diff options
Diffstat (limited to 'net')
83 files changed, 1669 insertions, 1102 deletions
diff --git a/net/802/fddi.c b/net/802/fddi.c index ebcf4830d6f1..5ce24c4bb840 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -122,10 +122,10 @@ static int fddi_rebuild_header(struct sk_buff *skb) * the proper pointer to the start of packet data (skb->data). */ -unsigned short fddi_type_trans(struct sk_buff *skb, struct net_device *dev) +__be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev) { struct fddihdr *fddi = (struct fddihdr *)skb->data; - unsigned short type; + __be16 type; /* * Set mac.raw field to point to FC byte, set data field to point diff --git a/net/8021q/Kconfig b/net/8021q/Kconfig new file mode 100644 index 000000000000..c4a382e450e2 --- /dev/null +++ b/net/8021q/Kconfig @@ -0,0 +1,19 @@ +# +# Configuration for 802.1Q VLAN support +# + +config VLAN_8021Q + tristate "802.1Q VLAN Support" + ---help--- + Select this and you will be able to create 802.1Q VLAN interfaces + on your ethernet interfaces. 802.1Q VLAN supports almost + everything a regular ethernet interface does, including + firewalling, bridging, and of course IP traffic. You will need + the 'vconfig' tool from the VLAN project in order to effectively + use VLANs. See the VLAN web page for more information: + <http://www.candelatech.com/~greear/vlan.html> + + To compile this code as a module, choose M here: the module + will be called 8021q. + + If unsure, say N. diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 1f6d31670bc7..91e412b0ab00 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -578,6 +578,14 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!vlandev) continue; + if (netif_carrier_ok(dev)) { + if (!netif_carrier_ok(vlandev)) + netif_carrier_on(vlandev); + } else { + if (netif_carrier_ok(vlandev)) + netif_carrier_off(vlandev); + } + if ((vlandev->state & VLAN_LINK_STATE_MASK) != flgs) { vlandev->state = (vlandev->state &~ VLAN_LINK_STATE_MASK) | flgs; diff --git a/net/Kconfig b/net/Kconfig index 8a12ea8f0c05..3ae4a47e60ae 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -2,7 +2,7 @@ # Network configuration # -menu "Networking support" +menu "Networking" config NET bool "Networking support" @@ -10,7 +10,9 @@ config NET Unless you really know what you are doing, you should say Y here. The reason is that some programs need kernel networking support even when running on a stand-alone machine that isn't connected to any - other computer. If you are upgrading from an older kernel, you + other computer. + + If you are upgrading from an older kernel, you should consider updating your networking tools too because changes in the kernel and the tools often go hand in hand. The tools are contained in the package net-tools, the location and version number @@ -20,57 +22,14 @@ config NET recommended to read the NET-HOWTO, available from <http://www.tldp.org/docs.html#howto>. -menu "Networking options" - depends on NET - -config PACKET - tristate "Packet socket" - ---help--- - The Packet protocol is used by applications which communicate - directly with network devices without an intermediate network - protocol implemented in the kernel, e.g. tcpdump. If you want them - to work, choose Y. +# Make sure that all config symbols are dependent on NET +if NET - To compile this driver as a module, choose M here: the module will - be called af_packet. - - If unsure, say Y. - -config PACKET_MMAP - bool "Packet socket: mmapped IO" - depends on PACKET - help - If you say Y here, the Packet protocol driver will use an IO - mechanism that results in faster communication. - - If unsure, say N. - -config UNIX - tristate "Unix domain sockets" - ---help--- - If you say Y here, you will include support for Unix domain sockets; - sockets are the standard Unix mechanism for establishing and - accessing network connections. Many commonly used programs such as - the X Window system and syslog use these sockets even if your - machine is not connected to any network. Unless you are working on - an embedded system or something similar, you therefore definitely - want to say Y here. - - To compile this driver as a module, choose M here: the module will be - called unix. Note that several important services won't work - correctly if you say M here and then neglect to load the module. - - Say Y unless you know what you are doing. - -config NET_KEY - tristate "PF_KEY sockets" - select XFRM - ---help--- - PF_KEYv2 socket family, compatible to KAME ones. - They are required if you are going to use IPsec tools ported - from KAME. +menu "Networking options" - Say Y unless you know what you are doing. +source "net/packet/Kconfig" +source "net/unix/Kconfig" +source "net/xfrm/Kconfig" config INET bool "TCP/IP networking" @@ -94,30 +53,12 @@ config INET Short answer: say Y. +if INET source "net/ipv4/Kconfig" - -# IPv6 as module will cause a CRASH if you try to unload it -config IPV6 - tristate "The IPv6 protocol" - depends on INET - default m - select CRYPTO if IPV6_PRIVACY - select CRYPTO_MD5 if IPV6_PRIVACY - ---help--- - This is complemental support for the IP version 6. - You will still be able to do traditional IPv4 networking as well. - - For general information about IPv6, see - <http://playground.sun.com/pub/ipng/html/ipng-main.html>. - For Linux IPv6 development information, see <http://www.linux-ipv6.org>. - For specific information about IPv6 under Linux, read the HOWTO at - <http://www.bieringer.de/linux/IPv6/>. - - To compile this protocol support as a module, choose M here: the - module will be called ipv6. - source "net/ipv6/Kconfig" +endif # if INET + menuconfig NETFILTER bool "Network packet filtering (replaces ipchains)" ---help--- @@ -206,269 +147,16 @@ source "net/bridge/netfilter/Kconfig" endif -config XFRM - bool - depends on NET - -source "net/xfrm/Kconfig" - source "net/sctp/Kconfig" - -config ATM - tristate "Asynchronous Transfer Mode (ATM) (EXPERIMENTAL)" - depends on EXPERIMENTAL - ---help--- - ATM is a high-speed networking technology for Local Area Networks - and Wide Area Networks. It uses a fixed packet size and is - connection oriented, allowing for the negotiation of minimum - bandwidth requirements. - - In order to participate in an ATM network, your Linux box needs an - ATM networking card. If you have that, say Y here and to the driver - of your ATM card below. - - Note that you need a set of user-space programs to actually make use - of ATM. See the file <file:Documentation/networking/atm.txt> for - further details. - -config ATM_CLIP - tristate "Classical IP over ATM (EXPERIMENTAL)" - depends on ATM && INET - help - Classical IP over ATM for PVCs and SVCs, supporting InARP and - ATMARP. If you want to communication with other IP hosts on your ATM - network, you will typically either say Y here or to "LAN Emulation - (LANE)" below. - -config ATM_CLIP_NO_ICMP - bool "Do NOT send ICMP if no neighbour (EXPERIMENTAL)" - depends on ATM_CLIP - help - Normally, an "ICMP host unreachable" message is sent if a neighbour - cannot be reached because there is no VC to it in the kernel's - ATMARP table. This may cause problems when ATMARP table entries are - briefly removed during revalidation. If you say Y here, packets to - such neighbours are silently discarded instead. - -config ATM_LANE - tristate "LAN Emulation (LANE) support (EXPERIMENTAL)" - depends on ATM - help - LAN Emulation emulates services of existing LANs across an ATM - network. Besides operating as a normal ATM end station client, Linux - LANE client can also act as an proxy client bridging packets between - ELAN and Ethernet segments. You need LANE if you want to try MPOA. - -config ATM_MPOA - tristate "Multi-Protocol Over ATM (MPOA) support (EXPERIMENTAL)" - depends on ATM && INET && ATM_LANE!=n - help - Multi-Protocol Over ATM allows ATM edge devices such as routers, - bridges and ATM attached hosts establish direct ATM VCs across - subnetwork boundaries. These shortcut connections bypass routers - enhancing overall network performance. - -config ATM_BR2684 - tristate "RFC1483/2684 Bridged protocols" - depends on ATM && INET - help - ATM PVCs can carry ethernet PDUs according to rfc2684 (formerly 1483) - This device will act like an ethernet from the kernels point of view, - with the traffic being carried by ATM PVCs (currently 1 PVC/device). - This is sometimes used over DSL lines. If in doubt, say N. - -config ATM_BR2684_IPFILTER - bool "Per-VC IP filter kludge" - depends on ATM_BR2684 - help - This is an experimental mechanism for users who need to terminating a - large number of IP-only vcc's. Do not enable this unless you are sure - you know what you are doing. - -config BRIDGE - tristate "802.1d Ethernet Bridging" - ---help--- - If you say Y here, then your Linux box will be able to act as an - Ethernet bridge, which means that the different Ethernet segments it - is connected to will appear as one Ethernet to the participants. - Several such bridges can work together to create even larger - networks of Ethernets using the IEEE 802.1 spanning tree algorithm. - As this is a standard, Linux bridges will cooperate properly with - other third party bridge products. - - In order to use the Ethernet bridge, you'll need the bridge - configuration tools; see <file:Documentation/networking/bridge.txt> - for location. Please read the Bridge mini-HOWTO for more - information. - - If you enable iptables support along with the bridge support then you - turn your bridge into a bridging IP firewall. - iptables will then see the IP packets being bridged, so you need to - take this into account when setting up your firewall rules. - Enabling arptables support when bridging will let arptables see - bridged ARP traffic in the arptables FORWARD chain. - - To compile this code as a module, choose M here: the module - will be called bridge. - - If unsure, say N. - -config VLAN_8021Q - tristate "802.1Q VLAN Support" - ---help--- - Select this and you will be able to create 802.1Q VLAN interfaces - on your ethernet interfaces. 