */ + __be16 vlan_tci; /* 802.1Q TCI (VLAN ID and priority). */ +}; + +/** + * enum ovs_action_attr - Action types. + * + * @OVS_ACTION_ATTR_OUTPUT: Output packet to port. + * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested + * %OVS_USERSPACE_ATTR_* attributes. + * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header. The + * single nested %OVS_KEY_ATTR_* attribute specifies a header to modify and its + * value. + * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q header onto the + * packet. + * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet. + * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in + * the nested %OVS_SAMPLE_ATTR_* attributes. + * + * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all + * fields within a header are modifiable, e.g. the IPv4 protocol and fragment + * type may not be changed. + */ + +enum ovs_action_attr { + OVS_ACTION_ATTR_UNSPEC, + OVS_ACTION_ATTR_OUTPUT, /* u32 port number. */ + OVS_ACTION_ATTR_USERSPACE, /* Nested OVS_USERSPACE_ATTR_*. */ + OVS_ACTION_ATTR_SET, /* One nested OVS_KEY_ATTR_*. */ + OVS_ACTION_ATTR_PUSH_VLAN, /* struct ovs_action_push_vlan. */ + OVS_ACTION_ATTR_POP_VLAN, /* No argument. */ + OVS_ACTION_ATTR_SAMPLE, /* Nested OVS_SAMPLE_ATTR_*. */ + __OVS_ACTION_ATTR_MAX +}; + +#define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1) + +#endif /* _LINUX_OPENVSWITCH_H */ -- cgit v1.2.3 From a691ce7fe451363d2f1fa48d30c8f4b87c2475d4 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Thu, 28 Mar 2013 15:24:53 +0000 Subject: include/linux: printk is needed in filter.h when CONFIG_BPF_JIT is defined for make V=1 EXTRA_CFLAGS=-W ARCH=arm allmodconfig printk is need when CONFIG_BPF_JIT is defined or it will report pr_err and print_hex_dump are implicit declaration Signed-off-by: Chen Gang Signed-off-by: David S. Miller --- include/linux/filter.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index d7d25083130b..d1248f401a56 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -48,6 +48,9 @@ extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen); extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len); #ifdef CONFIG_BPF_JIT +#include +#include + extern void bpf_jit_compile(struct sk_filter *fp); extern void bpf_jit_free(struct sk_filter *fp); -- cgit v1.2.3 From 4c3d5e7b41dda1b1372bfc2545ef092a1bc5ad33 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 30 Mar 2013 06:31:03 +0000 Subject: net: reorder some fields of net_device As time passed, some fields were added in net_device, and not at sensible offsets. Lets reorder some fields to reduce number of cache lines in RX path. Fields not used in data path should be moved out of this critical cache line. In particular, move broadcast[] to the end of the rx section, as it is less used, and ethernet uses only the beginning of the 32bytes field. Before patch : offsetof(struct net_device,dev_addr)=0x258 offsetof(struct net_device,rx_handler)=0x2b8 offsetof(struct net_device,ingress_queue)=0x2c8 offsetof(struct net_device,broadcast)=0x278 After : offsetof(struct net_device,dev_addr)=0x280 offsetof(struct net_device,rx_handler)=0x298 offsetof(struct net_device,ingress_queue)=0x2a8 offsetof(struct net_device,broadcast)=0x2b0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1dbb02c98946..4491414a9218 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1071,6 +1071,8 @@ struct net_device { struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; + struct list_head upper_dev_list; /* List of upper devices */ + /* currently active device features */ netdev_features_t features; @@ -1143,6 +1145,13 @@ struct net_device { spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; /* Unicast mac addresses */ struct netdev_hw_addr_list mc; /* Multicast mac addresses */ + struct netdev_hw_addr_list dev_addrs; /* list of device + * hw addresses + */ +#ifdef CONFIG_SYSFS + struct kset *queues_kset; +#endif + bool uc_promisc; unsigned int promiscuity; unsigned int allmulti; @@ -1175,21 +1184,11 @@ struct net_device { * avoid dirtying this cache line. */ - struct list_head upper_dev_list; /* List of upper devices */ - /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; /* hw address, (before bcast because most packets are unicast) */ - struct netdev_hw_addr_list dev_addrs; /* list of device - hw addresses */ - - unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ - -#ifdef CONFIG_SYSFS - struct kset *queues_kset; -#endif #ifdef CONFIG_RPS struct netdev_rx_queue *_rx; @@ -1200,18 +1199,14 @@ struct net_device { /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; -#ifdef CONFIG_RFS_ACCEL - /* CPU reverse-mapping for RX completion interrupts, indexed - * by RX queue number. Assigned by driver. This must only be - * set if the ndo_rx_flow_steer operation is defined. */ - struct cpu_rmap *rx_cpu_rmap; -#endif #endif rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; struct netdev_queue __rcu *ingress_queue; + unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ + /* * Cache lines mostly used on transmit path @@ -1233,6 +1228,12 @@ struct net_device { #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps; #endif +#ifdef CONFIG_RFS_ACCEL + /* CPU reverse-mapping for RX completion interrupts, indexed + * by RX queue number. Assigned by driver. This must only be + * set if the ndo_rx_flow_steer operation is defined. */ + struct cpu_rmap *rx_cpu_rmap; +#endif /* These may be needed for future network-power-down code. */ -- cgit v1.2.3 From 7d4c04fc170087119727119074e72445f2bb192b Mon Sep 17 00:00:00 2001 From: "Keller, Jacob E" Date: Thu, 28 Mar 2013 11:19:25 +0000 Subject: net: add option to enable error queue packets waking select Currently, when a socket receives something on the error queue it only wakes up the socket on select if it is in the "read" list, that is the socket has something to read. It is useful also to wake the socket if it is in the error list, which would enable software to wait on error queue packets without waking up for regular data on the socket. The main use case is for receiving timestamped transmit packets which return the timestamp to the socket via the error queue. This enables an application to select on the socket for the error queue only instead of for the regular traffic. -v2- * Added the SO_SELECT_ERR_QUEUE socket option to every architechture specific file * Modified every socket poll function that checks error queue Signed-off-by: Jacob Keller Cc: Jeffrey Kirsher Cc: Richard Cochran Cc: Matthew Vick Signed-off-by: David S. Miller --- include/net/sock.h | 1 + include/uapi/asm-generic/socket.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 14f6e9d19dc7..08f05f964737 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -667,6 +667,7 @@ enum sock_flags { * user-space instead. */ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ + SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 4ef3acbba5da..c5d2e3a1cf68 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -74,4 +74,6 @@ #define SO_LOCK_FILTER 44 +#define SO_SELECT_ERR_QUEUE 45 + #endif /* __ASM_GENERIC_SOCKET_H */ -- cgit v1.2.3 From 932bc4d7a53ba418de67fdab533248df5b36c752 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:57:58 +0200 Subject: net: add skb_dst_set_noref_force Rename skb_dst_set_noref to __skb_dst_set_noref and add force flag as suggested by David Miller. The new wrapper skb_dst_set_noref_force will force dst entries that are not cached to be attached as skb dst without taking reference as long as provided dst is reclaimed after RCU grace period. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Acked-by: David S. Miller Signed-off-by: Simon Horman --- include/linux/skbuff.h | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 878e0ee81068..364e2440a7ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -575,7 +575,40 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) skb->_skb_refdst = (unsigned long)dst; } -extern void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst); +extern void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, + bool force); + +/** + * skb_dst_set_noref - sets skb dst, hopefully, without taking reference + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was not taken on dst. + * If dst entry is cached, we do not take reference and dst_release + * will be avoided by refdst_drop. If dst entry is not cached, we take + * reference, so that last dst_release can destroy the dst immediately. + */ +static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) +{ + __skb_dst_set_noref(skb, dst, false); +} + +/** + * skb_dst_set_noref_force - sets skb dst, without taking reference + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was not taken on dst. + * No reference is taken and no dst_release will be called. While for + * cached dsts deferred reclaim is a basic feature, for entries that are + * not cached it is caller's job to guarantee that last dst_release for + * provided dst happens when nobody uses it, eg. after a RCU grace period. + */ +static inline void skb_dst_set_noref_force(struct sk_buff *skb, + struct dst_entry *dst) +{ + __skb_dst_set_noref(skb, dst, true); +} /** * skb_dst_is_noref - Test if skb dst isn't refcounted -- cgit v1.2.3 From c90558dae51cef334f3d9d447cf7c0fd1bfe725d Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:57:59 +0200 Subject: ipvs: avoid routing by TOS for real server Avoid replacing the cached route for real server on every packet with different TOS. I doubt that routing by TOS for real server is used at all, so we should be better with such optimization. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index bee87badabef..64db11769cc2 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -753,7 +753,6 @@ struct ip_vs_dest { /* for destination cache */ spinlock_t dst_lock; /* lock of dst_cache */ struct dst_entry *dst_cache; /* destination cache entry */ - u32 dst_rtos; /* RT_TOS(tos) for dst */ u32 dst_cookie; union nf_inet_addr dst_saddr; -- cgit v1.2.3 From d1deae4d3ab37d833f278fec975a8f2ddeb78f3b Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:58:02 +0200 Subject: ipvs: rename functions related to dst_cache reset Move and give better names to two functions: - ip_vs_dst_reset to __ip_vs_dst_cache_reset - __ip_vs_dev_reset to ip_vs_forget_dev Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 64db11769cc2..8ad73a834655 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1427,7 +1427,6 @@ extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, int offset, unsigned int hooknum, struct ip_vs_iphdr *iph); -extern void ip_vs_dst_reset(struct ip_vs_dest *dest); #ifdef CONFIG_IP_VS_IPV6 extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, -- cgit v1.2.3 From 026ace060dfe29275d2188297a62fa37d6c1a02c Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:58:06 +0200 Subject: ipvs: optimize dst usage for real server Currently when forwarding requests to real servers we use dst_lock and atomic operations when cloning the dst_cache value. As the dst_cache value does not change most of the time it is better to use RCU and to lock dst_lock only when we need to replace the obsoleted dst. For this to work we keep dst_cache in new structure protected by RCU. For packets to remote real servers we will use noref version of dst_cache, it will be valid while we are in RCU read-side critical section because now dst_release for replaced dsts will be invoked after the grace period. Packets to local real servers that are passed to local stack with NF_ACCEPT need a dst clone. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 8ad73a834655..a150ff5d838c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -724,6 +724,13 @@ struct ip_vs_service { struct ip_vs_pe *pe; }; +/* Information for cached dst */ +struct ip_vs_dest_dst { + struct dst_entry *dst_cache; /* destination cache entry */ + u32 dst_cookie; + union nf_inet_addr dst_saddr; + struct rcu_head rcu_head; +}; /* * The real server destination forwarding entry @@ -752,9 +759,7 @@ struct ip_vs_dest { /* for destination cache */ spinlock_t dst_lock; /* lock of dst_cache */ - struct dst_entry *dst_cache; /* destination cache entry */ - u32 dst_cookie; - union nf_inet_addr dst_saddr; + struct ip_vs_dest_dst __rcu *dest_dst; /* cached dst info */ /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ @@ -1427,6 +1432,7 @@ extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, int offset, unsigned int hooknum, struct ip_vs_iphdr *iph); +extern void ip_vs_dest_dst_rcu_free(struct rcu_head *head); #ifdef CONFIG_IP_VS_IPV6 extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, -- cgit v1.2.3 From 363c97d7435ebba8a040f86e29bdec79ee182f0c Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:58:07 +0200 Subject: ipvs: convert app locks We use locks like tcp_app_lock, udp_app_lock, sctp_app_lock to protect access to the protocol hash tables from readers in packet context while the application instances (inc) are [un]registered under global mutex. As the hash tables are mostly read when conns are created and bound to app, use RCU for readers and reclaim app instance after grace period. Simplify ip_vs_app_inc_get because we use usecnt only for statistics and rely on module refcounting. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a150ff5d838c..84ca17141a44 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -823,6 +823,7 @@ struct ip_vs_app { struct ip_vs_app *app; /* its real application */ __be16 port; /* port number in net order */ atomic_t usecnt; /* usage counter */ + struct rcu_head rcu_head; /* * output hook: Process packet in inout direction, diff set for TCP. @@ -908,7 +909,6 @@ struct netns_ipvs { #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) struct list_head tcp_apps[TCP_APP_TAB_SIZE]; - spinlock_t tcp_app_lock; #endif /* ip_vs_proto_udp */ #ifdef CONFIG_IP_VS_PROTO_UDP @@ -916,7 +916,6 @@ struct netns_ipvs { #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) struct list_head udp_apps[UDP_APP_TAB_SIZE]; - spinlock_t udp_app_lock; #endif /* ip_vs_proto_sctp */ #ifdef CONFIG_IP_VS_PROTO_SCTP @@ -925,7 +924,6 @@ struct netns_ipvs { #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) /* Hash table for SCTP application incarnations */ struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; - spinlock_t sctp_app_lock; #endif /* ip_vs_conn */ atomic_t conn_count; /* connection counter */ -- cgit v1.2.3 From 276472eae063d717b775fdfc87529937402d0e08 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:58:08 +0200 Subject: ipvs: remove rs_lock by using RCU rs_lock was used to protect rs_table (hash table) from updaters (under global mutex) and readers (packet handlers). We can remove rs_lock by using RCU lock for readers. Reclaiming dest only with kfree_rcu is enough because the readers access only fields from the ip_vs_dest structure. Use hlist for rs_table. As we are now using hlist_del_rcu, introduce in_rs_table flag as replacement for the list_empty checks which do not work with RCU. It is needed because only NAT dests are in the rs_table. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 84ca17141a44..b06aa6c939fa 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -738,7 +738,7 @@ struct ip_vs_dest_dst { */ struct ip_vs_dest { struct list_head n_list; /* for the dests in the service */ - struct list_head d_list; /* for table with all the dests */ + struct hlist_node d_list; /* for table with all the dests */ u16 af; /* address family */ __be16 port; /* port number of the server */ @@ -767,6 +767,9 @@ struct ip_vs_dest { __be16 vport; /* virtual port number */ union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ + + struct rcu_head rcu_head; + unsigned int in_rs_table:1; /* we are in rs_table */ }; @@ -897,7 +900,7 @@ struct netns_ipvs { #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) - struct list_head rs_table[IP_VS_RTAB_SIZE]; + struct hlist_head rs_table[IP_VS_RTAB_SIZE]; /* ip_vs_app */ struct list_head app_list; /* ip_vs_proto */ @@ -933,7 +936,6 @@ struct netns_ipvs { int num_services; /* no of virtual services */ - rwlock_t rs_lock; /* real services table */ /* Trash for destinations */ struct list_head dest_trash; /* Service counters */ @@ -1376,9 +1378,9 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc) atomic_dec(&svc->usecnt); } -extern struct ip_vs_dest * -ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, - const union nf_inet_addr *daddr, __be16 dport); +extern bool +ip_vs_has_real_service(struct net *net, int af, __u16 protocol, + const union nf_inet_addr *daddr, __be16 dport); extern int ip_vs_use_count_inc(void); extern void ip_vs_use_count_dec(void); -- cgit v1.2.3 From 088339a57d6042a8a19a3d5794594b558cd7b624 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:58:10 +0200 Subject: ipvs: convert connection locking Convert __ip_vs_conntbl_lock_array as follows: - readers that do not modify conn lists will use RCU lock - updaters that modify lists will use spinlock_t Now for conn lookups we will use RCU read-side critical section. Without using __ip_vs_conn_get such places have access to connection fields and can dereference some pointers like pe and pe_data plus the ability to update timer expiration. If full access is required we contend for reference. We add barrier in __ip_vs_conn_put, so that other CPUs see the refcnt operation after other writes. With the introduction of ip_vs_conn_unlink() we try to reorganize ip_vs_conn_expire(), so that unhashing of connections that should stay more time is avoided, even if it is for very short time. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b06aa6c939fa..5700b07b5186 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -620,6 +620,8 @@ struct ip_vs_conn { const struct ip_vs_pe *pe; char *pe_data; __u8 pe_data_len; + + struct rcu_head rcu_head; }; /* @@ -1185,9 +1187,19 @@ struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, int inverse); +/* Get reference to gain full access to conn. + * By default, RCU read-side critical sections have access only to + * conn fields and its PE data, see ip_vs_conn_rcu_free() for reference. + */ +static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp) +{ + return atomic_inc_not_zero(&cp->refcnt); +} + /* put back the conn without restarting its timer */ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp) { + smp_mb__before_atomic_dec(); atomic_dec(&cp->refcnt); } extern void ip_vs_conn_put(struct ip_vs_conn *cp); -- cgit v1.2.3 From 1845ed0bb29fa7864781021e0c8d06af318f358a Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:58:11 +0200 Subject: ipvs: reorder keys in connection structure __ip_vs_conn_in_get and ip_vs_conn_out_get are hot places. Optimize them, so that ports are matched first. By moving net and fwmark below, on 32-bit arch we can fit caddr in 32-byte cache line and all addresses in 64-byte cache line. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 5700b07b5186..929e04c6b82e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -566,20 +566,19 @@ struct ip_vs_conn_param { */ struct ip_vs_conn { struct hlist_node c_list; /* hashed list heads */ -#ifdef CONFIG_NET_NS - struct net *net; /* Name space */ -#endif /* Protocol, addresses and port numbers */ - u16 af; /* address family */ __be16 cport; - __be16 vport; __be16 dport; - __u32 fwmark; /* Fire wall mark from skb */ + __be16 vport; + u16 af; /* address family */ union nf_inet_addr caddr; /* client address */ union nf_inet_addr vaddr; /* virtual address */ union nf_inet_addr daddr; /* destination address */ volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ +#ifdef CONFIG_NET_NS + struct net *net; /* Name space */ +#endif /* counter and timer */ atomic_t refcnt; /* reference count */ @@ -593,6 +592,7 @@ struct ip_vs_conn { * state transition triggerd * synchronization */ + __u32 fwmark; /* Fire wall mark from skb */ unsigned long sync_endtime; /* jiffies + sent_retries */ /* Control members */ -- cgit v1.2.3 From 9a05475cebdd6341884b5901e53870be26e65158 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:58:12 +0200 Subject: ipvs: avoid kmem_cache_zalloc in ip_vs_conn_new We have many fields to set and few to reset, use kmem_cache_alloc instead to save some cycles. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Signed-off-by: Simon Horman --- include/net/ip_vs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 929e04c6b82e..43886bb282fb 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -233,6 +233,21 @@ static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, dst->ip = src->ip; } +static inline void ip_vs_addr_set(int af, union nf_inet_addr *dst, + const union nf_inet_addr *src) +{ +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + dst->in6 = src->in6; + return; + } +#endif + dst->ip = src->ip; + dst->all[1] = 0; + dst->all[2] = 0; + dst->all[3] = 0; +} + static inline int ip_vs_addr_equal(int af, const union nf_inet_addr *a, const union nf_inet_addr *b) { -- cgit v1.2.3 From 6b6df46663e7aa6f7b1d82435a3488f9b81316b3 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Mar 2013 11:46:37 +0200 Subject: ipvs: preparations for using rcu in schedulers Allow schedulers to use rcu_dereference when returning destination on lookup. The RCU read-side critical section will allow ip_vs_bind_dest to get dest refcnt as preparation for the step where destinations will be deleted without an IP_VS_WAIT_WHILE guard that holds the packet processing during update. Add new optional scheduler methods add_dest, del_dest and upd_dest. For now the methods are called together with update_service but update_service will be removed in a following change. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 43886bb282fb..d91385c1b3a2 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -805,6 +805,12 @@ struct ip_vs_scheduler { int (*done_service)(struct ip_vs_service *svc); /* scheduler updating service */ int (*update_service)(struct ip_vs_service *svc); + /* dest is linked */ + int (*add_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest); + /* dest is unlinked */ + int (*del_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest); + /* dest is updated */ + int (*upd_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest); /* selecting a server from the given service */ struct ip_vs_dest* (*schedule)(struct ip_vs_service *svc, -- cgit v1.2.3 From fca9c20ae1e510525f8a2aaa25861789fd721193 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Mar 2013 11:46:38 +0200 Subject: ipvs: add ip_vs_dest_hold and ip_vs_dest_put ip_vs_dest_hold will be used under RCU lock while ip_vs_dest_put can be called even after dest is removed from service, as it happens for conns and some schedulers. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d91385c1b3a2..7d3027f2c06e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1427,6 +1427,16 @@ ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, __u16 protocol, __u32 fwmark, __u32 flags); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); +static inline void ip_vs_dest_hold(struct ip_vs_dest *dest) +{ + atomic_inc(&dest->refcnt); +} + +static inline void ip_vs_dest_put(struct ip_vs_dest *dest) +{ + smp_mb__before_atomic_dec(); + atomic_dec(&dest->refcnt); +} /* * IPVS sync daemon data and function prototypes -- cgit v1.2.3 From 578bc3ef1e473abb9ea99046a307fef0094b22af Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Mar 2013 11:46:49 +0200 Subject: ipvs: reorganize dest trash All dests will go to trash, no exceptions. But we have to use new list node t_list for this, due to RCU changes in following patches. Dests will wait there initial grace period and later all conns and schedulers to put their reference. The dests don't get reference for staying in dest trash as before. As result, we do not load ip_vs_dest_put with extra checks for last refcnt and the schedulers do not need to play games with atomic_inc_not_zero while selecting best destination. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 7d3027f2c06e..18aeb85079f8 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -749,6 +749,8 @@ struct ip_vs_dest_dst { struct rcu_head rcu_head; }; +/* In grace period after removing */ +#define IP_VS_DEST_STATE_REMOVING 0x01 /* * The real server destination forwarding entry * with ip address, port number, and so on. @@ -766,6 +768,7 @@ struct ip_vs_dest { atomic_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ + unsigned long state; /* state flags */ /* connection counters and thresholds */ atomic_t activeconns; /* active connections */ @@ -785,6 +788,7 @@ struct ip_vs_dest { union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ + struct list_head t_list; /* in dest_trash */ struct rcu_head rcu_head; unsigned int in_rs_table:1; /* we are in rs_table */ }; @@ -912,6 +916,9 @@ struct ipvs_master_sync_state { struct netns_ipvs *ipvs; }; +/* How much time to keep dests in trash */ +#define IP_VS_DEST_TRASH_PERIOD (120 * HZ) + /* IPVS in network namespace */ struct netns_ipvs { int gen; /* Generation */ @@ -961,6 +968,8 @@ struct netns_ipvs { /* Trash for destinations */ struct list_head dest_trash; + spinlock_t dest_trash_lock; + struct timer_list dest_trash_timer; /* expiration timer */ /* Service counters */ atomic_t ftpsvc_counter; atomic_t nullsvc_counter; -- cgit v1.2.3 From ed3ffc4e48e2b03d5b23988f3cfa0ad8d79e0092 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Mar 2013 11:46:50 +0200 Subject: ipvs: do not expect result from done_service This method releases the scheduler state, it can not fail. Such change will help to properly replace the scheduler in following patch. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 18aeb85079f8..4990de698576 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -806,7 +806,7 @@ struct ip_vs_scheduler { /* scheduler initializing service */ int (*init_service)(struct ip_vs_service *svc); /* scheduling service finish */ - int (*done_service)(struct ip_vs_service *svc); + void (*done_service)(struct ip_vs_service *svc); /* scheduler updating service */ int (*update_service)(struct ip_vs_service *svc); /* dest is linked */ @@ -1392,7 +1392,7 @@ extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); extern int ip_vs_bind_scheduler(struct ip_vs_service *svc, struct ip_vs_scheduler *scheduler); -extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc); +extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc); extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * -- cgit v1.2.3 From ba3a3ce14ea26d602b253ef13a56d540827cd51d Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Mar 2013 11:46:51 +0200 Subject: ipvs: convert sched_lock to spin lock As all read_locks are gone spin lock is preferred. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4990de698576..4a7bc63b9cba 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -734,7 +734,7 @@ struct ip_vs_service { /* for scheduling */ struct ip_vs_scheduler *scheduler; /* bound scheduler object */ - rwlock_t sched_lock; /* lock sched_data */ + spinlock_t sched_lock; /* lock sched_data */ void *sched_data; /* scheduler application data */ /* alternate persistence engine */ -- cgit v1.2.3 From 413c2d04e9494ca38629d8a7ffeff1e4398a9fe3 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Mar 2013 11:46:52 +0200 Subject: ipvs: convert dests to rcu In previous commits the schedulers started to access svc->destinations with _rcu list traversal primitives because the IP_VS_WAIT_WHILE macro still plays the role of grace period. Now it is time to finish the updating part, i.e. adding and deleting of dests with _rcu suffix before removing the IP_VS_WAIT_WHILE in next commit. We use the same rule for conns as for the schedulers: dests can be searched in RCU read-side critical section where ip_vs_dest_hold can be called by ip_vs_bind_dest. Some things are not perfect, for example, calling functions like ip_vs_lookup_dest from updating code under RCU, just because we use some function both from reader and from updater. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4a7bc63b9cba..78a6634653a2 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1434,7 +1434,7 @@ extern struct ip_vs_dest * ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol, __u32 fwmark, __u32 flags); -extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); +extern void ip_vs_try_bind_dest(struct ip_vs_conn *cp); static inline void ip_vs_dest_hold(struct ip_vs_dest *dest) { -- cgit v1.2.3 From ceec4c3816818459d90c92152e61371ff5b1d5a1 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Mar 2013 11:46:53 +0200 Subject: ipvs: convert services to rcu This is the final step in RCU conversion. Things that are removed: - svc->usecnt: now svc is accessed under RCU read lock - svc->inc: and some unused code - ip_vs_bind_pe and ip_vs_unbind_pe: no ability to replace PE - __ip_vs_svc_lock: replaced with RCU - IP_VS_WAIT_WHILE: now readers lookup svcs and dests under RCU and work in parallel with configuration Other changes: - before now, a RCU read-side critical section included the calling of the schedule method, now it is extended to include service lookup - ip_vs_svc_table and ip_vs_svc_fwm_table are now using hlist - svc->pe and svc->scheduler remain to the end (of grace period), the schedulers are prepared for such RCU readers even after done_service is called but they need to use synchronize_rcu because last ip_vs_scheduler_put can happen while RCU read-side critical sections use an outdated svc->scheduler pointer - as planned, update_service is removed - empty services can be freed immediately after grace period. If dests were present, the services are freed from the dest trash code Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 28 +++++++++------------------- 1 file changed, 9 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 78a6634653a2..f9f5b057b480 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -359,8 +359,6 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len, #define LeaveFunction(level) do {} while (0) #endif -#define IP_VS_WAIT_WHILE(expr) while (expr) { cpu_relax(); } - /* * The port number of FTP service (in network order). @@ -712,10 +710,9 @@ struct ip_vs_dest_user_kern { * and the forwarding entries */ struct ip_vs_service { - struct list_head s_list; /* for normal service table */ - struct list_head f_list; /* for fwmark-based service table */ + struct hlist_node s_list; /* for normal service table */ + struct hlist_node f_list; /* for fwmark-based service table */ atomic_t refcnt; /* reference counter */ - atomic_t usecnt; /* use counter */ u16 af; /* address family */ __u16 protocol; /* which protocol (TCP/UDP) */ @@ -730,15 +727,16 @@ struct ip_vs_service { struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ struct ip_vs_stats stats; /* statistics for the service */ - struct ip_vs_app *inc; /* bind conns to this app inc */ /* for scheduling */ - struct ip_vs_scheduler *scheduler; /* bound scheduler object */ + struct ip_vs_scheduler __rcu *scheduler; /* bound scheduler object */ spinlock_t sched_lock; /* lock sched_data */ void *sched_data; /* scheduler application data */ /* alternate persistence engine */ - struct ip_vs_pe *pe; + struct ip_vs_pe __rcu *pe; + + struct rcu_head rcu_head; }; /* Information for cached dst */ @@ -807,8 +805,6 @@ struct ip_vs_scheduler { int (*init_service)(struct ip_vs_service *svc); /* scheduling service finish */ void (*done_service)(struct ip_vs_service *svc); - /* scheduler updating service */ - int (*update_service)(struct ip_vs_service *svc); /* dest is linked */ int (*add_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest); /* dest is unlinked */ @@ -1344,8 +1340,6 @@ extern void ip_vs_app_inc_put(struct ip_vs_app *inc); extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb); extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb); -void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe); -void ip_vs_unbind_pe(struct ip_vs_service *svc); int register_ip_vs_pe(struct ip_vs_pe *pe); int unregister_ip_vs_pe(struct ip_vs_pe *pe); struct ip_vs_pe *ip_vs_pe_getbyname(const char *name); @@ -1392,7 +1386,8 @@ extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); extern int ip_vs_bind_scheduler(struct ip_vs_service *svc, struct ip_vs_scheduler *scheduler); -extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc); +extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc, + struct ip_vs_scheduler *sched); extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * @@ -1412,14 +1407,9 @@ extern struct ip_vs_stats ip_vs_stats; extern int sysctl_ip_vs_sync_ver; extern struct ip_vs_service * -ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, +ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); -static inline void ip_vs_service_put(struct ip_vs_service *svc) -{ - atomic_dec(&svc->usecnt); -} - extern bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); -- cgit v1.2.3 From 8746ddcf12bb263ad240e095ef16531006caeb50 Mon Sep 17 00:00:00 2001 From: "holger@eitzenberger.org" Date: Sat, 23 Mar 2013 10:04:03 +0000 Subject: netfilter: xt_NFQUEUE: introduce CPU fanout Current NFQUEUE target uses a hash, computed over source and destination address (and other parameters), for steering the packet to the actual NFQUEUE. This, however forgets about the fact that the packet eventually is handled by a particular CPU on user request. If E. g. 1) IRQ affinity is used to handle packets on a particular CPU already (both single-queue or multi-queue case) and/or 2) RPS is used to steer packets to a specific softirq the target easily chooses an NFQUEUE which is not handled by a process pinned to the same CPU. The idea is therefore to use the CPU index for determining the NFQUEUE handling the packet. E. g. when having a system with 4 CPUs, 4 MQ queues and 4 NFQUEUEs it looks like this: +-----+ +-----+ +-----+ +-----+ |NFQ#0| |NFQ#1| |NFQ#2| |NFQ#3| +-----+ +-----+ +-----+ +-----+ ^ ^ ^ ^ | |NFQUEUE | | + + + + +-----+ +-----+ +-----+ +-----+ |rx-0 | |rx-1 | |rx-2 | |rx-3 | +-----+ +-----+ +-----+ +-----+ The NFQUEUEs not necessarily have to start with number 0, setups with less NFQUEUEs than packet-handling CPUs are not a problem as well. This patch extends the NFQUEUE target to accept a new NFQ_FLAG_CPU_FANOUT flag. If this is specified the target uses the CPU index for determining the NFQUEUE being used. I have to introduce rev3 for this. The 'flags' are folded into _v2 'bypass'. By changing the way which queue is assigned, I'm able to improve the performance if the processes reading on the NFQUEUs are pinned correctly. Signed-off-by: Holger Eitzenberger Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_NFQUEUE.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/xt_NFQUEUE.h b/include/uapi/linux/netfilter/xt_NFQUEUE.h index 9eafdbbb401c..8bb5fe657d34 100644 --- a/include/uapi/linux/netfilter/xt_NFQUEUE.h +++ b/include/uapi/linux/netfilter/xt_NFQUEUE.h @@ -26,4 +26,13 @@ struct xt_NFQ_info_v2 { __u16 bypass; }; +struct xt_NFQ_info_v3 { + __u16 queuenum; + __u16 queues_total; + __u16 flags; +#define NFQ_FLAG_BYPASS 0x01 /* for compatibility with v2 */ +#define NFQ_FLAG_CPU_FANOUT 0x02 /* use current CPU (no hashing) */ +#define NFQ_FLAG_MASK 0x03 +}; + #endif /* _XT_NFQ_TARGET_H */ -- cgit v1.2.3 From 152b0f5da798c56566737f4d0bd85f69688e7d7b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Tue, 2 Apr 2013 08:12:11 +0200 Subject: netfilter: fix struct ip6t_frag field description Signed-off-by: Michal Kubecek Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter_ipv6/ip6t_frag.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_frag.h b/include/uapi/linux/netfilter_ipv6/ip6t_frag.h index b47f61b9e082..dfd8bc2268cf 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_frag.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_frag.h @@ -4,9 +4,9 @@ #include struct ip6t_frag { - __u32 ids[2]; /* Security Parameter Index */ + __u32 ids[2]; /* Identification range */ __u32 hdrlen; /* Header Length */ - __u8 flags; /* */ + __u8 flags; /* Flags */ __u8 invflags; /* Inverse flags */ }; -- cgit v1.2.3 From 8466563e16d5198b6efeb3b51791b95b6aaacb6b Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Tue, 2 Apr 2013 13:13:07 -0400 Subject: tcp: Remove dead sysctl_tcp_cookie_size declaration Remove a declaration left over from the TCPCT-ectomy. This sysctl is no longer referenced anywhere since 1a2c6181c4 ("tcp: Remove TCPCT"). Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index d1dcb596230e..4475aaf0af57 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -282,7 +282,6 @@ extern int sysctl_tcp_base_mss; 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 int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; -- cgit v1.2.3 From 65b3841b9cb5fe1b239f12dbf033f9827d73d032 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 2 Apr 2013 09:35:07 +0000 Subject: of_net.h: Provide empty functions if OF_NET is not configured of_get_mac_address() and of_get_phy_mode() are only provided if OF_NET is configured. While most callers check for the define, not all do, and those who do require #ifdef around the code. For those who don't, the missing check can result in errors such as arch/powerpc/sysdev/tsi108_dev.c:107:3: error: implicit declaration of function 'of_get_mac_address' [-Werror=implicit-function-declaration] arch/powerpc/sysdev/mv64x60_dev.c:253:2: error: implicit declaration of function 'of_get_mac_address' [-Werror=implicit-function-declaration] Provide empty functions if OF_NET is not configured. This is safe because all callers do check the return values. Cc: David Daney Signed-off-by: Guenter Roeck Acked-by: Rob Herring Signed-off-by: David S. Miller --- include/linux/of_net.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index f47464188710..61bf53b02779 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -11,6 +11,16 @@ #include extern const int of_get_phy_mode(struct device_node *np); extern const void *of_get_mac_address(struct device_node *np); +#else +static inline const int of_get_phy_mode(struct device_node *np) +{ + return -ENODEV; +} + +static inline const void *of_get_mac_address(struct device_node *np) +{ + return NULL; +} #endif #endif /* __LINUX_OF_NET_H */ -- cgit v1.2.3 From d4299ce6b33c0afd22cf6a170cfaf89c63d1114d Mon Sep 17 00:00:00 2001 From: Andre Guedes Date: Wed, 27 Mar 2013 20:04:57 -0300 Subject: Bluetooth: Remove unneeded hci_req_cmd_status function This patch removes the hci_req_cmd_status function since it is not used anymore. The HCI request framework now considers the HCI command has complete once the Command Status or Command Complete Event is received. Signed-off-by: Andre Guedes Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 358a6983d3bb..0e7ee892d7ab 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1055,7 +1055,6 @@ void hci_req_init(struct hci_request *req, struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); -void hci_req_cmd_status(struct hci_dev *hdev, u16 opcode, u8 status); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); -- cgit v1.2.3 From b6ddb638235d90ed67af9af40e63880fd66a1939 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 2 Apr 2013 13:34:31 +0300 Subject: Bluetooth: Track received events in hdev This patch adds tracking of received HCI events to the hci_dev struct. This is necessary so that a subsequent patch can implement a function for sending a single command synchronously and returning the resulting command complete parameters in the function return value. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 0e7ee892d7ab..89eda2ef2380 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -244,6 +244,7 @@ struct hci_dev { struct sk_buff_head raw_q; struct sk_buff_head cmd_q; + struct sk_buff *recv_evt; struct sk_buff *sent_cmd; struct sk_buff *reassembly[NUM_REASSEMBLY]; -- cgit v1.2.3 From 75e84b7c522c6e07964cd1f5bf28535768a1e9fa Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 2 Apr 2013 13:35:04 +0300 Subject: Bluetooth: Add __hci_cmd_sync() helper function This patch adds a helper function for sending a single HCI command waiting for its completion and then returning back the parameters in the resulting command complete event (if there was one). The implementation is very similar to that of hci_req_sync() except that instead of invocing a callback for sending HCI commands the function constructs and sends one itself and after being woken up picks the last received event from hdev->recv_evt (if it matches the right criteria) and returns it. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 89eda2ef2380..755743d508aa 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1057,6 +1057,9 @@ int hci_req_run(struct hci_request *req, hci_req_complete_t complete); void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); +struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, + void *param, u32 timeout); + int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); -- cgit v1.2.3 From 02350a725f5bc44490c30a10e7e04a12a5ecd406 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 3 Apr 2013 21:50:29 +0300 Subject: Bluetooth: Add support for custom event terminated commands This patch adds support for having commands within HCI requests that do not result in a command complete but some other event. This is at least needed for some vendor specific commands to be issued in the hdev->setup() procecure, but might also be useful for other commands. The way that the support is implemented is by extending the skb control buffer to have a field to indicate that the command is expected to terminate with a special event. After sending the command each received event can then be compared against this field through hdev->sent_cmd. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 1 + include/net/bluetooth/hci_core.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index ed6e9552252e..591fee7d0060 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -266,6 +266,7 @@ typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status); struct hci_req_ctrl { bool start; + u8 event; hci_req_complete_t complete; }; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 755743d508aa..b85eefb230fd 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1055,6 +1055,8 @@ struct hci_request { void hci_req_init(struct hci_request *req, struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); +void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, void *param, + u8 event); void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, -- cgit v1.2.3 From 7b1abbbed0f2a1bc19bb8c0d48a284466043092a Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 3 Apr 2013 21:54:47 +0300 Subject: Bluetooth: Add __hci_cmd_sync_ev function This patch adds a __hci_cmd_sync_ev function, analogous to __hci_cmd_sync except that it also takes an event parameter to indicate that the command completes with a special event instead of command complete. Internally this new function takes advantage of the hci_req_add_ev function introduced in the previous patch. The primary expected user of this new function are the setup routines of HCI drivers which may want to send custom commands and return only when they have completed. Signed-off-by: Johan Hedberg Acked-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 b85eefb230fd..47129b1ee20b 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1061,6 +1061,8 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, void *param, u32 timeout); +struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, + void *param, u8 event, u32 timeout); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); -- cgit v1.2.3 From f41c70c4d5e3f6c2a7f9e5dfc10af452591a2484 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 12 Nov 2012 14:02:14 +0900 Subject: Bluetooth: Add driver setup stage for early init Some drivers require a special stage for their early init. This is always specific to the driver or transport. So call back into driver to allow bringing up the device. The advantage with this stage is that the Bluetooth core is actually handling the HCI layer now. This means that command and event processing is available. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 47129b1ee20b..395e8f6982f9 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -293,6 +293,7 @@ struct hci_dev { int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); + int (*setup)(struct hci_dev *hdev); int (*send)(struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); int (*ioctl)(struct hci_dev *hdev, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From 5afff03815e26abf34702ec10422535224cdfe38 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 12 Nov 2012 14:02:16 +0900 Subject: Bluetooth: Remove driver init queue from core The driver init queue is no longer needed. This can be all handled inside the drivers now. So remove it. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 395e8f6982f9..d4e13bf5ae59 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -269,8 +269,6 @@ struct hci_dev { struct hci_dev_stats stat; - struct sk_buff_head driver_init; - atomic_t promisc; struct dentry *debugfs; -- cgit v1.2.3 From 19952cc4f8f572493293a8caed27c4be89c5fc9d Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 3 Apr 2013 23:38:16 +0000 Subject: net: frag queue per hash bucket locking This patch implements per hash bucket locking for the frag queue hash. This removes two write locks, and the only remaining write lock is for protecting hash rebuild. This essentially reduce the readers-writer lock to a rebuild lock. This patch is part of "net: frag performance followup" http://thread.gmane.org/gmane.linux.network/263644 of which two patches have already been accepted: Same test setup as previous: (http://thread.gmane.org/gmane.linux.network/257155) Two 10G interfaces, on seperate NUMA nodes, are under-test, and uses Ethernet flow-control. A third interface is used for generating the DoS attack (with trafgen). Notice, I have changed the frag DoS generator script to be more efficient/deadly. Before it would only hit one RX queue, now its sending packets causing multi-queue RX, due to "better" RX hashing. Test types summary (netperf UDP_STREAM): Test-20G64K == 2x10G with 65K fragments Test-20G3F == 2x10G with 3x fragments (3*1472 bytes) Test-20G64K+DoS == Same as 20G64K with frag DoS Test-20G3F+DoS == Same as 20G3F with frag DoS Test-20G64K+MQ == Same as 20G64K with Multi-Queue frag DoS Test-20G3F+MQ == Same as 20G3F with Multi-Queue frag DoS When I rebased this-patch(03) (on top of net-next commit a210576c) and removed the _bh spinlock, I saw a performance regression. BUT this was caused by some unrelated change in-between. See tests below. Test (A) is what I reported before for patch-02, accepted in commit 1b5ab0de. Test (B) verifying-retest of commit 1b5ab0de corrospond to patch-02. Test (C) is what I reported before for this-patch Test (D) is net-next master HEAD (commit a210576c), which reveals some (unknown) performance regression (compared against test (B)). Test (D) function as a new base-test. Performance table summary (in Mbit/s): (#) Test-type: 20G64K 20G3F 20G64K+DoS 20G3F+DoS 20G64K+MQ 20G3F+MQ ---------- ------- ------- ---------- --------- -------- ------- (A) Patch-02 : 18848.7 13230.1 4103.04 5310.36 130.0 440.2 (B) 1b5ab0de : 18841.5 13156.8 4101.08 5314.57 129.0 424.2 (C) Patch-03v1: 18838.0 13490.5 4405.11 6814.72 196.6 461.6 (D) a210576c : 18321.5 11250.4 3635.34 5160.13 119.1 405.2 (E) with _bh : 17247.3 11492.6 3994.74 6405.29 166.7 413.6 (F) without bh: 17471.3 11298.7 3818.05 6102.11 165.7 406.3 Test (E) and (F) is this-patch(03), with(V1) and without(V2) the _bh spinlocks. I cannot explain the slow down for 20G64K (but its an artificial "lab-test" so I'm not worried). But the other results does show improvements. And test (E) "with _bh" version is slightly better. Signed-off-by: Jesper Dangaard Brouer Acked-by: Hannes Frederic Sowa Acked-by: Eric Dumazet ---- V2: - By analysis from Hannes Frederic Sowa and Eric Dumazet, we don't need the spinlock _bh versions, as Netfilter currently does a local_bh_disable() before entering inet_fragment. - Fold-in desc from cover-mail V3: - Drop the chain_len counter per hash bucket. Signed-off-by: David S. Miller --- include/net/inet_frag.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 7cac9c5789b5..6f41b45e819e 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -50,10 +50,16 @@ struct inet_frag_queue { */ #define INETFRAGS_MAXDEPTH 128 +struct inet_frag_bucket { + struct hlist_head chain; + spinlock_t chain_lock; +}; + struct inet_frags { - struct hlist_head hash[INETFRAGS_HASHSZ]; + struct inet_frag_bucket hash[INETFRAGS_HASHSZ]; /* This rwlock is a global lock (seperate per IPv4, IPv6 and * netfilter). Important to keep this on a seperate cacheline. + * Its primarily a rebuild protection rwlock. */ rwlock_t lock ____cacheline_aligned_in_smp; int secret_interval; -- cgit v1.2.3 From f3c1a44a2208d14b061ad665d9549c9b321f38e5 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Sun, 24 Mar 2013 23:50:39 +0000 Subject: netfilter: make /proc/net/netfilter pernet This patch makes this proc dentry pernet. So far only init_net had a /proc/net/netfilter directory. Signed-off-by: Gao feng Signed-off-by: Pablo Neira Ayuso --- include/net/net_namespace.h | 2 ++ include/net/netns/netfilter.h | 11 +++++++++++ 2 files changed, 13 insertions(+) create mode 100644 include/net/netns/netfilter.h (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index de644bcd8613..b17697827482 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include @@ -94,6 +95,7 @@ struct net { struct netns_dccp dccp; #endif #ifdef CONFIG_NETFILTER + struct netns_nf nf; struct netns_xt xt; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h new file mode 100644 index 000000000000..248ca1c68dba --- /dev/null +++ b/include/net/netns/netfilter.h @@ -0,0 +1,11 @@ +#ifndef __NETNS_NETFILTER_H +#define __NETNS_NETFILTER_H + +#include + +struct netns_nf { +#if defined CONFIG_PROC_FS + struct proc_dir_entry *proc_netfilter; +#endif +}; +#endif -- cgit v1.2.3 From 30e0c6a6bee24db0166b7ca709277cd693e179f2 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Sun, 24 Mar 2013 23:50:40 +0000 Subject: netfilter: nf_log: prepare net namespace support for loggers This patch adds netns support to nf_log and it prepares netns support for existing loggers. It is composed of four major changes. 1) nf_log_register has been split to two functions: nf_log_register and nf_log_set. The new nf_log_register is used to globally register the nf_logger and nf_log_set is used for enabling pernet support from nf_loggers. Per netns is not yet complete after this patch, it comes in separate follow up patches. 2) Add net as a parameter of nf_log_bind_pf. Per netns is not yet complete after this patch, it only allows to bind the nf_logger to the protocol family from init_net and it skips other cases. 3) Adapt all nf_log_packet callers to pass netns as parameter. After this patch, this function only works for init_net. 4) Make the sysctl net/netfilter/nf_log pernet. Signed-off-by: Gao feng Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_log.h | 14 ++++++++++---- include/net/netns/netfilter.h | 7 +++++++ 2 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index e991bd0a27af..31f1fb9eb784 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -49,12 +49,18 @@ struct nf_logger { int nf_log_register(u_int8_t pf, struct nf_logger *logger); void nf_log_unregister(struct nf_logger *logger); -int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger); -void nf_log_unbind_pf(u_int8_t pf); +void nf_log_set(struct net *net, u_int8_t pf, + const struct nf_logger *logger); +void nf_log_unset(struct net *net, const struct nf_logger *logger); + +int nf_log_bind_pf(struct net *net, u_int8_t pf, + const struct nf_logger *logger); +void nf_log_unbind_pf(struct net *net, u_int8_t pf); /* Calls the registered backend logging function */ -__printf(7, 8) -void nf_log_packet(u_int8_t pf, +__printf(8, 9) +void nf_log_packet(struct net *net, + u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 248ca1c68dba..88740024ccf3 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -2,10 +2,17 @@ #define __NETNS_NETFILTER_H #include +#include + +struct nf_logger; struct netns_nf { #if defined CONFIG_PROC_FS struct proc_dir_entry *proc_netfilter; +#endif + const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; +#ifdef CONFIG_SYSCTL + struct ctl_table_header *nf_log_dir_header; #endif }; #endif -- cgit v1.2.3 From 12202fa7573d32aa0915cde6e8fab4c86b63ca2c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 5 Apr 2013 19:40:10 +0200 Subject: netfilter: remove unneeded variable proc_net_netfilter Now that this supports net namespace for nflog and nfqueue, we can remove the global proc_net_netfilter which has no clients anymore. Based on patch from Gao feng. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index ee142846f56a..0060fde3160e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -289,11 +289,6 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif } -#ifdef CONFIG_PROC_FS -#include -extern struct proc_dir_entry *proc_net_netfilter; -#endif - #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) #define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb) -- cgit v1.2.3 From b3916db32c4a3124eee9f3742a2f4723731d7602 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 5 Apr 2013 14:57:34 +0200 Subject: Bluetooth: hidp: verify l2cap sockets We need to verify that the given sockets actually are l2cap sockets. If they aren't, we are not supposed to access bt_sk(sock) and we shouldn't start the session if the offsets turn out to be valid local BT addresses. That is, if someone passes a TCP socket to HIDCONNADD, then we access some random offset in the TCP socket (which isn't even guaranteed to be valid). Fix this by checking that the socket is an l2cap socket. Signed-off-by: David Herrmann Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/l2cap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index cdd33021f831..278830ef92cd 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -786,6 +786,7 @@ extern bool disable_ertm; int l2cap_init_sockets(void); void l2cap_cleanup_sockets(void); +bool l2cap_is_socket(struct socket *sock); void __l2cap_connect_rsp_defer(struct l2cap_chan *chan); int __l2cap_wait_ack(struct sock *sk); -- cgit v1.2.3 From 540b3a39eea0056d305f17dda47eb185c4d56ddc Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 7 Apr 2013 03:44:07 +0000 Subject: net/mlx4_en: Enable DCB ETS ops only when supported by the firmware Enable the DCB ETS ops only when supported by the firmware. For older firmware/cards which don't support ETS, advertize only PFC DCB ops. Signed-off-by: Eugenia Emantayev Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 811f91cf5e8c..1bc5a750b330 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -140,6 +140,7 @@ enum { MLX4_DEV_CAP_FLAG_VEP_UC_STEER = 1LL << 41, MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42, MLX4_DEV_CAP_FLAG_COUNTERS = 1LL << 48, + MLX4_DEV_CAP_FLAG_SET_ETH_SCHED = 1LL << 53, MLX4_DEV_CAP_FLAG_SENSE_SUPPORT = 1LL << 55, MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV = 1LL << 59, MLX4_DEV_CAP_FLAG_64B_EQE = 1LL << 61, -- cgit v1.2.3 From 6b0ee8c036ecb3ac92e18e6ca0dca7bff88beaf0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 3 Apr 2013 17:28:16 +0000 Subject: scm: Stop passing struct cred Now that uids and gids are completely encapsulated in kuid_t and kgid_t we no longer need to pass struct cred which allowed us to test both the uid and the user namespace for equality. Passing struct cred potentially allows us to pass the entire group list as BSD does but I don't believe the cost of cache line misses justifies retaining code for a future potential application. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/af_unix.h | 3 ++- include/net/scm.h | 16 ++++++---------- 2 files changed, 8 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 0a996a3517ed..a8836e8445cc 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -29,7 +29,8 @@ struct unix_address { struct unix_skb_parms { struct pid *pid; /* Skb credentials */ - const struct cred *cred; + kuid_t uid; + kgid_t gid; struct scm_fp_list *fp; /* Passed files */ #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ diff --git a/include/net/scm.h b/include/net/scm.h index 975cca01048b..5a4c6a9eb122 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -26,7 +26,6 @@ struct scm_fp_list { struct scm_cookie { struct pid *pid; /* Skb credentials */ - const struct cred *cred; struct scm_fp_list *fp; /* Passed files */ struct scm_creds creds; /* Skb credentials */ #ifdef CONFIG_SECURITY_NETWORK @@ -51,23 +50,18 @@ static __inline__ void unix_get_peersec_dgram(struct socket *sock, struct scm_co #endif /* CONFIG_SECURITY_NETWORK */ static __inline__ void scm_set_cred(struct scm_cookie *scm, - struct pid *pid, const struct cred *cred) + struct pid *pid, kuid_t uid, kgid_t gid) { scm->pid = get_pid(pid); - scm->cred = cred ? get_cred(cred) : NULL; scm->creds.pid = pid_vnr(pid); - scm->creds.uid = cred ? cred->euid : INVALID_UID; - scm->creds.gid = cred ? cred->egid : INVALID_GID; + scm->creds.uid = uid; + scm->creds.gid = gid; } static __inline__ void scm_destroy_cred(struct scm_cookie *scm) { put_pid(scm->pid); scm->pid = NULL; - - if (scm->cred) - put_cred(scm->cred); - scm->cred = NULL; } static __inline__ void scm_destroy(struct scm_cookie *scm) @@ -81,8 +75,10 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, bool forcecreds) { memset(scm, 0, sizeof(*scm)); + scm->creds.uid = INVALID_UID; + scm->creds.gid = INVALID_GID; if (forcecreds) - scm_set_cred(scm, task_tgid(current), current_cred()); + scm_set_cred(scm, task_tgid(current), current_euid(), current_egid()); unix_get_peersec_dgram(sock, scm); if (msg->msg_controllen <= 0) return 0; -- cgit v1.2.3 From 79ba1d8910f517c3bd39d794ddb1a5b4c03795c4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 27 Mar 2013 14:38:07 +0100 Subject: mac80211: parse Timeout Interval Element using a struct Instead of open-coding the accesses and length check do the length check in the IE parser and assign a struct pointer for use in the remaining code. Signed-off-by: Johannes Berg --- 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 d10b5bba3268..e46fea8b972e 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1955,6 +1955,16 @@ enum ieee80211_timeout_interval_type { WLAN_TIMEOUT_ASSOC_COMEBACK = 3 /* 802.11w */, }; +/** + * struct ieee80211_timeout_interval_ie - Timeout Interval element + * @type: type, see &enum ieee80211_timeout_interval_type + * @value: timeout interval value + */ +struct ieee80211_timeout_interval_ie { + u8 type; + __le32 value; +} __packed; + /* BACK action code */ enum ieee80211_back_actioncode { WLAN_ACTION_ADDBA_REQ = 0, -- cgit v1.2.3 From d87c8c6d1562f12df101c5b9857170d110e7353a Mon Sep 17 00:00:00 2001 From: Werner Almesberger Date: Thu, 4 Apr 2013 06:32:12 +0000 Subject: IEEE 802.15.4: remove get_bsn from "struct ieee802154_mlme_ops" It served no purpose: we never call it from anywhere in the stack and the only driver that did implement it (fakehard) merely provided a dummy value. There is also considerable doubt whether it would make sense to even attempt beacon processing at this level in the Linux kernel. Signed-off-by: Werner Almesberger Signed-off-by: David S. Miller --- include/net/ieee802154_netdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index d104c882fc29..642f94c0fa2f 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -110,7 +110,6 @@ struct ieee802154_mlme_ops { u16 (*get_pan_id)(const struct net_device *dev); u16 (*get_short_addr)(const struct net_device *dev); u8 (*get_dsn)(const struct net_device *dev); - u8 (*get_bsn)(const struct net_device *dev); }; /* The IEEE 802.15.4 standard defines 2 type of the devices: -- cgit v1.2.3 From 56aa091d60a63fee83d2c894edb69b7c159966c7 Mon Sep 17 00:00:00 2001 From: Werner Almesberger Date: Thu, 4 Apr 2013 06:32:35 +0000 Subject: ieee802154/nl-mac.c: make some MLME operations optional Check for NULL before calling the following operations from "struct ieee802154_mlme_ops": assoc_req, assoc_resp, disassoc_req, start_req, and scan_req. This fixes a current oops where those functions are called but not implemented. It also updates the documentation to clarify that they are now optional by design. If a call to an unimplemented function is attempted, the kernel returns EOPNOTSUPP via netlink. The following operations are still required: get_phy, get_pan_id, get_short_addr, and get_dsn. Note that the places where this patch changes the initialization of "ret" should not affect the rest of the code since "ret" was always set (again) before returning its value. Signed-off-by: Werner Almesberger Signed-off-by: David S. Miller --- include/net/ieee802154_netdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 642f94c0fa2f..8196d5d40359 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -85,6 +85,8 @@ struct wpan_phy; * Use wpan_wpy_put to put that reference. */ struct ieee802154_mlme_ops { + /* The following fields are optional (can be NULL). */ + int (*assoc_req)(struct net_device *dev, struct ieee802154_addr *addr, u8 channel, u8 page, u8 cap); @@ -101,6 +103,8 @@ struct ieee802154_mlme_ops { int (*scan_req)(struct net_device *dev, u8 type, u32 channels, u8 page, u8 duration); + /* The fields below are required. */ + struct wpan_phy *(*get_phy)(const struct net_device *dev); /* -- cgit v1.2.3 From f53adae4eae5ad9f7343ff4a0fc68b468c981138 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 8 Apr 2013 04:01:30 +0000 Subject: net: ipv6: add tokenized interface identifier support This patch adds support for IPv6 tokenized IIDs, that allow for administrators to assign well-known host-part addresses to nodes whilst still obtaining global network prefix from Router Advertisements. It is currently in draft status. The primary target for such support is server platforms where addresses are usually manually configured, rather than using DHCPv6 or SLAAC. By using tokenised identifiers, hosts can still determine their network prefix by use of SLAAC, but more readily be automatically renumbered should their network prefix change. [...] The disadvantage with static addresses is that they are likely to require manual editing should the network prefix in use change. If instead there were a method to only manually configure the static identifier part of the IPv6 address, then the address could be automatically updated when a new prefix was introduced, as described in [RFC4192] for example. In such cases a DNS server might be configured with such a tokenised interface identifier of ::53, and SLAAC would use the token in constructing the interface address, using the advertised prefix. [...] http://tools.ietf.org/html/draft-chown-6man-tokenised-ipv6-identifiers-02 The implementation is partially based on top of Mark K. Thompson's proof of concept. However, it uses the Netlink interface for configuration resp. data retrival, so that it can be easily extended in future. Successfully tested by myself. Cc: Hannes Frederic Sowa Cc: YOSHIFUJI Hideaki Cc: Thomas Graf Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/if_inet6.h | 2 ++ include/uapi/linux/if_link.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 93563221d29a..f1063d62cd13 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -187,6 +187,8 @@ struct inet6_dev { struct list_head tempaddr_list; #endif + struct in6_addr token; + struct neigh_parms *nd_parms; struct inet6_dev *next; struct ipv6_devconf cnf; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c4edfe11f1f7..6b35c4211f65 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -201,6 +201,7 @@ enum { IFLA_INET6_MCAST, /* MC things. What of them? */ IFLA_INET6_CACHEINFO, /* time values and max reasm size */ IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ + IFLA_INET6_TOKEN, /* device token */ __IFLA_INET6_MAX }; -- cgit v1.2.3 From 617fe29d45bdfffba2739e6512c83e766e6ae72c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2013 03:47:16 +0000 Subject: net: ipv6: only invalidate previously tokenized addresses Instead of invalidating all IPv6 addresses with global scope when one decides to use IPv6 tokens, we should only invalidate previous tokens and leave the rest intact until they expire eventually (or are intact forever). For doing this less greedy approach, we're adding a bool at the end of inet6_ifaddr structure instead, for two reasons: i) per-inet6_ifaddr flag space is already used up, making it wider might not be a good idea, since ii) also we do not necessarily need to export this information into user space. Suggested-by: Hannes Frederic Sowa Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/if_inet6.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index f1063d62cd13..100fb8cec17c 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -71,6 +71,8 @@ struct inet6_ifaddr { struct inet6_ifaddr *ifpub; int regen_count; #endif + bool tokenized; + struct rcu_head rcu; }; -- cgit v1.2.3 From 211d2f97e936d206a5e45f6f64ecbc2c51a2b46c Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Mon, 8 Apr 2013 20:03:35 +0000 Subject: cls_cgroup: remove task_struct parameter from sock_update_classid() The callers always pass current to sock_update_classid(). Signed-off-by: Li Zefan Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/cls_cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 2581638f4a3d..0fee0617fb7d 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -24,7 +24,7 @@ struct cgroup_cls_state u32 classid; }; -extern void sock_update_classid(struct sock *sk, struct task_struct *task); +extern void sock_update_classid(struct sock *sk); #if IS_BUILTIN(CONFIG_NET_CLS_CGROUP) static inline u32 task_cls_classid(struct task_struct *p) @@ -61,7 +61,7 @@ static inline u32 task_cls_classid(struct task_struct *p) } #endif #else /* !CGROUP_NET_CLS_CGROUP */ -static inline void sock_update_classid(struct sock *sk, struct task_struct *task) +static inline void sock_update_classid(struct sock *sk) { } -- cgit v1.2.3 From 6ffd46410248ee39b46c2cdafb79791c2e618932 Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Mon, 8 Apr 2013 20:03:47 +0000 Subject: netprio_cgroup: remove task_struct parameter from sock_update_netprio() The callers always pass current to sock_update_netprio(). Signed-off-by: Li Zefan Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/netprio_cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index 1d04b6f0fbd4..50ab8c26ab59 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -29,7 +29,7 @@ struct cgroup_netprio_state { struct cgroup_subsys_state css; }; -extern void sock_update_netprioidx(struct sock *sk, struct task_struct *task); +extern void sock_update_netprioidx(struct sock *sk); #if IS_BUILTIN(CONFIG_NETPRIO_CGROUP) @@ -68,7 +68,7 @@ static inline u32 task_netprioidx(struct task_struct *p) return 0; } -#define sock_update_netprioidx(sk, task) +#define sock_update_netprioidx(sk) #endif /* CONFIG_NETPRIO_CGROUP */ -- cgit v1.2.3 From 1b8664341100716202c29d67f24d67094a82971e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2013 05:54:01 +0000 Subject: net: sctp: introduce uapi header for sctp This patch introduces an UAPI header for the SCTP protocol, so that we can facilitate the maintenance and development of user land applications or libraries, in particular in terms of header synchronization. To not break compatibility, some fragments from lksctp-tools' netinet/sctp.h have been carefully included, while taking care that neither kernel nor user land breaks, so both compile fine with this change (for lksctp-tools I tested with the old netinet/sctp.h header and with a newly adapted one that includes the uapi sctp header). lksctp-tools smoke test run through successfully as well in both cases. Suggested-by: Neil Horman Cc: Neil Horman Cc: Vlad Yasevich Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +- include/net/sctp/constants.h | 1 - include/net/sctp/user.h | 782 --------------------------------------- include/uapi/linux/Kbuild | 1 + include/uapi/linux/sctp.h | 846 +++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 849 insertions(+), 787 deletions(-) delete mode 100644 include/net/sctp/user.h create mode 100644 include/uapi/linux/sctp.h (limited to 'include') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index c11a28706fa4..3bfe8d6ee248 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -53,7 +53,9 @@ #include /* We need in_addr. */ #include /* We need in6_addr. */ +#include +#include /* Section 3.1. SCTP Common Header Format */ typedef struct sctphdr { @@ -63,14 +65,10 @@ typedef struct sctphdr { __le32 checksum; } __packed sctp_sctphdr_t; -#ifdef __KERNEL__ -#include - static inline struct sctphdr *sctp_hdr(const struct sk_buff *skb) { return (struct sctphdr *)skb_transport_header(skb); } -#endif /* Section 3.2. Chunk Field Descriptions. */ typedef struct sctp_chunkhdr { diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index a7dd5c50df79..ca50e0751e47 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -49,7 +49,6 @@ #include #include /* For ipv6hdr. */ -#include #include /* For TCP states used in sctp_sock_state_t */ /* Value used for stream negotiation. */ diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h deleted file mode 100644 index 9a0ae091366d..000000000000 --- a/include/net/sctp/user.h +++ /dev/null @@ -1,782 +0,0 @@ -/* SCTP kernel implementation - * (C) Copyright IBM Corp. 2001, 2004 - * Copyright (c) 1999-2000 Cisco, Inc. - * Copyright (c) 1999-2001 Motorola, Inc. - * Copyright (c) 2002 Intel Corp. - * - * This file is part of the SCTP kernel implementation - * - * This header represents the structures and constants needed to support - * the SCTP Extension to the Sockets API. - * - * This SCTP implementation is free software; - * you can redistribute it and/or modify it under the terms of - * the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This SCTP implementation is distributed in the hope that it - * will be useful, but WITHOUT ANY WARRANTY; without even the implied - * ************************ - * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - * See the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. - * - * Please send any bug reports or fixes you make to the - * email address(es): - * lksctp developers - * - * Or submit a bug report through the following website: - * http://www.sf.net/projects/lksctp - * - * Written or modified by: - * La Monte H.P. Yarroll - * R. Stewart - * K. Morneau - * Q. Xie - * Karl Knutson - * Jon Grimm - * Daisy Chang - * Ryan Layer - * Ardelle Fan - * Sridhar Samudrala - * - * Any bugs reported given to us we will try to fix... any fixes shared will - * be incorporated into the next SCTP release. - */ - -#ifndef __net_sctp_user_h__ -#define __net_sctp_user_h__ - -#include -#include - -typedef __s32 sctp_assoc_t; - -/* The following symbols come from the Sockets API Extensions for - * SCTP . - */ -#define SCTP_RTOINFO 0 -#define SCTP_ASSOCINFO 1 -#define SCTP_INITMSG 2 -#define SCTP_NODELAY 3 /* Get/set nodelay option. */ -#define SCTP_AUTOCLOSE 4 -#define SCTP_SET_PEER_PRIMARY_ADDR 5 -#define SCTP_PRIMARY_ADDR 6 -#define SCTP_ADAPTATION_LAYER 7 -#define SCTP_DISABLE_FRAGMENTS 8 -#define SCTP_PEER_ADDR_PARAMS 9 -#define SCTP_DEFAULT_SEND_PARAM 10 -#define SCTP_EVENTS 11 -#define SCTP_I_WANT_MAPPED_V4_ADDR 12 /* Turn on/off mapped v4 addresses */ -#define SCTP_MAXSEG 13 /* Get/set maximum fragment. */ -#define SCTP_STATUS 14 -#define SCTP_GET_PEER_ADDR_INFO 15 -#define SCTP_DELAYED_ACK_TIME 16 -#define SCTP_DELAYED_ACK SCTP_DELAYED_ACK_TIME -#define SCTP_DELAYED_SACK SCTP_DELAYED_ACK_TIME -#define SCTP_CONTEXT 17 -#define SCTP_FRAGMENT_INTERLEAVE 18 -#define SCTP_PARTIAL_DELIVERY_POINT 19 /* Set/Get partial delivery point */ -#define SCTP_MAX_BURST 20 /* Set/Get max burst */ -#define SCTP_AUTH_CHUNK 21 /* Set only: add a chunk type to authenticate */ -#define SCTP_HMAC_IDENT 22 -#define SCTP_AUTH_KEY 23 -#define SCTP_AUTH_ACTIVE_KEY 24 -#define SCTP_AUTH_DELETE_KEY 25 -#define SCTP_PEER_AUTH_CHUNKS 26 /* Read only */ -#define SCTP_LOCAL_AUTH_CHUNKS 27 /* Read only */ -#define SCTP_GET_ASSOC_NUMBER 28 /* Read only */ -#define SCTP_GET_ASSOC_ID_LIST 29 /* Read only */ -#define SCTP_AUTO_ASCONF 30 -#define SCTP_PEER_ADDR_THLDS 31 - -/* Internal Socket Options. Some of the sctp library functions are - * implemented using these socket options. - */ -#define SCTP_SOCKOPT_BINDX_ADD 100 /* BINDX requests for adding addrs */ -#define SCTP_SOCKOPT_BINDX_REM 101 /* BINDX requests for removing addrs. */ -#define SCTP_SOCKOPT_PEELOFF 102 /* peel off association. */ -/* Options 104-106 are deprecated and removed. Do not use this space */ -#define SCTP_SOCKOPT_CONNECTX_OLD 107 /* CONNECTX old requests. */ -#define SCTP_GET_PEER_ADDRS 108 /* Get all peer address. */ -#define SCTP_GET_LOCAL_ADDRS 109 /* Get all local address. */ -#define SCTP_SOCKOPT_CONNECTX 110 /* CONNECTX requests. */ -#define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ -#define SCTP_GET_ASSOC_STATS 112 /* Read only */ - -/* - * 5.2.1 SCTP Initiation Structure (SCTP_INIT) - * - * This cmsghdr structure provides information for initializing new - * SCTP associations with sendmsg(). The SCTP_INITMSG socket option - * uses this same data structure. This structure is not used for - * recvmsg(). - * - * cmsg_level cmsg_type cmsg_data[] - * ------------ ------------ ---------------------- - * IPPROTO_SCTP SCTP_INIT struct sctp_initmsg - * - */ -struct sctp_initmsg { - __u16 sinit_num_ostreams; - __u16 sinit_max_instreams; - __u16 sinit_max_attempts; - __u16 sinit_max_init_timeo; -}; - -/* - * 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV) - * - * This cmsghdr structure specifies SCTP options for sendmsg() and - * describes SCTP header information about a received message through - * recvmsg(). - * - * cmsg_level cmsg_type cmsg_data[] - * ------------ ------------ ---------------------- - * IPPROTO_SCTP SCTP_SNDRCV struct sctp_sndrcvinfo - * - */ -struct sctp_sndrcvinfo { - __u16 sinfo_stream; - __u16 sinfo_ssn; - __u16 sinfo_flags; - __u32 sinfo_ppid; - __u32 sinfo_context; - __u32 sinfo_timetolive; - __u32 sinfo_tsn; - __u32 sinfo_cumtsn; - sctp_assoc_t sinfo_assoc_id; -}; - -/* - * sinfo_flags: 16 bits (unsigned integer) - * - * This field may contain any of the following flags and is composed of - * a bitwise OR of these values. - */ - -enum sctp_sinfo_flags { - SCTP_UNORDERED = 1, /* Send/receive message unordered. */ - SCTP_ADDR_OVER = 2, /* Override the primary destination. */ - SCTP_ABORT=4, /* Send an ABORT message to the peer. */ - SCTP_SACK_IMMEDIATELY = 8, /* SACK should be sent without delay */ - SCTP_EOF=MSG_FIN, /* Initiate graceful shutdown process. */ -}; - - -/* These are cmsg_types. */ -typedef enum sctp_cmsg_type { - SCTP_INIT, /* 5.2.1 SCTP Initiation Structure */ - SCTP_SNDRCV, /* 5.2.2 SCTP Header Information Structure */ -} sctp_cmsg_t; - - -/* - * 5.3.1.1 SCTP_ASSOC_CHANGE - * - * Communication notifications inform the ULP that an SCTP association - * has either begun or ended. The identifier for a new association is - * provided by this notificaion. The notification information has the - * following format: - * - */ -struct sctp_assoc_change { - __u16 sac_type; - __u16 sac_flags; - __u32 sac_length; - __u16 sac_state; - __u16 sac_error; - __u16 sac_outbound_streams; - __u16 sac_inbound_streams; - sctp_assoc_t sac_assoc_id; - __u8 sac_info[0]; -}; - -/* - * sac_state: 32 bits (signed integer) - * - * This field holds one of a number of values that communicate the - * event that happened to the association. They include: - * - * Note: The following state names deviate from the API draft as - * the names clash too easily with other kernel symbols. - */ -enum sctp_sac_state { - SCTP_COMM_UP, - SCTP_COMM_LOST, - SCTP_RESTART, - SCTP_SHUTDOWN_COMP, - SCTP_CANT_STR_ASSOC, -}; - -/* - * 5.3.1.2 SCTP_PEER_ADDR_CHANGE - * - * When a destination address on a multi-homed peer encounters a change - * an interface details event is sent. The information has the - * following structure: - */ -struct sctp_paddr_change { - __u16 spc_type; - __u16 spc_flags; - __u32 spc_length; - struct sockaddr_storage spc_aaddr; - int spc_state; - int spc_error; - sctp_assoc_t spc_assoc_id; -} __attribute__((packed, aligned(4))); - -/* - * spc_state: 32 bits (signed integer) - * - * This field holds one of a number of values that communicate the - * event that happened to the address. They include: - */ -enum sctp_spc_state { - SCTP_ADDR_AVAILABLE, - SCTP_ADDR_UNREACHABLE, - SCTP_ADDR_REMOVED, - SCTP_ADDR_ADDED, - SCTP_ADDR_MADE_PRIM, - SCTP_ADDR_CONFIRMED, -}; - - -/* - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * A remote peer may send an Operational Error message to its peer. - * This message indicates a variety of error conditions on an - * association. The entire error TLV as it appears on the wire is - * included in a SCTP_REMOTE_ERROR event. Please refer to the SCTP - * specification [SCTP] and any extensions for a list of possible - * error formats. SCTP error TLVs have the format: - */ -struct sctp_remote_error { - __u16 sre_type; - __u16 sre_flags; - __u32 sre_length; - __u16 sre_error; - sctp_assoc_t sre_assoc_id; - __u8 sre_data[0]; -}; - - -/* - * 5.3.1.4 SCTP_SEND_FAILED - * - * If SCTP cannot deliver a message it may return the message as a - * notification. - */ -struct sctp_send_failed { - __u16 ssf_type; - __u16 ssf_flags; - __u32 ssf_length; - __u32 ssf_error; - struct sctp_sndrcvinfo ssf_info; - sctp_assoc_t ssf_assoc_id; - __u8 ssf_data[0]; -}; - -/* - * ssf_flags: 16 bits (unsigned integer) - * - * The flag value will take one of the following values - * - * SCTP_DATA_UNSENT - Indicates that the data was never put on - * the wire. - * - * SCTP_DATA_SENT - Indicates that the data was put on the wire. - * Note that this does not necessarily mean that the - * data