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/linux') 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/linux') 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/linux') 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 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/linux') 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/linux') 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/linux') 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 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 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') 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 -- 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/linux') 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/linux') 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 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/linux') 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 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/linux') 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 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 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/vm_sockets.h (limited to 'include/linux') 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 */ -- 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/linux') 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/linux') 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/linux') 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 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/linux') 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 + 1 file changed, 1 insertion(+) (limited to 'include/linux') 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 -- 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/linux') 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 - 1 file changed, 1 deletion(-) (limited to 'include/linux') 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 */ -- 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 + 1 file changed, 1 insertion(+) (limited to 'include/linux') 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 */ -- 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/linux') 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/linux') 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/linux') 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/linux') 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 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/linux') 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 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') 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 -- 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/linux') 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 + 1 file changed, 1 insertion(+) (limited to 'include/linux') 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__ */ -- 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 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') 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 */ -- 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 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') 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 */ -- 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/linux') 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 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/linux') 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/linux') 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 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/linux') 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/linux') 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 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/linux') 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/linux') 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/linux') 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 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 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') 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 */ -- 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/linux') 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 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/linux') 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/linux') 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/linux') 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/linux') 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 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') 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; } -- 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/linux') 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/linux') 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 +------------------------------------------- 1 file changed, 1 insertion(+), 432 deletions(-) (limited to 'include/linux') 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 */ -- 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/linux') 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/linux') 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 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/linux') 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 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/linux') 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 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/linux') 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 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/linux') 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 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/linux') 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 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 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') 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 { -- 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/linux') 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/linux') 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 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/linux') 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/linux') 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/linux') 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 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/linux') 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/linux') 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 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/linux') 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 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') 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, -- 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/linux') 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/linux') 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 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/linux') 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 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/linux') 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/linux') 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/linux') 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/linux') 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 ++++++ 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') 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) -- 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/linux') 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/linux') 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 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/linux') 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/linux') 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 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 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') 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); -- 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/linux') 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/linux') 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/linux') 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 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/linux') 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/linux') 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/linux') 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/linux') 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 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/linux') 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/linux') 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/linux') 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/linux') 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 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 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') 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 -- 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/linux') 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/linux') 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/linux') 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/linux') 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/linux') 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/linux') 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 ++++++++++++++++++++++++++++++++-- 1 file changed, 71 insertions(+), 4 deletions(-) (limited to 'include/linux') 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 */ -- 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 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') 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 -- 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/linux') 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 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/linux') 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