802.1Q VLAN supports almost - everything a regular ethernet interface does, including - firewalling, bridging, and of course IP traffic. You will need - the 'vconfig' tool from the VLAN project in order to effectively - use VLANs. See the VLAN web page for more information: - <http://www.candelatech.com/~greear/vlan.html> - - To compile this code as a module, choose M here: the module - will be called 8021q. - - If unsure, say N. - -config DECNET - tristate "DECnet Support" - ---help--- - The DECnet networking protocol was used in many products made by - Digital (now Compaq). It provides reliable stream and sequenced - packet communications over which run a variety of services similar - to those which run over TCP/IP. - - To find some tools to use with the kernel layer support, please - look at Patrick Caulfield's web site: - <http://linux-decnet.sourceforge.net/>. - - More detailed documentation is available in - <file:Documentation/networking/decnet.txt>. - - Be sure to say Y to "/proc file system support" and "Sysctl support" - below when using DECnet, since you will need sysctl support to aid - in configuration at run time. - - The DECnet code is also available as a module ( = code which can be - inserted in and removed from the running kernel whenever you want). - The module is called decnet. - +source "net/atm/Kconfig" +source "net/bridge/Kconfig" +source "net/8021q/Kconfig" source "net/decnet/Kconfig" - source "net/llc/Kconfig" - -config IPX - tristate "The IPX protocol" - select LLC - ---help--- - This is support for the Novell networking protocol, IPX, commonly - used for local networks of Windows machines. You need it if you - want to access Novell NetWare file or print servers using the Linux - Novell client ncpfs (available from - <ftp://platan.vc.cvut.cz/pub/linux/ncpfs/>) or from - within the Linux DOS emulator DOSEMU (read the DOSEMU-HOWTO, - available from <http://www.tldp.org/docs.html#howto>). In order - to do the former, you'll also have to say Y to "NCP file system - support", below. - - IPX is similar in scope to IP, while SPX, which runs on top of IPX, - is similar to TCP. There is also experimental support for SPX in - Linux (see "SPX networking", below). - - To turn your Linux box into a fully featured NetWare file server and - IPX router, say Y here and fetch either lwared from - <ftp://ibiblio.org/pub/Linux/system/network/daemons/> or - mars_nwe from <ftp://www.compu-art.de/mars_nwe/>. For more - information, read the IPX-HOWTO available from - <http://www.tldp.org/docs.html#howto>. - - General information about how to connect Linux, Windows machines and - Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. - - The IPX driver would enlarge your kernel by about 16 KB. To compile - this driver as a module, choose M here: the module will be called ipx. - Unless you want to integrate your Linux box with a local Novell - network, say N. - source "net/ipx/Kconfig" - -config ATALK - tristate "Appletalk protocol support" - select LLC - ---help--- - AppleTalk is the protocol that Apple computers can use to communicate - on a network. If your Linux box is connected to such a network and you - wish to connect to it, say Y. You will need to use the netatalk package - so that your Linux box can act as a print and file server for Macs as - well as access AppleTalk printers. Check out - <http://www.zettabyte.net/netatalk/> on the WWW for details. - EtherTalk is the name used for AppleTalk over Ethernet and the - cheaper and slower LocalTalk is AppleTalk over a proprietary Apple - network using serial links. EtherTalk and LocalTalk are fully - supported by Linux. - - General information about how to connect Linux, Windows machines and - Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. The - NET-3-HOWTO, available from - <http://www.tldp.org/docs.html#howto>, contains valuable - information as well. - - To compile this driver as a module, choose M here: the module will be - called appletalk. You almost certainly want to compile it as a - module so you can restart your AppleTalk stack without rebooting - your machine. I hear that the GNU boycott of Apple is over, so - even politically correct people are allowed to say Y here. - source "drivers/net/appletalk/Kconfig" - -config X25 - tristate "CCITT X.25 Packet Layer (EXPERIMENTAL)" - depends on EXPERIMENTAL - ---help--- - X.25 is a set of standardized network protocols, similar in scope to - frame relay; the one physical line from your box to the X.25 network - entry point can carry several logical point-to-point connections - (called "virtual circuits") to other computers connected to the X.25 - network. Governments, banks, and other organizations tend to use it - to connect to each other or to form Wide Area Networks (WANs). Many - countries have public X.25 networks. X.25 consists of two - protocols: the higher level Packet Layer Protocol (PLP) (say Y here - if you want that) and the lower level data link layer protocol LAPB - (say Y to "LAPB Data Link Driver" below if you want that). - - You can read more about X.25 at <http://www.sangoma.com/x25.htm> and - <http://www.cisco.com/univercd/cc/td/doc/product/software/ios11/cbook/cx25.htm>. - Information about X.25 for Linux is contained in the files - <file:Documentation/networking/x25.txt> and - <file:Documentation/networking/x25-iface.txt>. - - One connects to an X.25 network either with a dedicated network card - using the X.21 protocol (not yet supported by Linux) or one can do - X.25 over a standard telephone line using an ordinary modem (say Y - to "X.25 async driver" below) or over Ethernet using an ordinary - Ethernet card and the LAPB over Ethernet (say Y to "LAPB Data Link - Driver" and "LAPB over Ethernet driver" below). - - To compile this driver as a module, choose M here: the module - will be called x25. If unsure, say N. - -config LAPB - tristate "LAPB Data Link Driver (EXPERIMENTAL)" - depends on EXPERIMENTAL - ---help--- - Link Access Procedure, Balanced (LAPB) is the data link layer (i.e. - the lower) part of the X.25 protocol. It offers a reliable - connection service to exchange data frames with one other host, and - it is used to transport higher level protocols (mostly X.25 Packet - Layer, the higher part of X.25, but others are possible as well). - Usually, LAPB is used with specialized X.21 network cards, but Linux - currently supports LAPB only over Ethernet connections. If you want - to use LAPB connections over Ethernet, say Y here and to "LAPB over - Ethernet driver" below. Read - <file:Documentation/networking/lapb-module.txt> for technical - details. - - To compile this driver as a module, choose M here: the - module will be called lapb. If unsure, say N. +source "net/x25/Kconfig" +source "net/lapb/Kconfig" config NET_DIVERT bool "Frame Diverter (EXPERIMENTAL)" @@ -496,107 +184,10 @@ config NET_DIVERT If unsure, say N. -config ECONET - tristate "Acorn Econet/AUN protocols (EXPERIMENTAL)" - depends on EXPERIMENTAL && INET - ---help--- - Econet is a fairly old and slow networking protocol mainly used by - Acorn computers to access file and print servers. It uses native - Econet network cards. AUN is an implementation of the higher level - parts of Econet that runs over ordinary Ethernet connections, on - top of the UDP packet protocol, which in turn runs on top of the - Internet protocol IP. - - If you say Y here, you can choose with the next two options whether - to send Econet/AUN traffic over a UDP Ethernet connection or over - a native Econet network card. - - To compile this driver as a module, choose M here: the module - will be called econet. - -config ECONET_AUNUDP - bool "AUN over UDP" - depends on ECONET - help - Say Y here if you want to send Econet/AUN traffic over a UDP - connection (UDP is a packet based protocol that runs on top of the - Internet protocol IP) using an ordinary Ethernet network card. - -config ECONET_NATIVE - bool "Native Econet" - depends on ECONET - help - Say Y here if you have a native Econet network card installed in - your computer. - -config WAN_ROUTER - tristate "WAN router" - depends on EXPERIMENTAL - ---help--- - Wide Area Networks (WANs), such as X.25, frame relay and leased - lines, are used to interconnect Local Area Networks (LANs) over vast - distances with data transfer rates significantly higher than those - achievable with commonly used asynchronous modem connections. - Usually, a quite expensive external device called a `WAN router' is - needed to connect to a WAN. - - As an alternative, WAN routing can be built into the Linux kernel. - With relatively inexpensive WAN interface cards available on the - market, a perfectly usable router can be built for less than half - the price of an external router. If you have one of those cards and - wish to use your Linux box as a WAN router, say Y here and also to - the WAN driver for your card, below. You will then need the - wan-tools package which is available from <ftp://ftp.sangoma.com/>. - Read <file:Documentation/networking/wan-router.txt> for more - information. - - To compile WAN routing support as a module, choose M here: the - module will be called wanrouter. - - If unsure, say N. - -menu "QoS and/or fair queueing" - -config NET_SCHED - bool "QoS and/or fair queueing" - ---help--- - When the kernel has several packets to send out over a network - device, it has to decide which ones to send first, which ones to - delay, and which ones to drop. This is the job of the packet - scheduler, and several different algorithms for how to do this - "fairly" have been proposed. - - If you say N here, you will get the standard packet scheduler, which - is a FIFO (first come, first served). If you say Y here, you will be - able to choose from among several alternative algorithms which can - then be attached to different network devices. This is useful for - example if some of your network devices are real time devices that - need a certain minimum data flow rate, or if you need to limit the - maximum data flow rate for traffic which matches specified criteria. - This code is considered to be experimental. - - To administer these schedulers, you'll need the user-level utilities - from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>. - That package also contains some documentation; for more, check out - <http://snafu.freedom.org/linux2.2/iproute-notes.html>. - - This Quality of Service (QoS) support will enable you to use - Differentiated Services (diffserv) and Resource Reservation Protocol - (RSVP) on your Linux router if you also say Y to "QoS support", - "Packet classifier API" and to some classifiers below. Documentation - and software is at <http://diffserv.sourceforge.net/>. - - If you say Y here and to "/proc file system" below, you will be able - to read status information about packet schedulers from the file - /proc/net/psched. - - The available schedulers are listed in the following questions; you - can say Y to as many as you like. If unsure, say N now. - +source "net/econet/Kconfig" +source "net/wanrouter/Kconfig" source "net/sched/Kconfig" -endmenu - menu "Network testing" config NET_PKTGEN @@ -635,14 +226,10 @@ config NET_POLL_CONTROLLER def_bool NETPOLL source "net/ax25/Kconfig" - source "net/irda/Kconfig" - source "net/bluetooth/Kconfig" - source "net/ieee80211/Kconfig" -source "drivers/net/Kconfig" - -endmenu +endif # if NET +endmenu # Networking diff --git a/net/atm/Kconfig b/net/atm/Kconfig new file mode 100644 index 000000000000..bea2426229b1 --- /dev/null +++ b/net/atm/Kconfig @@ -0,0 +1,74 @@ +# +# Asynchronous Transfer Mode (ATM) (EXPERIMENTAL) +# + +config ATM + tristate "Asynchronous Transfer Mode (ATM) (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + ATM is a high-speed networking technology for Local Area Networks + and Wide Area Networks. It uses a fixed packet size and is + connection oriented, allowing for the negotiation of minimum + bandwidth requirements. + + In order to participate in an ATM network, your Linux box needs an + ATM networking card. If you have that, say Y here and to the driver + of your ATM card below. + + Note that you need a set of user-space programs to actually make use + of ATM. See the file <file:Documentation/networking/atm.txt> for + further details. + +config ATM_CLIP + tristate "Classical IP over ATM (EXPERIMENTAL)" + depends on ATM && INET + help + Classical IP over ATM for PVCs and SVCs, supporting InARP and + ATMARP. If you want to communication with other IP hosts on your ATM + network, you will typically either say Y here or to "LAN Emulation + (LANE)" below. + +config ATM_CLIP_NO_ICMP + bool "Do NOT send ICMP if no neighbour (EXPERIMENTAL)" + depends on ATM_CLIP + help + Normally, an "ICMP host unreachable" message is sent if a neighbour + cannot be reached because there is no VC to it in the kernel's + ATMARP table. This may cause problems when ATMARP table entries are + briefly removed during revalidation. If you say Y here, packets to + such neighbours are silently discarded instead. + +config ATM_LANE + tristate "LAN Emulation (LANE) support (EXPERIMENTAL)" + depends on ATM + help + LAN Emulation emulates services of existing LANs across an ATM + network. Besides operating as a normal ATM end station client, Linux + LANE client can also act as an proxy client bridging packets between + ELAN and Ethernet segments. You need LANE if you want to try MPOA. + +config ATM_MPOA + tristate "Multi-Protocol Over ATM (MPOA) support (EXPERIMENTAL)" + depends on ATM && INET && ATM_LANE!=n + help + Multi-Protocol Over ATM allows ATM edge devices such as routers, + bridges and ATM attached hosts establish direct ATM VCs across + subnetwork boundaries. These shortcut connections bypass routers + enhancing overall network performance. + +config ATM_BR2684 + tristate "RFC1483/2684 Bridged protocols" + depends on ATM && INET + help + ATM PVCs can carry ethernet PDUs according to rfc2684 (formerly 1483) + This device will act like an ethernet from the kernels point of view, + with the traffic being carried by ATM PVCs (currently 1 PVC/device). + This is sometimes used over DSL lines. If in doubt, say N. + +config ATM_BR2684_IPFILTER + bool "Per-VC IP filter kludge" + depends on ATM_BR2684 + help + This is an experimental mechanism for users who need to terminating a + large number of IP-only vcc's. Do not enable this unless you are sure + you know what you are doing. diff --git a/net/atm/br2684.c b/net/atm/br2684.c index e6954cf1459d..289956c4dd3e 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -289,8 +289,7 @@ xmit will add the additional header part in that case */ * This is similar to eth_type_trans, which cannot be used because of * our dev->hard_header_len */ -static inline unsigned short br_type_trans(struct sk_buff *skb, - struct net_device *dev) +static inline __be16 br_type_trans(struct sk_buff *skb, struct net_device *dev) { struct ethhdr *eth; unsigned char *rawp; diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 2e341de3e763..901eff7ebe74 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -213,7 +213,7 @@ static int cmtp_send_frame(struct cmtp_session *session, unsigned char *data, in return kernel_sendmsg(sock, &msg, &iv, 1, len); } -static int cmtp_process_transmit(struct cmtp_session *session) +static void cmtp_process_transmit(struct cmtp_session *session) { struct sk_buff *skb, *nskb; unsigned char *hdr; @@ -223,7 +223,7 @@ static int cmtp_process_transmit(struct cmtp_session *session) if (!(nskb = alloc_skb(session->mtu, GFP_ATOMIC))) { BT_ERR("Can't allocate memory for new frame"); - return -ENOMEM; + return; } while ((skb = skb_dequeue(&session->transmit))) { @@ -275,8 +275,6 @@ static int cmtp_process_transmit(struct cmtp_session *session) cmtp_send_frame(session, nskb->data, nskb->len); kfree_skb(nskb); - - return skb_queue_len(&session->transmit); } static int cmtp_session(void *arg) diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index affbc55462e8..de8af5f42394 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -428,7 +428,7 @@ static int hidp_send_frame(struct socket *sock, unsigned char *data, int len) return kernel_sendmsg(sock, &msg, &iv, 1, len); } -static int hidp_process_transmit(struct hidp_session *session) +static void hidp_process_transmit(struct hidp_session *session) { struct sk_buff *skb; @@ -453,9 +453,6 @@ static int hidp_process_transmit(struct hidp_session *session) hidp_set_timer(session); kfree_skb(skb); } - - return skb_queue_len(&session->ctrl_transmit) + - skb_queue_len(&session->intr_transmit); } static int hidp_session(void *arg) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index f3f6355a2786..63a123c5c41b 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -590,8 +590,11 @@ static long rfcomm_sock_data_wait(struct sock *sk, long timeo) for (;;) { set_current_state(TASK_INTERRUPTIBLE); - if (skb_queue_len(&sk->sk_receive_queue) || sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN) || - signal_pending(current) || !timeo) + if (!skb_queue_empty(&sk->sk_receive_queue) || + sk->sk_err || + (sk->sk_shutdown & RCV_SHUTDOWN) || + signal_pending(current) || + !timeo) break; set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 6d689200bcf3..6304590fd36a 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -781,7 +781,7 @@ static int rfcomm_tty_chars_in_buffer(struct tty_struct *tty) BT_DBG("tty %p dev %p", tty, dev); - if (skb_queue_len(&dlc->tx_queue)) + if (!skb_queue_empty(&dlc->tx_queue)) return dlc->mtu; return 0; diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig new file mode 100644 index 000000000000..db23d59746cf --- /dev/null +++ b/net/bridge/Kconfig @@ -0,0 +1,31 @@ +# +# 802.1d Ethernet Bridging +# + +config BRIDGE + tristate "802.1d Ethernet Bridging" + ---help--- + If you say Y here, then your Linux box will be able to act as an + Ethernet bridge, which means that the different Ethernet segments it + is connected to will appear as one Ethernet to the participants. + Several such bridges can work together to create even larger + networks of Ethernets using the IEEE 802.1 spanning tree algorithm. + As this is a standard, Linux bridges will cooperate properly with + other third party bridge products. + + In order to use the Ethernet bridge, you'll need the bridge + configuration tools; see <file:Documentation/networking/bridge.txt> + for location. Please read the Bridge mini-HOWTO for more + information. + + If you enable iptables support along with the bridge support then you + turn your bridge into a bridging IP firewall. + iptables will then see the IP packets being bridged, so you need to + take this into account when setting up your firewall rules. + Enabling arptables support when bridging will let arptables see + bridged ARP traffic in the arptables FORWARD chain. + + To compile this code as a module, choose M here: the module + will be called bridge. + + If unsure, say N. diff --git a/net/core/dev.c b/net/core/dev.c index 7016e0c36b3d..ff9dc029233a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1127,7 +1127,7 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) extern void skb_release_data(struct sk_buff *); /* Keep head the same: replace data */ -int __skb_linearize(struct sk_buff *skb, int gfp_mask) +int __skb_linearize(struct sk_buff *skb, unsigned int __nocast gfp_mask) { unsigned int size; u8 *data; @@ -2089,10 +2089,11 @@ void dev_set_promiscuity(struct net_device *dev, int inc) { unsigned short old_flags = dev->flags; - dev->flags |= IFF_PROMISC; if ((dev->promiscuity += inc) == 0) dev->flags &= ~IFF_PROMISC; - if (dev->flags ^ old_flags) { + else + dev->flags |= IFF_PROMISC; + if (dev->flags != old_flags) { dev_mc_upload(dev); printk(KERN_INFO "device %s %s promiscuous mode\n", dev->name, (dev->flags & IFF_PROMISC) ? "entered" : diff --git a/net/core/filter.c b/net/core/filter.c index f3b88205ace2..cd91a24f9720 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -36,7 +36,7 @@ #include <linux/filter.h> /* No hurry in this branch */ -static u8 *load_pointer(struct sk_buff *skb, int k) +static void *__load_pointer(struct sk_buff *skb, int k) { u8 *ptr = NULL; @@ -50,6 +50,18 @@ static u8 *load_pointer(struct sk_buff *skb, int k) return NULL; } +static inline void *load_pointer(struct sk_buff *skb, int k, + unsigned