was (or was not) successfully delivered. - */ -enum sctp_ssf_flags { - SCTP_DATA_UNSENT, - SCTP_DATA_SENT, -}; - -/* - * 5.3.1.5 SCTP_SHUTDOWN_EVENT - * - * When a peer sends a SHUTDOWN, SCTP delivers this notification to - * inform the application that it should cease sending data. - */ -struct sctp_shutdown_event { - __u16 sse_type; - __u16 sse_flags; - __u32 sse_length; - sctp_assoc_t sse_assoc_id; -}; - -/* - * 5.3.1.6 SCTP_ADAPTATION_INDICATION - * - * When a peer sends a Adaptation Layer Indication parameter , SCTP - * delivers this notification to inform the application - * that of the peers requested adaptation layer. - */ -struct sctp_adaptation_event { - __u16 sai_type; - __u16 sai_flags; - __u32 sai_length; - __u32 sai_adaptation_ind; - sctp_assoc_t sai_assoc_id; -}; - -/* - * 5.3.1.7 SCTP_PARTIAL_DELIVERY_EVENT - * - * When a receiver is engaged in a partial delivery of a - * message this notification will be used to indicate - * various events. - */ -struct sctp_pdapi_event { - __u16 pdapi_type; - __u16 pdapi_flags; - __u32 pdapi_length; - __u32 pdapi_indication; - sctp_assoc_t pdapi_assoc_id; -}; - -enum { SCTP_PARTIAL_DELIVERY_ABORTED=0, }; - -struct sctp_authkey_event { - __u16 auth_type; - __u16 auth_flags; - __u32 auth_length; - __u16 auth_keynumber; - __u16 auth_altkeynumber; - __u32 auth_indication; - sctp_assoc_t auth_assoc_id; -}; - -enum { SCTP_AUTH_NEWKEY = 0, }; - -/* - * 6.1.9. SCTP_SENDER_DRY_EVENT - * - * When the SCTP stack has no more user data to send or retransmit, this - * notification is given to the user. Also, at the time when a user app - * subscribes to this event, if there is no data to be sent or - * retransmit, the stack will immediately send up this notification. - */ -struct sctp_sender_dry_event { - __u16 sender_dry_type; - __u16 sender_dry_flags; - __u32 sender_dry_length; - sctp_assoc_t sender_dry_assoc_id; -}; - -/* - * Described in Section 7.3 - * Ancillary Data and Notification Interest Options - */ -struct sctp_event_subscribe { - __u8 sctp_data_io_event; - __u8 sctp_association_event; - __u8 sctp_address_event; - __u8 sctp_send_failure_event; - __u8 sctp_peer_error_event; - __u8 sctp_shutdown_event; - __u8 sctp_partial_delivery_event; - __u8 sctp_adaptation_layer_event; - __u8 sctp_authentication_event; - __u8 sctp_sender_dry_event; -}; - -/* - * 5.3.1 SCTP Notification Structure - * - * The notification structure is defined as the union of all - * notification types. - * - */ -union sctp_notification { - struct { - __u16 sn_type; /* Notification type. */ - __u16 sn_flags; - __u32 sn_length; - } sn_header; - struct sctp_assoc_change sn_assoc_change; - struct sctp_paddr_change sn_paddr_change; - struct sctp_remote_error sn_remote_error; - struct sctp_send_failed sn_send_failed; - struct sctp_shutdown_event sn_shutdown_event; - struct sctp_adaptation_event sn_adaptation_event; - struct sctp_pdapi_event sn_pdapi_event; - struct sctp_authkey_event sn_authkey_event; - struct sctp_sender_dry_event sn_sender_dry_event; -}; - -/* Section 5.3.1 - * All standard values for sn_type flags are greater than 2^15. - * Values from 2^15 and down are reserved. - */ - -enum sctp_sn_type { - SCTP_SN_TYPE_BASE = (1<<15), - SCTP_ASSOC_CHANGE, - SCTP_PEER_ADDR_CHANGE, - SCTP_SEND_FAILED, - SCTP_REMOTE_ERROR, - SCTP_SHUTDOWN_EVENT, - SCTP_PARTIAL_DELIVERY_EVENT, - SCTP_ADAPTATION_INDICATION, - SCTP_AUTHENTICATION_EVENT, -#define SCTP_AUTHENTICATION_INDICATION SCTP_AUTHENTICATION_EVENT - SCTP_SENDER_DRY_EVENT, -}; - -/* Notification error codes used to fill up the error fields in some - * notifications. - * SCTP_PEER_ADDRESS_CHAGE : spc_error - * SCTP_ASSOC_CHANGE : sac_error - * These names should be potentially included in the draft 04 of the SCTP - * sockets API specification. - */ -typedef enum sctp_sn_error { - SCTP_FAILED_THRESHOLD, - SCTP_RECEIVED_SACK, - SCTP_HEARTBEAT_SUCCESS, - SCTP_RESPONSE_TO_USER_REQ, - SCTP_INTERNAL_ERROR, - SCTP_SHUTDOWN_GUARD_EXPIRES, - SCTP_PEER_FAULTY, -} sctp_sn_error_t; - -/* - * 7.1.1 Retransmission Timeout Parameters (SCTP_RTOINFO) - * - * The protocol parameters used to initialize and bound retransmission - * timeout (RTO) are tunable. See [SCTP] for more information on how - * these parameters are used in RTO calculation. - */ -struct sctp_rtoinfo { - sctp_assoc_t srto_assoc_id; - __u32 srto_initial; - __u32 srto_max; - __u32 srto_min; -}; - -/* - * 7.1.2 Association Parameters (SCTP_ASSOCINFO) - * - * This option is used to both examine and set various association and - * endpoint parameters. - */ -struct sctp_assocparams { - sctp_assoc_t sasoc_assoc_id; - __u16 sasoc_asocmaxrxt; - __u16 sasoc_number_peer_destinations; - __u32 sasoc_peer_rwnd; - __u32 sasoc_local_rwnd; - __u32 sasoc_cookie_life; -}; - -/* - * 7.1.9 Set Peer Primary Address (SCTP_SET_PEER_PRIMARY_ADDR) - * - * Requests that the peer mark the enclosed address as the association - * primary. The enclosed address must be one of the association's - * locally bound addresses. The following structure is used to make a - * set primary request: - */ -struct sctp_setpeerprim { - sctp_assoc_t sspp_assoc_id; - struct sockaddr_storage sspp_addr; -} __attribute__((packed, aligned(4))); - -/* - * 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR) - * - * Requests that the local SCTP stack use the enclosed peer address as - * the association primary. The enclosed address must be one of the - * association peer's addresses. The following structure is used to - * make a set peer primary request: - */ -struct sctp_prim { - sctp_assoc_t ssp_assoc_id; - struct sockaddr_storage ssp_addr; -} __attribute__((packed, aligned(4))); - -/* - * 7.1.11 Set Adaptation Layer Indicator (SCTP_ADAPTATION_LAYER) - * - * Requests that the local endpoint set the specified Adaptation Layer - * Indication parameter for all future INIT and INIT-ACK exchanges. - */ -struct sctp_setadaptation { - __u32 ssb_adaptation_ind; -}; - -/* - * 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS) - * - * Applications can enable or disable heartbeats for any peer address - * of an association, modify an address's heartbeat interval, force a - * heartbeat to be sent immediately, and adjust the address's maximum - * number of retransmissions sent before an address is considered - * unreachable. The following structure is used to access and modify an - * address's parameters: - */ -enum sctp_spp_flags { - SPP_HB_ENABLE = 1<<0, /*Enable heartbeats*/ - SPP_HB_DISABLE = 1<<1, /*Disable heartbeats*/ - SPP_HB = SPP_HB_ENABLE | SPP_HB_DISABLE, - SPP_HB_DEMAND = 1<<2, /*Send heartbeat immediately*/ - SPP_PMTUD_ENABLE = 1<<3, /*Enable PMTU discovery*/ - SPP_PMTUD_DISABLE = 1<<4, /*Disable PMTU discovery*/ - SPP_PMTUD = SPP_PMTUD_ENABLE | SPP_PMTUD_DISABLE, - SPP_SACKDELAY_ENABLE = 1<<5, /*Enable SACK*/ - SPP_SACKDELAY_DISABLE = 1<<6, /*Disable SACK*/ - SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE, - SPP_HB_TIME_IS_ZERO = 1<<7, /* Set HB delay to 0 */ -}; - -struct sctp_paddrparams { - sctp_assoc_t spp_assoc_id; - struct sockaddr_storage spp_address; - __u32 spp_hbinterval; - __u16 spp_pathmaxrxt; - __u32 spp_pathmtu; - __u32 spp_sackdelay; - __u32 spp_flags; -} __attribute__((packed, aligned(4))); - -/* - * 7.1.18. Add a chunk that must be authenticated (SCTP_AUTH_CHUNK) - * - * This set option adds a chunk type that the user is requesting to be - * received only in an authenticated way. Changes to the list of chunks - * will only effect future associations on the socket. - */ -struct sctp_authchunk { - __u8 sauth_chunk; -}; - -/* - * 7.1.19. Get or set the list of supported HMAC Identifiers (SCTP_HMAC_IDENT) - * - * This option gets or sets the list of HMAC algorithms that the local - * endpoint requires the peer to use. -*/ -struct sctp_hmacalgo { - __u32 shmac_num_idents; - __u16 shmac_idents[]; -}; - -/* - * 7.1.20. Set a shared key (SCTP_AUTH_KEY) - * - * This option will set a shared secret key which is used to build an - * association shared key. - */ -struct sctp_authkey { - sctp_assoc_t sca_assoc_id; - __u16 sca_keynumber; - __u16 sca_keylength; - __u8 sca_key[]; -}; - -/* - * 7.1.21. Get or set the active shared key (SCTP_AUTH_ACTIVE_KEY) - * - * This option will get or set the active shared key to be used to build - * the association shared key. - */ - -struct sctp_authkeyid { - sctp_assoc_t scact_assoc_id; - __u16 scact_keynumber; -}; - - -/* - * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) - * - * This option will effect the way delayed acks are performed. This - * option allows you to get or set the delayed ack time, in - * milliseconds. It also allows changing the delayed ack frequency. - * Changing the frequency to 1 disables the delayed sack algorithm. If - * the assoc_id is 0, then this sets or gets the endpoints default - * values. If the assoc_id field is non-zero, then the set or get - * effects the specified association for the one to many model (the - * assoc_id field is ignored by the one to one model). Note that if - * sack_delay or sack_freq are 0 when setting this option, then the - * current values will remain unchanged. - */ -struct sctp_sack_info { - sctp_assoc_t sack_assoc_id; - uint32_t sack_delay; - uint32_t sack_freq; -}; - -struct sctp_assoc_value { - sctp_assoc_t assoc_id; - uint32_t assoc_value; -}; - -/* - * 7.2.2 Peer Address Information - * - * Applications can retrieve information about a specific peer address - * of an association, including its reachability state, congestion - * window, and retransmission timer values. This information is - * read-only. The following structure is used to access this - * information: - */ -struct sctp_paddrinfo { - sctp_assoc_t spinfo_assoc_id; - struct sockaddr_storage spinfo_address; - __s32 spinfo_state; - __u32 spinfo_cwnd; - __u32 spinfo_srtt; - __u32 spinfo_rto; - __u32 spinfo_mtu; -} __attribute__((packed, aligned(4))); - -/* Peer addresses's state. */ -/* UNKNOWN: Peer address passed by the upper layer in sendmsg or connect[x] - * calls. - * UNCONFIRMED: Peer address received in INIT/INIT-ACK address parameters. - * Not yet confirmed by a heartbeat and not available for data - * transfers. - * ACTIVE : Peer address confirmed, active and available for data transfers. - * INACTIVE: Peer address inactive and not available for data transfers. - */ -enum sctp_spinfo_state { - SCTP_INACTIVE, - SCTP_PF, - SCTP_ACTIVE, - SCTP_UNCONFIRMED, - SCTP_UNKNOWN = 0xffff /* Value used for transport state unknown */ -}; - -/* - * 7.2.1 Association Status (SCTP_STATUS) - * - * Applications can retrieve current status information about an - * association, including association state, peer receiver window size, - * number of unacked data chunks, and number of data chunks pending - * receipt. This information is read-only. The following structure is - * used to access this information: - */ -struct sctp_status { - sctp_assoc_t sstat_assoc_id; - __s32 sstat_state; - __u32 sstat_rwnd; - __u16 sstat_unackdata; - __u16 sstat_penddata; - __u16 sstat_instrms; - __u16 sstat_outstrms; - __u32 sstat_fragmentation_point; - struct sctp_paddrinfo sstat_primary; -}; - -/* - * 7.2.3. Get the list of chunks the peer requires to be authenticated - * (SCTP_PEER_AUTH_CHUNKS) - * - * This option gets a list of chunks for a specified association that - * the peer requires to be received authenticated only. - */ -struct sctp_authchunks { - sctp_assoc_t gauth_assoc_id; - __u32 gauth_number_of_chunks; - uint8_t gauth_chunks[]; -}; - -/* - * 8.2.6. Get the Current Identifiers of Associations - * (SCTP_GET_ASSOC_ID_LIST) - * - * This option gets the current list of SCTP association identifiers of - * the SCTP associations handled by a one-to-many style socket. - */ -struct sctp_assoc_ids { - __u32 gaids_number_of_ids; - sctp_assoc_t gaids_assoc_id[]; -}; - -/* - * 8.3, 8.5 get all peer/local addresses in an association. - * This parameter struct is used by SCTP_GET_PEER_ADDRS and - * SCTP_GET_LOCAL_ADDRS socket options used internally to implement - * sctp_getpaddrs() and sctp_getladdrs() API. - */ -struct sctp_getaddrs_old { - sctp_assoc_t assoc_id; - int addr_num; - struct sockaddr __user *addrs; -}; -struct sctp_getaddrs { - sctp_assoc_t assoc_id; /*input*/ - __u32 addr_num; /*output*/ - __u8 addrs[0]; /*output, variable size*/ -}; - -/* A socket user request obtained via SCTP_GET_ASSOC_STATS that retrieves - * association stats. All stats are counts except sas_maxrto and - * sas_obs_rto_ipaddr. maxrto is the max observed rto + transport since - * the last call. Will return 0 when RTO was not update since last call - */ -struct sctp_assoc_stats { - sctp_assoc_t sas_assoc_id; /* Input */ - /* Transport of observed max RTO */ - struct sockaddr_storage sas_obs_rto_ipaddr; - __u64 sas_maxrto; /* Maximum Observed RTO for period */ - __u64 sas_isacks; /* SACKs received */ - __u64 sas_osacks; /* SACKs sent */ - __u64 sas_opackets; /* Packets sent */ - __u64 sas_ipackets; /* Packets received */ - __u64 sas_rtxchunks; /* Retransmitted Chunks */ - __u64 sas_outofseqtsns;/* TSN received > next expected */ - __u64 sas_idupchunks; /* Dups received (ordered+unordered) */ - __u64 sas_gapcnt; /* Gap Acknowledgements Received */ - __u64 sas_ouodchunks; /* Unordered data chunks sent */ - __u64 sas_iuodchunks; /* Unordered data chunks received */ - __u64 sas_oodchunks; /* Ordered data chunks sent */ - __u64 sas_iodchunks; /* Ordered data chunks received */ - __u64 sas_octrlchunks; /* Control chunks sent */ - __u64 sas_ictrlchunks; /* Control chunks received */ -}; - -/* These are bit fields for msghdr->msg_flags. See section 5.1. */ -/* On user space Linux, these live in as an enum. */ -enum sctp_msg_flags { - MSG_NOTIFICATION = 0x8000, -#define MSG_NOTIFICATION MSG_NOTIFICATION -}; - -/* - * 8.1 sctp_bindx() - * - * The flags parameter is formed from the bitwise OR of zero or more of the - * following currently defined flags: - */ -#define SCTP_BINDX_ADD_ADDR 0x01 -#define SCTP_BINDX_REM_ADDR 0x02 - -/* This is the structure that is passed as an argument(optval) to - * getsockopt(SCTP_SOCKOPT_PEELOFF). - */ -typedef struct { - sctp_assoc_t associd; - int sd; -} sctp_peeloff_arg_t; - -/* - * Peer Address Thresholds socket option - */ -struct sctp_paddrthlds { - sctp_assoc_t spt_assoc_id; - struct sockaddr_storage spt_address; - __u16 spt_pathmaxrxt; - __u16 spt_pathpfthld; -}; -#endif /* __net_sctp_user_h__ */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 5c8a1d25e21c..7df190525337 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -331,6 +331,7 @@ header-y += rtnetlink.h header-y += scc.h header-y += sched.h header-y += screen_info.h +header-y += sctp.h header-y += sdla.h header-y += seccomp.h header-y += securebits.h diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h new file mode 100644 index 000000000000..66b466e4ca08 --- /dev/null +++ b/include/uapi/linux/sctp.h @@ -0,0 +1,846 @@ +/* SCTP kernel implementation + * (C) Copyright IBM Corp. 2001, 2004 + * Copyright (c) 1999-2000 Cisco, Inc. + * Copyright (c) 1999-2001 Motorola, Inc. + * Copyright (c) 2002 Intel Corp. + * + * This file is part of the SCTP kernel implementation + * + * This header represents the structures and constants needed to support + * the SCTP Extension to the Sockets API. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, write to + * the Free Software Foundation, 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + * + * Please send any bug reports or fixes you make to the + * email address(es): + * lksctp developers + * + * Or submit a bug report through the following website: + * http://www.sf.net/projects/lksctp + * + * Written or modified by: + * La Monte H.P. Yarroll + * R. Stewart + * K. Morneau + * Q. Xie + * Karl Knutson + * Jon Grimm + * Daisy Chang + * Ryan Layer + * Ardelle Fan + * Sridhar Samudrala + * Inaky Perez-Gonzalez + * Vlad Yasevich + * + * Any bugs reported given to us we will try to fix... any fixes shared will + * be incorporated into the next SCTP release. + */ + +#ifndef _UAPI_SCTP_H +#define _UAPI_SCTP_H + +#include +#include + +typedef __s32 sctp_assoc_t; + +/* The following symbols come from the Sockets API Extensions for + * SCTP . + */ +#define SCTP_RTOINFO 0 +#define SCTP_ASSOCINFO 1 +#define SCTP_INITMSG 2 +#define SCTP_NODELAY 3 /* Get/set nodelay option. */ +#define SCTP_AUTOCLOSE 4 +#define SCTP_SET_PEER_PRIMARY_ADDR 5 +#define SCTP_PRIMARY_ADDR 6 +#define SCTP_ADAPTATION_LAYER 7 +#define SCTP_DISABLE_FRAGMENTS 8 +#define SCTP_PEER_ADDR_PARAMS 9 +#define SCTP_DEFAULT_SEND_PARAM 10 +#define SCTP_EVENTS 11 +#define SCTP_I_WANT_MAPPED_V4_ADDR 12 /* Turn on/off mapped v4 addresses */ +#define SCTP_MAXSEG 13 /* Get/set maximum fragment. */ +#define SCTP_STATUS 14 +#define SCTP_GET_PEER_ADDR_INFO 15 +#define SCTP_DELAYED_ACK_TIME 16 +#define SCTP_DELAYED_ACK SCTP_DELAYED_ACK_TIME +#define SCTP_DELAYED_SACK SCTP_DELAYED_ACK_TIME +#define SCTP_CONTEXT 17 +#define SCTP_FRAGMENT_INTERLEAVE 18 +#define SCTP_PARTIAL_DELIVERY_POINT 19 /* Set/Get partial delivery point */ +#define SCTP_MAX_BURST 20 /* Set/Get max burst */ +#define SCTP_AUTH_CHUNK 21 /* Set only: add a chunk type to authenticate */ +#define SCTP_HMAC_IDENT 22 +#define SCTP_AUTH_KEY 23 +#define SCTP_AUTH_ACTIVE_KEY 24 +#define SCTP_AUTH_DELETE_KEY 25 +#define SCTP_PEER_AUTH_CHUNKS 26 /* Read only */ +#define SCTP_LOCAL_AUTH_CHUNKS 27 /* Read only */ +#define SCTP_GET_ASSOC_NUMBER 28 /* Read only */ +#define SCTP_GET_ASSOC_ID_LIST 29 /* Read only */ +#define SCTP_AUTO_ASCONF 30 +#define SCTP_PEER_ADDR_THLDS 31 + +/* Internal Socket Options. Some of the sctp library functions are + * implemented using these socket options. + */ +#define SCTP_SOCKOPT_BINDX_ADD 100 /* BINDX requests for adding addrs */ +#define SCTP_SOCKOPT_BINDX_REM 101 /* BINDX requests for removing addrs. */ +#define SCTP_SOCKOPT_PEELOFF 102 /* peel off association. */ +/* Options 104-106 are deprecated and removed. Do not use this space */ +#define SCTP_SOCKOPT_CONNECTX_OLD 107 /* CONNECTX old requests. */ +#define SCTP_GET_PEER_ADDRS 108 /* Get all peer address. */ +#define SCTP_GET_LOCAL_ADDRS 109 /* Get all local address. */ +#define SCTP_SOCKOPT_CONNECTX 110 /* CONNECTX requests. */ +#define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ +#define SCTP_GET_ASSOC_STATS 112 /* Read only */ + +/* + * 5.2.1 SCTP Initiation Structure (SCTP_INIT) + * + * This cmsghdr structure provides information for initializing new + * SCTP associations with sendmsg(). The SCTP_INITMSG socket option + * uses this same data structure. This structure is not used for + * recvmsg(). + * + * cmsg_level cmsg_type cmsg_data[] + * ------------ ------------ ---------------------- + * IPPROTO_SCTP SCTP_INIT struct sctp_initmsg + * + */ +struct sctp_initmsg { + __u16 sinit_num_ostreams; + __u16 sinit_max_instreams; + __u16 sinit_max_attempts; + __u16 sinit_max_init_timeo; +}; + +/* + * 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV) + * + * This cmsghdr structure specifies SCTP options for sendmsg() and + * describes SCTP header information about a received message through + * recvmsg(). + * + * cmsg_level cmsg_type cmsg_data[] + * ------------ ------------ ---------------------- + * IPPROTO_SCTP SCTP_SNDRCV struct sctp_sndrcvinfo + * + */ +struct sctp_sndrcvinfo { + __u16 sinfo_stream; + __u16 sinfo_ssn; + __u16 sinfo_flags; + __u32 sinfo_ppid; + __u32 sinfo_context; + __u32 sinfo_timetolive; + __u32 sinfo_tsn; + __u32 sinfo_cumtsn; + sctp_assoc_t sinfo_assoc_id; +}; + +/* + * sinfo_flags: 16 bits (unsigned integer) + * + * This field may contain any of the following flags and is composed of + * a bitwise OR of these values. + */ + +enum sctp_sinfo_flags { + SCTP_UNORDERED = 1, /* Send/receive message unordered. */ + SCTP_ADDR_OVER = 2, /* Override the primary destination. */ + SCTP_ABORT=4, /* Send an ABORT message to the peer. */ + SCTP_SACK_IMMEDIATELY = 8, /* SACK should be sent without delay */ + SCTP_EOF=MSG_FIN, /* Initiate graceful shutdown process. */ +}; + +typedef union { + __u8 raw; + struct sctp_initmsg init; + struct sctp_sndrcvinfo sndrcv; +} sctp_cmsg_data_t; + +/* These are cmsg_types. */ +typedef enum sctp_cmsg_type { + SCTP_INIT, /* 5.2.1 SCTP Initiation Structure */ +#define SCTP_INIT SCTP_INIT + SCTP_SNDRCV, /* 5.2.2 SCTP Header Information Structure */ +#define SCTP_SNDRCV SCTP_SNDRCV +} sctp_cmsg_t; + +/* + * 5.3.1.1 SCTP_ASSOC_CHANGE + * + * Communication notifications inform the ULP that an SCTP association + * has either begun or ended. The identifier for a new association is + * provided by this notificaion. The notification information has the + * following format: + * + */ +struct sctp_assoc_change { + __u16 sac_type; + __u16 sac_flags; + __u32 sac_length; + __u16 sac_state; + __u16 sac_error; + __u16 sac_outbound_streams; + __u16 sac_inbound_streams; + sctp_assoc_t sac_assoc_id; + __u8 sac_info[0]; +}; + +/* + * sac_state: 32 bits (signed integer) + * + * This field holds one of a number of values that communicate the + * event that happened to the association. They include: + * + * Note: The following state names deviate from the API draft as + * the names clash too easily with other kernel symbols. + */ +enum sctp_sac_state { + SCTP_COMM_UP, + SCTP_COMM_LOST, + SCTP_RESTART, + SCTP_SHUTDOWN_COMP, + SCTP_CANT_STR_ASSOC, +}; + +/* + * 5.3.1.2 SCTP_PEER_ADDR_CHANGE + * + * When a destination address on a multi-homed peer encounters a change + * an interface details event is sent. The information has the + * following structure: + */ +struct sctp_paddr_change { + __u16 spc_type; + __u16 spc_flags; + __u32 spc_length; + struct sockaddr_storage spc_aaddr; + int spc_state; + int spc_error; + sctp_assoc_t spc_assoc_id; +} __attribute__((packed, aligned(4))); + +/* + * spc_state: 32 bits (signed integer) + * + * This field holds one of a number of values that communicate the + * event that happened to the address. They include: + */ +enum sctp_spc_state { + SCTP_ADDR_AVAILABLE, + SCTP_ADDR_UNREACHABLE, + SCTP_ADDR_REMOVED, + SCTP_ADDR_ADDED, + SCTP_ADDR_MADE_PRIM, + SCTP_ADDR_CONFIRMED, +}; + + +/* + * 5.3.1.3 SCTP_REMOTE_ERROR + * + * A remote peer may send an Operational Error message to its peer. + * This message indicates a variety of error conditions on an + * association. The entire error TLV as it appears on the wire is + * included in a SCTP_REMOTE_ERROR event. Please refer to the SCTP + * specification [SCTP] and any extensions for a list of possible + * error formats. SCTP error TLVs have the format: + */ +struct sctp_remote_error { + __u16 sre_type; + __u16 sre_flags; + __u32 sre_length; + __u16 sre_error; + sctp_assoc_t sre_assoc_id; + __u8 sre_data[0]; +}; + + +/* + * 5.3.1.4 SCTP_SEND_FAILED + * + * If SCTP cannot deliver a message it may return the message as a + * notification. + */ +struct sctp_send_failed { + __u16 ssf_type; + __u16 ssf_flags; + __u32 ssf_length; + __u32 ssf_error; + struct sctp_sndrcvinfo ssf_info; + sctp_assoc_t ssf_assoc_id; + __u8 ssf_data[0]; +}; + +/* + * ssf_flags: 16 bits (unsigned integer) + * + * The flag value will take one of the following values + * + * SCTP_DATA_UNSENT - Indicates that the data was never put on + * the wire. + * + * SCTP_DATA_SENT - Indicates that the data was put on the wire. + * Note that this does not necessarily mean that the + * data was (or was not) successfully delivered. + */ +enum sctp_ssf_flags { + SCTP_DATA_UNSENT, + SCTP_DATA_SENT, +}; + +/* + * 5.3.1.5 SCTP_SHUTDOWN_EVENT + * + * When a peer sends a SHUTDOWN, SCTP delivers this notification to + * inform the application that it should cease sending data. + */ +struct sctp_shutdown_event { + __u16 sse_type; + __u16 sse_flags; + __u32 sse_length; + sctp_assoc_t sse_assoc_id; +}; + +/* + * 5.3.1.6 SCTP_ADAPTATION_INDICATION + * + * When a peer sends a Adaptation Layer Indication parameter , SCTP + * delivers this notification to inform the application + * that of the peers requested adaptation layer. + */ +struct sctp_adaptation_event { + __u16 sai_type; + __u16 sai_flags; + __u32 sai_length; + __u32 sai_adaptation_ind; + sctp_assoc_t sai_assoc_id; +}; + +/* + * 5.3.1.7 SCTP_PARTIAL_DELIVERY_EVENT + * + * When a receiver is engaged in a partial delivery of a + * message this notification will be used to indicate + * various events. + */ +struct sctp_pdapi_event { + __u16 pdapi_type; + __u16 pdapi_flags; + __u32 pdapi_length; + __u32 pdapi_indication; + sctp_assoc_t pdapi_assoc_id; +}; + +enum { SCTP_PARTIAL_DELIVERY_ABORTED=0, }; + +/* + * 5.3.1.8. SCTP_AUTHENTICATION_EVENT + * + * When a receiver is using authentication this message will provide + * notifications regarding new keys being made active as well as errors. + */ +struct sctp_authkey_event { + __u16 auth_type; + __u16 auth_flags; + __u32 auth_length; + __u16 auth_keynumber; + __u16 auth_altkeynumber; + __u32 auth_indication; + sctp_assoc_t auth_assoc_id; +}; + +enum { SCTP_AUTH_NEWKEY = 0, }; + +/* + * 6.1.9. SCTP_SENDER_DRY_EVENT + * + * When the SCTP stack has no more user data to send or retransmit, this + * notification is given to the user. Also, at the time when a user app + * subscribes to this event, if there is no data to be sent or + * retransmit, the stack will immediately send up this notification. + */ +struct sctp_sender_dry_event { + __u16 sender_dry_type; + __u16 sender_dry_flags; + __u32 sender_dry_length; + sctp_assoc_t sender_dry_assoc_id; +}; + +/* + * Described in Section 7.3 + * Ancillary Data and Notification Interest Options + */ +struct sctp_event_subscribe { + __u8 sctp_data_io_event; + __u8 sctp_association_event; + __u8 sctp_address_event; + __u8 sctp_send_failure_event; + __u8 sctp_peer_error_event; + __u8 sctp_shutdown_event; + __u8 sctp_partial_delivery_event; + __u8 sctp_adaptation_layer_event; + __u8 sctp_authentication_event; + __u8 sctp_sender_dry_event; +}; + +/* + * 5.3.1 SCTP Notification Structure + * + * The notification structure is defined as the union of all + * notification types. + * + */ +union sctp_notification { + struct { + __u16 sn_type; /* Notification type. */ + __u16 sn_flags; + __u32 sn_length; + } sn_header; + struct sctp_assoc_change sn_assoc_change; + struct sctp_paddr_change sn_paddr_change; + struct sctp_remote_error sn_remote_error; + struct sctp_send_failed sn_send_failed; + struct sctp_shutdown_event sn_shutdown_event; + struct sctp_adaptation_event sn_adaptation_event; + struct sctp_pdapi_event sn_pdapi_event; + struct sctp_authkey_event sn_authkey_event; + struct sctp_sender_dry_event sn_sender_dry_event; +}; + +/* Section 5.3.1 + * All standard values for sn_type flags are greater than 2^15. + * Values from 2^15 and down are reserved. + */ + +enum sctp_sn_type { + SCTP_SN_TYPE_BASE = (1<<15), + SCTP_ASSOC_CHANGE, +#define SCTP_ASSOC_CHANGE SCTP_ASSOC_CHANGE + SCTP_PEER_ADDR_CHANGE, +#define SCTP_PEER_ADDR_CHANGE SCTP_PEER_ADDR_CHANGE + SCTP_SEND_FAILED, +#define SCTP_SEND_FAILED SCTP_SEND_FAILED + SCTP_REMOTE_ERROR, +#define SCTP_REMOTE_ERROR SCTP_REMOTE_ERROR + SCTP_SHUTDOWN_EVENT, +#define SCTP_SHUTDOWN_EVENT SCTP_SHUTDOWN_EVENT + SCTP_PARTIAL_DELIVERY_EVENT, +#define SCTP_PARTIAL_DELIVERY_EVENT SCTP_PARTIAL_DELIVERY_EVENT + SCTP_ADAPTATION_INDICATION, +#define SCTP_ADAPTATION_INDICATION SCTP_ADAPTATION_INDICATION + SCTP_AUTHENTICATION_EVENT, +#define SCTP_AUTHENTICATION_INDICATION SCTP_AUTHENTICATION_EVENT + SCTP_SENDER_DRY_EVENT, +#define SCTP_SENDER_DRY_EVENT SCTP_SENDER_DRY_EVENT +}; + +/* Notification error codes used to fill up the error fields in some + * notifications. + * SCTP_PEER_ADDRESS_CHAGE : spc_error + * SCTP_ASSOC_CHANGE : sac_error + * These names should be potentially included in the draft 04 of the SCTP + * sockets API specification. + */ +typedef enum sctp_sn_error { + SCTP_FAILED_THRESHOLD, + SCTP_RECEIVED_SACK, + SCTP_HEARTBEAT_SUCCESS, + SCTP_RESPONSE_TO_USER_REQ, + SCTP_INTERNAL_ERROR, + SCTP_SHUTDOWN_GUARD_EXPIRES, + SCTP_PEER_FAULTY, +} sctp_sn_error_t; + +/* + * 7.1.1 Retransmission Timeout Parameters (SCTP_RTOINFO) + * + * The protocol parameters used to initialize and bound retransmission + * timeout (RTO) are tunable. See [SCTP] for more information on how + * these parameters are used in RTO calculation. + */ +struct sctp_rtoinfo { + sctp_assoc_t srto_assoc_id; + __u32 srto_initial; + __u32 srto_max; + __u32 srto_min; +}; + +/* + * 7.1.2 Association Parameters (SCTP_ASSOCINFO) + * + * This option is used to both examine and set various association and + * endpoint parameters. + */ +struct sctp_assocparams { + sctp_assoc_t sasoc_assoc_id; + __u16 sasoc_asocmaxrxt; + __u16 sasoc_number_peer_destinations; + __u32 sasoc_peer_rwnd; + __u32 sasoc_local_rwnd; + __u32 sasoc_cookie_life; +}; + +/* + * 7.1.9 Set Peer Primary Address (SCTP_SET_PEER_PRIMARY_ADDR) + * + * Requests that the peer mark the enclosed address as the association + * primary. The enclosed address must be one of the association's + * locally bound addresses. The following structure is used to make a + * set primary request: + */ +struct sctp_setpeerprim { + sctp_assoc_t sspp_assoc_id; + struct sockaddr_storage sspp_addr; +} __attribute__((packed, aligned(4))); + +/* + * 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR) + * + * Requests that the local SCTP stack use the enclosed peer address as + * the association primary. The enclosed address must be one of the + * association peer's addresses. The following structure is used to + * make a set peer primary request: + */ +struct sctp_prim { + sctp_assoc_t ssp_assoc_id; + struct sockaddr_storage ssp_addr; +} __attribute__((packed, aligned(4))); + +/* For backward compatibility use, define the old name too */ +#define sctp_setprim sctp_prim + +/* + * 7.1.11 Set Adaptation Layer Indicator (SCTP_ADAPTATION_LAYER) + * + * Requests that the local endpoint set the specified Adaptation Layer + * Indication parameter for all future INIT and INIT-ACK exchanges. + */ +struct sctp_setadaptation { + __u32 ssb_adaptation_ind; +}; + +/* + * 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS) + * + * Applications can enable or disable heartbeats for any peer address + * of an association, modify an address's heartbeat interval, force a + * heartbeat to be sent immediately, and adjust the address's maximum + * number of retransmissions sent before an address is considered + * unreachable. The following structure is used to access and modify an + * address's parameters: + */ +enum sctp_spp_flags { + SPP_HB_ENABLE = 1<<0, /*Enable heartbeats*/ + SPP_HB_DISABLE = 1<<1, /*Disable heartbeats*/ + SPP_HB = SPP_HB_ENABLE | SPP_HB_DISABLE, + SPP_HB_DEMAND = 1<<2, /*Send heartbeat immediately*/ + SPP_PMTUD_ENABLE = 1<<3, /*Enable PMTU discovery*/ + SPP_PMTUD_DISABLE = 1<<4, /*Disable PMTU discovery*/ + SPP_PMTUD = SPP_PMTUD_ENABLE | SPP_PMTUD_DISABLE, + SPP_SACKDELAY_ENABLE = 1<<5, /*Enable SACK*/ + SPP_SACKDELAY_DISABLE = 1<<6, /*Disable SACK*/ + SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE, + SPP_HB_TIME_IS_ZERO = 1<<7, /* Set HB delay to 0 */ +}; + +struct sctp_paddrparams { + sctp_assoc_t spp_assoc_id; + struct sockaddr_storage spp_address; + __u32 spp_hbinterval; + __u16 spp_pathmaxrxt; + __u32 spp_pathmtu; + __u32 spp_sackdelay; + __u32 spp_flags; +} __attribute__((packed, aligned(4))); + +/* + * 7.1.18. Add a chunk that must be authenticated (SCTP_AUTH_CHUNK) + * + * This set option adds a chunk type that the user is requesting to be + * received only in an authenticated way. Changes to the list of chunks + * will only effect future associations on the socket. + */ +struct sctp_authchunk { + __u8 sauth_chunk; +}; + +/* + * 7.1.19. Get or set the list of supported HMAC Identifiers (SCTP_HMAC_IDENT) + * + * This option gets or sets the list of HMAC algorithms that the local + * endpoint requires the peer to use. + */ +#ifndef __KERNEL__ +/* This here is only used by user space as is. It might not be a good idea + * to export/reveal the whole structure with reserved fields etc. + */ +enum { + SCTP_AUTH_HMAC_ID_SHA1 = 1, + SCTP_AUTH_HMAC_ID_SHA256 = 3, +}; +#endif + +struct sctp_hmacalgo { + __u32 shmac_num_idents; + __u16 shmac_idents[]; +}; + +/* Sadly, user and kernel space have different names for + * this structure member, so this is to not break anything. + */ +#define shmac_number_of_idents shmac_num_idents + +/* + * 7.1.20. Set a shared key (SCTP_AUTH_KEY) + * + * This option will set a shared secret key which is used to build an + * association shared key. + */ +struct sctp_authkey { + sctp_assoc_t sca_assoc_id; + __u16 sca_keynumber; + __u16 sca_keylength; + __u8 sca_key[]; +}; + +/* + * 7.1.21. Get or set the active shared key (SCTP_AUTH_ACTIVE_KEY) + * + * This option will get or set the active shared key to be used to build + * the association shared key. + */ + +struct sctp_authkeyid { + sctp_assoc_t scact_assoc_id; + __u16 scact_keynumber; +}; + + +/* + * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) + * + * This option will effect the way delayed acks are performed. This + * option allows you to get or set the delayed ack time, in + * milliseconds. It also allows changing the delayed ack frequency. + * Changing the frequency to 1 disables the delayed sack algorithm. If + * the assoc_id is 0, then this sets or gets the endpoints default + * values. If the assoc_id field is non-zero, then the set or get + * effects the specified association for the one to many model (the + * assoc_id field is ignored by the one to one model). Note that if + * sack_delay or sack_freq are 0 when setting this option, then the + * current values will remain unchanged. + */ +struct sctp_sack_info { + sctp_assoc_t sack_assoc_id; + uint32_t sack_delay; + uint32_t sack_freq; +}; + +struct sctp_assoc_value { + sctp_assoc_t assoc_id; + uint32_t assoc_value; +}; + +/* + * 7.2.2 Peer Address Information + * + * Applications can retrieve information about a specific peer address + * of an association, including its reachability state, congestion + * window, and retransmission timer values. This information is + * read-only. The following structure is used to access this + * information: + */ +struct sctp_paddrinfo { + sctp_assoc_t spinfo_assoc_id; + struct sockaddr_storage spinfo_address; + __s32 spinfo_state; + __u32 spinfo_cwnd; + __u32 spinfo_srtt; + __u32 spinfo_rto; + __u32 spinfo_mtu; +} __attribute__((packed, aligned(4))); + +/* Peer addresses's state. */ +/* UNKNOWN: Peer address passed by the upper layer in sendmsg or connect[x] + * calls. + * UNCONFIRMED: Peer address received in INIT/INIT-ACK address parameters. + * Not yet confirmed by a heartbeat and not available for data + * transfers. + * ACTIVE : Peer address confirmed, active and available for data transfers. + * INACTIVE: Peer address inactive and not available for data transfers. + */ +enum sctp_spinfo_state { + SCTP_INACTIVE, + SCTP_PF, + SCTP_ACTIVE, + SCTP_UNCONFIRMED, + SCTP_UNKNOWN = 0xffff /* Value used for transport state unknown */ +}; + +/* + * 7.2.1 Association Status (SCTP_STATUS) + * + * Applications can retrieve current status information about an + * association, including association state, peer receiver window size, + * number of unacked data chunks, and number of data chunks pending + * receipt. This information is read-only. The following structure is + * used to access this information: + */ +struct sctp_status { + sctp_assoc_t sstat_assoc_id; + __s32 sstat_state; + __u32 sstat_rwnd; + __u16 sstat_unackdata; + __u16 sstat_penddata; + __u16 sstat_instrms; + __u16 sstat_outstrms; + __u32 sstat_fragmentation_point; + struct sctp_paddrinfo sstat_primary; +}; + +/* + * 7.2.3. Get the list of chunks the peer requires to be authenticated + * (SCTP_PEER_AUTH_CHUNKS) + * + * This option gets a list of chunks for a specified association that + * the peer requires to be received authenticated only. + */ +struct sctp_authchunks { + sctp_assoc_t gauth_assoc_id; + __u32 gauth_number_of_chunks; + uint8_t gauth_chunks[]; +}; + +/* The broken spelling has been released already in lksctp-tools header, + * so don't break anyone, now that it's fixed. + */ +#define guth_number_of_chunks gauth_number_of_chunks + +/* Association states. */ +enum sctp_sstat_state { + SCTP_EMPTY = 0, + SCTP_CLOSED = 1, + SCTP_COOKIE_WAIT = 2, + SCTP_COOKIE_ECHOED = 3, + SCTP_ESTABLISHED = 4, + SCTP_SHUTDOWN_PENDING = 5, + SCTP_SHUTDOWN_SENT = 6, + SCTP_SHUTDOWN_RECEIVED = 7, + SCTP_SHUTDOWN_ACK_SENT = 8, +}; + +/* + * 8.2.6. Get the Current Identifiers of Associations + * (SCTP_GET_ASSOC_ID_LIST) + * + * This option gets the current list of SCTP association identifiers of + * the SCTP associations handled by a one-to-many style socket. + */ +struct sctp_assoc_ids { + __u32 gaids_number_of_ids; + sctp_assoc_t gaids_assoc_id[]; +}; + +/* + * 8.3, 8.5 get all peer/local addresses in an association. + * This parameter struct is used by SCTP_GET_PEER_ADDRS and + * SCTP_GET_LOCAL_ADDRS socket options used internally to implement + * sctp_getpaddrs() and sctp_getladdrs() API. + */ +struct sctp_getaddrs_old { + sctp_assoc_t assoc_id; + int addr_num; +#ifdef __KERNEL__ + struct sockaddr __user *addrs; +#else + struct sockaddr *addrs; +#endif +}; + +struct sctp_getaddrs { + sctp_assoc_t assoc_id; /*input*/ + __u32 addr_num; /*output*/ + __u8 addrs[0]; /*output, variable size*/ +}; + +/* A socket user request obtained via SCTP_GET_ASSOC_STATS that retrieves + * association stats. All stats are counts except sas_maxrto and + * sas_obs_rto_ipaddr. maxrto is the max observed rto + transport since + * the last call. Will return 0 when RTO was not update since last call + */ +struct sctp_assoc_stats { + sctp_assoc_t sas_assoc_id; /* Input */ + /* Transport of observed max RTO */ + struct sockaddr_storage sas_obs_rto_ipaddr; + __u64 sas_maxrto; /* Maximum Observed RTO for period */ + __u64 sas_isacks; /* SACKs received */ + __u64 sas_osacks; /* SACKs sent */ + __u64 sas_opackets; /* Packets sent */ + __u64 sas_ipackets; /* Packets received */ + __u64 sas_rtxchunks; /* Retransmitted Chunks */ + __u64 sas_outofseqtsns;/* TSN received > next expected */ + __u64 sas_idupchunks; /* Dups received (ordered+unordered) */ + __u64 sas_gapcnt; /* Gap Acknowledgements Received */ + __u64 sas_ouodchunks; /* Unordered data chunks sent */ + __u64 sas_iuodchunks; /* Unordered data chunks received */ + __u64 sas_oodchunks; /* Ordered data chunks sent */ + __u64 sas_iodchunks; /* Ordered data chunks received */ + __u64 sas_octrlchunks; /* Control chunks sent */ + __u64 sas_ictrlchunks; /* Control chunks received */ +}; + +/* These are bit fields for msghdr->msg_flags. See section 5.1. */ +/* On user space Linux, these live in as an enum. */ +enum sctp_msg_flags { + MSG_NOTIFICATION = 0x8000, +#define MSG_NOTIFICATION MSG_NOTIFICATION +}; + +/* + * 8.1 sctp_bindx() + * + * The flags parameter is formed from the bitwise OR of zero or more of the + * following currently defined flags: + */ +#define SCTP_BINDX_ADD_ADDR 0x01 +#define SCTP_BINDX_REM_ADDR 0x02 + +/* This is the structure that is passed as an argument(optval) to + * getsockopt(SCTP_SOCKOPT_PEELOFF). + */ +typedef struct { + sctp_assoc_t associd; + int sd; +} sctp_peeloff_arg_t; + +/* + * Peer Address Thresholds socket option + */ +struct sctp_paddrthlds { + sctp_assoc_t spt_assoc_id; + struct sockaddr_storage spt_address; + __u16 spt_pathmaxrxt; + __u16 spt_pathpfthld; +}; + +#endif /* _UAPI_SCTP_H */ -- cgit v1.2.3 From 0ca54f6c5fd4ce58aa044d1fc7f00d7f6cf2801c Mon Sep 17 00:00:00 2001 From: Marek Puzyniak Date: Wed, 10 Apr 2013 13:19:13 +0200 Subject: mac80211: provide SSID in IBSS mode Some drivers need SSID in AP and IBSS mode. AP SSID is provided through BSS_CHANGED_SSID notification. There was no easy way to do the same for IBSS. In IBSS mode SSID is known but was not stored in BSS configuration. Extend the AP-mode functionality to also work in IBSS mode. Signed-off-by: Marek Puzyniak Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 64faf015dd1e..0dde213dd3b6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -209,7 +209,7 @@ struct ieee80211_chanctx_conf { * @BSS_CHANGED_QOS: QoS for this association was enabled/disabled. Note * that it is only ever disabled for station mode. * @BSS_CHANGED_IDLE: Idle changed for this BSS/interface. - * @BSS_CHANGED_SSID: SSID changed for this BSS (AP mode) + * @BSS_CHANGED_SSID: SSID changed for this BSS (AP and IBSS mode) * @BSS_CHANGED_AP_PROBE_RESP: Probe Response changed for this BSS (AP mode) * @BSS_CHANGED_PS: PS changed for this BSS (STA mode) * @BSS_CHANGED_TXPOWER: TX power setting changed for this interface @@ -326,7 +326,7 @@ enum ieee80211_rssi_event { * your driver/device needs to do. * @ps: power-save mode (STA only). This flag is NOT affected by * offchannel/dynamic_ps operations. - * @ssid: The SSID of the current vif. Only valid in AP-mode. + * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. * @ssid_len: Length of SSID given in @ssid. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. * @txpower: TX power in dBm -- cgit v1.2.3 From 064f370c5fd982e1264c03f5b704e00f5e41eb36 Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Tue, 2 Apr 2013 10:25:16 +0200 Subject: NFC: llcp: Add support in getsockopt for RW, LTO, and MIU remote parameters Useful for LLCP validation tests. Signed-off-by: Thierry Escande Signed-off-by: Samuel Ortiz --- include/uapi/linux/nfc.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index 7440bc81a04b..7c6f627a717d 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -233,7 +233,10 @@ struct sockaddr_nfc_llcp { #define NFC_LLCP_DIRECTION_TX 0x01 /* socket option names */ -#define NFC_LLCP_RW 0 -#define NFC_LLCP_MIUX 1 +#define NFC_LLCP_RW 0 +#define NFC_LLCP_MIUX 1 +#define NFC_LLCP_REMOTE_MIU 2 +#define NFC_LLCP_REMOTE_LTO 3 +#define NFC_LLCP_REMOTE_RW 4 #endif /*__LINUX_NFC_H */ -- cgit v1.2.3 From 76a68ba0ae097be72dfa8f918b3139130da769a4 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 6 Apr 2013 20:28:37 +0200 Subject: Bluetooth: rename hci_conn_put to hci_conn_drop We use _get() and _put() for device ref-counting in the kernel. However, hci_conn_put() is _not_ used for ref-counting, hence, rename it to hci_conn_drop() so we can later fix ref-counting and introduce hci_conn_put(). hci_conn_hold() and hci_conn_put() are currently used to manage how long a connection should be held alive. When the last user drops the connection, we spawn a delayed work that performs the disconnect. Obviously, this has nothing to do with ref-counting for the _object_ but rather for the keep-alive of the connection. But we really _need_ proper ref-counting for the _object_ to allow connection-users like rfcomm-tty, HIDP or others. Signed-off-by: David Herrmann Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d4e13bf5ae59..78ea9c7c202c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -612,7 +612,7 @@ static inline void hci_conn_hold(struct hci_conn *conn) cancel_delayed_work(&conn->disc_work); } -static inline void hci_conn_put(struct hci_conn *conn) +static inline void hci_conn_drop(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); -- cgit v1.2.3 From ac64995da872c8ae6f74a5556fdad565829985b0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 11 Apr 2013 04:40:30 +0000 Subject: usbnet: introduce usbnet_link_change API This patch introduces the API of usbnet_link_change, so that usbnet can handle link change centrally, which may help to implement killing traffic URBs for saving USB bus bandwidth and host controller power. Signed-off-by: Ming Lei Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 0e5ac93bab10..eb021b8f53bd 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -245,5 +245,6 @@ extern void usbnet_get_drvinfo(struct net_device *, struct ethtool_drvinfo *); extern int usbnet_nway_reset(struct net_device *net); extern int usbnet_manage_power(struct usbnet *, int); +extern void usbnet_link_change(struct usbnet *, bool, bool); #endif /* __LINUX_USB_USBNET_H */ -- cgit v1.2.3 From 4b49f58fff00e6e9b24eaa31d4c6324393d76b0a Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 11 Apr 2013 04:40:40 +0000 Subject: usbnet: handle link change The link change is detected via the interrupt pipe, and bulk pipes are responsible for transfering packets, so it is reasonable to stop bulk transfer after link is reported as off. Two adavantages may be obtained with stopping bulk transfer after link becomes off: - USB bus bandwidth is saved(USB bus is shared bus except for USB3.0), for example, lots of 'IN' token packets and 'NYET' handshake packets is transfered on 2.0 bus. - probabaly power might be saved for usb host controller since cancelling bulk transfer may disable the asynchronous schedule of host controller. With this patch, when link becomes off, about ~10% performance boost can be found on bulk transfer of anther usb device which is attached to same bus with the usbnet device, see below test on next-20130410: - read from usb mass storage(Sandisk Extreme USB 3.0) on pandaboard with below command after unplugging ethernet cable: dd if=/dev/sda iflag=direct of=/dev/null bs=1M count=800 - without the patch 1, 838860800 bytes (839 MB) copied, 36.2216 s, 23.2 MB/s 2, 838860800 bytes (839 MB) copied, 35.8368 s, 23.4 MB/s 3, 838860800 bytes (839 MB) copied, 35.823 s, 23.4 MB/s 4, 838860800 bytes (839 MB) copied, 35.937 s, 23.3 MB/s 5, 838860800 bytes (839 MB) copied, 35.7365 s, 23.5 MB/s average: 23.6MB/s - with the patch 1, 838860800 bytes (839 MB) copied, 32.3817 s, 25.9 MB/s 2, 838860800 bytes (839 MB) copied, 31.7389 s, 26.4 MB/s 3, 838860800 bytes (839 MB) copied, 32.438 s, 25.9 MB/s 4, 838860800 bytes (839 MB) copied, 32.5492 s, 25.8 MB/s 5, 838860800 bytes (839 MB) copied, 31.6178 s, 26.5 MB/s average: 26.1MB/s Signed-off-by: Ming Lei Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index eb021b8f53bd..da46327fca17 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -72,6 +72,7 @@ struct usbnet { # define EVENT_DEVICE_REPORT_IDLE 8 # define EVENT_NO_RUNTIME_PM 9 # define EVENT_RX_KILL 10 +# define EVENT_LINK_CHANGE 11 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) -- cgit v1.2.3 From 44b3decb414919760c7327df05e63372c1bf5d9a Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Thu, 11 Apr 2013 11:51:36 +0200 Subject: rfkill: Add NFC to the list of supported radios And return the proper string for it. Acked-by: Johannes Berg Acked-by: Marcel Holtmann Signed-off-by: Samuel Ortiz --- include/uapi/linux/rfkill.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 2753c6cc9740..058757f7a733 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -37,6 +37,7 @@ * @RFKILL_TYPE_WWAN: switch is on a wireless WAN device. * @RFKILL_TYPE_GPS: switch is on a GPS device. * @RFKILL_TYPE_FM: switch is on a FM radio device. + * @RFKILL_TYPE_NFC: switch is on an NFC device. * @NUM_RFKILL_TYPES: number of defined rfkill types */ enum rfkill_type { @@ -48,6 +49,7 @@ enum rfkill_type { RFKILL_TYPE_WWAN, RFKILL_TYPE_GPS, RFKILL_TYPE_FM, + RFKILL_TYPE_NFC, NUM_RFKILL_TYPES, }; -- cgit v1.2.3 From be055b2f89b5842f41363b5655a33dffb51a8294 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Thu, 11 Apr 2013 11:52:20 +0200 Subject: NFC: RFKILL support All NFC devices will now get proper RFKILL support as long as they provide some dev_up and dev_down hooks. Rfkilling an NFC device will bring it down while it is left to userspace to bring it back up when being rfkill unblocked. This is very similar to what Bluetooth does. Acked-by: Marcel Holtmann Signed-off-by: Samuel Ortiz --- include/net/nfc/nfc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 87a6417fc934..5eb80bb3cbb2 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -122,6 +122,8 @@ struct nfc_dev { bool shutting_down; + struct rfkill *rfkill; + struct nfc_ops *ops; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) -- cgit v1.2.3 From 1640f28f6b839637d9b82a3c4a19120601e59c66 Mon Sep 17 00:00:00 2001 From: Franky Lin Date: Thu, 11 Apr 2013 13:28:51 +0200 Subject: brcmfmac: add support for dongle ARM CR4 core Newer WiFi chip use ARM CR4 core to achieve higher performance. Add necessary code for host driver in order to support CR4 core. Reviewed-by: Arend van Spriel Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Franky Lin Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 1 + include/linux/bcma/bcma_regs.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 0ab6712fd76b..f14a98a79c9d 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -134,6 +134,7 @@ struct bcma_host_ops { #define BCMA_CORE_I2S 0x834 #define BCMA_CORE_SDR_DDR1_MEM_CTL 0x835 /* SDR/DDR1 memory controller core */ #define BCMA_CORE_SHIM 0x837 /* SHIM component in ubus/6362 */ +#define BCMA_CORE_ARM_CR4 0x83e #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h index 7e8104bb7a7e..917dcd7965e7 100644 --- a/include/linux/bcma/bcma_regs.h +++ b/include/linux/bcma/bcma_regs.h @@ -37,6 +37,7 @@ #define BCMA_IOST_BIST_DONE 0x8000 #define BCMA_RESET_CTL 0x0800 #define BCMA_RESET_CTL_RESET 0x0001 +#define BCMA_RESET_ST 0x0804 /* BCMA PCI config space registers. */ #define BCMA_PCI_PMCSR 0x44 -- cgit v1.2.3 From 1e9ab4dd258ecbb0f1c377fd4dbe227cdb93d9bd Mon Sep 17 00:00:00 2001 From: Piotr Haber Date: Thu, 11 Apr 2013 13:28:52 +0200 Subject: brcmfmac: setup SDIO reset behavior Set device in a manner that SDIO I/O card reset will lead to WLAN backplane and PMU state reset. Reviewed-by: Hante Meuleman Reviewed-by: Arend van Spriel Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Franky (Zhenhui) Lin Signed-off-by: Piotr Haber Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 453fcc914683..b8b09eac60a4 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -316,6 +316,9 @@ #define BCMA_CC_PMU_CTL 0x0600 /* PMU control */ #define BCMA_CC_PMU_CTL_ILP_DIV 0xFFFF0000 /* ILP div mask */ #define BCMA_CC_PMU_CTL_ILP_DIV_SHIFT 16 +#define BCMA_CC_PMU_CTL_RES 0x00006000 /* reset control mask */ +#define BCMA_CC_PMU_CTL_RES_SHIFT 13 +#define BCMA_CC_PMU_CTL_RES_RELOAD 0x2 /* reload POR values */ #define BCMA_CC_PMU_CTL_PLL_UPD 0x00000400 #define BCMA_CC_PMU_CTL_NOILPONW 0x00000200 /* No ILP on wait */ #define BCMA_CC_PMU_CTL_HTREQEN 0x00000100 /* HT req enable */ -- cgit v1.2.3 From 668761ac01d6f5a36b8e5a24d4e154550e2c4c3b Mon Sep 17 00:00:00 2001 From: Hante Meuleman Date: Fri, 12 Apr 2013 10:55:55 +0200 Subject: brcmfmac: define and use platform specific data for SDIO. This patch adds support for platform specific data for SDIO fullmac devices. Currently OOB interrupts are configured by Kconfig BRCMFMAC_SDIO_OOB but that is now determined dynamically by checking availibility of platform data. Cc: Hauke Mehrtens Reviewed-by: Arend Van Spriel Reviewed-by: Franky (Zhenhui) Lin Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Piotr Haber Signed-off-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/platform_data/brcmfmac-sdio.h | 124 ++++++++++++++++++++++++++++ 1 file changed, 124 insertions(+) create mode 100644 include/linux/platform_data/brcmfmac-sdio.h (limited to 'include') diff --git a/include/linux/platform_data/brcmfmac-sdio.h b/include/linux/platform_data/brcmfmac-sdio.h new file mode 100644 index 000000000000..1ade657d5fc1 --- /dev/null +++ b/include/linux/platform_data/brcmfmac-sdio.h @@ -0,0 +1,124 @@ +/* + * Copyright (c) 2013 Broadcom Corporation + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION + * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN + * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef _LINUX_BRCMFMAC_PLATFORM_H +#define _LINUX_BRCMFMAC_PLATFORM_H + +/* + * Platform specific driver functions and data. Through the platform specific + * device data functions can be provided to help the brcmfmac driver to + * operate with the device in combination with the used platform. + * + * Use the platform data in the following (similar) way: + * + * +#include + + +static void brcmfmac_power_on(void) +{ +} + +static void brcmfmac_power_off(void) +{ +} + +static void brcmfmac_reset(void) +{ +} + +static struct brcmfmac_sdio_platform_data brcmfmac_sdio_pdata = { + .power_on = brcmfmac_power_on, + .power_off = brcmfmac_power_off, + .reset = brcmfmac_reset +}; + +static struct platform_device brcmfmac_device = { + .name = BRCMFMAC_SDIO_PDATA_NAME, + .id = PLATFORM_DEVID_NONE, + .dev.platform_data = &brcmfmac_sdio_pdata +}; + +void __init brcmfmac_init_pdata(void) +{ + brcmfmac_sdio_pdata.oob_irq_supported = true; + brcmfmac_sdio_pdata.oob_irq_nr = gpio_to_irq(GPIO_BRCMF_SDIO_OOB); + brcmfmac_sdio_pdata.oob_irq_flags = IORESOURCE_IRQ | + IORESOURCE_IRQ_HIGHLEVEL; + platform_device_register(&brcmfmac_device); +} + * + * + * Note: the brcmfmac can be loaded as module or be statically built-in into + * the kernel. If built-in then do note that it uses module_init (and + * module_exit) routines which equal device_initcall. So if you intend to + * create a module with the platform specific data for the brcmfmac and have + * it built-in to the kernel then use a higher initcall then device_initcall + * (see init.h). If this is not done then brcmfmac will load without problems + * but will not pickup the platform data. + * + * When the driver does not "detect" platform driver data then it will continue + * without reporting anything and just assume there is no data needed. Which is + * probably true for most platforms. + * + * Explanation of the platform_data fields: + * + * drive_strength: is the preferred drive_strength to be used for the SDIO + * pins. If 0 then a default value will be used. This is the target drive + * strength, the exact drive strength which will be used depends on the + * capabilities of the device. + * + * oob_irq_supported: does the board have support for OOB interrupts. SDIO + * in-band interrupts are relatively slow and for having less overhead on + * interrupt processing an out of band interrupt can be used. If the HW + * supports this then enable this by setting this field to true and configure + * the oob related fields. + * + * oob_irq_nr, oob_irq_flags: the OOB interrupt information. The values are + * used for registering the irq using request_irq function. + * + * power_on: This function is called by the brcmfmac when the module gets + * loaded. This can be particularly useful for low power devices. The platform + * spcific routine may for example decide to power up the complete device. + * If there is no use-case for this function then provide NULL. + * + * power_off: This function is called by the brcmfmac when the module gets + * unloaded. At this point the device can be powered down or otherwise be reset. + * So if an actual power_off is not supported but reset is then reset the device + * when this function gets called. This can be particularly useful for low power + * devices. If there is no use-case for this function (either power-down or + * reset) then provide NULL. + * + * reset: This function can get called if the device communication broke down. + * This functionality is particularly useful in case of SDIO type devices. It is + * possible to reset a dongle via sdio data interface, but it requires that + * this is fully functional. This function is chip/module specific and this + * function should return only after the complete reset has completed. + */ + +#define BRCMFMAC_SDIO_PDATA_NAME "brcmfmac_sdio" + +struct brcmfmac_sdio_platform_data { + unsigned int drive_strength; + bool oob_irq_supported; + unsigned int oob_irq_nr; + unsigned long oob_irq_flags; + void (*power_on)(void); + void (*power_off)(void); + void (*reset)(void); +}; + +#endif /* _LINUX_BRCMFMAC_PLATFORM_H */ -- cgit v1.2.3 From d6a4a10411764cf1c3a5dad4f06c5ebe5194488b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 12 Apr 2013 11:31:52 +0000 Subject: tcp: GSO should be TSQ friendly I noticed that TSQ (TCP Small queues) was less effective when TSO is turned off, and GSO is on. If BQL is not enabled, TSQ has then no effect. It turns out the GSO engine frees the original gso_skb at the time the fragments are generated and queued to the NIC. We should instead call the tcp_wfree() destructor for the last fragment, to keep the flow control as intended in TSQ. This effectively limits the number of queued packets on qdisc + NIC layers. Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Yuchung Cheng Cc: Nandita Dukkipati Cc: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 4475aaf0af57..5bba80fbd1d9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -370,6 +370,7 @@ extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, extern int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); extern void tcp_release_cb(struct sock *sk); +extern void tcp_wfree(struct sk_buff *skb); extern void tcp_write_timer_handler(struct sock *sk); extern void tcp_delack_timer_handler(struct sock *sk); extern int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); -- cgit v1.2.3 From bf84a01063eaab2f1a37d72d1b903445b3a25a4e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 14 Apr 2013 08:08:13 +0000 Subject: net: sock: make sock_tx_timestamp void Currently, sock_tx_timestamp() always returns 0. The comment that describes the sock_tx_timestamp() function wrongly says that it returns an error when an invalid argument is passed (from commit 20d4947353be, ``net: socket infrastructure for SO_TIMESTAMPING''). Make the function void, so that we can also remove all the unneeded if conditions that check for such a _non-existant_ error case in the output path. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/sock.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 08f05f964737..5c97b0fc5623 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2159,10 +2159,9 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, * @sk: socket sending this packet * @tx_flags: filled with instructions for time stamping * - * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if - * parameters are invalid. + * Currently only depends on SOCK_TIMESTAMPING* flags. */ -extern int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags); +extern void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags); /** * sk_eat_skb - Release a skb if it is no longer needed -- cgit v1.2.3 From ff2266cddd69f5e0c9d5121ed9218d2f694406cc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 15 Apr 2013 03:27:17 +0000 Subject: net: sctp: remove sctp_ep_common struct member 'malloced' There is actually no need to keep this member in the structure, because after init it's always 1 anyway, thus always kfree called. This seems to be an ancient leftover from the very initial implementation from 2.5 times. Only in case the initialization of an association fails, we leave base.malloced as 0, but we nevertheless kfree it in the error path in sctp_association_new(). Signed-off-by: Daniel Borkmann Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0e0f9d2322e3..3e80eedab17d 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1174,11 +1174,9 @@ struct sctp_ep_common { /* Some fields to help us manage this object. * refcnt - Reference count access to this object. * dead - Do not attempt to use this object. - * malloced - Do we need to kfree this object? */ atomic_t refcnt; char dead; - char malloced; /* What socket does this endpoint belong to? */ struct sock *sk; -- cgit v1.2.3 From 0022d2dd4d76e0e7d5c241c343a5016fdfa2ad4f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 15 Apr 2013 03:27:18 +0000 Subject: net: sctp: minor: make sctp_ep_common's member 'dead' a bool Since dead only holds two states (0,1), make it a bool instead of a 'char', which is more appropriate for its purpose. Signed-off-by: Daniel Borkmann Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 3e80eedab17d..e12aa77abc59 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1176,7 +1176,7 @@ struct sctp_ep_common { * dead - Do not attempt to use this object. */ atomic_t refcnt; - char dead; + bool dead; /* What socket does this endpoint belong to? */ struct sock *sk; -- cgit v1.2.3 From 4cd729b04285b7330edaf5a7080aa795d6d15ff3 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 15 Apr 2013 09:54:25 +0000 Subject: net: add dev_uc_sync_multiple() and dev_mc_sync_multiple() api The current implementation of dev_uc_sync/unsync() assumes that there is a strict 1-to-1 relationship between the source and destination of the sync. In other words, once an address has been synced to a destination device, it will not be synced to any other device through the sync API. However, there are some virtual devices that aggreate a number of lower devices and need to sync addresses to all of them. The current API falls short there. This patch introduces a new dev_uc_sync_multiple() api that can be called in the above circumstances and allows sync to work for every invocation. CC: Jiri Pirko Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 53d3939358a7..623b57b52195 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -209,6 +209,7 @@ struct netdev_hw_addr { #define NETDEV_HW_ADDR_T_UNICAST 4 #define NETDEV_HW_ADDR_T_MULTICAST 5 bool global_use; + int sync_cnt; int refcount; int synced; struct rcu_head rcu_head; @@ -2627,6 +2628,7 @@ extern int dev_uc_add(struct net_device *dev, const unsigned char *addr); extern int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); extern int dev_uc_del(struct net_device *dev, const unsigned char *addr); extern int dev_uc_sync(struct net_device *to, struct net_device *from); +extern int dev_uc_sync_multiple(struct net_device *to, struct net_device *from); extern void dev_uc_unsync(struct net_device *to, struct net_device *from); extern void dev_uc_flush(struct net_device *dev); extern void dev_uc_init(struct net_device *dev); @@ -2638,6 +2640,7 @@ extern int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); extern int dev_mc_del(struct net_device *dev, const unsigned char *addr); extern int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); extern int dev_mc_sync(struct net_device *to, struct net_device *from); +extern int dev_mc_sync_multiple(struct net_device *to, struct net_device *from); extern void dev_mc_unsync(struct net_device *to, struct net_device *from); extern void dev_mc_flush(struct net_device *dev); extern void dev_mc_init(struct net_device *dev); -- cgit v1.2.3 From 37799e52a29af2268d1fbe18908a0d6b9f68af88 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 14:02:26 +0100 Subject: mac80211: unify CSA action frame/beacon processing CSA action frame content should be processed as variable IEs rather than fixed to make it extensible. Unify the code and process them just like CSA in beacons to make it easier to extend for HT/VHT. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e46fea8b972e..8f80b3a93501 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -840,9 +840,7 @@ struct ieee80211_mgmt { } __packed wme_action; struct{ u8 action_code; - u8 element_id; - u8 length; - struct ieee80211_channel_sw_ie sw_elem; + u8 variable[0]; } __packed chan_switch; struct{ u8 action_code; -- cgit v1.2.3 From 1ce3e82b0eb472161313183be0033e46d5c4bbaf Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 1 Aug 2012 17:00:55 +0200 Subject: cfg80211: add ieee80211_operating_class_to_band This function converts a (global only!) operating class to an internal band identifier. This will be needed for extended channel switch support. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 57870b646974..dff96d8cafcd 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4024,6 +4024,17 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, void cfg80211_ch_switch_notify(struct net_device *dev, struct cfg80211_chan_def *chandef); +/** + * ieee80211_operating_class_to_band - convert operating class to band + * + * @operating_class: the operating class to convert + * @band: band pointer to fill + * + * Returns %true if the conversion was successful, %false otherwise. + */ +bool ieee80211_operating_class_to_band(u8 operating_class, + enum ieee80211_band *band); + /* * cfg80211_tdls_oper_request - request userspace to perform TDLS operation * @dev: the device on which the operation is requested -- cgit v1.2.3 From b4f286a1c0ad0b84c2d502b354d4d98d5a86c64b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 14:13:58 +0100 Subject: mac80211: support extended channel switch Support extended channel switch when the operating class is one of the global operating classes as defined in Annex E of 802.11-2012. If it isn't, disconnect from the AP instead. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8f80b3a93501..2a10acc65a54 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -672,6 +672,18 @@ struct ieee80211_channel_sw_ie { u8 count; } __packed; +/** + * struct ieee80211_ext_chansw_ie + * + * This structure represents the "Extended Channel Switch Announcement element" + */ +struct ieee80211_ext_chansw_ie { + u8 mode; + u8 new_operating_class; + u8 new_ch_num; + u8 count; +} __packed; + /** * struct ieee80211_tim * -- cgit v1.2.3 From 85220d71bf3ca1ba9129e0744247ae5f61bec559 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 25 Mar 2013 18:29:27 +0100 Subject: mac80211: support secondary channel offset in CSA Add support for the secondary channel offset IE in channel switch announcements. This is necessary for proper handling of CSA on HT access points. For this to work it is also necessary to convert everything here to use chandef structs instead of just channels. The driver updates aren't really correct though. In particular, the TI wl18xx driver update can't possibly be right since it just ignores the new channel width for lack of firmware API. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 11 +++++++++++ include/net/mac80211.h | 4 ++-- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2a10acc65a54..95621528436c 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -684,6 +684,16 @@ struct ieee80211_ext_chansw_ie { u8 count; } __packed; +/** + * struct ieee80211_sec_chan_offs_ie - secondary channel offset IE + * @sec_chan_offs: secondary channel offset, uses IEEE80211_HT_PARAM_CHA_SEC_* + * values here + * This structure represents the "Secondary Channel Offset element" + */ +struct ieee80211_sec_chan_offs_ie { + u8 sec_chan_offs; +} __packed; + /** * struct ieee80211_tim * @@ -1648,6 +1658,7 @@ enum ieee80211_eid { WLAN_EID_HT_CAPABILITY = 45, WLAN_EID_HT_OPERATION = 61, + WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62, WLAN_EID_RSN = 48, WLAN_EID_MMIE = 76, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0dde213dd3b6..9ff10b33b711 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1017,13 +1017,13 @@ struct ieee80211_conf { * the driver passed into mac80211. * @block_tx: Indicates whether transmission must be blocked before the * scheduled channel switch, as indicated by the AP. - * @channel: the new channel to switch to + * @chandef: the new channel to switch to * @count: the number of TBTT's until the channel switch event */ struct ieee80211_channel_switch { u64 timestamp; bool block_tx; - struct ieee80211_channel *channel; + struct cfg80211_chan_def chandef; u8 count; }; -- cgit v1.2.3 From 1b3a2e494bc793445f576c5476e9767cf7621684 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 15:17:18 +0100 Subject: mac80211: handle extended channel switch announcement Handle the (public) extended channel switch announcement action frames. Parts of the data in these frames isn't really in IEs, but put it into the elems struct anyway to simplify the handling. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 95621528436c..ce07161c8735 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -864,6 +864,11 @@ struct ieee80211_mgmt { u8 action_code; u8 variable[0]; } __packed chan_switch; + struct{ + u8 action_code; + struct ieee80211_ext_chansw_ie data; + u8 variable[0]; + } __packed ext_chan_switch; struct{ u8 action_code; u8 dialog_token; @@ -1816,6 +1821,7 @@ enum ieee80211_key_len { /* Public action codes */ enum ieee80211_pub_actioncode { + WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, WLAN_PUB_ACTION_TDLS_DISCOVER_RES = 14, }; -- cgit v1.2.3 From b2e506bfc4d752b68a0ccaae1e977898263eba4c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 14:54:16 +0100 Subject: mac80211: parse VHT channel switch IEs VHT introduces multiple IEs that need to be parsed for a wide bandwidth channel switch. Two are (currently) needed in mac80211: * wide bandwidth channel switch element * channel switch wrapper element The former is contained in the latter for beacons and probe responses, but not for the spectrum management action frames so the IE parser needs a new argument to differentiate them. Signed-off-by: Johannes Berg --- 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 ce07161c8735..06b0ed0154a4 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -694,6 +694,14 @@ struct ieee80211_sec_chan_offs_ie { u8 sec_chan_offs; } __packed; +/** + * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE + */ +struct ieee80211_wide_bw_chansw_ie { + u8 new_channel_width; + u8 new_center_freq_seg0, new_center_freq_seg1; +} __packed; + /** * struct ieee80211_tim * @@ -1698,6 +1706,8 @@ enum ieee80211_eid { WLAN_EID_VHT_CAPABILITY = 191, WLAN_EID_VHT_OPERATION = 192, WLAN_EID_OPMODE_NOTIF = 199, + WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, + WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, /* 802.11ad */ WLAN_EID_NON_TX_BSSID_CAP = 83, -- cgit v1.2.3 From 6bc8312f95f982c0a6f26e87d0a6c299a697ed53 Mon Sep 17 00:00:00 2001 From: Karl Beldan Date: Mon, 15 Apr 2013 17:09:29 +0200 Subject: mac80211: VHT off-by-one NSS The number of VHT spatial streams (NSS) is found in: - s8 ieee80211_tx_rate.rate.idx[6:4] (tx - filled by rate control) - u8 ieee80211_rx_status.vht_nss (rx - filled by driver) Tx discriminates valid rates indexes with the sign bit and encodes NSS starting from 0 to 7 (note this matches some hw encodings e.g IWLMVM). Rx does not have the same constraints, and encodes NSS starting from 1 to 8 (note this matches what wireshark expects in the radiotap header). To handle ieee80211_tx_rate.rate.idx[6:4] ieee80211_rate_set_vht() and ieee80211_rate_get_vht_nss() assume their nss parameter and return value respectively runs from 0 to 7. ATM, there are only 2 users of these: cfg.c:sta_set_rate_info_t() and iwlwifi/mvm/tx.c:iwl_mvm_hwrate_to_tx_control(), but both assume nss runs from 1 to 8. This patch fixes this inconsistency by making ieee80211_rate_set_vht() and ieee80211_rate_get_vht_nss() handle an nss running from 1 to 8. Signed-off-by: Karl Beldan Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9ff10b33b711..bc5d8184c489 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -601,8 +601,8 @@ static inline void ieee80211_rate_set_vht(struct ieee80211_tx_rate *rate, u8 mcs, u8 nss) { WARN_ON(mcs & ~0xF); - WARN_ON(nss & ~0x7); - rate->idx = (nss << 4) | mcs; + WARN_ON((nss - 1) & ~0x7); + rate->idx = ((nss - 1) << 4) | mcs; } static inline u8 @@ -614,7 +614,7 @@ ieee80211_rate_get_vht_mcs(const struct ieee80211_tx_rate *rate) static inline u8 ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) { - return rate->idx >> 4; + return (rate->idx >> 4) + 1; } /** -- cgit v1.2.3 From 43b5abe0640100a9e9424c91298c7993d443ffb7 Mon Sep 17 00:00:00 2001 From: Sascha Herrmann Date: Sun, 14 Apr 2013 22:33:28 +0000 Subject: at86rf230: add irq type configuration option Add option to at86rf230 platform data to configure the type of the interrupt used by the driver. The irq polarity of the device will be configured accordingly. Signed-off-by: Sascha Herrmann Signed-off-by: David S. Miller --- include/linux/spi/at86rf230.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h index b2b1afbb3202..aa327a8105ad 100644 --- a/include/linux/spi/at86rf230.h +++ b/include/linux/spi/at86rf230.h @@ -26,6 +26,20 @@ struct at86rf230_platform_data { int rstn; int slp_tr; int dig2; + + /* Setting the irq_type will configure the driver to request + * the platform irq trigger type according to the given value + * and configure the interrupt polarity of the device to the + * corresponding polarity. + * + * Allowed values are: IRQF_TRIGGER_RISING, IRQF_TRIGGER_FALLING, + * IRQF_TRIGGER_HIGH and IRQF_TRIGGER_LOW + * + * Setting it to 0, the driver does not touch the trigger type + * configuration of the interrupt and sets the interrupt polarity + * of the device to high active (the default value). + */ + int irq_type; }; #endif -- cgit v1.2.3 From c7995c43facc6e5dea4de63fa9d283a337aabeb1 Mon Sep 17 00:00:00 2001 From: Atzm Watanabe Date: Tue, 16 Apr 2013 02:50:52 +0000 Subject: vxlan: Allow setting destination to unicast address. This patch allows setting VXLAN destination to unicast address. It allows that VXLAN can be used as peer-to-peer tunnel without multicast. v4: generalize struct vxlan_dev, "gaddr" is replaced with vxlan_rdst. "GROUP" attribute is replaced with "REMOTE". they are based by David Stevens's comments. v3: move a new attribute REMOTE into the last of an enum list based by Stephen Hemminger's comments. v2: use a new attribute REMOTE instead of GROUP based by Cong Wang's comments. Signed-off-by: Atzm Watanabe Acked-by: David L Stevens Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6b35c4211f65..9922704f08af 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -296,7 +296,7 @@ enum macvlan_mode { enum { IFLA_VXLAN_UNSPEC, IFLA_VXLAN_ID, - IFLA_VXLAN_GROUP, + IFLA_VXLAN_REMOTE, IFLA_VXLAN_LINK, IFLA_VXLAN_LOCAL, IFLA_VXLAN_TTL, -- cgit v1.2.3 From 2ffbe6d333664a089f17b13aa79eefe38f794bb7 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 16 Apr 2013 13:38:42 +0200 Subject: mac80211: fix and optimize MCS mask handling Currently the code always copies the configured MCS mask (even if it is set to default), but only uses it if legacy rates were also masked out. Fix this by adding a flag that tracks whether the configured MCS mask is set to default or not. Optimize the code further by storing a pointer to the configured rate mask in txrc instead of using memcpy. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index bc5d8184c489..05dbb9788504 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4107,7 +4107,7 @@ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn); * (deprecated; this will be removed once drivers get updated to use * rate_idx_mask) * @rate_idx_mask: user-requested (legacy) rate mask - * @rate_idx_mcs_mask: user-requested MCS rate mask + * @rate_idx_mcs_mask: user-requested MCS rate mask (NULL if not in use) * @bss: whether this frame is sent out in AP or IBSS mode */ struct ieee80211_tx_rate_control { @@ -4119,7 +4119,7 @@ struct ieee80211_tx_rate_control { bool rts, short_preamble; u8 max_rate_idx; u32 rate_idx_mask; - u8 rate_idx_mcs_mask[IEEE80211_HT_MCS_MASK_LEN]; + u8 *rate_idx_mcs_mask; bool bss; }; -- cgit v1.2.3 From 991fec091061b901e4fdcc8af4fd25d24a5a7bab Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 16 Apr 2013 13:38:43 +0200 Subject: mac80211: fix CTS protection handling The rates[0] CTS and RTS flags are only set after rate control has been called, so minstrel cannot use them to for setting the number of retries. This patch adds two new flags to explicitly indicate RTS/CTS use. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 05dbb9788504..4f693a5c54de 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -655,7 +655,9 @@ struct ieee80211_tx_info { struct ieee80211_tx_rate rates[ IEEE80211_TX_MAX_RATES]; s8 rts_cts_rate_idx; - /* 3 bytes free */ + u8 use_rts:1; + u8 use_cts_prot:1; + /* 2 bytes free */ }; /* only needed before rate control */ unsigned long jiffies; -- cgit v1.2.3 From fc225c3f5d1b6aa6f99c5c300af4605e4923ce79 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 6 Apr 2013 20:28:38 +0200 Subject: Bluetooth: remove unneeded hci_conn_hold/put_device() hci_conn_hold/put_device() is used to control when hci_conn->dev is no longer needed and can be deleted from the system. Lets first look how they are currently used throughout the code (excluding HIDP!). All code that uses hci_conn_hold_device() looks like this: ... hci_conn_hold_device(); hci_conn_add_sysfs(); ... On the other side, hci_conn_put_device() is exclusively used in hci_conn_del(). So, considering that hci_conn_del() must not be called twice (which would fail horribly), we know that hci_conn_put_device() is only called _once_ (which is in hci_conn_del()). On the other hand, hci_conn_add_sysfs() must not be called twice, either (it would call device_add twice, which breaks the device, see drivers/base/core.c). So we know that hci_conn_hold_device() is also called only once (it's only called directly before hci_conn_add_sysfs()). So hold and put are known to be called only once. That means we can safely remove them and directly call hci_conn_del_sysfs() in hci_conn_del(). But there is one issue left: HIDP also uses hci_conn_hold/put_device(). However, this case can be ignored and simply removed as it is totally broken. The issue is, the only thing HIDP delays with hci_conn_hold_device() is the removal of the hci_conn->dev from sysfs. But, the hci_conn device has no mechanism to get notified when its own parent (hci_dev) gets removed from sysfs. hci_dev_hold/put() does _not_ control when it is removed but only when the device object is created and destroyed. And hci_dev calls hci_conn_flush_*() when it removes itself from sysfs, which itself causes hci_conn_del() to be called, but it does _not_ cause hci_conn_del_sysfs() to be called, which is wrong. Hence, we fix it to call hci_conn_del_sysfs() in hci_conn_del(). This guarantees that a hci_conn object is removed from sysfs _before_ its parent hci_dev is removed. The changes to HIDP look scary, wrong and broken. However, if you look at the HIDP session management, you will notice they're already broken in the exact _same_ way (ever tried "unplugging" HIDP devices? Breaks _all_ the time). So this patch only makes HIDP look _scary_ and _obviously broken_. It does not break HIDP itself, it already is! See later patches in this series which fix HIDP to use proper session-management. Signed-off-by: David Herrmann Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 78ea9c7c202c..5590cc4412c6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -345,7 +345,6 @@ struct hci_conn { struct timer_list auto_accept_timer; struct device dev; - atomic_t devref; struct hci_dev *hdev; void *l2cap_data; @@ -601,9 +600,6 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); -void hci_conn_hold_device(struct hci_conn *conn); -void hci_conn_put_device(struct hci_conn *conn); - static inline void hci_conn_hold(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); -- cgit v1.2.3 From 8d12356f33f819ec0d064e233f7ca8e59eaa38ef Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 6 Apr 2013 20:28:39 +0200 Subject: Bluetooth: introduce hci_conn ref-counting We currently do not allow using hci_conn from outside of HCI-core. However, several other users could make great use of it. This includes HIDP, rfcomm and all other sub-protocols that rely on an active connection. Hence, we now introduce hci_conn ref-counting. We currently never call get_device(). put_device() is exclusively used in hci_conn_del_sysfs(). Hence, we currently never have a greater device-refcnt than 1. Therefore, it is safe to move the put_device() call from hci_conn_del_sysfs() to hci_conn_del() (it's the only caller). In fact, this even fixes a "use-after-free" bug as we access hci_conn after calling hci_conn_del_sysfs() in hci_conn_del(). From now on we can add references to hci_conn objects in other layers (like l2cap_sock, HIDP, rfcomm, ...) and grab a reference via hci_conn_get(). This does _not_ guarantee, that the connection is still alive. But, this isn't what we want. We can simply lock the hci_conn device and use "device_is_registered(hci_conn->dev)" to test that. However, this is hardly necessary as outside users should never rely on the HCI connection to be alive, anyway. Instead, they should solely rely on the device-object to be available. But if sub-devices want the hci_conn object as sysfs parent, they need to be notified when the connection drops. This will be introduced in later patches with l2cap_users. Signed-off-by: David Herrmann Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 5590cc4412c6..d324b11a0c8f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -600,6 +600,37 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); +/* + * hci_conn_get() and hci_conn_put() are used to control the life-time of an + * "hci_conn" object. They do not guarantee that the hci_conn object is running, + * working or anything else. They just guarantee that the object is available + * and can be dereferenced. So you can use its locks, local variables and any + * other constant data. + * Before accessing runtime data, you _must_ lock the object and then check that + * it is still running. As soon as you release the locks, the connection might + * get dropped, though. + * + * On the other hand, hci_conn_hold() and hci_conn_drop() are used to control + * how long the underlying connection is held. So every channel that runs on the + * hci_conn object calls this to prevent the connection from disappearing. As + * long as you hold a device, you must also guarantee that you have a valid + * reference to the device via hci_conn_get() (or the initial reference from + * hci_conn_add()). + * The hold()/drop() ref-count is known to drop below 0 sometimes, which doesn't + * break because nobody cares for that. But this means, we cannot use + * _get()/_drop() in it, but require the caller to have a valid ref (FIXME). + */ + +static inline void hci_conn_get(struct hci_conn *conn) +{ + get_device(&conn->dev); +} + +static inline void hci_conn_put(struct hci_conn *conn) +{ + put_device(&conn->dev); +} + static inline void hci_conn_hold(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); -- cgit v1.2.3 From f53c20e93612f708ed3b378ec9735b779dcd7d59 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 6 Apr 2013 20:28:42 +0200 Subject: Bluetooth: allow constant arguments for bacmp()/bacpy() There is no reason to require the source arguments to be writeable so fix this to allow constant source addresses. Signed-off-by: David Herrmann Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/bluetooth.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 591fee7d0060..6912ef9a1881 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -193,11 +193,11 @@ static inline bool bdaddr_type_is_le(__u8 type) #define BDADDR_LOCAL (&(bdaddr_t) {{0, 0, 0, 0xff, 0xff, 0xff} }) /* Copy, swap, convert BD Address */ -static inline int bacmp(bdaddr_t *ba1, bdaddr_t *ba2) +static inline int bacmp(const bdaddr_t *ba1, const bdaddr_t *ba2) { return memcmp(ba1, ba2, sizeof(bdaddr_t)); } -static inline void bacpy(bdaddr_t *dst, bdaddr_t *src) +static inline void bacpy(bdaddr_t *dst, const bdaddr_t *src) { memcpy(dst, src, sizeof(bdaddr_t)); } -- cgit v1.2.3 From 9c903e373c11f62d62bce1209f662ca92589a075 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 6 Apr 2013 20:28:44 +0200 Subject: Bluetooth: l2cap: introduce l2cap_conn ref-counting If we want to use l2cap_conn outside of l2cap_core.c, we need refcounting for these objects. Otherwise, we cannot synchronize l2cap locks with outside locks and end up with deadlocks. Hence, introduce ref-counting for l2cap_conn objects. This doesn't affect l2cap internals at all, as they use a direct synchronization. We also keep a reference to the parent hci_conn for locking purposes as l2cap_conn depends on this. This doesn't affect the connection itself but only the lifetime of the (dead) object. Signed-off-by: David Herrmann Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/l2cap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 278830ef92cd..7b4cc5b98535 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -583,6 +583,7 @@ struct l2cap_conn { struct list_head chan_l; struct mutex chan_lock; + struct kref ref; }; #define L2CAP_INFO_CL_MTU_REQ_SENT 0x01 @@ -813,4 +814,7 @@ void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, u8 status); void __l2cap_physical_cfm(struct l2cap_chan *chan, int result); +void l2cap_conn_get(struct l2cap_conn *conn); +void l2cap_conn_put(struct l2cap_conn *conn); + #endif /* __L2CAP_H */ -- cgit v1.2.3 From 2c8e1411e93391c5a78f55b09697a997474a4707 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 6 Apr 2013 20:28:45 +0200 Subject: Bluetooth: l2cap: add l2cap_user sub-modules Several sub-modules like HIDP, rfcomm, ... need to track l2cap connections. The l2cap_conn->hcon->dev object is used as parent for sysfs devices so the sub-modules need to be notified when the hci_conn object is removed from sysfs. As submodules normally use the l2cap layer, the l2cap_user objects are registered there instead of on the underlying hci_conn object. This avoids any direct dependency on the HCI layer and lets the l2cap core handle any specifics. This patch introduces l2cap_user objects which contain a "probe" and "remove" callback. You can register them on any l2cap_conn object and if it is active, the "probe" callback will get called. Otherwise, an error is returned. The l2cap_conn object will call your "remove" callback directly before it is removed from user-space. This allows you to remove your submodules _before_ the parent l2cap_conn and hci_conn object is removed. At any time you can asynchronously unregister your l2cap_user object if your submodule vanishes before the l2cap_conn object does. There is no way around l2cap_user. If we want wire-protocols in the kernel, we always want the hci_conn object as parent in the sysfs tree. We cannot use a channel here since we might need multiple channels for a single protocol. But the problem is, we _must_ get notified when an l2cap_conn object is removed. We cannot use reference-counting for object-removal! This is not how it works. If a hardware is removed, we should immediately remove the object from sysfs. Any other behavior would be inconsistent with the rest of the system. Also note that device_del() might sleep, but it doesn't wait for user-space or block very long. It only _unlinks_ the object from sysfs and the whole device-tree. Everything else is handled by ref-counts! This is exactly what the other sub-modules must do: unlink their devices when the "remove" l2cap_user callback is called. They should not do any cleanup or synchronous shutdowns. Signed-off-by: David Herrmann Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/l2cap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 7b4cc5b98535..fb94cf13c777 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -584,6 +584,13 @@ struct l2cap_conn { struct list_head chan_l; struct mutex chan_lock; struct kref ref; + struct list_head users; +}; + +struct l2cap_user { + struct list_head list; + int (*probe) (struct l2cap_conn *conn, struct l2cap_user *user); + void (*remove) (struct l2cap_conn *conn, struct l2cap_user *user); }; #define L2CAP_INFO_CL_MTU_REQ_SENT 0x01 @@ -817,4 +824,7 @@ void __l2cap_physical_cfm(struct l2cap_chan *chan, int result); void l2cap_conn_get(struct l2cap_conn *conn); void l2cap_conn_put(struct l2cap_conn *conn); +int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user); +void l2cap_unregister_user(struct l2cap_conn *conn, struct l2cap_user *user); + #endif /* __L2CAP_H */ -- cgit v1.2.3 From 542c2d832087aa78566be49aa4284779a0a687b3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 11:07:10 +0000 Subject: net: sctp: sctp_ssnmap: remove 'malloced' element from struct sctp_ssnmap_init() can only be called from sctp_ssnmap_new() where malloced is always set to 1. Thus, when we call sctp_ssnmap_free() the test for map->malloced evaluates always to true. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e12aa77abc59..3c1bb8dd1e26 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -399,7 +399,6 @@ struct sctp_stream { struct sctp_ssnmap { struct sctp_stream in; struct sctp_stream out; - int malloced; }; struct sctp_ssnmap *sctp_ssnmap_new(__u16 in, __u16 out, -- cgit v1.2.3 From ee16371e6c737684215ee10b4b9756b610d81272 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 11:07:11 +0000 Subject: net: sctp: sctp_inq: remove dead code sctp_inq is never kmalloced, since it's integrated into sctp_ep_common and only initialized from eps and assocs. Therefore, remove the dead code from there. Signed-off-by: Daniel Borkmann Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 3c1bb8dd1e26..125a19c73531 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -991,8 +991,6 @@ struct sctp_inq { * messages. */ struct work_struct immediate; - - int malloced; /* Is this structure kfree()able? */ }; void sctp_inq_init(struct sctp_inq *); -- cgit v1.2.3 From 165a4c31278c980862b2c2ddec408cf30341f3ec Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 11:07:12 +0000 Subject: net: sctp: sctp_outq: remove 'malloced' from its struct sctp_outq is embedded into sctp_association, and thus never kmalloced in any way. Also, malloced is always 0, thus kfree() is never called. Therefore, remove that dead piece of code. Signed-off-by: Daniel Borkmann Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 125a19c73531..73fd5de4d4cc 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1059,9 +1059,6 @@ struct sctp_outq { /* Is this structure empty? */ char empty; - - /* Are we kfree()able? */ - char malloced; }; void sctp_outq_init(struct sctp_association *, struct sctp_outq *); -- cgit v1.2.3 From 8fa5df6d210a09241876b74d156c57d833dd057b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 11:07:15 +0000 Subject: net: sctp: sctp_transport: remove unused variable sctp_transport's member 'malloced' is set to 1, never evaluated and the structure is kfreed anyway. So just remove it. Signed-off-by: Daniel Borkmann Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 73fd5de4d4cc..d581af00120b 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -779,10 +779,7 @@ struct sctp_transport { hb_sent:1, /* Is the Path MTU update pending on this tranport */ - pmtu_pending:1, - - /* Is this structure kfree()able? */ - malloced:1; + pmtu_pending:1; /* Has this transport moved the ctsn since we last sacked */ __u32 sack_generation; -- cgit v1.2.3 From 50181c07cbde370986c4925b830ca291a2fc31ab Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 11:07:16 +0000 Subject: net: sctp: sctp_bind_addr: remove dead code The sctp_bind_addr structure has a 'malloced' member that is always set to 0, thus in sctp_bind_addr_free() the kfree() part can never be called. This part is embedded into sctp_ep_common anyway and never alloced. Signed-off-by: Daniel Borkmann Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d581af00120b..64d469845f25 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1093,8 +1093,6 @@ struct sctp_bind_addr { * peer(s) in INIT and INIT ACK chunks. */ struct list_head address_list; - - int malloced; /* Are we kfree()able? */ }; void sctp_bind_addr_init(struct sctp_bind_addr *, __u16 port); -- cgit v1.2.3 From c1db7a26ac3f7223a38eaeb46a77d0cf9e6a0d8f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 11:07:17 +0000 Subject: net: sctp: sctp_ulpq: remove 'malloced' struct member The structure sctp_ulpq is embedded into sctp_association and never separately allocated, also ulpq->malloced is always 0, so that kfree() is never called. Therefore, remove this code. Signed-off-by: Daniel Borkmann Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/ulpqueue.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h index ff1b8ba73ab1..00e50ba3f24b 100644 --- a/include/net/sctp/ulpqueue.h +++ b/include/net/sctp/ulpqueue.h @@ -49,7 +49,6 @@ /* A structure to carry information to the ULP (e.g. Sockets API) */ struct sctp_ulpq { - char malloced; char pd_mode; struct sctp_association *asoc; struct sk_buff_head reasm; -- cgit v1.2.3 From fa5513be2b709c8ce6ff0b11d0715760a9a70ffd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fr=C3=A9d=C3=A9ric=20Dalleau?= Date: Tue, 16 Apr 2013 17:28:58 +0200 Subject: Bluetooth: Move and rename hci_conn_accept MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since this function is only used by sco, move it from hci_event.c to sco.c and rename to sco_conn_defer_accept. Make it static. Signed-off-by: Frédéric Dalleau Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d324b11a0c8f..74f77b7ef136 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -583,7 +583,6 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst); int hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); void hci_conn_check_pending(struct hci_dev *hdev); -void hci_conn_accept(struct hci_conn *conn, int mask); struct hci_chan *hci_chan_create(struct hci_conn *conn); void hci_chan_del(struct hci_chan *chan); -- cgit v1.2.3 From cad718ed2f6fd204b2c5cac6b611fc3fcde7b183 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 17 Apr 2013 15:00:51 +0300 Subject: Bluetooth: Track feature pages in a single table The local and remote features are organized by page number. Page 0 are the LMP features, page 1 the host features, and any pages beyond 1 features that future core specification versions may define. So far we've only had the first two pages and two separate variables has been convenient enough, however with the introduction of Core Specification Addendum 4 there are features defined on page 2. Instead of requiring the addition of a new variable each time a new page number is defined, this patch refactors the code to use a single table for the features. The patch needs to update both the hci_dev and hci_conn structures since there are macros that depend on the features being represented in the same way in both of them. Signed-off-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 49 ++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 74f77b7ef136..26822967e29c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -134,6 +134,8 @@ struct amp_assoc { __u8 data[HCI_MAX_AMP_ASSOC_SIZE]; }; +#define HCI_MAX_PAGES 2 + #define NUM_REASSEMBLY 4 struct hci_dev { struct list_head list; @@ -151,8 +153,7 @@ struct hci_dev { __u8 dev_class[3]; __u8 major_class; __u8 minor_class; - __u8 features[8]; - __u8 host_features[8]; + __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[8]; __u8 le_white_list_size; __u8 le_states[8]; @@ -313,7 +314,7 @@ struct hci_conn { bool out; __u8 attempt; __u8 dev_class[3]; - __u8 features[8]; + __u8 features[HCI_MAX_PAGES][8]; __u16 interval; __u16 pkt_type; __u16 link_policy; @@ -786,29 +787,29 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define SET_HCIDEV_DEV(hdev, pdev) ((hdev)->dev.parent = (pdev)) /* ----- LMP capabilities ----- */ -#define lmp_encrypt_capable(dev) ((dev)->features[0] & LMP_ENCRYPT) -#define lmp_rswitch_capable(dev) ((dev)->features[0] & LMP_RSWITCH) -#define lmp_hold_capable(dev) ((dev)->features[0] & LMP_HOLD) -#define lmp_sniff_capable(dev) ((dev)->features[0] & LMP_SNIFF) -#define lmp_park_capable(dev) ((dev)->features[1] & LMP_PARK) -#define lmp_inq_rssi_capable(dev) ((dev)->features[3] & LMP_RSSI_INQ) -#define lmp_esco_capable(dev) ((dev)->features[3] & LMP_ESCO) -#define lmp_bredr_capable(dev) (!((dev)->features[4] & LMP_NO_BREDR)) -#define lmp_le_capable(dev) ((dev)->features[4] & LMP_LE) -#define lmp_sniffsubr_capable(dev) ((dev)->features[5] & LMP_SNIFF_SUBR) -#define lmp_pause_enc_capable(dev) ((dev)->features[5] & LMP_PAUSE_ENC) -#define lmp_ext_inq_capable(dev) ((dev)->features[6] & LMP_EXT_INQ) -#define lmp_le_br_capable(dev) !!((dev)->features[6] & LMP_SIMUL_LE_BR) -#define lmp_ssp_capable(dev) ((dev)->features[6] & LMP_SIMPLE_PAIR) -#define lmp_no_flush_capable(dev) ((dev)->features[6] & LMP_NO_FLUSH) -#define lmp_lsto_capable(dev) ((dev)->features[7] & LMP_LSTO) -#define lmp_inq_tx_pwr_capable(dev) ((dev)->features[7] & LMP_INQ_TX_PWR) -#define lmp_ext_feat_capable(dev) ((dev)->features[7] & LMP_EXTFEATURES) +#define lmp_encrypt_capable(dev) ((dev)->features[0][0] & LMP_ENCRYPT) +#define lmp_rswitch_capable(dev) ((dev)->features[0][0] & LMP_RSWITCH) +#define lmp_hold_capable(dev) ((dev)->features[0][0] & LMP_HOLD) +#define lmp_sniff_capable(dev) ((dev)->features[0][0] & LMP_SNIFF) +#define lmp_park_capable(dev) ((dev)->features[0][1] & LMP_PARK) +#define lmp_inq_rssi_capable(dev) ((dev)->features[0][3] & LMP_RSSI_INQ) +#define lmp_esco_capable(dev) ((dev)->features[0][3] & LMP_ESCO) +#define lmp_bredr_capable(dev) (!((dev)->features[0][4] & LMP_NO_BREDR)) +#define lmp_le_capable(dev) ((dev)->features[0][4] & LMP_LE) +#define lmp_sniffsubr_capable(dev) ((dev)->features[0][5] & LMP_SNIFF_SUBR) +#define lmp_pause_enc_capable(dev) ((dev)->features[0][5] & LMP_PAUSE_ENC) +#define lmp_ext_inq_capable(dev) ((dev)->features[0][6] & LMP_EXT_INQ) +#define lmp_le_br_capable(dev) (!!((dev)->features[0][6] & LMP_SIMUL_LE_BR)) +#define lmp_ssp_capable(dev) ((dev)->features[0][6] & LMP_SIMPLE_PAIR) +#define lmp_no_flush_capable(dev) ((dev)->features[0][6] & LMP_NO_FLUSH) +#define lmp_lsto_capable(dev) ((dev)->features[0][7] & LMP_LSTO) +#define lmp_inq_tx_pwr_capable(dev) ((dev)->features[0][7] & LMP_INQ_TX_PWR) +#define lmp_ext_feat_capable(dev) ((dev)->features[0][7] & LMP_EXTFEATURES) /* ----- Extended LMP capabilities ----- */ -#define lmp_host_ssp_capable(dev) ((dev)->host_features[0] & LMP_HOST_SSP) -#define lmp_host_le_capable(dev) !!((dev)->host_features[0] & LMP_HOST_LE) -#define lmp_host_le_br_capable(dev) !!((dev)->host_features[0] & LMP_HOST_LE_BREDR) +#define lmp_host_ssp_capable(dev) ((dev)->features[1][0] & LMP_HOST_SSP) +#define lmp_host_le_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE)) +#define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR)) /* returns true if at least one AMP active */ static inline bool hci_amp_capable(void) -- cgit v1.2.3 From d2c5d77fff6ac0f43fc36f4fde020f726f773c1d Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 17 Apr 2013 15:00:52 +0300 Subject: Bluetooth: Add reading of all local feature pages With the introduction of CSA4 there is now also a features page number 2 available. This patch increments the maximum supported page number to 2 and adds code for reading all available pages (as long as we have support for them - indicated by HCI_MAX_PAGES). Signed-off-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 26822967e29c..80d718a9b31f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -134,7 +134,7 @@ struct amp_assoc { __u8 data[HCI_MAX_AMP_ASSOC_SIZE]; }; -#define HCI_MAX_PAGES 2 +#define HCI_MAX_PAGES 3 #define NUM_REASSEMBLY 4 struct hci_dev { @@ -153,6 +153,7 @@ struct hci_dev { __u8 dev_class[3]; __u8 major_class; __u8 minor_class; + __u8 max_page; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[8]; __u8 le_white_list_size; -- cgit v1.2.3 From 5df480b56e427d83830576862463226c8fcc95d7 Mon Sep 17 00:00:00 2001 From: Andre Guedes Date: Thu, 4 Apr 2013 20:21:00 -0300 Subject: Bluetooth: Add LE scan type macros This patch adds macros for active and passive LE scan type values. The LE_SCAN_PASSIVE was also defined since it will be used in future by LE connection routine and GAP Observer Role support. Signed-off-by: Andre Guedes Acked-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index b3308927a0a1..3f4266b3c3ba 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -984,6 +984,9 @@ struct hci_cp_le_set_adv_data { #define HCI_OP_LE_SET_ADV_ENABLE 0x200a +#define LE_SCAN_PASSIVE 0x00 +#define LE_SCAN_ACTIVE 0x01 + #define HCI_OP_LE_SET_SCAN_PARAM 0x200b struct hci_cp_le_set_scan_param { __u8 type; -- cgit v1.2.3 From 525e296a28561659d85a63befb694f36e6ec3429 Mon Sep 17 00:00:00 2001 From: Andre Guedes Date: Thu, 4 Apr 2013 20:21:01 -0300 Subject: Bluetooth: Add macros for filter duplicates values This patch adds macros for filter_duplicates parameter values from HCI LE Set Scan Enable command. It also fixes le_scan_enable_req function so it uses the LE_SCAN_FILTER_DUP_ENABLE macro instead of a magic number. The LE_SCAN_FILTER_DUP_DISABLE was also defined since it will be required to properly support the GAP Observer Role. Signed-off-by: Andre Guedes Acked-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 3f4266b3c3ba..84c37abc48c1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -998,6 +998,8 @@ struct hci_cp_le_set_scan_param { #define LE_SCANNING_DISABLED 0x00 #define LE_SCANNING_ENABLED 0x01 +#define LE_SCAN_FILTER_DUP_DISABLE 0x00 +#define LE_SCAN_FILTER_DUP_ENABLE 0x01 #define HCI_OP_LE_SET_SCAN_ENABLE 0x200c struct hci_cp_le_set_scan_enable { -- cgit v1.2.3 From 76a388beaf92cc75b829d4a0b7d69afaaeaa4b0a Mon Sep 17 00:00:00 2001 From: Andre Guedes Date: Thu, 4 Apr 2013 20:21:02 -0300 Subject: Bluetooth: Rename LE_SCANNING_* macros This patch renames LE_SCANNING_ENABLED and LE_SCANNING_DISABLED macros to LE_SCAN_ENABLE and LE_SCAN_DISABLE in order to keep the same prefix others LE scan macros have. It also fixes le_scan_enable_req function so it uses the LE_SCAN_ ENABLE macro instead of a magic number. Signed-off-by: Andre Guedes Acked-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 84c37abc48c1..e0512aaef4b8 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -996,8 +996,8 @@ struct hci_cp_le_set_scan_param { __u8 filter_policy; } __packed; -#define LE_SCANNING_DISABLED 0x00 -#define LE_SCANNING_ENABLED 0x01 +#define LE_SCAN_DISABLE 0x00 +#define LE_SCAN_ENABLE 0x01 #define LE_SCAN_FILTER_DUP_DISABLE 0x00 #define LE_SCAN_FILTER_DUP_ENABLE 0x01 -- cgit v1.2.3 From 0e280af026a5662ffd57c4e623b822df1f7f47ff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Apr 2013 06:52:51 +0000 Subject: tcp: introduce TCPSpuriousRtxHostQueues SNMP counter Host queues (Qdisc + NIC) can hold packets so long that TCP can eventually retransmit a packet before the first transmit even left the host. Its not clear right now if we could avoid this in the first place : - We could arm RTO timer not at the time we enqueue packets, but at the time we TX complete them (tcp_wfree()) - Cancel the sending of the new copy of the packet if prior one is still in queue. This patch adds instrumentation so that we can at least see how often this problem happens. TCPSpuriousRtxHostQueues SNMP counter is incremented every time we detect the fast clone is not yet freed in tcp_transmit_skb() Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Tom Herbert Cc: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index e00013a1debc..fefdec91c68b 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -247,6 +247,7 @@ enum LINUX_MIB_TCPFASTOPENPASSIVEFAIL, /* TCPFastOpenPassiveFail */ LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */ LINUX_MIB_TCPFASTOPENCOOKIEREQD, /* TCPFastOpenCookieReqd */ + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */ __LINUX_MIB_MAX }; -- cgit v1.2.3 From 07dc93dd14957dc1faba08f0aadd27b082e35ba2 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 19 Apr 2013 10:14:51 +0300 Subject: Bluetooth: Fix HCI command send functions to use const specifier All HCI command send functions that take a pointer to the command parameters do not need to modify the content in any way (they merely copy the data to an skb). Therefore, the parameter type should be declared const. This also allows passing already const parameters to these APIs which previously would have generated a compiler warning. Signed-off-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- include/net/bluetooth/hci_core.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 80d718a9b31f..35a57cd1704c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1081,17 +1081,19 @@ struct hci_request { void hci_req_init(struct hci_request *req, struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); -void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, void *param); -void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, void *param, - u8 event); +void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, + const void *param); +void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, + const void *param, u8 event); void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, - void *param, u32 timeout); + const void *param, u32 timeout); struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, - void *param, u8 event, u32 timeout); + const void *param, u8 event, u32 timeout); -int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); +int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, + const void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); -- cgit v1.2.3 From f646968f8f7c624587de729115d802372b9063dd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:27 +0000 Subject: net: vlan: rename NETIF_F_HW_VLAN_* feature flags to NETIF_F_HW_VLAN_CTAG_* Rename the hardware VLAN acceleration features to include "CTAG" to indicate that they only support CTAGs. Follow up patches will introduce 802.1ad server provider tagging (STAGs) and require the distinction for hardware not supporting acclerating both. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++-- include/linux/netdev_features.h | 12 ++++++------ include/linux/netdevice.h | 6 ++++-- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 70962f3fdb79..fee28291a824 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -238,7 +238,7 @@ static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb, */ static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) { - if (skb->dev->features & NETIF_F_HW_VLAN_TX) { + if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_put_tag(skb, vlan_tci); } else { return __vlan_put_tag(skb, vlan_tci); @@ -294,7 +294,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { - if (skb->dev->features & NETIF_F_HW_VLAN_TX) { + if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_get_tag(skb, vlan_tci); } else { return __vlan_get_tag(skb, vlan_tci); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index d6ee2d008ee4..785913b8983d 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -22,9 +22,9 @@ enum { NETIF_F_IPV6_CSUM_BIT, /* Can checksum TCP/UDP over IPV6 */ NETIF_F_HIGHDMA_BIT, /* Can DMA to high memory. */ NETIF_F_FRAGLIST_BIT, /* Scatter/gather IO. */ - NETIF_F_HW_VLAN_TX_BIT, /* Transmit VLAN hw acceleration */ - NETIF_F_HW_VLAN_RX_BIT, /* Receive VLAN hw acceleration */ - NETIF_F_HW_VLAN_FILTER_BIT, /* Receive filtering on VLAN */ + NETIF_F_HW_VLAN_CTAG_TX_BIT, /* Transmit VLAN CTAG HW acceleration */ + NETIF_F_HW_VLAN_CTAG_RX_BIT, /* Receive VLAN CTAG HW acceleration */ + NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ @@ -80,9 +80,9 @@ enum { #define NETIF_F_GSO_ROBUST __NETIF_F(GSO_ROBUST) #define NETIF_F_HIGHDMA __NETIF_F(HIGHDMA) #define NETIF_F_HW_CSUM __NETIF_F(HW_CSUM) -#define NETIF_F_HW_VLAN_FILTER __NETIF_F(HW_VLAN_FILTER) -#define NETIF_F_HW_VLAN_RX __NETIF_F(HW_VLAN_RX) -#define NETIF_F_HW_VLAN_TX __NETIF_F(HW_VLAN_TX) +#define NETIF_F_HW_VLAN_CTAG_FILTER __NETIF_F(HW_VLAN_CTAG_FILTER) +#define NETIF_F_HW_VLAN_CTAG_RX __NETIF_F(HW_VLAN_CTAG_RX) +#define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) #define NETIF_F_LLTX __NETIF_F(LLTX) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 623b57b52195..7eb7e03ee417 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -785,11 +785,13 @@ struct netdev_fcoe_hbainfo { * neither operation. * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER) + * If device support VLAN filtering (dev->features & + * NETIF_F_HW_VLAN_CTAG_FILTER) * this function is called when a VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER) + * If device support VLAN filtering (dev->features & + * NETIF_F_HW_VLAN_CTAG_FILTER) * this function is called when a VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); -- cgit v1.2.3 From 80d5c3689b886308247da295a228a54df49a44f6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:28 +0000 Subject: net: vlan: prepare for 802.1ad VLAN filtering offload Change the rx_{add,kill}_vid callbacks to take a protocol argument in preparation of 802.1ad support. The protocol argument used so far is always htons(ETH_P_8021Q). Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++-- include/linux/netdevice.h | 16 +++++++--------- 2 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index fee28291a824..fcb9ef82aae1 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -93,8 +93,8 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern bool vlan_do_receive(struct sk_buff **skb); extern struct sk_buff *vlan_untag(struct sk_buff *skb); -extern int vlan_vid_add(struct net_device *dev, unsigned short vid); -extern void vlan_vid_del(struct net_device *dev, unsigned short vid); +extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); +extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7eb7e03ee417..f8898a435dc5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -784,15 +784,13 @@ struct netdev_fcoe_hbainfo { * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & - * NETIF_F_HW_VLAN_CTAG_FILTER) - * this function is called when a VLAN id is registered. + * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid); + * If device support VLAN filtering this function is called when a + * VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & - * NETIF_F_HW_VLAN_CTAG_FILTER) - * this function is called when a VLAN id is unregistered. + * If device support VLAN filtering this function is called when a + * VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); * @@ -936,9 +934,9 @@ struct net_device_ops { struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, - unsigned short vid); + __be16 proto, u16 vid); int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, - unsigned short vid); + __be16 proto, u16 vid); #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, -- cgit v1.2.3 From 1fd9b1fc310314911f66d2f14a8e4f0ef37bf47b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:29 +0000 Subject: net: vlan: prepare for 802.1ad support Make the encapsulation protocol value a property of VLAN devices and change the device lookup functions to take the protocol value into account. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index fcb9ef82aae1..2c9fb65f8267 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -86,7 +86,7 @@ static inline int is_vlan_dev(struct net_device *dev) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, - u16 vlan_id); + __be16 vlan_proto, u16 vlan_id); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); -- cgit v1.2.3 From 86a9bad3ab6b6f858fd4443b48738cabbb6d094c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:30 +0000 Subject: net: vlan: add protocol argument to packet tagging functions Add a protocol argument to the VLAN packet tagging functions. In case of HW tagging, we need that protocol available in the ndo_start_xmit functions, so it is stored in a new field in the skb. The new field fits into a hole (on 64 bit) and doesn't increase the sks's size. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 33 ++++++++++++++++++++++++--------- include/linux/skbuff.h | 2 ++ 2 files changed, 26 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 2c9fb65f8267..8086ff9988b1 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -157,9 +157,18 @@ static inline bool vlan_uses_dev(const struct net_device *dev) } #endif +static inline bool vlan_hw_offload_capable(netdev_features_t features, + __be16 proto) +{ + if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) + return true; + return false; +} + /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload @@ -170,7 +179,8 @@ static inline bool vlan_uses_dev(const struct net_device *dev) * * Does not change skb->protocol so this function can be used during receive. */ -static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { struct vlan_ethhdr *veth; @@ -185,7 +195,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) skb->mac_header -= VLAN_HLEN; /* first, the ethernet type */ - veth->h_vlan_proto = htons(ETH_P_8021Q); + veth->h_vlan_proto = vlan_proto; /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); @@ -204,24 +214,28 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ -static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { - skb = vlan_insert_tag(skb, vlan_tci); + skb = vlan_insert_tag(skb, vlan_proto, vlan_tci); if (skb) - skb->protocol = htons(ETH_P_8021Q); + skb->protocol = vlan_proto; return skb; } /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest */ static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { + skb->vlan_proto = vlan_proto; skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci; return skb; } @@ -236,12 +250,13 @@ static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb, * Assumes skb->dev is the target that will xmit this frame. * Returns a VLAN tagged skb. */ -static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { - if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { - return __vlan_hwaccel_put_tag(skb, vlan_tci); + if (vlan_hw_offload_capable(skb->dev->features, vlan_proto)) { + return __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); } else { - return __vlan_put_tag(skb, vlan_tci); + return __vlan_put_tag(skb, vlan_proto, vlan_tci); } } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e27d1c782f32..f5bed7b31954 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -387,6 +387,7 @@ typedef unsigned char *sk_buff_data_t; * @secmark: security marking * @mark: Generic packet mark * @dropcount: total number of sk_receive_queue overflows + * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) @@ -465,6 +466,7 @@ struct sk_buff { __u32 rxhash; + __be16 vlan_proto; __u16 vlan_tci; #ifdef CONFIG_NET_SCHED -- cgit v1.2.3 From 8ad227ff89a7e6f05d07cd0acfd95ed3a24450ca Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:31 +0000 Subject: net: vlan: add 802.1ad support Add support for 802.1ad VLAN devices. This mainly consists of checking for ETH_P_8021AD in addition to ETH_P_8021Q in a couple of places and check offloading capabilities based on the used protocol. Configuration is done using "ip link": # ip link add link eth0 eth0.1000 \ type vlan proto 802.1ad id 1000 # ip link add link eth0.1000 eth0.1000.1000 \ type vlan proto 802.1q id 1000 52:54:00:12:34:56 > 92:b1:54:28:e4:8c, ethertype 802.1Q (0x8100), length 106: vlan 1000, p 0, ethertype 802.1Q, vlan 1000, p 0, ethertype IPv4, (tos 0x0, ttl 64, id 0, offset 0, flags [DF], proto ICMP (1), length 84) 20.1.0.2 > 20.1.0.1: ICMP echo request, id 3003, seq 8, length 64 92:b1:54:28:e4:8c > 52:54:00:12:34:56, ethertype 802.1Q-QinQ (0x88a8), length 106: vlan 1000, p 0, ethertype 802.1Q, vlan 1000, p 0, ethertype IPv4, (tos 0x0, ttl 64, id 47944, offset 0, flags [none], proto ICMP (1), length 84) 20.1.0.1 > 20.1.0.2: ICMP echo reply, id 3003, seq 8, length 64 Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 ++++-- include/linux/netdev_features.h | 6 ++++++ include/uapi/linux/if_link.h | 1 + 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8086ff9988b1..a78f9390da87 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -162,6 +162,8 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features, { if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) return true; + if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX) + return true; return false; } @@ -271,9 +273,9 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data; - if (veth->h_vlan_proto != htons(ETH_P_8021Q)) { + if (veth->h_vlan_proto != htons(ETH_P_8021Q) && + veth->h_vlan_proto != htons(ETH_P_8021AD)) return -EINVAL; - } *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 785913b8983d..cbaa027ef5a7 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -25,6 +25,9 @@ enum { NETIF_F_HW_VLAN_CTAG_TX_BIT, /* Transmit VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_RX_BIT, /* Receive VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ + NETIF_F_HW_VLAN_STAG_TX_BIT, /* Transmit VLAN STAG HW acceleration */ + NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */ + NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ @@ -83,6 +86,9 @@ enum { #define NETIF_F_HW_VLAN_CTAG_FILTER __NETIF_F(HW_VLAN_CTAG_FILTER) #define NETIF_F_HW_VLAN_CTAG_RX __NETIF_F(HW_VLAN_CTAG_RX) #define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) +#define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) +#define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) +#define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) #define NETIF_F_LLTX __NETIF_F(LLTX) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9922704f08af..e3163544f339 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -250,6 +250,7 @@ enum { IFLA_VLAN_FLAGS, IFLA_VLAN_EGRESS_QOS, IFLA_VLAN_INGRESS_QOS, + IFLA_VLAN_PROTOCOL, __IFLA_VLAN_MAX, }; -- cgit v1.2.3 From e32123e59871b9389d5b3fe9318611c7f1d1307a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:46:57 +0000 Subject: netlink: rename ssk to sk in struct netlink_skb_params Memory mapped netlink needs to store the receiving userspace socket when sending from the kernel to userspace. Rename 'ssk' to 'sk' to avoid confusion. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index e0f746b7b95c..d8e9264ae04a 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -19,7 +19,7 @@ struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ __u32 portid; __u32 dst_group; - struct sock *ssk; + struct sock *sk; }; #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) -- cgit v1.2.3 From 0ebd0ac5ff01ebf412e1bd3c33620ef7ffc5d866 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:46:58 +0000 Subject: net: add function to allocate sk_buff head without data area Add a function to allocate a sk_buff head without any data. This will be used by memory mapped netlink to attach data from the mmaped area to the skb. Additionally change skb_release_all() to check whether the skb has a data area to allow the skb destructor to clear the data pointer in case only a head has been allocated. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f5bed7b31954..2e0ced1af3b1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -651,6 +651,12 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } +extern struct sk_buff *__alloc_skb_head(gfp_t priority, int node); +static inline struct sk_buff *alloc_skb_head(gfp_t priority) +{ + return __alloc_skb_head(priority, -1); +} + extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); extern struct sk_buff *skb_clone(struct sk_buff *skb, -- cgit v1.2.3 From ccdfcc398594ddf3f77348c5a10938dbe9efefbe Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:01 +0000 Subject: netlink: mmaped netlink: ring setup Add support for mmap'ed RX and TX ring setup and teardown based on the af_packet.c code. The following patches will use this to add the real mmap'ed receive and transmit functionality. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 32a354f67ba4..1a85940f8ab7 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -1,6 +1,7 @@ #ifndef _UAPI__LINUX_NETLINK_H #define _UAPI__LINUX_NETLINK_H +#include #include /* for __kernel_sa_family_t */ #include @@ -105,11 +106,42 @@ struct nlmsgerr { #define NETLINK_PKTINFO 3 #define NETLINK_BROADCAST_ERROR 4 #define NETLINK_NO_ENOBUFS 5 +#define NETLINK_RX_RING 6 +#define NETLINK_TX_RING 7 struct nl_pktinfo { __u32 group; }; +struct nl_mmap_req { + unsigned int nm_block_size; + unsigned int nm_block_nr; + unsigned int nm_frame_size; + unsigned int nm_frame_nr; +}; + +struct nl_mmap_hdr { + unsigned int nm_status; + unsigned int nm_len; + __u32 nm_group; + /* credentials */ + __u32 nm_pid; + __u32 nm_uid; + __u32 nm_gid; +}; + +enum nl_mmap_status { + NL_MMAP_STATUS_UNUSED, + NL_MMAP_STATUS_RESERVED, + NL_MMAP_STATUS_VALID, + NL_MMAP_STATUS_COPY, + NL_MMAP_STATUS_SKIP, +}; + +#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO +#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) +#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) + #define NET_MAJOR 36 /* Major 36 is reserved for networking */ enum { -- cgit v1.2.3 From 9652e931e73be7e54a9c40e9bcd4bbdafe92a406 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:02 +0000 Subject: netlink: add mmap'ed netlink helper functions Add helper functions for looking up mmap'ed frame headers, reading and writing their status, allocating skbs with mmap'ed data areas and a poll function. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index d8e9264ae04a..07c473848dbd 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -15,10 +15,17 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) return (struct nlmsghdr *)skb->data; } +enum netlink_skb_flags { + NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ + NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ + NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ +}; + struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ __u32 portid; __u32 dst_group; + __u32 flags; struct sock *sk; }; -- cgit v1.2.3 From f9c2288837ba072b21dba955f04a4c97eaa77b1e Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:04 +0000 Subject: netlink: implement memory mapped recvmsg() Add support for mmap'ed recvmsg(). To allow the kernel to construct messages into the mapped area, a dataless skb is allocated and the data pointer is set to point into the ring frame. This means frames will be delivered to userspace in order of allocation instead of order of transmission. This usually doesn't matter since the order is either not determinable by userspace or message creation/transmission is serialized. The only case where this can have a visible difference is nfnetlink_queue. Userspace can't assume mmap'ed messages have ordered IDs anymore and needs to check this if using batched verdicts. For non-mapped sockets, nothing changes. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 07c473848dbd..6358da5eeee8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -64,6 +64,8 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group) extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); +extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, + u32 dst_portid, gfp_t gfp_mask); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); -- cgit v1.2.3 From 4ae9fbee1690848a6aace1e0193ab27e981e35a5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:06 +0000 Subject: netlink: add RX/TX-ring support to netlink diag Based on AF_PACKET. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/uapi/linux/netlink_diag.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index 88009a31cd06..4e31db4eea41 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -25,9 +25,18 @@ struct netlink_diag_msg { __u32 ndiag_cookie[2]; }; +struct netlink_diag_ring { + __u32 ndr_block_size; + __u32 ndr_block_nr; + __u32 ndr_frame_size; + __u32 ndr_frame_nr; +}; + enum { NETLINK_DIAG_MEMINFO, NETLINK_DIAG_GROUPS, + NETLINK_DIAG_RX_RING, + NETLINK_DIAG_TX_RING, __NETLINK_DIAG_MAX, }; @@ -38,5 +47,6 @@ enum { #define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */ #define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */ +#define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */ #endif -- cgit v1.2.3 From ec464e5dc504a164c5dbff4a06812d495e44e34d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:08 +0000 Subject: netfilter: rename netlink related "pid" variables to "portid" Get rid of the confusing mix of pid and portid and use portid consistently for all netlink related socket identities. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 9 +++++---- include/net/netfilter/nf_conntrack.h | 2 +- include/net/netfilter/nf_conntrack_expect.h | 4 ++-- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index ecbb8e495912..60b164171daf 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -29,10 +29,11 @@ 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(struct net *net, unsigned int group); -extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, - int echo, gfp_t flags); -extern int 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 int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, + unsigned int group, int echo, gfp_t flags); +extern int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); +extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, + u32 portid, int flags); extern void nfnl_lock(__u8 subsys_id); extern void nfnl_unlock(__u8 subsys_id); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index caca0c4d6b4b..644d9c223d24 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -184,7 +184,7 @@ extern int nf_conntrack_hash_check_insert(struct nf_conn *ct); extern void nf_ct_delete_from_lists(struct nf_conn *ct); extern void nf_ct_dying_timeout(struct nf_conn *ct); -extern void nf_conntrack_flush_report(struct net *net, u32 pid, int report); +extern void nf_conntrack_flush_report(struct net *net, u32 portid, int report); extern bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index cbbae7621e22..3f3aecbc8632 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -88,7 +88,7 @@ nf_ct_find_expectation(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple); void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, - u32 pid, int report); + u32 portid, int report); static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) { nf_ct_unlink_expect_report(exp, 0, 0); @@ -106,7 +106,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *, unsigned int, u_int8_t, u_int8_t, const __be16 *, const __be16 *); void nf_ct_expect_put(struct nf_conntrack_expect *exp); int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, - u32 pid, int report); + u32 portid, int report); static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect) { return nf_ct_expect_related_report(expect, 0, 0); -- cgit v1.2.3 From 3ab1f683bf8be7aa7869cc3ffb8d1db2ec8c8307 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:09 +0000 Subject: nfnetlink: add support for memory mapped netlink Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 60b164171daf..cadb7402d7a7 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -29,6 +29,8 @@ 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(struct net *net, unsigned int group); +extern struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size, + u32 dst_portid, gfp_t gfp_mask); extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); extern int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); -- cgit v1.2.3 From 6e94d1ef37e439bf45659cc071553574ccb98080 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 01:29:10 +0000 Subject: net: socket: move ktime2ts to ktime header api Currently, ktime2ts is a small helper function that is only used in net/socket.c. Move this helper into the ktime API as a small inline function, so that i) it's maintained together with ktime routines, and ii) also other files can make use of it. The function is named ktime_to_timespec_cond() and placed into the generic part of ktime, since we internally make use of ktime_to_timespec(). ktime_to_timespec() itself does not check the ktime variable for zero, hence, we name this function ktime_to_timespec_cond() for only a conditional conversion, and adapt its users to it. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/ktime.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index e83512f63df5..bbca12804d12 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -330,6 +330,24 @@ static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); +/** + * ktime_to_timespec_cond - convert a ktime_t variable to timespec + * format only if the variable contains data + * @kt: the ktime_t variable to convert + * @ts: the timespec variable to store the result in + * + * Returns true if there was a successful conversion, false if kt was 0. + */ +static inline bool ktime_to_timespec_cond(const ktime_t kt, struct timespec *ts) +{ + if (kt.tv64) { + *ts = ktime_to_timespec(kt); + return true; + } else { + return false; + } +} + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an -- cgit v1.2.3 From 9fae27b33785cb6350f21449073d9f7d1a2bbfd6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 20 Apr 2013 23:51:41 +0000 Subject: net: vlan: fix dummy function signatures for CONFIG_VLAN=n Fix up some function signatures for CONFIG_VLAN=n that were missed during the 802.1ad support patches. Found by the kbuild robot. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index a78f9390da87..52bd03b38962 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -104,7 +104,8 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); #else static inline struct net_device * -__vlan_find_dev_deep(struct net_device *real_dev, u16 vlan_id) +__vlan_find_dev_deep(struct net_device *real_dev, + __be16 vlan_proto, u16 vlan_id) { return NULL; } @@ -131,12 +132,12 @@ static inline struct sk_buff *vlan_untag(struct sk_buff *skb) return skb; } -static inline int vlan_vid_add(struct net_device *dev, unsigned short vid) +static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; } -static inline void vlan_vid_del(struct net_device *dev, unsigned short vid) +static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { } -- cgit v1.2.3 From 908f8d07e9774c2476e0683f6a0ce50562a2da45 Mon Sep 17 00:00:00 2001 From: Alexander Bondar Date: Sun, 7 Apr 2013 09:53:30 +0300 Subject: mac80211: indicate admission control in TX queue parameters Some driver implementations need to know whether mandatory admission control is required by the AP for some ACs. Add a parameter to the TX queue parameters indicating this. As there's currently no support for admission control in mac80211's AP implementation, it's only ever set for the client implementation. Signed-off-by: Alexander Bondar Signed-off-by: Johannes Berg --- 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 4f693a5c54de..b77d57a070e5 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -128,6 +128,7 @@ enum ieee80211_ac_numbers { * 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 + * @acm: is mandatory admission control required for the access category * @uapsd: is U-APSD mode enabled for the queue */ struct ieee80211_tx_queue_params { @@ -135,6 +136,7 @@ struct ieee80211_tx_queue_params { u16 cw_min; u16 cw_max; u8 aifs; + bool acm; bool uapsd; }; -- cgit v1.2.3 From 5de17984898c5758fc6ebe08eccea9f4b6548914 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Thu, 18 Apr 2013 15:49:00 +0200 Subject: cfg80211: introduce critical protocol indication from user-space Some protocols need a more reliable connection to complete successful in reasonable time. This patch adds a user-space API to indicate the wireless driver that a critical protocol is about to commence and when it is done, using nl80211 primitives NL80211_CMD_CRIT_PROTOCOL_START and NL80211_CRIT_PROTOCOL_STOP. There can be only on critical protocol session started per registered cfg80211 device. The driver can support this by implementing the cfg80211 callbacks .crit_proto_start() and .crit_proto_stop(). Examples of protocols that can benefit from this are DHCP, EAPOL, APIPA. Exactly how the link can/should be made more reliable is up to the driver. Things to consider are avoid scanning, no multi-channel operations, and alter coexistence schemes. Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Franky (Zhenhui) Lin Signed-off-by: Arend van Spriel Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 23 +++++++++++++++++++++++ include/uapi/linux/nl80211.h | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 62 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index dff96d8cafcd..26b5b692c22b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2002,6 +2002,12 @@ struct cfg80211_update_ft_ies_params { * @update_ft_ies: Provide updated Fast BSS Transition information to the * driver. If the SME is in the driver/firmware, this information can be * used in building Authentication and Reassociation Request frames. + * + * @crit_proto_start: Indicates a critical protocol needs more link reliability + * for a given duration (milliseconds). The protocol is provided so the + * driver can take the most appropriate actions. + * @crit_proto_stop: Indicates critical protocol no longer needs increased link + * reliability. This operation can not fail. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -2231,6 +2237,12 @@ struct cfg80211_ops { struct cfg80211_chan_def *chandef); int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie); + int (*crit_proto_start)(struct wiphy *wiphy, + struct wireless_dev *wdev, + enum nl80211_crit_proto_id protocol, + u16 duration); + void (*crit_proto_stop)(struct wiphy *wiphy, + struct wireless_dev *wdev); }; /* @@ -4137,6 +4149,17 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev, struct cfg80211_wowlan_wakeup *wakeup, gfp_t gfp); +/** + * cfg80211_crit_proto_stopped() - indicate critical protocol stopped by driver. + * + * @wdev: the wireless device for which critical protocol is stopped. + * + * This function can be called by the driver to indicate it has reverted + * operation back to normal. One reason could be that the duration given + * by .crit_proto_start() has expired. + */ +void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 79da8710448e..d1e48b5e348f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -639,6 +639,13 @@ * with the relevant Information Elements. This event is used to report * received FT IEs (MDIE, FTIE, RSN IE, TIE, RICIE). * + * @NL80211_CMD_CRIT_PROTOCOL_START: Indicates user-space will start running + * a critical protocol that needs more reliability in the connection to + * complete. + * + * @NL80211_CMD_CRIT_PROTOCOL_STOP: Indicates the connection reliability can + * return back to normal. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -798,6 +805,9 @@ enum nl80211_commands { NL80211_CMD_UPDATE_FT_IES, NL80211_CMD_FT_EVENT, + NL80211_CMD_CRIT_PROTOCOL_START, + NL80211_CMD_CRIT_PROTOCOL_STOP, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1414,6 +1424,11 @@ enum nl80211_commands { * @NL80211_ATTR_IE_RIC: Resource Information Container Information * Element * + * @NL80211_ATTR_CRIT_PROT_ID: critical protocol identifier requiring increased + * reliability, see &enum nl80211_crit_proto_id (u16). + * @NL80211_ATTR_MAX_CRIT_PROT_DURATION: duration in milliseconds in which + * the connection should have increased reliability (u16). + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1709,6 +1724,9 @@ enum nl80211_attrs { NL80211_ATTR_MDID, NL80211_ATTR_IE_RIC, + NL80211_ATTR_CRIT_PROT_ID, + NL80211_ATTR_MAX_CRIT_PROT_DURATION, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3682,4 +3700,25 @@ enum nl80211_protocol_features { NL80211_PROTOCOL_FEATURE_SPLIT_WIPHY_DUMP = 1 << 0, }; +/** + * enum nl80211_crit_proto_id - nl80211 critical protocol identifiers + * + * @NL80211_CRIT_PROTO_UNSPEC: protocol unspecified. + * @NL80211_CRIT_PROTO_DHCP: BOOTP or DHCPv6 protocol. + * @NL80211_CRIT_PROTO_EAPOL: EAPOL protocol. + * @NL80211_CRIT_PROTO_APIPA: APIPA protocol. + * @NUM_NL80211_CRIT_PROTO: must be kept last. + */ +enum nl80211_crit_proto_id { + NL80211_CRIT_PROTO_UNSPEC, + NL80211_CRIT_PROTO_DHCP, + NL80211_CRIT_PROTO_EAPOL, + NL80211_CRIT_PROTO_APIPA, + /* add other protocols before this one */ + NUM_NL80211_CRIT_PROTO +}; + +/* maximum duration for critical protocol measures */ +#define NL80211_CRIT_PROTO_MAX_DURATION 5000 /* msec */ + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 0d528d85c519b755b6f4e1bafa3a39984370e1c1 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 22 Apr 2013 16:14:41 +0200 Subject: mac80211: improve the rate control API Allow rate control modules to pass a rate selection table to mac80211 and the driver. This allows drivers to fetch the most recent rate selection from the sta pointer for already buffered frames. This allows rate control to respond faster to sudden link changes and it is also a step towards adding minstrel_ht support to drivers like iwlwifi. When a driver sets IEEE80211_HW_SUPPORTS_RC_TABLE, mac80211 will not fill info->control.rates with rates from the rate table (to preserve explicit overrides by the rate control module). The driver then explicitly calls ieee80211_get_tx_rates to merge overrides from info->control.rates with defaults from the sta rate table. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/net/mac80211.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index b77d57a070e5..04c2d4670dc6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -563,6 +563,9 @@ enum mac80211_rate_control_flags { /* maximum number of rate stages */ #define IEEE80211_TX_MAX_RATES 4 +/* maximum number of rate table entries */ +#define IEEE80211_TX_RATE_TABLE_SIZE 4 + /** * struct ieee80211_tx_rate - rate selection/status * @@ -659,6 +662,8 @@ struct ieee80211_tx_info { s8 rts_cts_rate_idx; u8 use_rts:1; u8 use_cts_prot:1; + u8 short_preamble:1; + u8 skip_table:1; /* 2 bytes free */ }; /* only needed before rate control */ @@ -680,6 +685,8 @@ struct ieee80211_tx_info { struct { struct ieee80211_tx_rate driver_rates[ IEEE80211_TX_MAX_RATES]; + u8 pad[4]; + void *rate_driver_data[ IEEE80211_TX_INFO_RATE_DRIVER_DATA_SIZE / sizeof(void *)]; }; @@ -1224,6 +1231,24 @@ enum ieee80211_sta_rx_bandwidth { IEEE80211_STA_RX_BW_160, }; +/** + * struct ieee80211_sta_rates - station rate selection table + * + * @rcu_head: RCU head used for freeing the table on update + * @rates: transmit rates/flags to be used by default. + * Overriding entries per-packet is possible by using cb tx control. + */ +struct ieee80211_sta_rates { + struct rcu_head rcu_head; + struct { + s8 idx; + u8 count; + u8 count_cts; + u8 count_rts; + u16 flags; + } rate[IEEE80211_TX_RATE_TABLE_SIZE]; +}; + /** * struct ieee80211_sta - station table entry * @@ -1251,6 +1276,7 @@ enum ieee80211_sta_rx_bandwidth { * notifications and capabilities. The value is only valid after * the station moves to associated state. * @smps_mode: current SMPS mode (off, static or dynamic) + * @tx_rates: rate control selection table */ struct ieee80211_sta { u32 supp_rates[IEEE80211_NUM_BANDS]; @@ -1264,6 +1290,7 @@ struct ieee80211_sta { u8 rx_nss; enum ieee80211_sta_rx_bandwidth bandwidth; enum ieee80211_smps_mode smps_mode; + struct ieee80211_sta_rates __rcu *rates; /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); @@ -1419,6 +1446,9 @@ struct ieee80211_tx_control { * for different virtual interfaces. See the doc section on HW queue * control for more details. * + * @IEEE80211_HW_SUPPORTS_RC_TABLE: The driver supports using a rate + * selection table provided by the rate control algorithm. + * * @IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF: Use the P2P Device address for any * P2P Interface. This will be honoured even if more than one interface * is supported. @@ -1451,6 +1481,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_PER_STA_GTK = 1<<21, IEEE80211_HW_AP_LINK_PS = 1<<22, IEEE80211_HW_TX_AMPDU_SETUP_IN_HW = 1<<23, + IEEE80211_HW_SUPPORTS_RC_TABLE = 1<<24, IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF = 1<<25, IEEE80211_HW_TIMING_BEACON_ONLY = 1<<26, }; @@ -3136,6 +3167,25 @@ static inline int ieee80211_sta_ps_transition_ni(struct ieee80211_sta *sta, void ieee80211_sta_set_buffered(struct ieee80211_sta *sta, u8 tid, bool buffered); +/** + * ieee80211_get_tx_rates - get the selected transmit rates for a packet + * + * Call this function in a driver with per-packet rate selection support + * to combine the rate info in the packet tx info with the most recent + * rate selection table for the station entry. + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @sta: the receiver station to which this packet is sent. + * @skb: the frame to be transmitted. + * @dest: buffer for extracted rate/retry information + * @max_rates: maximum number of rates to fetch + */ +void ieee80211_get_tx_rates(struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct sk_buff *skb, + struct ieee80211_tx_rate *dest, + int max_rates); + /** * ieee80211_tx_status - transmit status callback * @@ -4212,6 +4262,22 @@ bool rate_usable_index_exists(struct ieee80211_supported_band *sband, return false; } +/** + * rate_control_set_rates - pass the sta rate selection to mac80211/driver + * + * When not doing a rate control probe to test rates, rate control should pass + * its rate selection to mac80211. If the driver supports receiving a station + * rate table, it will use it to ensure that frames are always sent based on + * the most recent rate control module decision. + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @pubsta: &struct ieee80211_sta pointer to the target destination. + * @rates: new tx rate set to be used for this station. + */ +int rate_control_set_rates(struct ieee80211_hw *hw, + struct ieee80211_sta *pubsta, + struct ieee80211_sta_rates *rates); + int ieee80211_rate_control_register(struct rate_control_ops *ops); void ieee80211_rate_control_unregister(struct rate_control_ops *ops); -- cgit v1.2.3 From 9ecd1a75d977e2e8c48139c7d3efed183f898d94 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 22 Apr 2013 02:20:41 +0000 Subject: xen-netfront: reduce gso_max_size to account for max TCP header The maximum packet including header that can be handled by netfront / netback wire format is 65535. Reduce gso_max_size accordingly. Drop skb and print warning when skb->len > 65535. This can 1) save the effort to send malformed packet to netback, 2) help spotting misconfiguration of netfront in the future. Signed-off-by: Wei Liu Acked-by: Ian Campbell Signed-off-by: David S. Miller --- include/xen/interface/io/netif.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index 9dfc12000980..58fadcac33a1 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -47,6 +47,7 @@ #define _XEN_NETTXF_extra_info (3) #define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info) +#define XEN_NETIF_MAX_TX_SIZE 0xFFFF struct xen_netif_tx_request { grant_ref_t gref; /* Reference to buffer page */ uint16_t offset; /* Offset within buffer page */ -- cgit v1.2.3 From 2810e5b9a7731ca5fce22bfbe12c96e16ac44b6f Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 22 Apr 2013 02:20:42 +0000 Subject: xen-netback: coalesce slots in TX path and fix regressions This patch tries to coalesce tx requests when constructing grant copy structures. It enables netback to deal with situation when frontend's MAX_SKB_FRAGS is larger than backend's MAX_SKB_FRAGS. With the help of coalescing, this patch tries to address two regressions avoid reopening the security hole in XSA-39. Regression 1. The reduction of the number of supported ring entries (slots) per packet (from 18 to 17). This regression has been around for some time but remains unnoticed until XSA-39 security fix. This is fixed by coalescing slots. Regression 2. The XSA-39 security fix turning "too many frags" errors from just dropping the packet to a fatal error and disabling the VIF. This is fixed by coalescing slots (handling 18 slots when backend's MAX_SKB_FRAGS is 17) which rules out false positive (using 18 slots is legit) and dropping packets using 19 to `max_skb_slots` slots. To avoid reopening security hole in XSA-39, frontend sending packet using more than max_skb_slots is considered malicious. The behavior of netback for packet is thus: 1-18 slots: valid 19-max_skb_slots slots: drop and respond with an error max_skb_slots+ slots: fatal error max_skb_slots is configurable by admin, default value is 20. Also change variable name from "frags" to "slots" in netbk_count_requests. Please note that RX path still has dependency on MAX_SKB_FRAGS. This will be fixed with separate patch. Signed-off-by: Wei Liu Acked-by: Ian Campbell Signed-off-by: David S. Miller --- include/xen/interface/io/netif.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index 58fadcac33a1..3ef3fe05ee99 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -12,6 +12,24 @@ #include #include +/* + * Older implementation of Xen network frontend / backend has an + * implicit dependency on the MAX_SKB_FRAGS as the maximum number of + * ring slots a skb can use. Netfront / netback may not work as + * expected when frontend and backend have different MAX_SKB_FRAGS. + * + * A better approach is to add mechanism for netfront / netback to + * negotiate this value. However we cannot fix all possible + * frontends, so we need to define a value which states the minimum + * slots backend must support. + * + * The minimum value derives from older Linux kernel's MAX_SKB_FRAGS + * (18), which is proved to work with most frontends. Any new backend + * which doesn't negotiate with frontend should expect frontend to + * send a valid packet using slots up to this value. + */ +#define XEN_NETIF_NR_SLOTS_MIN 18 + /* * Notifications after enqueuing any type of message should be conditional on * the appropriate req_event or rsp_event field in the shared ring. -- cgit v1.2.3 From 3fb62c5d3fc1821f50c6003e582713857a520f6b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Apr 2013 14:29:25 -0700 Subject: net: remove a stale comment for dl_next dl_next member in struct request_sock doesn't need to be first. We expect to insert a "struct common_sock" or a subset of it, so this claim had to be verified. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 9069e65c1c56..59795e42c8b6 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -48,7 +48,7 @@ extern int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); /* struct request_sock - mini sock to represent a connection request */ struct request_sock { - struct request_sock *dl_next; /* Must be first member! */ + struct request_sock *dl_next; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ -- cgit v1.2.3 From 3e3251b3f289528732edab386ddf73ac428359b7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 18 Apr 2013 21:59:37 +0000 Subject: net: sctp: minor: remove dead code from sctp_packet struct sctp_packet is currently embedded into sctp_transport or sits on the stack as 'singleton' in sctp_outq_flush(). Therefore, its member 'malloced' is always 0, thus a kfree() is never called. Because of that, we can just remove this code. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 64d469845f25..1bd4c4144fe8 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -714,8 +714,7 @@ struct sctp_packet { has_sack:1, /* This packet contains a SACK chunk. */ has_auth:1, /* This packet contains an AUTH chunk */ has_data:1, /* This packet contains at least 1 DATA chunk */ - ipfragok:1, /* So let ip fragment this packet */ - malloced:1; /* Is it malloced? */ + ipfragok:1; /* So let ip fragment this packet */ }; struct sctp_packet *sctp_packet_init(struct sctp_packet *, -- cgit v1.2.3 From 0a925864c1038a78fd1cc9b048d9a2b1ae04b63e Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Wed, 17 Apr 2013 23:50:49 +0300 Subject: ipvs: fix sparse warnings for some parameters Some service fields are in network order: - netmask: used once in network order and also as prefix len for IPv6 - port Other parameters are in host order: - struct ip_vs_flags: flags and mask moved between user and kernel only - sync state: moved between user and kernel only - syncid: sent over network as single octet Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 8 ++++---- include/uapi/linux/ip_vs.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f9f5b057b480..4c062ccff9aa 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -678,7 +678,7 @@ struct ip_vs_service_user_kern { u16 af; u16 protocol; union nf_inet_addr addr; /* virtual ip address */ - u16 port; + __be16 port; u32 fwmark; /* firwall mark of service */ /* virtual service options */ @@ -686,14 +686,14 @@ struct ip_vs_service_user_kern { char *pe_name; unsigned int flags; /* virtual service flags */ unsigned int timeout; /* persistent timeout in sec */ - u32 netmask; /* persistent netmask */ + __be32 netmask; /* persistent netmask or plen */ }; struct ip_vs_dest_user_kern { /* destination server address */ union nf_inet_addr addr; - u16 port; + __be16 port; /* real server options */ unsigned int conn_flags; /* connection flags */ @@ -721,7 +721,7 @@ struct ip_vs_service { __u32 fwmark; /* firewall mark of the service */ unsigned int flags; /* service status flags */ unsigned int timeout; /* persistent timeout in ticks */ - __be32 netmask; /* grouping granularity */ + __be32 netmask; /* grouping granularity, mask/plen */ struct net *net; struct list_head destinations; /* real server d-linked list */ diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index 8a2d438dc499..a24537725e80 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -280,8 +280,8 @@ struct ip_vs_daemon_user { #define IPVS_GENL_VERSION 0x1 struct ip_vs_flags { - __be32 flags; - __be32 mask; + __u32 flags; + __u32 mask; }; /* Generic Netlink command attributes */ -- cgit v1.2.3 From 26ee65e680f4a2291f6258e11beceae0ad4eeba3 Mon Sep 17 00:00:00 2001 From: "sjur.brandeland@stericsson.com" Date: Mon, 22 Apr 2013 23:57:01 +0000 Subject: caif: Remove my bouncing email address. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove my soon bouncing email address. Also remove the "Contact:" line in file header. The MAINTAINERS file is a better place to find the contact person anyway. Signed-off-by: Sjur Brændeland Signed-off-by: David S. Miller --- include/net/caif/caif_dev.h | 2 +- include/net/caif/caif_device.h | 2 +- include/net/caif/caif_hsi.h | 1 - include/net/caif/caif_layer.h | 2 +- include/net/caif/cfcnfg.h | 2 +- include/net/caif/cfctrl.h | 2 +- include/net/caif/cffrml.h | 2 +- include/net/caif/cfmuxl.h | 2 +- include/net/caif/cfpkt.h | 2 +- include/net/caif/cfserl.h | 2 +- include/net/caif/cfsrvl.h | 2 +- include/uapi/linux/caif/caif_socket.h | 2 +- include/uapi/linux/caif/if_caif.h | 2 +- 13 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h index ef2dd9438bb1..028b754ae9b1 100644 --- a/include/net/caif/caif_dev.h +++ b/include/net/caif/caif_dev.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/caif_device.h b/include/net/caif/caif_device.h index d02f044adb8a..d6e3c4267c81 100644 --- a/include/net/caif/caif_device.h +++ b/include/net/caif/caif_device.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/caif_hsi.h b/include/net/caif/caif_hsi.h index bcb9cc3ce98b..4795e817afe5 100644 --- a/include/net/caif/caif_hsi.h +++ b/include/net/caif/caif_hsi.h @@ -1,6 +1,5 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Contact: Sjur Brendeland / sjur.brandeland@stericsson.com * Author: Daniel Martensson / daniel.martensson@stericsson.com * Dmitry.Tarnyagin / dmitry.tarnyagin@stericsson.com * License terms: GNU General Public License (GPL) version 2 diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 0f3a39125f90..94e5ed64dc6d 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland / sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h index 90b4ff8bad83..70bfd017581f 100644 --- a/include/net/caif/cfcnfg.h +++ b/include/net/caif/cfcnfg.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/cfctrl.h b/include/net/caif/cfctrl.h index 9e5425b4a1d7..f2ae33d23baf 100644 --- a/include/net/caif/cfctrl.h +++ b/include/net/caif/cfctrl.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/cffrml.h b/include/net/caif/cffrml.h index afac1a48cce7..a06e33fbaa8b 100644 --- a/include/net/caif/cffrml.h +++ b/include/net/caif/cffrml.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/cfmuxl.h b/include/net/caif/cfmuxl.h index 5847a196b8ad..752999572f21 100644 --- a/include/net/caif/cfmuxl.h +++ b/include/net/caif/cfmuxl.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index 83a89ba3005b..1c1ad46250d5 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h index f121299a3427..b5b020f3c72e 100644 --- a/include/net/caif/cfserl.h +++ b/include/net/caif/cfserl.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h index 0f5905241843..cd47705c2cc3 100644 --- a/include/net/caif/cfsrvl.h +++ b/include/net/caif/cfsrvl.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/uapi/linux/caif/caif_socket.h b/include/uapi/linux/caif/caif_socket.h index 3f3bac6af7bc..586e9f98184f 100644 --- a/include/uapi/linux/caif/caif_socket.h +++ b/include/uapi/linux/caif/caif_socket.h @@ -1,7 +1,7 @@ /* linux/caif_socket.h * CAIF Definitions for CAIF socket and network layer * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ diff --git a/include/uapi/linux/caif/if_caif.h b/include/uapi/linux/caif/if_caif.h index 5e7eed4edf51..7618aabe8c6b 100644 --- a/include/uapi/linux/caif/if_caif.h +++ b/include/uapi/linux/caif/if_caif.h @@ -1,6 +1,6 @@ /* * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * Author: Sjur Brendeland * License terms: GNU General Public License (GPL) version 2 */ -- cgit v1.2.3 From d998735f443427c1530cac5eeda0a45c8cb60a57 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Tue, 23 Apr 2013 06:06:47 +0000 Subject: net/mlx4_core: Add timestamping device capability Add new device capability for timestamping support and query FW to retrieve it. Signed-off-by: Eugenia Emantayev Signed-off-by: Or Gerlitz Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 1bc5a750b330..86ae260c2e53 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -152,7 +152,8 @@ enum { MLX4_DEV_CAP_FLAG2_RSS_TOP = 1LL << 1, MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2, MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3, - MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4 + MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4, + MLX4_DEV_CAP_FLAG2_TS = 1LL << 5 }; enum { -- cgit v1.2.3 From ddd8a6c12d7e494902a9435a9a7a543ef730b2d8 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Tue, 23 Apr 2013 06:06:48 +0000 Subject: net/mlx4_core: Read HCA frequency and map internal clock Read HCA frequency, read PCI clock bar and offset, map internal clock to PCI bar. Signed-off-by: Eugenia Emantayev Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 86ae260c2e53..e088290d9792 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -445,6 +445,7 @@ struct mlx4_caps { u8 eqe_factor; u32 userspace_caps; /* userspace must be aware of these */ u32 function_caps; /* VFs must be aware of these */ + u16 hca_core_clock; }; struct mlx4_buf_list { -- cgit v1.2.3 From ec693d47010e8302e61e0bdf3f47496c5610641a Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 23 Apr 2013 06:06:49 +0000 Subject: net/mlx4_en: Add HW timestamping (TS) support The patch allows to enable/disable HW timestamping for incoming and/or outgoing packets. It adds and initializes all structs and callbacks needed by kernel TS API. To enable/disable HW timestamping appropriate ioctl should be used. Currently HWTSTAMP_FILTER_ALL/NONE and HWTSAMP_TX_ON/OFF only are supported. When enabling TS on receive flow - VLAN stripping will be disabled. Also were made all relevant changes in RX/TX flows to consider TS request and plant HW timestamps into relevant structures. mlx4_ib was fixed to compile with new mlx4_cq_alloc() signature. Signed-off-by: Eugenia Emantayev Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/cq.h | 16 ++++++++++++++++ include/linux/mlx4/device.h | 6 +++++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h index 6f65b2c8bb89..98fa492cf406 100644 --- a/include/linux/mlx4/cq.h +++ b/include/linux/mlx4/cq.h @@ -64,6 +64,22 @@ struct mlx4_err_cqe { u8 owner_sr_opcode; }; +struct mlx4_ts_cqe { + __be32 vlan_my_qpn; + __be32 immed_rss_invalid; + __be32 g_mlpath_rqpn; + __be32 timestamp_hi; + __be16 status; + u8 ipv6_ext_mask; + u8 badfcs_enc; + __be32 byte_cnt; + __be16 wqe_index; + __be16 checksum; + u8 reserved; + __be16 timestamp_lo; + u8 owner_sr_opcode; +} __packed; + enum { MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29, MLX4_CQE_QPN_MASK = 0xffffff, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e088290d9792..2fbc1464b53b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -40,6 +40,8 @@ #include +#include + #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 #define MSIX_LEGACY_SZ 4 @@ -840,7 +842,7 @@ void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres, int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq, - unsigned vector, int collapsed); + unsigned vector, int collapsed, int timestamp_en); void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq); int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base); @@ -1031,4 +1033,6 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid); __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave); +cycle_t mlx4_read_clock(struct mlx4_dev *dev); + #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 5a8eb24292ffd68604cedeb24ad2b4bc02cfc037 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 25 Apr 2013 04:42:29 +0000 Subject: pci: Add SRIOV helper function to determine if VFs are assigned to guest This function is meant to add a helper function that will determine if a PF has any VFs that are currently assigned to a guest. We currently have been implementing this function per driver, and going forward I would like to avoid that by making this function generic and using this helper. v2: Removed extern from declaration of pci_vfs_assigned in pci.h and return 0 if SR-IOV is disabled with is inline with other PCI SRIOV functions. Signed-off-by: Alexander Duyck Acked-by: Bjorn Helgaas Signed-off-by: Jeff Kirsher --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 710067f3618c..43e45ac36458 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1644,6 +1644,7 @@ 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); +int pci_vfs_assigned(struct pci_dev *dev); extern int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); extern int pci_sriov_get_totalvfs(struct pci_dev *dev); #else @@ -1662,6 +1663,10 @@ static inline int pci_num_vf(struct pci_dev *dev) { return 0; } +static inline int pci_vfs_assigned(struct pci_dev *dev) +{ + return 0; +} static inline int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs) { return 0; -- cgit v1.2.3 From 7276d5d743d775388bf382cd7bdea1a14e486d32 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 23 Apr 2013 00:39:30 +0000 Subject: packet: minor: convert status bits into shifting format This makes it more readable and clearer what bits are still free to use. The compiler reduces this to a constant for us anyway. Signed-off-by: Daniel Borkmann Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/if_packet.