int size, void *buffer) +{ + if (k >= 0) + return skb_header_pointer(skb, k, size, buffer); + else { + if (k >= SKF_AD_OFF) + return NULL; + return __load_pointer(skb, k); + } +} + /** * sk_run_filter - run a filter on a socket * @skb: buffer to run the filter on @@ -64,15 +76,12 @@ static u8 *load_pointer(struct sk_buff *skb, int k) int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) { - unsigned char *data = skb->data; - /* len is UNSIGNED. Byte wide insns relies only on implicit - type casts to prevent reading arbitrary memory locations. - */ - unsigned int len = skb->len-skb->data_len; struct sock_filter *fentry; /* We walk down these */ + void *ptr; u32 A = 0; /* Accumulator */ u32 X = 0; /* Index Register */ u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ + u32 tmp; int k; int pc; @@ -168,86 +177,35 @@ int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) case BPF_LD|BPF_W|BPF_ABS: k = fentry->k; load_w: - if (k >= 0 && (unsigned int)(k+sizeof(u32)) <= len) { - A = ntohl(*(u32*)&data[k]); + ptr = load_pointer(skb, k, 4, &tmp); + if (ptr != NULL) { + A = ntohl(*(u32 *)ptr); continue; } - if (k < 0) { - u8 *ptr; - - if (k >= SKF_AD_OFF) - break; - ptr = load_pointer(skb, k); - if (ptr) { - A = ntohl(*(u32*)ptr); - continue; - } - } else { - u32 _tmp, *p; - p = skb_header_pointer(skb, k, 4, &_tmp); - if (p != NULL) { - A = ntohl(*p); - continue; - } - } return 0; case BPF_LD|BPF_H|BPF_ABS: k = fentry->k; load_h: - if (k >= 0 && (unsigned int)(k + sizeof(u16)) <= len) { - A = ntohs(*(u16*)&data[k]); + ptr = load_pointer(skb, k, 2, &tmp); + if (ptr != NULL) { + A = ntohs(*(u16 *)ptr); continue; } - if (k < 0) { - u8 *ptr; - - if (k >= SKF_AD_OFF) - break; - ptr = load_pointer(skb, k); - if (ptr) { - A = ntohs(*(u16*)ptr); - continue; - } - } else { - u16 _tmp, *p; - p = skb_header_pointer(skb, k, 2, &_tmp); - if (p != NULL) { - A = ntohs(*p); - continue; - } - } return 0; case BPF_LD|BPF_B|BPF_ABS: k = fentry->k; load_b: - if (k >= 0 && (unsigned int)k < len) { - A = data[k]; + ptr = load_pointer(skb, k, 1, &tmp); + if (ptr != NULL) { + A = *(u8 *)ptr; continue; } - if (k < 0) { - u8 *ptr; - - if (k >= SKF_AD_OFF) - break; - ptr = load_pointer(skb, k); - if (ptr) { - A = *ptr; - continue; - } - } else { - u8 _tmp, *p; - p = skb_header_pointer(skb, k, 1, &_tmp); - if (p != NULL) { - A = *p; - continue; - } - } return 0; case BPF_LD|BPF_W|BPF_LEN: - A = len; + A = skb->len; continue; case BPF_LDX|BPF_W|BPF_LEN: - X = len; + X = skb->len; continue; case BPF_LD|BPF_W|BPF_IND: k = X + fentry->k; @@ -259,10 +217,12 @@ load_b: k = X + fentry->k; goto load_b; case BPF_LDX|BPF_B|BPF_MSH: - if (fentry->k >= len) - return 0; - X = (data[fentry->k] & 0xf) << 2; - continue; + ptr = load_pointer(skb, fentry->k, 1, &tmp); + if (ptr != NULL) { + X = (*(u8 *)ptr & 0xf) << 2; + continue; + } + return 0; case BPF_LD|BPF_IMM: A = fentry->k; continue; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bb73b2190ec7..d9f7b06fe886 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -129,7 +129,7 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ -struct sk_buff *alloc_skb(unsigned int size, int gfp_mask) +struct sk_buff *alloc_skb(unsigned int size, unsigned int __nocast gfp_mask) { struct sk_buff *skb; u8 *data; @@ -182,7 +182,8 @@ nodata: * %GFP_ATOMIC. */ struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, - unsigned int size, int gfp_mask) + unsigned int size, + unsigned int __nocast gfp_mask) { struct sk_buff *skb; u8 *data; @@ -322,7 +323,7 @@ void __kfree_skb(struct sk_buff *skb) * %GFP_ATOMIC. */ -struct sk_buff *skb_clone(struct sk_buff *skb, int gfp_mask) +struct sk_buff *skb_clone(struct sk_buff *skb, unsigned int __nocast gfp_mask) { struct sk_buff *n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); @@ -357,7 +358,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, int gfp_mask) C(ip_summed); C(priority); C(protocol); - C(security); n->destructor = NULL; #ifdef CONFIG_NETFILTER C(nfmark); @@ -422,7 +422,6 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->pkt_type = old->pkt_type; new->stamp = old->stamp; new->destructor = NULL; - new->security = old->security; #ifdef CONFIG_NETFILTER new->nfmark = old->nfmark; new->nfcache = old->nfcache; @@ -462,7 +461,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) * header is going to be modified. Use pskb_copy() instead. */ -struct sk_buff *skb_copy(const struct sk_buff *skb, int gfp_mask) +struct sk_buff *skb_copy(const struct sk_buff *skb, unsigned int __nocast gfp_mask) { int headerlen = skb->data - skb->head; /* @@ -501,7 +500,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, int gfp_mask) * The returned buffer has a reference count of 1. */ -struct sk_buff *pskb_copy(struct sk_buff *skb, int gfp_mask) +struct sk_buff *pskb_copy(struct sk_buff *skb, unsigned int __nocast gfp_mask) { /* * Allocate the copy buffer @@ -559,7 +558,8 @@ out: * reloaded after call to this function. */ -int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, int gfp_mask) +int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, + unsigned int __nocast gfp_mask) { int i; u8 *data; @@ -649,7 +649,8 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) * only by netfilter in the cases when checksum is recalculated? --ANK */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, - int newheadroom, int newtailroom, int gfp_mask) + int newheadroom, int newtailroom, + unsigned int __nocast gfp_mask) { /* * Allocate the copy buffer diff --git a/net/core/sock.c b/net/core/sock.c index a6ec3ada7f9e..8b35ccdc2b3b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -622,7 +622,8 @@ lenout: * @prot: struct proto associated with this new sock instance * @zero_it: if we should zero the newly allocated sock */ -struct sock *sk_alloc(int family, int priority, struct proto *prot, int zero_it) +struct sock *sk_alloc(int family, unsigned int __nocast priority, + struct proto *prot, int zero_it) { struct sock *sk = NULL; kmem_cache_t *slab = prot->slab; @@ -750,7 +751,8 @@ unsigned long sock_i_ino(struct sock *sk) /* * Allocate a skb from the socket's send buffer. */ -struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, int priority) +struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, + unsigned int __nocast priority) { if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { struct sk_buff * skb = alloc_skb(size, priority); @@ -765,7 +767,8 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, int /* * Allocate a skb from the socket's receive buffer. */ -struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, int priority) +struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, + unsigned int __nocast priority) { if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { struct sk_buff *skb = alloc_skb(size, priority); @@ -780,7 +783,7 @@ struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, int /* * Allocate a memory block from the socket's option memory buffer. */ -void *sock_kmalloc(struct sock *sk, int size, int priority) +void *sock_kmalloc(struct sock *sk, int size, unsigned int __nocast priority) { if ((unsigned)size <= sysctl_optmem_max && atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { diff --git a/net/decnet/Kconfig b/net/decnet/Kconfig index 2101da542ba8..92f2ec46fd22 100644 --- a/net/decnet/Kconfig +++ b/net/decnet/Kconfig @@ -1,6 +1,29 @@ # # DECnet configuration # +config DECNET + tristate "DECnet Support" + ---help--- + The DECnet networking protocol was used in many products made by + Digital (now Compaq). It provides reliable stream and sequenced + packet communications over which run a variety of services similar + to those which run over TCP/IP. + + To find some tools to use with the kernel layer support, please + look at Patrick Caulfield's web site: + <http://linux-decnet.sourceforge.net/>. + + More detailed documentation is available in + <file:Documentation/networking/decnet.txt>. + + Be sure to say Y to "/proc file system support" and "Sysctl support" + below when using DECnet, since you will need sysctl support to aid + in configuration at run time. + + The DECnet code is also available as a module ( = code which can be + inserted in and removed from the running kernel whenever you want). + The module is called decnet. + config DECNET_ROUTER bool "DECnet: router support (EXPERIMENTAL)" depends on DECNET && EXPERIMENTAL diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 29bb3cd21965..96a02800cd28 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -536,7 +536,7 @@ static void dn_keepalive(struct sock *sk) * we are double checking that we are not sending too * many of these keepalive frames. */ - if (skb_queue_len(&scp->other_xmit_queue) == 0) + if (skb_queue_empty(&scp->other_xmit_queue)) dn_nsp_send_link(sk, DN_NOCHANGE, 0); } @@ -1191,7 +1191,7 @@ static unsigned int dn_poll(struct file *file, struct socket *sock, poll_table struct dn_scp *scp = DN_SK(sk); int mask = datagram_poll(file, sock, wait); - if (skb_queue_len(&scp->other_receive_queue)) + if (!skb_queue_empty(&scp->other_receive_queue)) mask |= POLLRDBAND; return mask; @@ -1214,7 +1214,7 @@ static int dn_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCATMARK: lock_sock(sk); - val = (skb_queue_len(&scp->other_receive_queue) != 0); + val = !skb_queue_empty(&scp->other_receive_queue); if (scp->state != DN_RUN) val = -ENOTCONN; release_sock(sk); @@ -1630,7 +1630,7 @@ static int dn_data_ready(struct sock *sk, struct sk_buff_head *q, int flags, int int len = 0; if (flags & MSG_OOB) - return skb_queue_len(q) ? 1 : 0; + return !skb_queue_empty(q) ? 1 : 0; while(skb != (struct sk_buff *)q) { struct dn_skb_cb *cb = DN_SKB_CB(skb); @@ -1707,7 +1707,7 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock, if (sk->sk_err) goto out; - if (skb_queue_len(&scp->other_receive_queue)) { + if (!skb_queue_empty(&scp->other_receive_queue)) { if (!