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 8136658ea477..4dfc234d80e5 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -86,19 +86,19 @@ struct tpacket_auxdata { }; /* Rx ring - header status */ -#define TP_STATUS_KERNEL 0x0 -#define TP_STATUS_USER 0x1 -#define TP_STATUS_COPY 0x2 -#define TP_STATUS_LOSING 0x4 -#define TP_STATUS_CSUMNOTREADY 0x8 -#define TP_STATUS_VLAN_VALID 0x10 /* auxdata has valid tp_vlan_tci */ -#define TP_STATUS_BLK_TMO 0x20 +#define TP_STATUS_KERNEL 0 +#define TP_STATUS_USER (1 << 0) +#define TP_STATUS_COPY (1 << 1) +#define TP_STATUS_LOSING (1 << 2) +#define TP_STATUS_CSUMNOTREADY (1 << 3) +#define TP_STATUS_VLAN_VALID (1 << 4) /* auxdata has valid tp_vlan_tci */ +#define TP_STATUS_BLK_TMO (1 << 5) /* Tx ring - header status */ -#define TP_STATUS_AVAILABLE 0x0 -#define TP_STATUS_SEND_REQUEST 0x1 -#define TP_STATUS_SENDING 0x2 -#define TP_STATUS_WRONG_FORMAT 0x4 +#define TP_STATUS_AVAILABLE 0 +#define TP_STATUS_SEND_REQUEST (1 << 0) +#define TP_STATUS_SENDING (1 << 1) +#define TP_STATUS_WRONG_FORMAT (1 << 2) /* Rx ring - feature request bits */ #define TP_FT_REQ_FILL_RXHASH 0x1 -- cgit v1.2.3 From b9c32fb2717094231b31a7d7dcf5fd7f3638ac2f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 23 Apr 2013 00:39:31 +0000 Subject: packet: if hw/sw ts enabled in rx/tx ring, report which ts we got Currently, there is no way to find out which timestamp is reported in tpacket{,2,3}_hdr's tp_sec, tp_{n,u}sec members. It can be one of SOF_TIMESTAMPING_SYS_HARDWARE, SOF_TIMESTAMPING_RAW_HARDWARE, SOF_TIMESTAMPING_SOFTWARE, or a fallback variant late call from the PF_PACKET code in software. Therefore, report in the tp_status member of the ring buffer which timestamp has been reported for RX and TX path. This should not break anything for the following reasons: i) in RX ring path, the user needs to test for tp_status & TP_STATUS_USER, and later for other flags as well such as TP_STATUS_VLAN_VALID et al, so adding other flags will do no harm; ii) in TX ring path, time stamps with PACKET_TIMESTAMP socketoption are not available resp. had no effect except that the application setting this is buggy. Next to TP_STATUS_AVAILABLE, the user also should check for other flags such as TP_STATUS_WRONG_FORMAT to reclaim frames to the application. Thus, in case TX ts are turned off (default case), nothing happens to the application logic, and in case we want to use this new feature, we now can also check which of the ts source is reported in the status field as provided in the docs. Reported-by: Richard Cochran Signed-off-by: Daniel Borkmann Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/if_packet.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 4dfc234d80e5..b950c02030c0 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -100,6 +100,11 @@ struct tpacket_auxdata { #define TP_STATUS_SENDING (1 << 1) #define TP_STATUS_WRONG_FORMAT (1 << 2) +/* Rx and Tx ring - header status */ +#define TP_STATUS_TS_SOFTWARE (1 << 29) +#define TP_STATUS_TS_SYS_HARDWARE (1 << 30) +#define TP_STATUS_TS_RAW_HARDWARE (1 << 31) + /* Rx ring - feature request bits */ #define TP_FT_REQ_FILL_RXHASH 0x1 -- cgit v1.2.3 From def3117493eafd9dfa1f809d861e0031b2cc8a07 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Tue, 23 Apr 2013 07:48:30 +0000 Subject: genl: Allow concurrent genl callbacks. All genl callbacks are serialized by genl-mutex. This can become bottleneck in multi threaded case. Following patch adds an parameter to genl_family so that a particular family can get concurrent netlink callback without genl_lock held. New rw-sem is used to protect genl callback from genl family unregister. in case of parallel_ops genl-family read-lock is taken for callbacks and write lock is taken for register or unregistration for any family. In case of locked genl family semaphore and gel-mutex is locked for any openration. Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/net/genetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index bdfbe68c1c3b..93024a47e0e2 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -50,6 +50,7 @@ struct genl_family { unsigned int version; unsigned int maxattr; bool netnsok; + bool parallel_ops; int (*pre_doit)(struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); -- cgit v1.2.3 From 8f7ba3ca12f6f16526fa4a8aaf2cae91563eee69 Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:27 +0000 Subject: net/mlx4: Add set VF mac address support Add ndo_set_vf_mac support which allows to set the MAC address for mlx4 VF Ethernet NICs from the host. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 260695186256..f21ddc6203bd 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -232,6 +232,7 @@ struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev); void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox); u32 mlx4_comm_get_version(void); +int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) -- cgit v1.2.3 From 3f7fb021d081c8aaac1d0cf69a288d21625e872e Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:28 +0000 Subject: net/mlx4: Add set VF default vlan ID and priority support Add support to ndo_set_vf_vlan in the driver. Once this call is used the vport is considered to be in VST mode. In this mode, the PPF driver configures Ethernet QPs created by this VF to use this vlan id and priority. Currently RoCE isn't supported on that mode. The special values of VID=4095 or VID=0,UP=0 are considered as VGT. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 2 ++ include/linux/mlx4/device.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index f21ddc6203bd..7daead75a6f5 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -233,6 +233,8 @@ void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbo u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); +int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); + #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 2fbc1464b53b..6606d8f5862a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -155,7 +155,8 @@ enum { MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2, MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3, MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4, - MLX4_DEV_CAP_FLAG2_TS = 1LL << 5 + MLX4_DEV_CAP_FLAG2_TS = 1LL << 5, + MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6 }; enum { -- cgit v1.2.3 From e6b6a2316379feebebacec0979b3ebc5743e7502 Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:29 +0000 Subject: net/mlx4: Add VF MAC spoof checking support Add ndo_set_vf_spoofchk support Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + include/linux/mlx4/device.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 7daead75a6f5..95c3223719fa 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -234,6 +234,7 @@ void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbo u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); +int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6606d8f5862a..53acaf64189f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -156,7 +156,8 @@ enum { MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3, MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4, MLX4_DEV_CAP_FLAG2_TS = 1LL << 5, - MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6 + MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6, + MLX4_DEV_CAP_FLAG2_FSM = 1LL << 7 }; enum { -- cgit v1.2.3 From 2cccb9e4f3476da916146c2ec571c4f3eff738b1 Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:30 +0000 Subject: net/mlx4: Add support to get VF config Support getting VF config. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 95c3223719fa..adf6e0648f20 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -34,6 +34,7 @@ #define MLX4_CMD_H #include +#include enum { /* initialization and general commands */ @@ -235,6 +236,7 @@ u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); +int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) -- cgit v1.2.3 From 5d174dd80ce94b7ed0950e31fc9a0122c689523b Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Sat, 27 Apr 2013 11:31:55 +0000 Subject: vxlan: source compatiablity with IFLA_VXLAN_GROUP (v2) Source compatiability for build iproute2 was broken by: commit c7995c43facc6e5dea4de63fa9d283a337aabeb1 Author: Atzm Watanabe vxlan: Allow setting destination to unicast address. Since this commit has not made it upstream (still net-next), and better to avoid gratitious changes to exported API's; go back to original definition, and add a comment. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e3163544f339..5346131524e4 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -297,7 +297,7 @@ enum macvlan_mode { enum { IFLA_VXLAN_UNSPEC, IFLA_VXLAN_ID, - IFLA_VXLAN_REMOTE, + IFLA_VXLAN_GROUP, /* group or remote address */ IFLA_VXLAN_LINK, IFLA_VXLAN_LOCAL, IFLA_VXLAN_TTL, -- cgit v1.2.3 From 823aa873bc782f1c51b1ce8ec6da7cfcaf93836e Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Sat, 27 Apr 2013 11:31:57 +0000 Subject: vxlan: allow choosing destination port per vxlan Allow configuring the default destination port on a per-device basis. Adds new netlink paramater IFLA_VXLAN_PORT to allow setting destination port when creating new vxlan. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5346131524e4..b05823cae784 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -305,11 +305,12 @@ enum { IFLA_VXLAN_LEARNING, IFLA_VXLAN_AGEING, IFLA_VXLAN_LIMIT, - IFLA_VXLAN_PORT_RANGE, + IFLA_VXLAN_PORT_RANGE, /* source port */ IFLA_VXLAN_PROXY, IFLA_VXLAN_RSC, IFLA_VXLAN_L2MISS, IFLA_VXLAN_L3MISS, + IFLA_VXLAN_PORT, /* destination port */ __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) -- cgit v1.2.3 From 626419038a3e4a1f61119a4af08d01415961eb4e Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 25 Apr 2013 06:53:52 +0000 Subject: packet_diag: disclose uid value This value is disclosed via /proc/net/packet but not via netlink messages. The goal is to have the same level of information. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/uapi/linux/packet_diag.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index afafd703ad92..84f83a47b6f6 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -32,6 +32,7 @@ enum { PACKET_DIAG_RX_RING, PACKET_DIAG_TX_RING, PACKET_DIAG_FANOUT, + PACKET_DIAG_UID, __PACKET_DIAG_MAX, }; -- cgit v1.2.3 From 76d0eeb1a1579453cfd7c4da22004d4b34187ab4 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 25 Apr 2013 06:53:53 +0000 Subject: packet_diag: disclose meminfo values sk_rmem_alloc is disclosed via /proc/net/packet but not via netlink messages. The goal is to have the same level of information. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/uapi/linux/packet_diag.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index 84f83a47b6f6..c0802c18c8ad 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -16,6 +16,7 @@ struct packet_diag_req { #define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */ #define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */ #define PACKET_SHOW_FANOUT 0x00000008 +#define PACKET_SHOW_MEMINFO 0x00000010 struct packet_diag_msg { __u8 pdiag_family; @@ -33,6 +34,7 @@ enum { PACKET_DIAG_TX_RING, PACKET_DIAG_FANOUT, PACKET_DIAG_UID, + PACKET_DIAG_MEMINFO, __PACKET_DIAG_MAX, }; -- cgit v1.2.3 From e8d9612c181b1a68ba5f71384629343466f1bd13 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 25 Apr 2013 06:53:54 +0000 Subject: sock_diag: allow to dump bpf filters This patch allows to dump BPF filters attached to a socket with SO_ATTACH_FILTER. Note that we check CAP_SYS_ADMIN before allowing to dump this info. For now, only AF_PACKET sockets use this feature. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 3 +++ include/uapi/linux/packet_diag.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index e8d702e0fd89..54f91d35e5fd 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -1,6 +1,7 @@ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ +#include #include struct sk_buff; @@ -22,5 +23,7 @@ int sock_diag_check_cookie(void *sk, __u32 *cookie); void sock_diag_save_cookie(void *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); +int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, + struct sk_buff *skb, int attrtype); #endif diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index c0802c18c8ad..b2cc0cd9c4d9 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -17,6 +17,7 @@ struct packet_diag_req { #define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */ #define PACKET_SHOW_FANOUT 0x00000008 #define PACKET_SHOW_MEMINFO 0x00000010 +#define PACKET_SHOW_FILTER 0x00000020 struct packet_diag_msg { __u8 pdiag_family; @@ -35,6 +36,7 @@ enum { PACKET_DIAG_FANOUT, PACKET_DIAG_UID, PACKET_DIAG_MEMINFO, + PACKET_DIAG_FILTER, __PACKET_DIAG_MAX, }; -- cgit v1.2.3 From a4c4009f4f54dabaaea1bb2b2c3c8930e93cd409 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 25 Apr 2013 09:52:25 +0000 Subject: net: increase frag hash size Increase fragmentation hash bucket size to 1024 from old 64 elems. After we increased the frag mem limits commit c2a93660 (net: increase fragment memory usage limits) the hash size of 64 elements is simply too small. Also considering the mem limit is per netns and the hash table is shared for all netns. For the embedded people, note that this increase will change the hash table/array from using approx 1 Kbytes to 16 Kbytes. Signed-off-by: Jesper Dangaard Brouer Acked-by: Hannes Frederic Sowa Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 6f41b45e819e..4182c9be8bb5 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -41,7 +41,7 @@ struct inet_frag_queue { struct netns_frags *net; }; -#define INETFRAGS_HASHSZ 64 +#define INETFRAGS_HASHSZ 1024 /* averaged: * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ / -- cgit v1.2.3 From 5f5624cf156283687e11ea329c7a0523c677ea0e Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 25 Apr 2013 11:08:30 +0000 Subject: ipv6: Kill ipv6 dependency of icmpv6_send(). Following patch adds icmp-registration module for ipv6. It allows ipv6 protocol to register icmp_sender which is used for sending ipv6 icmp msgs. This extra layer allows us to kill ipv6 dependency for sending icmp packets. This patch also fixes ip_tunnel compilation problem when ip_tunnel is statically compiled in kernel but ipv6 is module Signed-off-by: Pravin B Shelar Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index b4f6c29caced..630f45335c73 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -11,9 +11,21 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #include -extern void icmpv6_send(struct sk_buff *skb, - u8 type, u8 code, - __u32 info); +#if IS_ENABLED(CONFIG_IPV6) +extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); + +typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info); +extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); +extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); + +#else + +static inline void icmpv6_send(struct sk_buff *skb, + u8 type, u8 code, __u32 info) +{ + +} +#endif extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, -- cgit v1.2.3 From 43c56e595bb81319230affd545392536c933317e Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 21:51:25 +0200 Subject: netfilter: ipset: Make possible to test elements marked with nomatch Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 7958e84a65af..970187187f5b 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -200,6 +200,14 @@ ip_set_eexist(int ret, u32 flags) return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST); } +/* Match elements marked with nomatch */ +static inline bool +ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt) +{ + return adt == IPSET_TEST && + ret == -ENOTEMPTY && ((flags >> 16) & IPSET_FLAG_NOMATCH); +} + /* Check the NLA_F_NET_BYTEORDER flag */ static inline bool ip_set_attr_netorder(struct nlattr *tb[], int type) -- cgit v1.2.3 From 8672d4d1a00b59057bb1f9659259967d2a19e086 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 20:54:37 +0200 Subject: netfilter: ipset: Move often used IPv6 address masking function to header file Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/pfxlen.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h index 199fd11fedc0..1afbb94b4b65 100644 --- a/include/linux/netfilter/ipset/pfxlen.h +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -41,4 +41,13 @@ do { \ to = from | ~ip_set_hostmask(cidr); \ } while (0) +static inline void +ip6_netmask(union nf_inet_addr *ip, u8 prefix) +{ + ip->ip6[0] &= ip_set_netmask6(prefix)[0]; + ip->ip6[1] &= ip_set_netmask6(prefix)[1]; + ip->ip6[2] &= ip_set_netmask6(prefix)[2]; + ip->ip6[3] &= ip_set_netmask6(prefix)[3]; +} + #endif /*_PFXLEN_H */ -- cgit v1.2.3 From 075e64c041b5d3c29651965608e1e76505e01d54 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 27 Apr 2013 14:28:55 +0200 Subject: netfilter: ipset: Introduce extensions to elements in the core Introduce extensions to elements in the core and prepare timeout as the first one. This patch also modifies the em_ipset classifier to use the new extension struct layout. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 46 +++++++++-- include/linux/netfilter/ipset/ip_set_timeout.h | 102 ++++++------------------- 2 files changed, 61 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 970187187f5b..bf0220cbf46a 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -1,7 +1,7 @@ /* Copyright (C) 2000-2002 Joakim Axelsson * Patrick Schaaf * Martin Josefsson - * Copyright (C) 2003-2011 Jozsef Kadlecsik + * Copyright (C) 2003-2013 Jozsef Kadlecsik * * 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 @@ -47,10 +47,30 @@ enum ip_set_feature { IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG), }; +/* Set extensions */ +enum ip_set_extension { + IPSET_EXT_NONE = 0, + IPSET_EXT_BIT_TIMEOUT = 1, + IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT), +}; + +/* Extension offsets */ +enum ip_set_offset { + IPSET_OFFSET_TIMEOUT = 0, + IPSET_OFFSET_MAX, +}; + +#define SET_WITH_TIMEOUT(s) ((s)->extensions & IPSET_EXT_TIMEOUT) + +struct ip_set_ext { + unsigned long timeout; +}; + struct ip_set; typedef int (*ipset_adtfn)(struct ip_set *set, void *value, - u32 timeout, u32 flags); + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); /* Kernel API function options */ struct ip_set_adt_opt { @@ -58,7 +78,7 @@ struct ip_set_adt_opt { u8 dim; /* Dimension of match/target */ u8 flags; /* Direction and negation flags */ u32 cmdflags; /* Command-like flags */ - u32 timeout; /* Timeout value */ + struct ip_set_ext ext; /* Extensions */ }; /* Set type, variant-specific part */ @@ -69,7 +89,7 @@ struct ip_set_type_variant { * positive for matching element */ int (*kadt)(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, - enum ipset_adt adt, const struct ip_set_adt_opt *opt); + enum ipset_adt adt, struct ip_set_adt_opt *opt); /* Userspace: test/add/del entries * returns negative error code, @@ -151,6 +171,8 @@ struct ip_set { u8 family; /* The type revision */ u8 revision; + /* Extensions */ + u8 extensions; /* The type specific data */ void *data; }; @@ -167,19 +189,21 @@ extern void ip_set_nfnl_put(ip_set_id_t index); extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, - const struct ip_set_adt_opt *opt); + struct ip_set_adt_opt *opt); extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, - const struct ip_set_adt_opt *opt); + struct ip_set_adt_opt *opt); extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, - const struct ip_set_adt_opt *opt); + struct ip_set_adt_opt *opt); /* Utility functions */ extern void *ip_set_alloc(size_t size); extern void ip_set_free(void *members); extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); +extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], + struct ip_set_ext *ext); static inline int ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) @@ -292,4 +316,12 @@ bitmap_bytes(u32 a, u32 b) return 4 * ((((b - a + 8) / 8) + 3) / 4); } +#include + +#define IP_SET_INIT_KEXT(skb, opt, map) \ + { .timeout = ip_set_adt_opt_timeout(opt, map) } + +#define IP_SET_INIT_UEXT(map) \ + { .timeout = (map)->timeout } + #endif /*_IP_SET_H */ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index 41d9cfa08167..3aac04167ca7 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -1,7 +1,7 @@ #ifndef _IP_SET_TIMEOUT_H #define _IP_SET_TIMEOUT_H -/* Copyright (C) 2003-2011 Jozsef Kadlecsik +/* Copyright (C) 2003-2013 Jozsef Kadlecsik * * 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 @@ -17,13 +17,14 @@ #define IPSET_GC_PERIOD(timeout) \ ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) -/* Set is defined without timeout support: timeout value may be 0 */ -#define IPSET_NO_TIMEOUT UINT_MAX +/* Entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT 0 -#define with_timeout(timeout) ((timeout) != IPSET_NO_TIMEOUT) +/* Set is defined with timeout support: timeout value may be 0 */ +#define IPSET_NO_TIMEOUT UINT_MAX -#define opt_timeout(opt, map) \ - (with_timeout((opt)->timeout) ? (opt)->timeout : (map)->timeout) +#define ip_set_adt_opt_timeout(opt, map) \ +((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (map)->timeout) static inline unsigned int ip_set_timeout_uget(struct nlattr *tb) @@ -38,61 +39,6 @@ ip_set_timeout_uget(struct nlattr *tb) return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout; } -#ifdef IP_SET_BITMAP_TIMEOUT - -/* Bitmap specific timeout constants and macros for the entries */ - -/* Bitmap entry is unset */ -#define IPSET_ELEM_UNSET 0 -/* Bitmap entry is set with no timeout value */ -#define IPSET_ELEM_PERMANENT (UINT_MAX/2) - -static inline bool -ip_set_timeout_test(unsigned long timeout) -{ - return timeout != IPSET_ELEM_UNSET && - (timeout == IPSET_ELEM_PERMANENT || - time_is_after_jiffies(timeout)); -} - -static inline bool -ip_set_timeout_expired(unsigned long timeout) -{ - return timeout != IPSET_ELEM_UNSET && - timeout != IPSET_ELEM_PERMANENT && - time_is_before_jiffies(timeout); -} - -static inline unsigned long -ip_set_timeout_set(u32 timeout) -{ - unsigned long t; - - if (!timeout) - return IPSET_ELEM_PERMANENT; - - t = msecs_to_jiffies(timeout * 1000) + jiffies; - if (t == IPSET_ELEM_UNSET || t == IPSET_ELEM_PERMANENT) - /* Bingo! */ - t++; - - return t; -} - -static inline u32 -ip_set_timeout_get(unsigned long timeout) -{ - return timeout == IPSET_ELEM_PERMANENT ? 0 : - jiffies_to_msecs(timeout - jiffies)/1000; -} - -#else - -/* Hash specific timeout constants and macros for the entries */ - -/* Hash entry is set with no timeout value */ -#define IPSET_ELEM_PERMANENT 0 - static inline bool ip_set_timeout_test(unsigned long timeout) { @@ -101,36 +47,32 @@ ip_set_timeout_test(unsigned long timeout) } static inline bool -ip_set_timeout_expired(unsigned long timeout) +ip_set_timeout_expired(unsigned long *timeout) { - return timeout != IPSET_ELEM_PERMANENT && - time_is_before_jiffies(timeout); + return *timeout != IPSET_ELEM_PERMANENT && + time_is_before_jiffies(*timeout); } -static inline unsigned long -ip_set_timeout_set(u32 timeout) +static inline void +ip_set_timeout_set(unsigned long *timeout, u32 t) { - unsigned long t; - - if (!timeout) - return IPSET_ELEM_PERMANENT; + if (!t) { + *timeout = IPSET_ELEM_PERMANENT; + return; + } - t = msecs_to_jiffies(timeout * 1000) + jiffies; - if (t == IPSET_ELEM_PERMANENT) + *timeout = msecs_to_jiffies(t * 1000) + jiffies; + if (*timeout == IPSET_ELEM_PERMANENT) /* Bingo! :-) */ - t++; - - return t; + (*timeout)--; } static inline u32 -ip_set_timeout_get(unsigned long timeout) +ip_set_timeout_get(unsigned long *timeout) { - return timeout == IPSET_ELEM_PERMANENT ? 0 : - jiffies_to_msecs(timeout - jiffies)/1000; + return *timeout == IPSET_ELEM_PERMANENT ? 0 : + jiffies_to_msecs(*timeout - jiffies)/1000; } -#endif /* ! IP_SET_BITMAP_TIMEOUT */ #endif /* __KERNEL__ */ - #endif /* _IP_SET_TIMEOUT_H */ -- cgit v1.2.3 From 4d73de38c256623b324474098f7d2bb4e97f7cf0 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 21:00:52 +0200 Subject: netfilter: ipset: Unified bitmap type generation Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_bitmap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h index 1a30646d5be8..5e4662a71e01 100644 --- a/include/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -5,6 +5,12 @@ #define IPSET_BITMAP_MAX_RANGE 0x0000FFFF +enum { + IPSET_ADD_FAILED = 1, + IPSET_ADD_STORE_PLAIN_TIMEOUT, + IPSET_ADD_START_STORED_TIMEOUT, +}; + /* Common functions */ static inline u32 -- cgit v1.2.3 From 1feab10d7e6ddb5e13d6a4bd93a1b877390262ec Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 21:05:44 +0200 Subject: netfilter: ipset: Unified hash type generation Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_ahash.h | 1241 -------------------------- 1 file changed, 1241 deletions(-) delete mode 100644 include/linux/netfilter/ipset/ip_set_ahash.h (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h deleted file mode 100644 index 0214c4c146fa..000000000000 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ /dev/null @@ -1,1241 +0,0 @@ -#ifndef _IP_SET_AHASH_H -#define _IP_SET_AHASH_H - -#include -#include -#include - -#define CONCAT(a, b, c) a##b##c -#define TOKEN(a, b, c) CONCAT(a, b, c) - -#define type_pf_next TOKEN(TYPE, PF, _elem) - -/* Hashing which uses arrays to resolve clashing. The hash table is resized - * (doubled) when searching becomes too long. - * Internally jhash is used with the assumption that the size of the - * stored data is a multiple of sizeof(u32). If storage supports timeout, - * the timeout field must be the last one in the data structure - that field - * is ignored when computing the hash key. - * - * Readers and resizing - * - * Resizing can be triggered by userspace command only, and those - * are serialized by the nfnl mutex. During resizing the set is - * read-locked, so the only possible concurrent operations are - * the kernel side readers. Those must be protected by proper RCU locking. - */ - -/* Number of elements to store in an initial array block */ -#define AHASH_INIT_SIZE 4 -/* Max number of elements to store in an array block */ -#define AHASH_MAX_SIZE (3*AHASH_INIT_SIZE) - -/* Max number of elements can be tuned */ -#ifdef IP_SET_HASH_WITH_MULTI -#define AHASH_MAX(h) ((h)->ahash_max) - -static inline u8 -tune_ahash_max(u8 curr, u32 multi) -{ - u32 n; - - if (multi < curr) - return curr; - - n = curr + AHASH_INIT_SIZE; - /* Currently, at listing one hash bucket must fit into a message. - * Therefore we have a hard limit here. - */ - return n > curr && n <= 64 ? n : curr; -} -#define TUNE_AHASH_MAX(h, multi) \ - ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi)) -#else -#define AHASH_MAX(h) AHASH_MAX_SIZE -#define TUNE_AHASH_MAX(h, multi) -#endif - -/* A hash bucket */ -struct hbucket { - void *value; /* the array of the values */ - u8 size; /* size of the array */ - u8 pos; /* position of the first free entry */ -}; - -/* The hash table: the table size stored here in order to make resizing easy */ -struct htable { - u8 htable_bits; /* size of hash table == 2^htable_bits */ - struct hbucket bucket[0]; /* hashtable buckets */ -}; - -#define hbucket(h, i) (&((h)->bucket[i])) - -/* Book-keeping of the prefixes added to the set */ -struct ip_set_hash_nets { - u8 cidr; /* the different cidr values in the set */ - u32 nets; /* number of elements per cidr */ -}; - -/* The generic ip_set hash structure */ -struct ip_set_hash { - struct htable *table; /* the hash table */ - u32 maxelem; /* max elements in the hash */ - u32 elements; /* current element (vs timeout) */ - u32 initval; /* random jhash init value */ - u32 timeout; /* timeout value, if enabled */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct type_pf_next next; /* temporary storage for uadd */ -#ifdef IP_SET_HASH_WITH_MULTI - u8 ahash_max; /* max elements in an array block */ -#endif -#ifdef IP_SET_HASH_WITH_NETMASK - u8 netmask; /* netmask value for subnets to store */ -#endif -#ifdef IP_SET_HASH_WITH_RBTREE - struct rb_root rbtree; -#endif -#ifdef IP_SET_HASH_WITH_NETS - struct ip_set_hash_nets nets[0]; /* book-keeping of prefixes */ -#endif -}; - -static size_t -htable_size(u8 hbits) -{ - size_t hsize; - - /* We must fit both into u32 in jhash and size_t */ - if (hbits > 31) - return 0; - hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable))/sizeof(struct hbucket) - < hsize) - return 0; - - return hsize * sizeof(struct hbucket) + sizeof(struct htable); -} - -/* Compute htable_bits from the user input parameter hashsize */ -static u8 -htable_bits(u32 hashsize) -{ - /* Assume that hashsize == 2^htable_bits */ - u8 bits = fls(hashsize - 1); - if (jhash_size(bits) != hashsize) - /* Round up to the first 2^n value */ - bits = fls(hashsize); - - return bits; -} - -#ifdef IP_SET_HASH_WITH_NETS -#ifdef IP_SET_HASH_WITH_NETS_PACKED -/* When cidr is packed with nomatch, cidr - 1 is stored in the entry */ -#define CIDR(cidr) (cidr + 1) -#else -#define CIDR(cidr) (cidr) -#endif - -#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) -#ifdef IP_SET_HASH_WITH_MULTI -#define NETS_LENGTH(family) (SET_HOST_MASK(family) + 1) -#else -#define NETS_LENGTH(family) SET_HOST_MASK(family) -#endif - -/* Network cidr size book keeping when the hash stores different - * sized networks */ -static void -add_cidr(struct ip_set_hash *h, u8 cidr, u8 nets_length) -{ - int i, j; - - /* Add in increasing prefix order, so larger cidr first */ - for (i = 0, j = -1; i < nets_length && h->nets[i].nets; i++) { - if (j != -1) - continue; - else if (h->nets[i].cidr < cidr) - j = i; - else if (h->nets[i].cidr == cidr) { - h->nets[i].nets++; - return; - } - } - if (j != -1) { - for (; i > j; i--) { - h->nets[i].cidr = h->nets[i - 1].cidr; - h->nets[i].nets = h->nets[i - 1].nets; - } - } - h->nets[i].cidr = cidr; - h->nets[i].nets = 1; -} - -static void -del_cidr(struct ip_set_hash *h, u8 cidr, u8 nets_length) -{ - u8 i, j; - - for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++) - ; - h->nets[i].nets--; - - if (h->nets[i].nets != 0) - return; - - for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) { - h->nets[j].cidr = h->nets[j + 1].cidr; - h->nets[j].nets = h->nets[j + 1].nets; - } -} -#else -#define NETS_LENGTH(family) 0 -#endif - -/* Destroy the hashtable part of the set */ -static void -ahash_destroy(struct htable *t) -{ - struct hbucket *n; - u32 i; - - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - if (n->size) - /* FIXME: use slab cache */ - kfree(n->value); - } - - ip_set_free(t); -} - -/* Calculate the actual memory size of the set data */ -static size_t -ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 nets_length) -{ - u32 i; - struct htable *t = h->table; - size_t memsize = sizeof(*h) - + sizeof(*t) -#ifdef IP_SET_HASH_WITH_NETS - + sizeof(struct ip_set_hash_nets) * nets_length -#endif - + jhash_size(t->htable_bits) * sizeof(struct hbucket); - - for (i = 0; i < jhash_size(t->htable_bits); i++) - memsize += t->bucket[i].size * dsize; - - return memsize; -} - -/* Flush a hash type of set: destroy all elements */ -static void -ip_set_hash_flush(struct ip_set *set) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct hbucket *n; - u32 i; - - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - if (n->size) { - n->size = n->pos = 0; - /* FIXME: use slab cache */ - kfree(n->value); - } - } -#ifdef IP_SET_HASH_WITH_NETS - memset(h->nets, 0, sizeof(struct ip_set_hash_nets) - * NETS_LENGTH(set->family)); -#endif - h->elements = 0; -} - -/* Destroy a hash type of set */ -static void -ip_set_hash_destroy(struct ip_set *set) -{ - struct ip_set_hash *h = set->data; - - if (with_timeout(h->timeout)) - del_timer_sync(&h->gc); - - ahash_destroy(h->table); -#ifdef IP_SET_HASH_WITH_RBTREE - rbtree_destroy(&h->rbtree); -#endif - kfree(h); - - set->data = NULL; -} - -#endif /* _IP_SET_AHASH_H */ - -#ifndef HKEY_DATALEN -#define HKEY_DATALEN sizeof(struct type_pf_elem) -#endif - -#define HKEY(data, initval, htable_bits) \ -(jhash2((u32 *)(data), HKEY_DATALEN/sizeof(u32), initval) \ - & jhash_mask(htable_bits)) - -/* Type/family dependent function prototypes */ - -#define type_pf_data_equal TOKEN(TYPE, PF, _data_equal) -#define type_pf_data_isnull TOKEN(TYPE, PF, _data_isnull) -#define type_pf_data_copy TOKEN(TYPE, PF, _data_copy) -#define type_pf_data_zero_out TOKEN(TYPE, PF, _data_zero_out) -#define type_pf_data_netmask TOKEN(TYPE, PF, _data_netmask) -#define type_pf_data_list TOKEN(TYPE, PF, _data_list) -#define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) -#define type_pf_data_next TOKEN(TYPE, PF, _data_next) -#define type_pf_data_flags TOKEN(TYPE, PF, _data_flags) -#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags) -#ifdef IP_SET_HASH_WITH_NETS -#define type_pf_data_match TOKEN(TYPE, PF, _data_match) -#else -#define type_pf_data_match(d) 1 -#endif - -#define type_pf_elem TOKEN(TYPE, PF, _elem) -#define type_pf_telem TOKEN(TYPE, PF, _telem) -#define type_pf_data_timeout TOKEN(TYPE, PF, _data_timeout) -#define type_pf_data_expired TOKEN(TYPE, PF, _data_expired) -#define type_pf_data_timeout_set TOKEN(TYPE, PF, _data_timeout_set) - -#define type_pf_elem_add TOKEN(TYPE, PF, _elem_add) -#define type_pf_add TOKEN(TYPE, PF, _add) -#define type_pf_del TOKEN(TYPE, PF, _del) -#define type_pf_test_cidrs TOKEN(TYPE, PF, _test_cidrs) -#define type_pf_test TOKEN(TYPE, PF, _test) - -#define type_pf_elem_tadd TOKEN(TYPE, PF, _elem_tadd) -#define type_pf_del_telem TOKEN(TYPE, PF, _ahash_del_telem) -#define type_pf_expire TOKEN(TYPE, PF, _expire) -#define type_pf_tadd TOKEN(TYPE, PF, _tadd) -#define type_pf_tdel TOKEN(TYPE, PF, _tdel) -#define type_pf_ttest_cidrs TOKEN(TYPE, PF, _ahash_ttest_cidrs) -#define type_pf_ttest TOKEN(TYPE, PF, _ahash_ttest) - -#define type_pf_resize TOKEN(TYPE, PF, _resize) -#define type_pf_tresize TOKEN(TYPE, PF, _tresize) -#define type_pf_flush ip_set_hash_flush -#define type_pf_destroy ip_set_hash_destroy -#define type_pf_head TOKEN(TYPE, PF, _head) -#define type_pf_list TOKEN(TYPE, PF, _list) -#define type_pf_tlist TOKEN(TYPE, PF, _tlist) -#define type_pf_same_set TOKEN(TYPE, PF, _same_set) -#define type_pf_kadt TOKEN(TYPE, PF, _kadt) -#define type_pf_uadt TOKEN(TYPE, PF, _uadt) -#define type_pf_gc TOKEN(TYPE, PF, _gc) -#define type_pf_gc_init TOKEN(TYPE, PF, _gc_init) -#define type_pf_variant TOKEN(TYPE, PF, _variant) -#define type_pf_tvariant TOKEN(TYPE, PF, _tvariant) - -/* Flavour without timeout */ - -/* Get the ith element from the array block n */ -#define ahash_data(n, i) \ - ((struct type_pf_elem *)((n)->value) + (i)) - -/* Add an element to the hash table when resizing the set: - * we spare the maintenance of the internal counters. */ -static int -type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value, - u8 ahash_max, u32 cadt_flags) -{ - struct type_pf_elem *data; - - if (n->pos >= n->size) { - void *tmp; - - if (n->size >= ahash_max) - /* Trigger rehashing */ - return -EAGAIN; - - tmp = kzalloc((n->size + AHASH_INIT_SIZE) - * sizeof(struct type_pf_elem), - GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - if (n->size) { - memcpy(tmp, n->value, - sizeof(struct type_pf_elem) * n->size); - kfree(n->value); - } - n->value = tmp; - n->size += AHASH_INIT_SIZE; - } - data = ahash_data(n, n->pos++); - type_pf_data_copy(data, value); -#ifdef IP_SET_HASH_WITH_NETS - /* Resizing won't overwrite stored flags */ - if (cadt_flags) - type_pf_data_flags(data, cadt_flags); -#endif - return 0; -} - -/* Resize a hash: create a new hash table with doubling the hashsize - * and inserting the elements to it. Repeat until we succeed or - * fail due to memory pressures. */ -static int -type_pf_resize(struct ip_set *set, bool retried) -{ - struct ip_set_hash *h = set->data; - struct htable *t, *orig = h->table; - u8 htable_bits = orig->htable_bits; - struct type_pf_elem *data; - struct hbucket *n, *m; - u32 i, j, flags = 0; - int ret; - -retry: - ret = 0; - htable_bits++; - pr_debug("attempt to resize set %s from %u to %u, t %p\n", - set->name, orig->htable_bits, htable_bits, orig); - if (!htable_bits) { - /* In case we have plenty of memory :-) */ - pr_warning("Cannot increase the hashsize of set %s further\n", - set->name); - return -IPSET_ERR_HASH_FULL; - } - t = ip_set_alloc(sizeof(*t) - + jhash_size(htable_bits) * sizeof(struct hbucket)); - if (!t) - return -ENOMEM; - t->htable_bits = htable_bits; - - read_lock_bh(&set->lock); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = hbucket(orig, i); - for (j = 0; j < n->pos; j++) { - data = ahash_data(n, j); -#ifdef IP_SET_HASH_WITH_NETS - flags = 0; - type_pf_data_reset_flags(data, &flags); -#endif - m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags); - if (ret < 0) { -#ifdef IP_SET_HASH_WITH_NETS - type_pf_data_flags(data, flags); -#endif - read_unlock_bh(&set->lock); - ahash_destroy(t); - if (ret == -EAGAIN) - goto retry; - return ret; - } - } - } - - rcu_assign_pointer(h->table, t); - read_unlock_bh(&set->lock); - - /* Give time to other readers of the set */ - synchronize_rcu_bh(); - - pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, - orig->htable_bits, orig, t->htable_bits, t); - ahash_destroy(orig); - - return 0; -} - -static inline void -type_pf_data_next(struct ip_set_hash *h, const struct type_pf_elem *d); - -/* Add an element to a hash and update the internal counters when succeeded, - * otherwise report the proper error code. */ -static int -type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t; - const struct type_pf_elem *d = value; - struct hbucket *n; - int i, ret = 0; - u32 key, multi = 0; - u32 cadt_flags = flags >> 16; - - if (h->elements >= h->maxelem) { - if (net_ratelimit()) - pr_warning("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; - } - - rcu_read_lock_bh(); - t = rcu_dereference_bh(h->table); - key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) - if (type_pf_data_equal(ahash_data(n, i), d, &multi)) { -#ifdef IP_SET_HASH_WITH_NETS - if (flags & IPSET_FLAG_EXIST) - /* Support overwriting just the flags */ - type_pf_data_flags(ahash_data(n, i), - cadt_flags); -#endif - ret = -IPSET_ERR_EXIST; - goto out; - } - TUNE_AHASH_MAX(h, multi); - ret = type_pf_elem_add(n, value, AHASH_MAX(h), cadt_flags); - if (ret != 0) { - if (ret == -EAGAIN) - type_pf_data_next(h, d); - goto out; - } - -#ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - h->elements++; -out: - rcu_read_unlock_bh(); - return ret; -} - -/* Delete an element from the hash: swap it with the last element - * and free up space if possible. - */ -static int -type_pf_del(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - const struct type_pf_elem *d = value; - struct hbucket *n; - int i; - struct type_pf_elem *data; - u32 key, multi = 0; - - key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - if (!type_pf_data_equal(data, d, &multi)) - continue; - if (i != n->pos - 1) - /* Not last one */ - type_pf_data_copy(data, ahash_data(n, n->pos - 1)); - - n->pos--; - h->elements--; -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * sizeof(struct type_pf_elem), - GFP_ATOMIC); - if (!tmp) - return 0; - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, - n->size * sizeof(struct type_pf_elem)); - kfree(n->value); - n->value = tmp; - } - return 0; - } - - return -IPSET_ERR_EXIST; -} - -#ifdef IP_SET_HASH_WITH_NETS - -/* Special test function which takes into account the different network - * sizes added to the set */ -static int -type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct hbucket *n; - const struct type_pf_elem *data; - int i, j = 0; - u32 key, multi = 0; - u8 nets_length = NETS_LENGTH(set->family); - - pr_debug("test by nets\n"); - for (; j < nets_length && h->nets[j].nets && !multi; j++) { - type_pf_data_netmask(d, h->nets[j].cidr); - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - if (type_pf_data_equal(data, d, &multi)) - return type_pf_data_match(data); - } - } - return 0; -} -#endif - -/* Test whether the element is added to the set */ -static int -type_pf_test(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct type_pf_elem *d = value; - struct hbucket *n; - const struct type_pf_elem *data; - int i; - u32 key, multi = 0; - -#ifdef IP_SET_HASH_WITH_NETS - /* If we test an IP address and not a network address, - * try all possible network sizes */ - if (CIDR(d->cidr) == SET_HOST_MASK(set->family)) - return type_pf_test_cidrs(set, d, timeout); -#endif - - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - if (type_pf_data_equal(data, d, &multi)) - return type_pf_data_match(data); - } - return 0; -} - -/* Reply a HEADER request: fill out the header part of the set */ -static int -type_pf_head(struct ip_set *set, struct sk_buff *skb) -{ - const struct ip_set_hash *h = set->data; - struct nlattr *nested; - size_t memsize; - - read_lock_bh(&set->lock); - memsize = ahash_memsize(h, with_timeout(h->timeout) - ? sizeof(struct type_pf_telem) - : sizeof(struct type_pf_elem), - NETS_LENGTH(set->family)); - read_unlock_bh(&set->lock); - - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); - if (!nested) - goto nla_put_failure; - if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, - htonl(jhash_size(h->table->htable_bits))) || - nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) - goto nla_put_failure; -#ifdef IP_SET_HASH_WITH_NETMASK - if (h->netmask != HOST_MASK && - nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) - goto nla_put_failure; -#endif - if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || - nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - (with_timeout(h->timeout) && - nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout)))) - goto nla_put_failure; - ipset_nest_end(skb, nested); - - return 0; -nla_put_failure: - return -EMSGSIZE; -} - -/* Reply a LIST/SAVE request: dump the elements of the specified set */ -static int -type_pf_list(const struct ip_set *set, - struct sk_buff *skb, struct netlink_callback *cb) -{ - const struct ip_set_hash *h = set->data; - const struct htable *t = h->table; - struct nlattr *atd, *nested; - const struct hbucket *n; - const struct type_pf_elem *data; - u32 first = cb->args[2]; - /* We assume that one hash bucket fills into one page */ - void *incomplete; - int i; - - atd = ipset_nest_start(skb, IPSET_ATTR_ADT); - if (!atd) - return -EMSGSIZE; - pr_debug("list hash set %s\n", set->name); - for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { - incomplete = skb_tail_pointer(skb); - n = hbucket(t, cb->args[2]); - pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - pr_debug("list hash %lu hbucket %p i %u, data %p\n", - cb->args[2], n, i, data); - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); - if (!nested) { - if (cb->args[2] == first) { - nla_nest_cancel(skb, atd); - return -EMSGSIZE; - } else - goto nla_put_failure; - } - if (type_pf_data_list(skb, data)) - goto nla_put_failure; - ipset_nest_end(skb, nested); - } - } - ipset_nest_end(skb, atd); - /* Set listing finished */ - cb->args[2] = 0; - - return 0; - -nla_put_failure: - nlmsg_trim(skb, incomplete); - ipset_nest_end(skb, atd); - if (unlikely(first == cb->args[2])) { - pr_warning("Can't list set %s: one bucket does not fit into " - "a message. Please report it!\n", set->name); - cb->args[2] = 0; - return -EMSGSIZE; - } - return 0; -} - -static int -type_pf_kadt(struct ip_set *set, const struct sk_buff *skb, - const struct xt_action_param *par, - enum ipset_adt adt, const struct ip_set_adt_opt *opt); -static int -type_pf_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried); - -static const struct ip_set_type_variant type_pf_variant = { - .kadt = type_pf_kadt, - .uadt = type_pf_uadt, - .adt = { - [IPSET_ADD] = type_pf_add, - [IPSET_DEL] = type_pf_del, - [IPSET_TEST] = type_pf_test, - }, - .destroy = type_pf_destroy, - .flush = type_pf_flush, - .head = type_pf_head, - .list = type_pf_list, - .resize = type_pf_resize, - .same_set = type_pf_same_set, -}; - -/* Flavour with timeout support */ - -#define ahash_tdata(n, i) \ - (struct type_pf_elem *)((struct type_pf_telem *)((n)->value) + (i)) - -static inline u32 -type_pf_data_timeout(const struct type_pf_elem *data) -{ - const struct type_pf_telem *tdata = - (const struct type_pf_telem *) data; - - return tdata->timeout; -} - -static inline bool -type_pf_data_expired(const struct type_pf_elem *data) -{ - const struct type_pf_telem *tdata = - (const struct type_pf_telem *) data; - - return ip_set_timeout_expired(tdata->timeout); -} - -static inline void -type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout) -{ - struct type_pf_telem *tdata = (struct type_pf_telem *) data; - - tdata->timeout = ip_set_timeout_set(timeout); -} - -static int -type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, - u8 ahash_max, u32 cadt_flags, u32 timeout) -{ - struct type_pf_elem *data; - - if (n->pos >= n->size) { - void *tmp; - - if (n->size >= ahash_max) - /* Trigger rehashing */ - return -EAGAIN; - - tmp = kzalloc((n->size + AHASH_INIT_SIZE) - * sizeof(struct type_pf_telem), - GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - if (n->size) { - memcpy(tmp, n->value, - sizeof(struct type_pf_telem) * n->size); - kfree(n->value); - } - n->value = tmp; - n->size += AHASH_INIT_SIZE; - } - data = ahash_tdata(n, n->pos++); - type_pf_data_copy(data, value); - type_pf_data_timeout_set(data, timeout); -#ifdef IP_SET_HASH_WITH_NETS - /* Resizing won't overwrite stored flags */ - if (cadt_flags) - type_pf_data_flags(data, cadt_flags); -#endif - return 0; -} - -/* Delete expired elements from the hashtable */ -static void -type_pf_expire(struct ip_set_hash *h, u8 nets_length) -{ - struct htable *t = h->table; - struct hbucket *n; - struct type_pf_elem *data; - u32 i; - int j; - - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - for (j = 0; j < n->pos; j++) { - data = ahash_tdata(n, j); - if (type_pf_data_expired(data)) { - pr_debug("expired %u/%u\n", i, j); -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(data->cidr), nets_length); -#endif - if (j != n->pos - 1) - /* Not last one */ - type_pf_data_copy(data, - ahash_tdata(n, n->pos - 1)); - n->pos--; - h->elements--; - } - } - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * sizeof(struct type_pf_telem), - GFP_ATOMIC); - if (!tmp) - /* Still try to delete expired elements */ - continue; - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, - n->size * sizeof(struct type_pf_telem)); - kfree(n->value); - n->value = tmp; - } - } -} - -static int -type_pf_tresize(struct ip_set *set, bool retried) -{ - struct ip_set_hash *h = set->data; - struct htable *t, *orig = h->table; - u8 htable_bits = orig->htable_bits; - struct type_pf_elem *data; - struct hbucket *n, *m; - u32 i, j, flags = 0; - int ret; - - /* Try to cleanup once */ - if (!retried) { - i = h->elements; - write_lock_bh(&set->lock); - type_pf_expire(set->data, NETS_LENGTH(set->family)); - write_unlock_bh(&set->lock); - if (h->elements < i) - return 0; - } - -retry: - ret = 0; - htable_bits++; - pr_debug("attempt to resize set %s from %u to %u, t %p\n", - set->name, orig->htable_bits, htable_bits, orig); - if (!htable_bits) { - /* In case we have plenty of memory :-) */ - pr_warning("Cannot increase the hashsize of set %s further\n", - set->name); - return -IPSET_ERR_HASH_FULL; - } - t = ip_set_alloc(sizeof(*t) - + jhash_size(htable_bits) * sizeof(struct hbucket)); - if (!t) - return -ENOMEM; - t->htable_bits = htable_bits; - - read_lock_bh(&set->lock); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = hbucket(orig, i); - for (j = 0; j < n->pos; j++) { - data = ahash_tdata(n, j); -#ifdef IP_SET_HASH_WITH_NETS - flags = 0; - type_pf_data_reset_flags(data, &flags); -#endif - m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags, - ip_set_timeout_get(type_pf_data_timeout(data))); - if (ret < 0) { -#ifdef IP_SET_HASH_WITH_NETS - type_pf_data_flags(data, flags); -#endif - read_unlock_bh(&set->lock); - ahash_destroy(t); - if (ret == -EAGAIN) - goto retry; - return ret; - } - } - } - - rcu_assign_pointer(h->table, t); - read_unlock_bh(&set->lock); - - /* Give time to other readers of the set */ - synchronize_rcu_bh(); - - ahash_destroy(orig); - - return 0; -} - -static int -type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - const struct type_pf_elem *d = value; - struct hbucket *n; - struct type_pf_elem *data; - int ret = 0, i, j = AHASH_MAX(h) + 1; - bool flag_exist = flags & IPSET_FLAG_EXIST; - u32 key, multi = 0; - u32 cadt_flags = flags >> 16; - - if (h->elements >= h->maxelem) - /* FIXME: when set is full, we slow down here */ - type_pf_expire(h, NETS_LENGTH(set->family)); - if (h->elements >= h->maxelem) { - if (net_ratelimit()) - pr_warning("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; - } - - rcu_read_lock_bh(); - t = rcu_dereference_bh(h->table); - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d, &multi)) { - if (type_pf_data_expired(data) || flag_exist) - /* Just timeout value may be updated */ - j = i; - else { - ret = -IPSET_ERR_EXIST; - goto out; - } - } else if (j == AHASH_MAX(h) + 1 && - type_pf_data_expired(data)) - j = i; - } - if (j != AHASH_MAX(h) + 1) { - data = ahash_tdata(n, j); -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(data->cidr), NETS_LENGTH(set->family)); - add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - type_pf_data_copy(data, d); - type_pf_data_timeout_set(data, timeout); -#ifdef IP_SET_HASH_WITH_NETS - type_pf_data_flags(data, cadt_flags); -#endif - goto out; - } - TUNE_AHASH_MAX(h, multi); - ret = type_pf_elem_tadd(n, d, AHASH_MAX(h), cadt_flags, timeout); - if (ret != 0) { - if (ret == -EAGAIN) - type_pf_data_next(h, d); - goto out; - } - -#ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - h->elements++; -out: - rcu_read_unlock_bh(); - return ret; -} - -static int -type_pf_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - const struct type_pf_elem *d = value; - struct hbucket *n; - int i; - struct type_pf_elem *data; - u32 key, multi = 0; - - key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - if (!type_pf_data_equal(data, d, &multi)) - continue; - if (type_pf_data_expired(data)) - return -IPSET_ERR_EXIST; - if (i != n->pos - 1) - /* Not last one */ - type_pf_data_copy(data, ahash_tdata(n, n->pos - 1)); - - n->pos--; - h->elements--; -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * sizeof(struct type_pf_telem), - GFP_ATOMIC); - if (!tmp) - return 0; - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, - n->size * sizeof(struct type_pf_telem)); - kfree(n->value); - n->value = tmp; - } - return 0; - } - - return -IPSET_ERR_EXIST; -} - -#ifdef IP_SET_HASH_WITH_NETS -static int -type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct type_pf_elem *data; - struct hbucket *n; - int i, j = 0; - u32 key, multi = 0; - u8 nets_length = NETS_LENGTH(set->family); - - for (; j < nets_length && h->nets[j].nets && !multi; j++) { - type_pf_data_netmask(d, h->nets[j].cidr); - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); -#ifdef IP_SET_HASH_WITH_MULTI - if (type_pf_data_equal(data, d, &multi)) { - if (!type_pf_data_expired(data)) - return type_pf_data_match(data); - multi = 0; - } -#else - if (type_pf_data_equal(data, d, &multi) && - !type_pf_data_expired(data)) - return type_pf_data_match(data); -#endif - } - } - return 0; -} -#endif - -static int -type_pf_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct type_pf_elem *data, *d = value; - struct hbucket *n; - int i; - u32 key, multi = 0; - -#ifdef IP_SET_HASH_WITH_NETS - if (CIDR(d->cidr) == SET_HOST_MASK(set->family)) - return type_pf_ttest_cidrs(set, d, timeout); -#endif - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d, &multi) && - !type_pf_data_expired(data)) - return type_pf_data_match(data); - } - return 0; -} - -static int -type_pf_tlist(const struct ip_set *set, - struct sk_buff *skb, struct netlink_callback *cb) -{ - const struct ip_set_hash *h = set->data; - const struct htable *t = h->table; - struct nlattr *atd, *nested; - const struct hbucket *n; - const struct type_pf_elem *data; - u32 first = cb->args[2]; - /* We assume that one hash bucket fills into one page */ - void *incomplete; - int i; - - atd = ipset_nest_start(skb, IPSET_ATTR_ADT); - if (!atd) - return -EMSGSIZE; - for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { - incomplete = skb_tail_pointer(skb); - n = hbucket(t, cb->args[2]); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - pr_debug("list %p %u\n", n, i); - if (type_pf_data_expired(data)) - continue; - pr_debug("do list %p %u\n", n, i); - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); - if (!nested) { - if (cb->args[2] == first) { - nla_nest_cancel(skb, atd); - return -EMSGSIZE; - } else - goto nla_put_failure; - } - if (type_pf_data_tlist(skb, data)) - goto nla_put_failure; - ipset_nest_end(skb, nested); - } - } - ipset_nest_end(skb, atd); - /* Set listing finished */ - cb->args[2] = 0; - - return 0; - -nla_put_failure: - nlmsg_trim(skb, incomplete); - ipset_nest_end(skb, atd); - if (unlikely(first == cb->args[2])) { - pr_warning("Can't list set %s: one bucket does not fit into " - "a message. Please report it!\n", set->name); - cb->args[2] = 0; - return -EMSGSIZE; - } - return 0; -} - -static const struct ip_set_type_variant type_pf_tvariant = { - .kadt = type_pf_kadt, - .uadt = type_pf_uadt, - .adt = { - [IPSET_ADD] = type_pf_tadd, - [IPSET_DEL] = type_pf_tdel, - [IPSET_TEST] = type_pf_ttest, - }, - .destroy = type_pf_destroy, - .flush = type_pf_flush, - .head = type_pf_head, - .list = type_pf_tlist, - .resize = type_pf_tresize, - .same_set = type_pf_same_set, -}; - -static void -type_pf_gc(unsigned long ul_set) -{ - struct ip_set *set = (struct ip_set *) ul_set; - struct ip_set_hash *h = set->data; - - pr_debug("called\n"); - write_lock_bh(&set->lock); - type_pf_expire(h, NETS_LENGTH(set->family)); - write_unlock_bh(&set->lock); - - h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; - add_timer(&h->gc); -} - -static void -type_pf_gc_init(struct ip_set *set) -{ - struct ip_set_hash *h = set->data; - - init_timer(&h->gc); - h->gc.data = (unsigned long) set; - h->gc.function = type_pf_gc; - h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; - add_timer(&h->gc); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(h->timeout)); -} - -#undef HKEY_DATALEN -#undef HKEY -#undef type_pf_data_equal -#undef type_pf_data_isnull -#undef type_pf_data_copy -#undef type_pf_data_zero_out -#undef type_pf_data_netmask -#undef type_pf_data_list -#undef type_pf_data_tlist -#undef type_pf_data_next -#undef type_pf_data_flags -#undef type_pf_data_reset_flags -#undef type_pf_data_match - -#undef type_pf_elem -#undef type_pf_telem -#undef type_pf_data_timeout -#undef type_pf_data_expired -#undef type_pf_data_timeout_set - -#undef type_pf_elem_add -#undef type_pf_add -#undef type_pf_del -#undef type_pf_test_cidrs -#undef type_pf_test - -#undef type_pf_elem_tadd -#undef type_pf_del_telem -#undef type_pf_expire -#undef type_pf_tadd -#undef type_pf_tdel -#undef type_pf_ttest_cidrs -#undef type_pf_ttest - -#undef type_pf_resize -#undef type_pf_tresize -#undef type_pf_flush -#undef type_pf_destroy -#undef type_pf_head -#undef type_pf_list -#undef type_pf_tlist -#undef type_pf_same_set -#undef type_pf_kadt -#undef type_pf_uadt -#undef type_pf_gc -#undef type_pf_gc_init -#undef type_pf_variant -#undef type_pf_tvariant -- cgit v1.2.3 From 34d666d489cf70c246ca99b2387741915c34b88c Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 27 Apr 2013 14:38:56 +0200 Subject: netfilter: ipset: Introduce the counter extension in the core Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 75 +++++++++++++++++++++++++++-- include/uapi/linux/netfilter/ipset/ip_set.h | 5 ++ 2 files changed, 76 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index bf0220cbf46a..0f978ebfaefb 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -52,18 +52,24 @@ enum ip_set_extension { IPSET_EXT_NONE = 0, IPSET_EXT_BIT_TIMEOUT = 1, IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT), + IPSET_EXT_BIT_COUNTER = 2, + IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER), }; /* Extension offsets */ enum ip_set_offset { IPSET_OFFSET_TIMEOUT = 0, + IPSET_OFFSET_COUNTER, IPSET_OFFSET_MAX, }; #define SET_WITH_TIMEOUT(s) ((s)->extensions & IPSET_EXT_TIMEOUT) +#define SET_WITH_COUNTER(s) ((s)->extensions & IPSET_EXT_COUNTER) struct ip_set_ext { unsigned long timeout; + u64 packets; + u64 bytes; }; struct ip_set; @@ -177,6 +183,65 @@ struct ip_set { void *data; }; +struct ip_set_counter { + atomic64_t bytes; + atomic64_t packets; +}; + +static inline void +ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) +{ + atomic64_add((long long)bytes, &(counter)->bytes); +} + +static inline void +ip_set_add_packets(u64 packets, struct ip_set_counter *counter) +{ + atomic64_add((long long)packets, &(counter)->packets); +} + +static inline u64 +ip_set_get_bytes(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->bytes); +} + +static inline u64 +ip_set_get_packets(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->packets); +} + +static inline void +ip_set_update_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) +{ + if (ext->packets != ULLONG_MAX) { + ip_set_add_bytes(ext->bytes, counter); + ip_set_add_packets(ext->packets, counter); + } +} + +static inline bool +ip_set_put_counter(struct sk_buff *skb, struct ip_set_counter *counter) +{ + return nla_put_net64(skb, IPSET_ATTR_BYTES, + cpu_to_be64(ip_set_get_bytes(counter))) || + nla_put_net64(skb, IPSET_ATTR_PACKETS, + cpu_to_be64(ip_set_get_packets(counter))); +} + +static inline void +ip_set_init_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext) +{ + if (ext->bytes != ULLONG_MAX) + atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); + if (ext->packets != ULLONG_MAX) + atomic64_set(&(counter)->packets, (long long)(ext->packets)); +} + /* register and unregister set references */ extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set); extern void ip_set_put_byindex(ip_set_id_t index); @@ -318,10 +383,12 @@ bitmap_bytes(u32 a, u32 b) #include -#define IP_SET_INIT_KEXT(skb, opt, map) \ - { .timeout = ip_set_adt_opt_timeout(opt, map) } +#define IP_SET_INIT_KEXT(skb, opt, map) \ + { .bytes = (skb)->len, .packets = 1, \ + .timeout = ip_set_adt_opt_timeout(opt, map) } -#define IP_SET_INIT_UEXT(map) \ - { .timeout = (map)->timeout } +#define IP_SET_INIT_UEXT(map) \ + { .bytes = ULLONG_MAX, .packets = ULLONG_MAX, \ + .timeout = (map)->timeout } #endif /*_IP_SET_H */ diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index fbee42807a11..ed452675d153 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -108,6 +108,8 @@ enum { IPSET_ATTR_CIDR2, IPSET_ATTR_IP2_TO, IPSET_ATTR_IFACE, + IPSET_ATTR_BYTES, + IPSET_ATTR_PACKETS, __IPSET_ATTR_ADT_MAX, }; #define IPSET_ATTR_ADT_MAX (__IPSET_ATTR_ADT_MAX - 1) @@ -137,6 +139,7 @@ enum ipset_errno { IPSET_ERR_REFERENCED, IPSET_ERR_IPADDR_IPV4, IPSET_ERR_IPADDR_IPV6, + IPSET_ERR_COUNTER, /* Type specific error codes */ IPSET_ERR_TYPE_SPECIFIC = 4352, @@ -161,6 +164,8 @@ enum ipset_cadt_flags { IPSET_FLAG_PHYSDEV = (1 << IPSET_FLAG_BIT_PHYSDEV), IPSET_FLAG_BIT_NOMATCH = 2, IPSET_FLAG_NOMATCH = (1 << IPSET_FLAG_BIT_NOMATCH), + IPSET_FLAG_BIT_WITH_COUNTERS = 3, + IPSET_FLAG_WITH_COUNTERS = (1 << IPSET_FLAG_BIT_WITH_COUNTERS), IPSET_FLAG_CADT_MAX = 15, /* Upper half */ }; -- cgit v1.2.3 From 6e01781d1c80e2e8263471252a631e86165b15c5 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 27 Apr 2013 14:40:50 +0200 Subject: netfilter: ipset: set match: add support to match the counters The new revision of the set match supports to match the counters and to suppress updating the counters at matching too. At the set:list types, the updating of the subcounters can be suppressed as well. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 9 +++++++-- include/uapi/linux/netfilter/ipset/ip_set.h | 31 +++++++++++++++++++++++++---- include/uapi/linux/netfilter/xt_set.h | 9 +++++++++ 3 files changed, 43 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 0f978ebfaefb..d80e2753847c 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -76,7 +76,7 @@ struct ip_set; typedef int (*ipset_adtfn)(struct ip_set *set, void *value, const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags); + struct ip_set_ext *mext, u32 cmdflags); /* Kernel API function options */ struct ip_set_adt_opt { @@ -217,10 +217,15 @@ ip_set_update_counter(struct ip_set_counter *counter, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { - if (ext->packets != ULLONG_MAX) { + if (ext->packets != ULLONG_MAX && + !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { ip_set_add_bytes(ext->bytes, counter); ip_set_add_packets(ext->packets, counter); } + if (flags & IPSET_FLAG_MATCH_COUNTERS) { + mext->packets = ip_set_get_packets(counter); + mext->bytes = ip_set_get_bytes(counter); + } } static inline bool diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index ed452675d153..8024cdf13b70 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -145,7 +145,7 @@ enum ipset_errno { IPSET_ERR_TYPE_SPECIFIC = 4352, }; -/* Flags at command level */ +/* Flags at command level or match/target flags, lower half of cmdattrs*/ enum ipset_cmd_flags { IPSET_FLAG_BIT_EXIST = 0, IPSET_FLAG_EXIST = (1 << IPSET_FLAG_BIT_EXIST), @@ -153,10 +153,20 @@ enum ipset_cmd_flags { IPSET_FLAG_LIST_SETNAME = (1 << IPSET_FLAG_BIT_LIST_SETNAME), IPSET_FLAG_BIT_LIST_HEADER = 2, IPSET_FLAG_LIST_HEADER = (1 << IPSET_FLAG_BIT_LIST_HEADER), - IPSET_FLAG_CMD_MAX = 15, /* Lower half */ + IPSET_FLAG_BIT_SKIP_COUNTER_UPDATE = 3, + IPSET_FLAG_SKIP_COUNTER_UPDATE = + (1 << IPSET_FLAG_BIT_SKIP_COUNTER_UPDATE), + IPSET_FLAG_BIT_SKIP_SUBCOUNTER_UPDATE = 4, + IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE = + (1 << IPSET_FLAG_BIT_SKIP_SUBCOUNTER_UPDATE), + IPSET_FLAG_BIT_MATCH_COUNTERS = 5, + IPSET_FLAG_MATCH_COUNTERS = (1 << IPSET_FLAG_BIT_MATCH_COUNTERS), + IPSET_FLAG_BIT_RETURN_NOMATCH = 7, + IPSET_FLAG_RETURN_NOMATCH = (1 << IPSET_FLAG_BIT_RETURN_NOMATCH), + IPSET_FLAG_CMD_MAX = 15, }; -/* Flags at CADT attribute level */ +/* Flags at CADT attribute level, upper half of cmdattrs */ enum ipset_cadt_flags { IPSET_FLAG_BIT_BEFORE = 0, IPSET_FLAG_BEFORE = (1 << IPSET_FLAG_BIT_BEFORE), @@ -166,7 +176,7 @@ enum ipset_cadt_flags { IPSET_FLAG_NOMATCH = (1 << IPSET_FLAG_BIT_NOMATCH), IPSET_FLAG_BIT_WITH_COUNTERS = 3, IPSET_FLAG_WITH_COUNTERS = (1 << IPSET_FLAG_BIT_WITH_COUNTERS), - IPSET_FLAG_CADT_MAX = 15, /* Upper half */ + IPSET_FLAG_CADT_MAX = 15, }; /* Commands with settype-specific attributes */ @@ -195,6 +205,7 @@ enum ip_set_dim { * If changed, new revision of iptables match/target is required. */ IPSET_DIM_MAX = 6, + /* Backward compatibility: set match revision 2 */ IPSET_BIT_RETURN_NOMATCH = 7, }; @@ -207,6 +218,18 @@ enum ip_set_kopt { IPSET_RETURN_NOMATCH = (1 << IPSET_BIT_RETURN_NOMATCH), }; +enum { + IPSET_COUNTER_NONE = 0, + IPSET_COUNTER_EQ, + IPSET_COUNTER_NE, + IPSET_COUNTER_LT, + IPSET_COUNTER_GT, +}; + +struct ip_set_counter_match { + __u8 op; + __u64 value; +}; /* Interface to iptables/ip6tables */ diff --git a/include/uapi/linux/netfilter/xt_set.h b/include/uapi/linux/netfilter/xt_set.h index e3a9978f259f..964d3d42f874 100644 --- a/include/uapi/linux/netfilter/xt_set.h +++ b/include/uapi/linux/netfilter/xt_set.h @@ -62,4 +62,13 @@ struct xt_set_info_target_v2 { __u32 timeout; }; +/* Revision 3 match */ + +struct xt_set_info_match_v3 { + struct xt_set_info match_set; + struct ip_set_counter_match packets; + struct ip_set_counter_match bytes; + __u32 flags; +}; + #endif /*_XT_SET_H*/ -- cgit v1.2.3 From a5fedd43d5f6c94c71053a66e4c3d2e35f1731a2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 19 Apr 2013 04:58:25 +0000 Subject: netfilter: move skb_gso_segment into nfnetlink_queue module skb_gso_segment is expensive, so it would be nice if we could avoid it in the future. However, userspace needs to be prepared to receive larger-than-mtu-packets (which will also have incorrect l3/l4 checksums), so we cannot simply remove it. The plan is to add a per-queue feature flag that userspace can set when binding the queue. The problem is that in nf_queue, we only have a queue number, not the queue context/configuration settings. This patch should have no impact other than the skb_gso_segment call now being in a function that has access to the queue config data. A new size attribute in nf_queue_entry is needed so nfnetlink_queue can duplicate the entry of the gso skb when segmenting the skb while also copying the route key. The follow up patch adds switch to disable skb_gso_segment when queue config says so. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_queue.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index fb1c0be38b6d..aaba4bbcdda0 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -9,10 +9,13 @@ struct nf_queue_entry { struct nf_hook_ops *elem; u_int8_t pf; + u16 size; /* sizeof(entry) + saved route keys */ unsigned int hook; struct net_device *indev; struct net_device *outdev; int (*okfn)(struct sk_buff *); + + /* extra space to store route keys */ }; #define nf_queue_entry_reroute(x) ((void *)x + sizeof(struct nf_queue_entry)) @@ -27,4 +30,7 @@ void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); extern void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); +void nf_queue_entry_release_refs(struct nf_queue_entry *entry); + #endif /* _NF_QUEUE_H */ -- cgit v1.2.3 From 7237190df8c4129241697530a4eecabdc4ecc66e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 19 Apr 2013 04:58:26 +0000 Subject: netfilter: nfnetlink_queue: add skb info attribute Once we allow userspace to receive gso/gro packets, userspace needs to be able to determine when checksums appear to be broken, but are not. NFQA_SKB_CSUMNOTREADY means 'checksums will be fixed in kernel later, pretend they are ok'. NFQA_SKB_GSO could be used for statistics, or to determine when packet size exceeds mtu. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_queue.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index 70ec8c2bc11a..0069da370464 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -45,6 +45,7 @@ enum nfqnl_attr_type { NFQA_CT, /* nf_conntrack_netlink.h */ NFQA_CT_INFO, /* enum ip_conntrack_info */ NFQA_CAP_LEN, /* __u32 length of captured packet */ + NFQA_SKB_INFO, /* __u32 skb meta information */ __NFQA_MAX }; @@ -98,4 +99,10 @@ enum nfqnl_attr_config { #define NFQA_CFG_F_CONNTRACK (1 << 1) #define NFQA_CFG_F_MAX (1 << 2) +/* flags for NFQA_SKB_INFO */ +/* packet appears to have wrong checksums, but they are ok */ +#define NFQA_SKB_CSUMNOTREADY (1 << 0) +/* packet is GSO (i.e., exceeds device mtu) */ +#define NFQA_SKB_GSO (1 << 1) + #endif /* _NFNETLINK_QUEUE_H */ -- cgit v1.2.3 From 00bd1cc24a7dd295ee095dc50791aab6ede46c7a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 19 Apr 2013 04:58:27 +0000 Subject: netfilter: nfnetlink_queue: avoid expensive gso segmentation and checksum fixup Userspace can now indicate that it can cope with larger-than-mtu sized packets and packets that have invalid ipv4/tcp checksums. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_queue.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index 0069da370464..a2308ae5a73d 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -97,7 +97,8 @@ enum nfqnl_attr_config { /* Flags for NFQA_CFG_FLAGS */ #define NFQA_CFG_F_FAIL_OPEN (1 << 0) #define NFQA_CFG_F_CONNTRACK (1 << 1) -#define NFQA_CFG_F_MAX (1 << 2) +#define NFQA_CFG_F_GSO (1 << 2) +#define NFQA_CFG_F_MAX (1 << 3) /* flags for NFQA_SKB_INFO */ /* packet appears to have wrong checksums, but they are ok */ -- cgit v1.2.3 From eee1d5a14780b9391ec51f3feaf4cffb521ddbb1 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 19 Apr 2013 10:54:58 +0900 Subject: sctp: Correct type and usage of sctp_end_cksum() Change the type of the crc32 parameter of sctp_end_cksum() from __be32 to __u32 to reflect that fact that it is passed to cpu_to_le32(). There are five in-tree users of sctp_end_cksum(). The following four had warnings flagged by sparse which are no longer present with this change. net/netfilter/ipvs/ip_vs_proto_sctp.c:sctp_nat_csum() net/netfilter/ipvs/ip_vs_proto_sctp.c:sctp_csum_check() net/sctp/input.c:sctp_rcv_checksum() net/sctp/output.c:sctp_packet_transmit() The fifth user is net/netfilter/nf_nat_proto_sctp.c:sctp_manip_pkt(). It has been updated to pass a __u32 instead of a __be32, the value in question was already calculated in cpu byte-order. net/netfilter/nf_nat_proto_sctp.c:sctp_manip_pkt() has also been updated to assign the return value of sctp_end_cksum() directly to a variable of type __le32, matching the type of the return value. Previously the return value was assigned to a variable of type __be32 and then that variable was finally assigned to another variable of type __le32. Problems flagged by sparse. Compile and sparse tested only. Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/sctp/checksum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index befc8d2a1b9f..5a2110d3176d 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -77,7 +77,7 @@ static inline __u32 sctp_update_cksum(__u8 *buffer, __u16 length, __u32 crc32) return sctp_crc32c(crc32, buffer, length); } -static inline __le32 sctp_end_cksum(__be32 crc32) +static inline __le32 sctp_end_cksum(__u32 crc32) { return cpu_to_le32(~crc32); } -- cgit v1.2.3 From aebda156a570782a86fc4426842152237a19427d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 29 Apr 2013 05:58:52 +0000 Subject: net: defer net_secret[] initialization Instead of feeding net_secret[] at boot time, defer the init at the point first socket is created. This permits some platforms to use better entropy sources than the ones available at boot time. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/secure_seq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index c2e542b27a5a..6ca975bebd37 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -3,6 +3,7 @@ #include +extern void net_secret_init(void); extern __u32 secure_ip_id(__be32 daddr); extern __u32 secure_ipv6_id(const __be32 daddr[4]); extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -- cgit v1.2.3 From 6a5dc9e598fe90160fee7de098fa319665f5253e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 29 Apr 2013 08:39:56 +0000 Subject: net: Add MIB counters for checksum errors Add MIB counters for checksum errors in IP layer, and TCP/UDP/ICMP layers, to help diagnose problems. $ nstat -a | grep Csum IcmpInCsumErrors 72 0.0 TcpInCsumErrors 382 0.0 UdpInCsumErrors 463221 0.0 Icmp6InCsumErrors 75 0.0 Udp6InCsumErrors 173442 0.0 IpExtInCsumErrors 10884 0.0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index fefdec91c68b..df2e8b4f9c03 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -50,6 +50,7 @@ enum IPSTATS_MIB_OUTMCASTOCTETS, /* OutMcastOctets */ IPSTATS_MIB_INBCASTOCTETS, /* InBcastOctets */ IPSTATS_MIB_OUTBCASTOCTETS, /* OutBcastOctets */ + IPSTATS_MIB_CSUMERRORS, /* InCsumErrors */ __IPSTATS_MIB_MAX }; @@ -87,6 +88,7 @@ enum ICMP_MIB_OUTTIMESTAMPREPS, /* OutTimestampReps */ ICMP_MIB_OUTADDRMASKS, /* OutAddrMasks */ ICMP_MIB_OUTADDRMASKREPS, /* OutAddrMaskReps */ + ICMP_MIB_CSUMERRORS, /* InCsumErrors */ __ICMP_MIB_MAX }; @@ -103,6 +105,7 @@ enum ICMP6_MIB_INERRORS, /* InErrors */ ICMP6_MIB_OUTMSGS, /* OutMsgs */ ICMP6_MIB_OUTERRORS, /* OutErrors */ + ICMP6_MIB_CSUMERRORS, /* InCsumErrors */ __ICMP6_MIB_MAX }; @@ -130,6 +133,7 @@ enum TCP_MIB_RETRANSSEGS, /* RetransSegs */ TCP_MIB_INERRS, /* InErrs */ TCP_MIB_OUTRSTS, /* OutRsts */ + TCP_MIB_CSUMERRORS, /* InCsumErrors */ __TCP_MIB_MAX }; @@ -147,6 +151,7 @@ enum UDP_MIB_OUTDATAGRAMS, /* OutDatagrams */ UDP_MIB_RCVBUFERRORS, /* RcvbufErrors */ UDP_MIB_SNDBUFERRORS, /* SndbufErrors */ + UDP_MIB_CSUMERRORS, /* InCsumErrors */ __UDP_MIB_MAX }; -- cgit v1.2.3 From bd7c4b604a6cd707803c7c6ba142bfa131f9a9f3 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 30 Apr 2013 05:35:05 +0000 Subject: netpoll: convert mutex into a semaphore Bart Van Assche recently reported a warning to me: [] warn_slowpath_common+0x7f/0xc0 [] warn_slowpath_null+0x1a/0x20 [] mutex_trylock+0x16d/0x180 [] netpoll_poll_dev+0x49/0xc30 [] ? __alloc_skb+0x82/0x2a0 [] netpoll_send_skb_on_dev+0x265/0x410 [] netpoll_send_udp+0x28a/0x3a0 [] ? write_msg+0x53/0x110 [netconsole] [] write_msg+0xcf/0x110 [netconsole] [] call_console_drivers.constprop.17+0xa1/0x1c0 [] console_unlock+0x2d6/0x450 [] vprintk_emit+0x1ee/0x510 [] printk+0x4d/0x4f [] scsi_print_command+0x7d/0xe0 [scsi_mod] This resulted from my commit ca99ca14c which introduced a mutex_trylock operation in a path that could execute in interrupt context. When mutex debugging is enabled, the above warns the user when we are in fact exectuting in interrupt context interrupt context. After some discussion, It seems that a semaphore is the proper mechanism to use here. While mutexes are defined to be unusable in interrupt context, no such condition exists for semaphores (save for the fact that the non blocking api calls, like up and down_trylock must be used when in irq context). Signed-off-by: Neil Horman Reported-by: Bart Van Assche CC: Bart Van Assche CC: David Miller CC: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 9d7d8c64f7c8..fa2cb76a7029 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -40,7 +40,7 @@ struct netpoll_info { unsigned long rx_flags; spinlock_t rx_lock; - struct mutex dev_lock; + struct semaphore dev_lock; struct list_head rx_np; /* netpolls that registered an rx_hook */ struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ -- cgit v1.2.3 From 60bc851ae59bfe99be6ee89d6bc50008c85ec75d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 1 May 2013 05:24:03 +0000 Subject: af_unix: fix a fatal race with bit fields Using bit fields is dangerous on ppc64/sparc64, as the compiler [1] uses 64bit instructions to manipulate them. If the 64bit word includes any atomic_t or spinlock_t, we can lose critical concurrent changes. This is happening in af_unix, where unix_sk(sk)->gc_candidate/ gc_maybe_cycle/lock share the same 64bit word. This leads to fatal deadlock, as one/several cpus spin forever on a spinlock that will never be available again. A safer way would be to use a long to store flags. This way we are sure compiler/arch wont do bad things. As we own unix_gc_lock spinlock when clearing or setting bits, we can use the non atomic __set_bit()/__clear_bit(). recursion_level can share the same 64bit location with the spinlock, as it is set only with this spinlock held. [1] bug fixed in gcc-4.8.0 : http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52080 Reported-by: Ambrose Feinstein Signed-off-by: Eric Dumazet Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: David S. Miller --- include/net/af_unix.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index a8836e8445cc..dbdfd2b0f3b3 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -57,9 +57,10 @@ struct unix_sock { struct list_head link; atomic_long_t inflight; spinlock_t lock; - unsigned int gc_candidate : 1; - unsigned int gc_maybe_cycle : 1; unsigned char recursion_level; + unsigned long gc_flags; +#define UNIX_GC_CANDIDATE 0 +#define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) -- cgit v1.2.3 From 20074f357da4a637430aec2879c9d864c5d2c23c Mon Sep 17 00:00:00 2001 From: Xi Wang Date: Wed, 1 May 2013 16:24:08 -0400 Subject: filter: fix va_list build error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes the following build error. In file included from include/linux/filter.h:52:0, from arch/arm/net/bpf_jit_32.c:14: include/linux/printk.h:54:2: error: unknown type name ‘va_list’ include/linux/printk.h:105:21: error: unknown type name ‘va_list’ include/linux/printk.h:108:30: error: unknown type name ‘va_list’ Signed-off-by: Xi Wang Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index d1248f401a56..c050dcc322a4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -48,6 +48,7 @@ extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen); extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len); #ifdef CONFIG_BPF_JIT +#include #include #include -- cgit v1.2.3