(flags & MSG_OOB)) { msg->msg_flags |= MSG_OOB; if (!scp->other_report) { diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 9934b25720e4..99bc061759c3 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -551,7 +551,8 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) if (t < s_t) continue; if (t > s_t) - memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(int)); + memset(&cb->args[1], 0, + sizeof(cb->args) - sizeof(cb->args[0])); tb = dn_fib_get_table(t, 0); if (tb == NULL) continue; diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 42abbf3f524f..8cce1fdbda90 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -342,7 +342,8 @@ int dn_nsp_xmit_timeout(struct sock *sk) dn_nsp_output(sk); - if (skb_queue_len(&scp->data_xmit_queue) || skb_queue_len(&scp->other_xmit_queue)) + if (!skb_queue_empty(&scp->data_xmit_queue) || + !skb_queue_empty(&scp->other_xmit_queue)) scp->persist = dn_nsp_persist(sk); return 0; diff --git a/net/econet/Kconfig b/net/econet/Kconfig new file mode 100644 index 000000000000..39a2d2975e0e --- /dev/null +++ b/net/econet/Kconfig @@ -0,0 +1,36 @@ +# +# Acorn Econet/AUN protocols +# + +config ECONET + tristate "Acorn Econet/AUN protocols (EXPERIMENTAL)" + depends on EXPERIMENTAL && INET + ---help--- + Econet is a fairly old and slow networking protocol mainly used by + Acorn computers to access file and print servers. It uses native + Econet network cards. AUN is an implementation of the higher level + parts of Econet that runs over ordinary Ethernet connections, on + top of the UDP packet protocol, which in turn runs on top of the + Internet protocol IP. + + If you say Y here, you can choose with the next two options whether + to send Econet/AUN traffic over a UDP Ethernet connection or over + a native Econet network card. + + To compile this driver as a module, choose M here: the module + will be called econet. + +config ECONET_AUNUDP + bool "AUN over UDP" + depends on ECONET + help + Say Y here if you want to send Econet/AUN traffic over a UDP + connection (UDP is a packet based protocol that runs on top of the + Internet protocol IP) using an ordinary Ethernet network card. + +config ECONET_NATIVE + bool "Native Econet" + depends on ECONET + help + Say Y here if you have a native Econet network card installed in + your computer. diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index ab60ea63688e..f6dbfb99b14d 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -155,7 +155,7 @@ int eth_rebuild_header(struct sk_buff *skb) * This is normal practice and works for any 'now in use' protocol. */ -unsigned short eth_type_trans(struct sk_buff *skb, struct net_device *dev) +__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) { struct ethhdr *eth; unsigned char *rawp; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 3e63123f7bbd..df5386885a90 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -3,7 +3,6 @@ # config IP_MULTICAST bool "IP: multicasting" - depends on INET help This is code for addressing several networked computers at once, enlarging your kernel by about 2 KB. You need multicasting if you @@ -17,7 +16,6 @@ config IP_MULTICAST config IP_ADVANCED_ROUTER bool "IP: advanced router" - depends on INET ---help--- If you intend to run your Linux box mostly as a router, i.e. as a computer that forwards and redistributes network packets, say Y; you @@ -183,7 +181,6 @@ config IP_ROUTE_VERBOSE config IP_PNP bool "IP: kernel level autoconfiguration" - depends on INET help This enables automatic configuration of IP addresses of devices and of the routing table during kernel boot, based on either information @@ -242,7 +239,6 @@ config IP_PNP_RARP # bool ' IP: ARP support' CONFIG_IP_PNP_ARP config NET_IPIP tristate "IP: tunneling" - depends on INET select INET_TUNNEL ---help--- Tunneling means encapsulating data of one protocol type within @@ -260,7 +256,6 @@ config NET_IPIP config NET_IPGRE tristate "IP: GRE tunnels over IP" - depends on INET select XFRM help Tunneling means encapsulating data of one protocol type within @@ -319,7 +314,7 @@ config IP_PIMSM_V2 config ARPD bool "IP: ARP daemon support (EXPERIMENTAL)" - depends on INET && EXPERIMENTAL + depends on EXPERIMENTAL ---help--- Normally, the kernel maintains an internal cache which maps IP addresses to hardware addresses on the local network, so that @@ -344,7 +339,6 @@ config ARPD config SYN_COOKIES bool "IP: TCP syncookie support (disabled per default)" - depends on INET ---help--- Normal TCP/IP networking is open to an attack known as "SYN flooding". This denial-of-service attack prevents legitimate remote @@ -381,7 +375,6 @@ config SYN_COOKIES config INET_AH tristate "IP: AH transformation" - depends on INET select XFRM select CRYPTO select CRYPTO_HMAC @@ -394,7 +387,6 @@ config INET_AH config INET_ESP tristate "IP: ESP transformation" - depends on INET select XFRM select CRYPTO select CRYPTO_HMAC @@ -408,7 +400,6 @@ config INET_ESP config INET_IPCOMP tristate "IP: IPComp transformation" - depends on INET select XFRM select INET_TUNNEL select CRYPTO @@ -421,7 +412,6 @@ config INET_IPCOMP config INET_TUNNEL tristate "IP: tunnel transformation" - depends on INET select XFRM ---help--- Support for generic IP tunnel transformation, which is required by @@ -431,7 +421,6 @@ config INET_TUNNEL config IP_TCPDIAG tristate "IP: TCP socket monitoring interface" - depends on INET default y ---help--- Support for TCP socket monitoring interface used by native Linux @@ -447,7 +436,6 @@ config IP_TCPDIAG_IPV6 config TCP_CONG_ADVANCED bool "TCP: advanced congestion control" - depends on INET ---help--- Support for selection of various TCP congestion control modules. @@ -463,7 +451,6 @@ menu "TCP congestion control" config TCP_CONG_BIC tristate "Binary Increase Congestion (BIC) control" - depends on INET default y ---help--- BIC-TCP is a sender-side only change that ensures a linear RTT @@ -478,7 +465,6 @@ config TCP_CONG_BIC config TCP_CONG_WESTWOOD tristate "TCP Westwood+" - depends on INET default m ---help--- TCP Westwood+ is a sender-side only modification of the TCP Reno @@ -493,7 +479,6 @@ config TCP_CONG_WESTWOOD config TCP_CONG_HTCP tristate "H-TCP" - depends on INET default m ---help--- H-TCP is a send-side only modifications of the TCP Reno @@ -505,7 +490,7 @@ config TCP_CONG_HTCP config TCP_CONG_HSTCP tristate "High Speed TCP" - depends on INET && EXPERIMENTAL + depends on EXPERIMENTAL default n ---help--- Sally Floyd's High Speed TCP (RFC 3649) congestion control. @@ -516,7 +501,7 @@ config TCP_CONG_HSTCP config TCP_CONG_HYBLA tristate "TCP-Hybla congestion control algorithm" - depends on INET && EXPERIMENTAL + depends on EXPERIMENTAL default n ---help--- TCP-Hybla is a sender-side only change that eliminates penalization of @@ -526,7 +511,7 @@ config TCP_CONG_HYBLA config TCP_CONG_VEGAS tristate "TCP Vegas" - depends on INET && EXPERIMENTAL + depends on EXPERIMENTAL default n ---help--- TCP Vegas is a sender-side only change to TCP that anticipates @@ -537,7 +522,7 @@ config TCP_CONG_VEGAS config TCP_CONG_SCALABLE tristate "Scalable TCP" - depends on INET && EXPERIMENTAL + depends on EXPERIMENTAL default n ---help--- Scalable TCP is a sender-side only change to TCP which uses a diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 658e7977924d..ef7468376ae6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1009,6 +1009,15 @@ static int __init init_ipv4_mibs(void) static int ipv4_proc_init(void); extern void ipfrag_init(void); +/* + * IP protocol layer initialiser + */ + +static struct packet_type ip_packet_type = { + .type = __constant_htons(ETH_P_IP), + .func = ip_rcv, +}; + static int __init inet_init(void) { struct sk_buff *dummy_skb; @@ -1102,6 +1111,8 @@ static int __init inet_init(void) ipfrag_init(); + dev_add_pack(&ip_packet_type); + rc = 0; out: return rc; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b56e88edf1b3..4be234c7d8c3 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -43,7 +43,7 @@ * 2 of the License, or (at your option) any later version. */ -#define VERSION "0.324" +#define VERSION "0.325" #include <linux/config.h> #include <asm/uaccess.h> @@ -136,6 +136,7 @@ struct trie_use_stats { unsigned int semantic_match_passed; unsigned int semantic_match_miss; unsigned int null_node_hit; + unsigned int resize_node_skipped; }; #endif @@ -164,8 +165,8 @@ static void put_child(struct trie *t, struct tnode *tn, int i, struct node *n); static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, int wasfull); static int tnode_child_length(struct tnode *tn); static struct node *resize(struct trie *t, struct tnode *tn); -static struct tnode *inflate(struct trie *t, struct tnode *tn); -static struct tnode *halve(struct trie *t, struct tnode *tn); +static struct tnode *inflate(struct trie *t, struct tnode *tn, int *err); +static struct tnode *halve(struct trie *t, struct tnode *tn, int *err); static void tnode_free(struct tnode *tn); static void trie_dump_seq(struct seq_file *seq, struct trie *t); extern struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio); @@ -358,11 +359,32 @@ static inline void free_leaf_info(struct leaf_info *li) kfree(li); } +static struct tnode *tnode_alloc(unsigned int size) +{ + if (size <= PAGE_SIZE) { + return kmalloc(size, GFP_KERNEL); + } else { + return (struct tnode *) + __get_free_pages(GFP_KERNEL, get_order(size)); + } +} + +static void __tnode_free(struct tnode *tn) +{ + unsigned int size = sizeof(struct tnode) + + (1<<tn->bits) * sizeof(struct node *); + + if (size <= PAGE_SIZE) + kfree(tn); + else + free_pages((unsigned long)tn, get_order(size)); +} + static struct tnode* tnode_new(t_key key, int pos, int bits) { int nchildren = 1<<bits; int sz = sizeof(struct tnode) + nchildren * sizeof(struct node *); - struct tnode *tn = kmalloc(sz, GFP_KERNEL); + struct tnode *tn = tnode_alloc(sz); if(tn) { memset(tn, 0, sz); @@ -390,7 +412,7 @@ static void tnode_free(struct tnode *tn) printk("FL %p \n", tn); } else if(IS_TNODE(tn)) { - kfree(tn); + __tnode_free(tn); if(trie_debug > 0 ) printk("FT %p \n", tn); } @@ -460,6 +482,7 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, int w static struct node *resize(struct trie *t, struct tnode *tn) { int i; + int err = 0; if (!tn) return NULL; @@ -556,12 +579,20 @@ static struct node *resize(struct trie *t, struct tnode *tn) */ check_tnode(tn); - + + err = 0; while ((tn->full_children > 0 && 50 * (tn->full_children + tnode_child_length(tn) - tn->empty_children) >= inflate_threshold * tnode_child_length(tn))) { - tn = inflate(t, tn); + tn = inflate(t, tn, &err); + + if(err) { +#ifdef CONFIG_IP_FIB_TRIE_STATS + t->stats.resize_node_skipped++; +#endif + break; + } } check_tnode(tn); @@ -570,11 +601,22 @@ static struct node *resize(struct trie *t, struct tnode *tn) * Halve as long as the number of empty children in this * node is above threshold. */ + + err = 0; while (tn->bits > 1 && 100 * (tnode_child_length(tn) - tn->empty_children) < - halve_threshold * tnode_child_length(tn)) + halve_threshold * tnode_child_length(tn)) { + + tn = halve(t, tn, &err); + + if(err) { +#ifdef CONFIG_IP_FIB_TRIE_STATS + t->stats.resize_node_skipped++; +#endif + break; + } + } - tn = halve(t, tn); /* Only one child remains */ @@ -599,7 +641,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) return (struct node *) tn; } -static struct tnode *inflate(struct trie *t, struct tnode *tn) +static struct tnode *inflate(struct trie *t, struct tnode *tn, int *err) { struct tnode *inode; struct tnode *oldtnode = tn; @@ -611,8 +653,63 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) tn = tnode_new(oldtnode->key, oldtnode->pos, oldtnode->bits + 1); - if (!tn) - trie_bug("tnode_new failed"); + if (!tn) { + *err = -ENOMEM; + return oldtnode; + } + + /* + * Preallocate and store tnodes before the actual work so we + * don't get into an inconsistent state if memory allocation + * fails. In case of failure we return the oldnode and inflate + * of tnode is ignored. + */ + + for(i = 0; i < olen; i++) { + struct tnode *inode = (struct tnode *) tnode_get_child(oldtnode, i); + + if (inode && + IS_TNODE(inode) && + inode->pos == oldtnode->pos + oldtnode->bits && + inode->bits > 1) { + struct tnode *left, *right; + + t_key m = TKEY_GET_MASK(inode->pos, 1); + + left = tnode_new(inode->key&(~m), inode->pos + 1, + inode->bits - 1); + + if(!left) { + *err = -ENOMEM; + break; + } + + right = tnode_new(inode->key|m, inode->pos + 1, + inode->bits - 1); + + if(!right) { + *err = -ENOMEM; + break; + } + + put_child(t, tn, 2*i, (struct node *) left); + put_child(t, tn, 2*i+1, (struct node *) right); + } + } + + if(*err) { + int size = tnode_child_length(tn); + int j; + + for(j = 0; j < size; j++) + if( tn->child[j]) + tnode_free((struct tnode *)tn->child[j]); + + tnode_free(tn); + + *err = -ENOMEM; + return oldtnode; + } for(i = 0; i < olen; i++) { struct node *node = tnode_get_child(oldtnode, i); @@ -625,7 +722,7 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) if(IS_LEAF(node) || ((struct tnode *) node)->pos > tn->pos + tn->bits - 1) { - if(tkey_extract_bits(node->key, tn->pos + tn->bits - 1, + if(tkey_extract_bits(node->key, oldtnode->pos + oldtnode->bits, 1) == 0) put_child(t, tn, 2*i, node); else @@ -665,27 +762,22 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) * the position (inode->pos) */ - t_key m = TKEY_GET_MASK(inode->pos, 1); - /* Use the old key, but set the new significant * bit to zero. */ - left = tnode_new(inode->key&(~m), inode->pos + 1, - inode->bits - 1); - if(!left) - trie_bug("tnode_new failed"); - - - /* Use the old key, but set the new significant - * bit to one. - */ - right = tnode_new(inode->key|m, inode->pos + 1, - inode->bits - 1); + left = (struct tnode *) tnode_get_child(tn, 2*i); + put_child(t, tn, 2*i, NULL); + + if(!left) + BUG(); + + right = (struct tnode *) tnode_get_child(tn, 2*i+1); + put_child(t, tn, 2*i+1, NULL); + + if(!right) + BUG(); - if(!right) - trie_bug("tnode_new failed"); - size = tnode_child_length(left); for(j = 0; j < size; j++) { put_child(t, left, j, inode->child[j]); @@ -701,7 +793,7 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) return tn; } -static struct tnode *halve(struct trie *t, struct tnode *tn) +static struct tnode *halve(struct trie *t, struct tnode *tn, int *err) { struct tnode *oldtnode = tn; struct node *left, *right; @@ -712,8 +804,48 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) tn=tnode_new(oldtnode->key, oldtnode->pos, oldtnode->bits - 1); - if(!tn) - trie_bug("tnode_new failed"); + if (!tn) { + *err = -ENOMEM; + return oldtnode; + } + + /* + * Preallocate and store tnodes before the actual work so we + * don't get into an inconsistent state if memory allocation + * fails. In case of failure we return the oldnode and halve + * of tnode is ignored. + */ + + for(i = 0; i < olen; i += 2) { + left = tnode_get_child(oldtnode, i); + right = tnode_get_child(oldtnode, i+1); + + /* Two nonempty children */ + if( left && right) { + struct tnode *newBinNode = + tnode_new(left->key, tn->pos + tn->bits, 1); + + if(!newBinNode) { + *err = -ENOMEM; + break; + } + put_child(t, tn, i/2, (struct node *)newBinNode); + } + } + + if(*err) { + int size = tnode_child_length(tn); + int j; + + for(j = 0; j < size; j++) + if( tn->child[j]) + tnode_free((struct tnode *)tn->child[j]); + + tnode_free(tn); + + *err = -ENOMEM; + return oldtnode; + } for(i = 0; i < olen; i += 2) { left = tnode_get_child(oldtnode, i); @@ -730,10 +862,11 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) /* Two nonempty children */ else { struct tnode *newBinNode = - tnode_new(left->key, tn->pos + tn->bits, 1); + (struct tnode *) tnode_get_child(tn, i/2); + put_child(t, tn, i/2, NULL); if(!newBinNode) - trie_bug("tnode_new failed"); + BUG(); put_child(t, newBinNode, 0, left); put_child(t, newBinNode, 1, right); @@ -2301,6 +2434,7 @@ static void collect_and_show(struct trie *t, struct seq_file *seq) seq_printf(seq,"semantic match passed = %d\n", t->stats.semantic_match_passed); seq_printf(seq,"semantic match miss = %d\n", t->stats.semantic_match_miss); seq_printf(seq,"null node hit= %d\n", t->stats.null_node_hit); + seq_printf(seq,"skipped node resize = %d\n", t->stats.resize_node_skipped); #ifdef CLEAR_STATS memset(&(t->stats), 0, sizeof(t->stats)); #endif diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index cb759484979d..279f57abfecb 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -970,7 +970,8 @@ int icmp_rcv(struct sk_buff *skb) * RFC 1122: 3.2.2.8 An ICMP_TIMESTAMP MAY be silently * discarded if to broadcast/multicast. */ - if (icmph->type == ICMP_ECHO && + if ((icmph->type == ICMP_ECHO || + icmph->type == ICMP_TIMESTAMP) && sysctl_icmp_echo_ignore_broadcasts) { goto error; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 1f3183168a90..5088f90835ae 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1615,9 +1615,10 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) { int err; u32 addr = imr->imr_multiaddr.s_addr; - struct ip_mc_socklist *iml, *i; + struct ip_mc_socklist *iml=NULL, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); + int ifindex; int count = 0; if (!MULTICAST(addr)) @@ -1633,37 +1634,30 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) goto done; } - iml = (struct ip_mc_socklist *)sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); - err = -EADDRINUSE; + ifindex = imr->imr_ifindex; for (i = inet->mc_list; i; i = i->next) { - if (memcmp(&i->multi, imr, sizeof(*imr)) == 0) { - /* New style additions are reference counted */ - if (imr->imr_address.s_addr == 0) { - i->count++; - err = 0; - } + if (i->multi.imr_multiaddr.s_addr == addr && + i->multi.imr_ifindex == ifindex) goto done; - } count++; } err = -ENOBUFS; - if (iml == NULL || count >= sysctl_igmp_max_memberships) + if (count >= sysctl_igmp_max_memberships) + goto done; + iml = (struct ip_mc_socklist *)sock_kmalloc(sk,sizeof(*iml),GFP_KERNEL); + if (iml == NULL) goto done; + memcpy(&iml->multi, imr, sizeof(*imr)); iml->next = inet->mc_list; - iml->count = 1; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; inet->mc_list = iml; ip_mc_inc_group(in_dev, addr); - iml = NULL; err = 0; - done: rtnl_shunlock(); - if (iml) - sock_kfree_s(sk, iml, sizeof(*iml)); return err; } @@ -1693,30 +1687,25 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml, **imlp; + struct in_device *in_dev; + u32 group = imr->imr_multiaddr.s_addr; + u32 ifindex; rtnl_lock(); + in_dev = ip_mc_find_dev(imr); + if (!in_dev) { + rtnl_unlock(); + return -ENODEV; + } + ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = *imlp) != NULL; imlp = &iml->next) { - if (iml->multi.imr_multiaddr.s_addr==imr->imr_multiaddr.s_addr && - iml->multi.imr_address.s_addr==imr->imr_address.s_addr && - (!imr->imr_ifindex || iml->multi.imr_ifindex==imr->imr_ifindex)) { - struct in_device *in_dev; - - in_dev = inetdev_by_index(iml->multi.imr_ifindex); - if (in_dev) - (void) ip_mc_leave_src(sk, iml, in_dev); - if (--iml->count) { - rtnl_unlock(); - if (in_dev) - in_dev_put(in_dev); - return 0; - } + if (iml->multi.imr_multiaddr.s_addr == group && + iml->multi.imr_ifindex == ifindex) { + (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next; - if (in_dev) { - ip_mc_dec_group(in_dev, imr->imr_multiaddr.s_addr); - in_dev_put(in_dev); - } + ip_mc_dec_group(in_dev, group); rtnl_unlock(); sock_kfree_s(sk, iml, sizeof(*iml)); return 0; @@ -1736,6 +1725,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; + int leavegroup = 0; int i, j, rv; if (!MULTICAST(addr)) @@ -1755,15 +1745,20 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct err = -EADDRNOTAVAIL; for (pmc=inet->mc_list; pmc; pmc=pmc->next) { - if (memcmp(&pmc->multi, mreqs, 2*sizeof(__u32)) == 0) + if (pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr + && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } - if (!pmc) /* must have a prior join */ + if (!pmc) { /* must have a prior join */ + err = -EINVAL; goto done; + } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { - if (pmc->sfmode != omode) + if (pmc->sfmode != omode) { + err = -EINVAL; goto done; + } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); @@ -1775,7 +1770,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct psl = pmc->sflist; if (!add) { if (!psl) - goto done; + goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i=0; i<psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, @@ -1784,7 +1779,13 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct break; } if (rv) /* source not found */ + goto done; /* err = -EADDRNOTAVAIL */ + + /* special case - (INCLUDE, empty) == LEAVE_GROUP */ + if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { + leavegroup = 1; goto done; + } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, @@ -1842,18 +1843,21 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct &mreqs->imr_sourceaddr, 1); done: rtnl_shunlock(); + if (leavegroup) + return ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { - int err; + int err = 0; struct ip_mreqn imr; u32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; + int leavegroup = 0; if (!MULTICAST(addr)) return -EINVAL; @@ -1872,15 +1876,22 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) err = -ENODEV; goto done; } - err = -EADDRNOTAVAIL; + + /* special case - (INCLUDE, empty) == LEAVE_GROUP */ + if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { + leavegroup = 1; + goto done; + } for (pmc=inet->mc_list; pmc; pmc=pmc->next) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } - if (!pmc) /* must have a prior join */ + if (!pmc) { /* must have a prior join */ + err = -EINVAL; goto done; + } if (msf->imsf_numsrc) { newpsl = (struct ip_sf_socklist *)sock_kmalloc(sk, IP_SFLSIZE(msf->imsf_numsrc), GFP_KERNEL); @@ -1909,8 +1920,11 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) 0, NULL, 0); pmc->sflist = newpsl; pmc->sfmode = msf->imsf_fmode; + err = 0; done: rtnl_shunlock(); + if (leavegroup) + err = ip_mc_leave_group(sk, &imr); return err; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6ce5c3292f9f..80d13103b2b0 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -107,7 +107,6 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; BUG_TRAP(newskb->dst); - nf_reset(newskb); netif_rx(newskb); return 0; } @@ -188,14 +187,6 @@ static inline int ip_finish_output2(struct sk_buff *skb) skb = skb2; } -#ifdef CONFIG_BRIDGE_NETFILTER - /* bridge-netfilter defers calling some IP hooks to the bridge layer - * and still needs the conntrack reference. - */ - if (skb->nf_bridge == NULL) -#endif - nf_reset(skb); - if (hh) { int hh_alen; @@ -389,7 +380,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; - to->security = from->security; dst_release(to->dst); to->dst = dst_clone(from->dst); to->dev = from->dev; @@ -1329,23 +1319,8 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar ip_rt_put(rt); } -/* - * IP protocol layer initialiser - */ - -static struct packet_type ip_packet_type = { - .type = __constant_htons(ETH_P_IP), - .func = ip_rcv, -}; - -/* - * IP registers the packet type and then calls the subprotocol initialisers - */ - void __init ip_init(void) { - dev_add_pack(&ip_packet_type); - ip_rt_init(); inet_initpeers(); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index f8b172f89811..fc7c481d0d79 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -677,11 +677,11 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, mreq.imr_address.s_addr = mreqs.imr_interface; mreq.imr_ifindex = 0; err = ip_mc_join_group(sk, &mreq); - if (err) + if (err && err != -EADDRINUSE) break; omode = MCAST_INCLUDE; add = 1; - } else /*IP_DROP_SOURCE_MEMBERSHIP */ { + } else /* IP_DROP_SOURCE_MEMBERSHIP */ { omode = MCAST_INCLUDE; add = 0; } @@ -754,7 +754,7 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, mreq.imr_address.s_addr = 0; mreq.imr_ifindex = greqs.gsr_interface; err = ip_mc_join_group(sk, &mreq); - if (err) + if (err && err != -EADDRINUSE) break; greqs.gsr_interface = mreq.imr_ifindex; omode = MCAST_INCLUDE; diff --git a/net/ipv4/ipvs/Kconfig b/net/ipv4/ipvs/Kconfig index 63a82b4b64bb..c9820bfc493a 100644 --- a/net/ipv4/ipvs/Kconfig +++ b/net/ipv4/ipvs/Kconfig @@ -2,11 +2,11 @@ # IP Virtual Server configuration # menu "IP: Virtual Server Configuration" - depends on INET && NETFILTER + depends on NETFILTER config IP_VS tristate "IP virtual server support (EXPERIMENTAL)" - depends on INET && NETFILTER + depends on NETFILTER ---help--- IP Virtual Server support will let you build a high-performance virtual server based on cluster of two or more real servers. This diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index 9f16ab309106..d0145a8b1551 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -758,7 +758,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp) return 1; } - +/* Called from keventd and must protect itself from softirqs */ void ip_vs_random_dropentry(void) { int idx; @@ -773,7 +773,7 @@ void ip_vs_random_dropentry(void) /* * Lock is actually needed in this loop. */ - ct_write_lock(hash); + ct_write_lock_bh(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (!cp->cport && !(cp->flags & IP_VS_CONN_F_NO_CPORT)) @@ -806,7 +806,7 @@ void ip_vs_random_dropentry(void) ip_vs_conn_expire_now(cp->control); } } - ct_write_unlock(hash); + ct_write_unlock_bh(hash); } } diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 12a82e91d22a..7d99ede2ef79 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -90,7 +90,8 @@ int ip_vs_get_debug_level(void) #endif /* - * update_defense_level is called from keventd and from sysctl. + * update_defense_level is called from keventd and from sysctl, + * so it needs to protect itself from softirqs */ static void update_defense_level(void) { @@ -110,6 +111,8 @@ static void update_defense_level(void) nomem = (availmem < sysctl_ip_vs_amemthresh); + local_bh_disable(); + /* drop_entry */ spin_lock(&__ip_vs_dropentry_lock); switch (sysctl_ip_vs_drop_entry) { @@ -206,6 +209,8 @@ static void update_defense_level(void) if (to_change >= 0) ip_vs_protocol_timeout_change(sysctl_ip_vs_secure_tcp>1); write_unlock(&__ip_vs_securetcp_lock); + + local_bh_enable(); } @@ -1360,9 +1365,7 @@ proc_do_defense_mode(ctl_table *table, int write, struct file * filp, /* Restore the correct value */ *valp = val; } else { - local_bh_disable(); update_defense_level(); - local_bh_enable(); } } return rc; diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 42dc95102873..1dd824f3cf0a 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -432,6 +432,13 @@ static unsigned int ip_conntrack_defrag(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { +#if !defined(CONFIG_IP_NF_NAT) && !defined(CONFIG_IP_NF_NAT_MODULE) + /* Previously seen (loopback)? Ignore. Do this before + fragment check. */ + if ((*pskb)->nfct) + return NF_ACCEPT; +#endif + /* Gather fragments. */ if ((*pskb)->nh.iph->frag_off & htons(IP_MF|IP_OFFSET)) { *pskb = ip_ct_gather_frags(*pskb, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 12a1cf306f67..d675ff80b04d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -54,6 +54,7 @@ * Marc Boucher : routing by fwmark * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file + * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -70,6 +71,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/mm.h> +#include <linux/bootmem.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> @@ -201,8 +203,37 @@ __u8 ip_tos2prio[16] = { struct rt_hash_bucket { struct rtable *chain; - spinlock_t lock; -} __attribute__((__aligned__(8))); +}; +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) +/* + * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks + * The size of this table is a power of two and depends on the number of CPUS. + */ +#if NR_CPUS >= 32 +#define RT_HASH_LOCK_SZ 4096 +#elif NR_CPUS >= 16 +#define RT_HASH_LOCK_SZ 2048 +#elif NR_CPUS >= 8 +#define RT_HASH_LOCK_SZ 1024 +#elif NR_CPUS >= 4 +#define RT_HASH_LOCK_SZ 512 +#else +#define RT_HASH_LOCK_SZ 256 +#endif + +static spinlock_t *rt_hash_locks; +# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)] +# define rt_hash_lock_init() { \ + int i; \ + rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ, GFP_KERNEL); \ + if (!rt_hash_locks) panic("IP: failed to allocate rt_hash_locks\n"); \ + for (i = 0; i < RT_HASH_LOCK_SZ; i++) \ + spin_lock_init(&rt_hash_locks[i]); \ + } +#else +# define rt_hash_lock_addr(slot) NULL +# define rt_hash_lock_init() +#endif static struct rt_hash_bucket *rt_hash_table; static unsigned rt_hash_mask; @@ -575,19 +606,26 @@ static struct rtable **rt_remove_balanced_route(struct rtable **chain_head, /* This runs via a timer and thus is always in BH context. */ static void rt_check_expire(unsigned long dummy) { - static int rover; - int i = rover, t; + static unsigned int rover; + unsigned int i = rover, goal; struct rtable *rth, **rthp; unsigned long now = jiffies; - - for (t = ip_rt_gc_interval << rt_hash_log; t >= 0; - t -= ip_rt_gc_timeout) { + u64 mult; + + mult = ((u64)ip_rt_gc_interval) << rt_hash_log; + if (ip_rt_gc_timeout > 1) + do_div(mult, ip_rt_gc_timeout); + goal = (unsigned int)mult; + if (goal > rt_hash_mask) goal = rt_hash_mask + 1; + for (; goal > 0; goal--) { unsigned long tmo = ip_rt_gc_timeout; i = (i + 1) & rt_hash_mask; rthp = &rt_hash_table[i].chain; - spin_lock(&rt_hash_table[i].lock); + if (*rthp == 0) + continue; + spin_lock(rt_hash_lock_addr(i)); while ((rth = *rthp) != NULL) { if (rth->u.dst.expires) { /* Entry is expired even if it is in use */ @@ -620,14 +658,14 @@ static void rt_check_expire(unsigned long dummy) rt_free(rth); #endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ } - spin_unlock(&rt_hash_table[i].lock); + spin_unlock(rt_hash_lock_addr(i)); /* Fallback loop breaker. */ if (time_after(jiffies, now)) break; } rover = i; - mod_timer(&rt_periodic_timer, now + ip_rt_gc_interval); + mod_timer(&rt_periodic_timer, jiffies + ip_rt_gc_interval); } /* This can run from both BH and non-BH contexts, the latter @@ -643,11 +681,11 @@ static void rt_run_flush(unsigned long dummy) get_random_bytes(&rt_hash_rnd, 4); for (i = rt_hash_mask; i >= 0; i--) { - spin_lock_bh(&rt_hash_table[i].lock); + spin_lock_bh(rt_hash_lock_addr(i)); rth = rt_hash_table[i].chain; if (rth) rt_hash_table[i].chain = NULL; - spin_unlock_bh(&rt_hash_table[i].lock); + spin_unlock_bh(rt_hash_lock_addr(i)); for (; rth; rth = next) { next = rth->u.rt_next; @@ -780,7 +818,7 @@ static int rt_garbage_collect(void) k = (k + 1) & rt_hash_mask; rthp = &rt_hash_table[k].chain; - spin_lock_bh(&rt_hash_table[k].lock); + spin_lock_bh(rt_hash_lock_addr(k)); while ((rth = *rthp) != NULL) { if (!rt_may_expire(rth, tmo, expire)) { tmo >>= 1; @@ -812,7 +850,7 @@ static int rt_garbage_collect(void) goal--; #endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ } - spin_unlock_bh(&rt_hash_table[k].lock); + spin_unlock_bh(rt_hash_lock_addr(k)); if (goal <= 0) break; } @@ -882,7 +920,7 @@ restart: rthp = &rt_hash_table[hash].chain; - spin_lock_bh(&rt_hash_table[hash].lock); + spin_lock_bh(rt_hash_lock_addr(hash)); while ((rth = *rthp) != NULL) { #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED if (!(rth->u.dst.flags & DST_BALANCED) && @@ -908,7 +946,7 @@ restart: rth->u.dst.__use++; dst_hold(&rth->u.dst); rth->u.dst.lastuse = now; - spin_unlock_bh(&rt_hash_table[hash].lock); + spin_unlock_bh(rt_hash_lock_addr(hash)); rt_drop(rt); *rp = rth; @@ -949,7 +987,7 @@ restart: if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { int err = arp_bind_neighbour(&rt->u.dst); if (err) { - spin_unlock_bh(&rt_hash_table[hash].lock); + spin_unlock_bh(rt_hash_lock_addr(hash)); if (err != -ENOBUFS) { rt_drop(rt); @@ -990,7 +1028,7 @@ restart: } #endif rt_hash_table[hash].chain = rt; - spin_unlock_bh(&rt_hash_table[hash].lock); + spin_unlock_bh(rt_hash_lock_addr(hash)); *rp = rt; return 0; } @@ -1058,7 +1096,7 @@ static void rt_del(unsigned hash, struct rtable *rt) { struct rtable **rthp; - spin_lock_bh(&rt_hash_table[hash].lock); + spin_lock_bh(rt_hash_lock_addr(hash)); ip_rt_put(rt); for (rthp = &rt_hash_table[hash].chain; *rthp; rthp = &(*rthp)->u.rt_next) @@ -1067,7 +1105,7 @@ static void rt_del(unsigned hash, struct rtable *rt) rt_free(rt); break; } - spin_unlock_bh(&rt_hash_table[hash].lock); + spin_unlock_bh(rt_hash_lock_addr(hash)); } void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, @@ -1647,7 +1685,7 @@ static void ip_handle_martian_source(struct net_device *dev, printk(KERN_WARNING "martian source %u.%u.%u.%u from " "%u.%u.%u.%u, on dev %s\n", NIPQUAD(daddr), NIPQUAD(saddr), dev->name); - if (dev->hard_header_len) { + if (dev->hard_header_len && skb->mac.raw) { int i; unsigned char *p = skb->mac.raw; printk(KERN_WARNING "ll header: "); @@ -3073,12 +3111,14 @@ __setup("rhash_entries=", set_rhash_entries); int __init ip_rt_init(void) { - int i, order, goal, rc = 0; + int rc = 0; rt_hash_rnd = (int) ((num_physpages ^ (num_physpages>>8)) ^ (jiffies ^ (jiffies >> 7))); #ifdef CONFIG_NET_CLS_ROUTE + { + int order; for (order = 0; (PAGE_SIZE << order) < 256 * sizeof(struct ip_rt_acct) * NR_CPUS; order++) /* NOTHING */; @@ -3086,6 +3126,7 @@ int __init ip_rt_init(void) if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); memset(ip_rt_acct, 0, PAGE_SIZE << order); + } #endif ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache", @@ -3096,36 +3137,19 @@ int __init ip_rt_init(void) if (!ipv4_dst_ops.kmem_cachep) panic("IP: failed to allocate ip_dst_cache\n"); - goal = num_physpages >> (26 - PAGE_SHIFT); - if (rhash_entries) - goal = (rhash_entries * sizeof(struct rt_hash_bucket)) >> PAGE_SHIFT; - for (order = 0; (1UL << order) < goal; order++) - /* NOTHING */; - - do { - rt_hash_mask = (1UL << order) * PAGE_SIZE / - sizeof(struct rt_hash_bucket); - while (rt_hash_mask & (rt_hash_mask - 1)) - rt_hash_mask--; - rt_hash_table = (struct rt_hash_bucket *) - __get_free_pages(GFP_ATOMIC, order); - } while (rt_hash_table == NULL && --order > 0); - - if (!rt_hash_table) - panic("Failed to allocate IP route cache hash table\n"); - - printk(KERN_INFO "IP: routing cache hash table of %u buckets, %ldKbytes\n", - rt_hash_mask, - (long) (rt_hash_mask * sizeof(struct rt_hash_bucket)) / 1024); - - for (rt_hash_log = 0; (1 << rt_hash_log) != rt_hash_mask; rt_hash_log++) - /* NOTHING */; - - rt_hash_mask--; - for (i = 0; i <= rt_hash_mask; i++) { - spin_lock_init(&rt_hash_table[i].lock); - rt_hash_table[i].chain = NULL; - } + rt_hash_table = (struct rt_hash_bucket *) + alloc_large_system_hash("IP route cache", + sizeof(struct rt_hash_bucket), + rhash_entries, + (num_physpages >= 128 * 1024) ? + (27 - PAGE_SHIFT) : + (29 - PAGE_SHIFT), + HASH_HIGHMEM, + &rt_hash_log, + &rt_hash_mask, + 0); + memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket)); + rt_hash_lock_init(); ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1); ip_rt_max_size = (rt_hash_mask + 1) * 16; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 882436da9a3a..ddb6ce4ecff2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -615,7 +615,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse size_t psize, int flags) { struct tcp_sock *tp = tcp_sk(sk); - int mss_now; + int mss_now, size_goal; int err; ssize_t copied; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); @@ -628,6 +628,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); mss_now = tcp_current_mss(sk, !(flags&MSG_OOB)); + size_goal = tp->xmit_size_goal; copied = 0; err = -EPIPE; @@ -641,7 +642,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse int offset = poffset % PAGE_SIZE; int size = min_t(size_t, psize, PAGE_SIZE - offset); - if (!sk->sk_send_head || (copy = mss_now - skb->len) <= 0) { + if (!sk->sk_send_head || (copy = size_goal - skb->len) <= 0) { new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; @@ -652,7 +653,7 @@ new_segment: goto wait_for_memory; skb_entail(sk, tp, skb); - copy = mss_now; + copy = size_goal; } if (copy > size) @@ -693,7 +694,7 @@ new_segment: if (!(psize -= copy)) goto out; - if (skb->len != mss_now || (flags & MSG_OOB)) + if (skb->len < mss_now || (flags & MSG_OOB)) continue; if (forced_push(tp)) { @@ -713,6 +714,7 @@ wait_for_memory: goto do_error; mss_now = tcp_current_mss(sk, !(flags&MSG_OOB)); + size_goal = tp->xmit_size_goal; } out: @@ -754,15 +756,20 @@ ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, static inline int select_size(struct sock *sk, struct tcp_sock *tp) { - int tmp = tp->mss_cache_std; + int tmp = tp->mss_cache; if (sk->sk_route_caps & NETIF_F_SG) { - int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); + if (sk->sk_route_caps & NETIF_F_TSO) + tmp = 0; + else { + int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); - if (tmp >= pgbreak && - tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE) - tmp = pgbreak; + if (tmp >= pgbreak && + tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE) + tmp = pgbreak; + } } + return tmp; } @@ -773,7 +780,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int iovlen, flags; - int mss_now; + int mss_now, size_goal; int err, copied; long timeo; @@ -792,6 +799,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); mss_now = tcp_current_mss(sk, !(flags&MSG_OOB)); + size_goal = tp->xmit_size_goal; /* Ok commence sending. */ iovlen = msg->msg_iovlen; @@ -814,7 +822,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, skb = sk->sk_write_queue.prev; if (!sk->sk_send_head || - (copy = mss_now - skb->len) <= 0) { + (copy = size_goal - skb->len) <= 0) { new_segment: /* Allocate new segment. If the interface is SG, @@ -837,7 +845,7 @@ new_segment: skb->ip_summed = CHECKSUM_HW; skb_entail(sk, tp, skb); - copy = mss_now; + copy = size_goal; } /* Try to append data to the end of skb. */ @@ -872,11 +880,6 @@ new_segment: tcp_mark_push(tp, skb); goto new_segment; } else if (page) { - /* If page is cached, align - * offset to L1 cache boundary - */ - off = (off + L1_CACHE_BYTES - 1) & - ~(L1_CACHE_BYTES - 1); if (off == PAGE_SIZE) { put_page(page); TCP_PAGE(sk) = page = NULL; @@ -937,7 +940,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len != mss_now || (flags & MSG_OOB)) + if (skb->len < mss_now || (flags & MSG_OOB)) continue; if (forced_push(tp)) { @@ -957,6 +960,7 @@ wait_for_memory: goto do_error; mss_now = tcp_current_mss(sk, !(flags&MSG_OOB)); + size_goal = tp->xmit_size_goal; } } @@ -1101,7 +1105,7 @@ static void tcp_prequeue_process(struct sock *sk) struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); - NET_ADD_STATS_USER(LINUX_MIB_TCPPREQUEUED, skb_queue_len(&tp->ucopy.prequeue)); + NET_INC_STATS_USER(LINUX_MIB_TCPPREQUEUED); /* RX process wants to run with disabled BHs, though it is not * necessary */ @@ -1365,7 +1369,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * is not empty. It is more elegant, but eats cycles, * unfortunately. */ - if (skb_queue_len(&tp->ucopy.prequeue)) + if (!skb_queue_empty(&tp->ucopy.prequeue)) goto do_prequeue; /* __ Set realtime policy in scheduler __ */ @@ -1390,7 +1394,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } if (tp->rcv_nxt == tp->copied_seq && - skb_queue_len(&tp->ucopy.prequeue)) { + !skb_queue_empty(&tp->ucopy.prequeue)) { do_prequeue: tcp_prequeue_process(sk); @@ -1472,7 +1476,7 @@ skip_copy: } while (len > 0); if (user_recv) { - if (skb_queue_len(&tp->ucopy.prequeue)) { + if (!skb_queue_empty(&tp->ucopy.prequeue)) { int chunk; tp->ucopy.len = copied > 0 ? len : 0; @@ -2128,7 +2132,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_rto = jiffies_to_usecs(tp->rto); info->tcpi_ato = jiffies_to_usecs(tp->ack.ato); - info->tcpi_snd_mss = tp->mss_cache_std; + info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = tp->ack.rcv_mss; info->tcpi_unacked = tp->packets_out; @@ -2178,7 +2182,7 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, switch (optname) { case TCP_MAXSEG: - val = tp->mss_cache_std; + val = tp->mss_cache; if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7bbbbc33eb4b..53a8a5399f1e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -740,10 +740,10 @@ __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst) __u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0); if (!cwnd) { - if (tp->mss_cache_std > 1460) + if (tp->mss_cache > 1460) cwnd = 2; else - cwnd = (tp->mss_cache_std > 1095) ? 3 : 4; + cwnd = (tp->mss_cache > 1095) ? 3 : 4; } return min_t(__u32, cwnd, tp->snd_cwnd_clamp); } @@ -914,7 +914,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ if (sk->sk_route_caps & NETIF_F_TSO) { sk->sk_route_caps &= ~NETIF_F_TSO; sock_set_flag(sk, SOCK_NO_LARGESEND); - tp->mss_cache = tp->mss_cache_std; + tp->mss_cache = tp->mss_cache; } if (!tp->sacked_out) @@ -1077,7 +1077,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ (IsFack(tp) || !before(lost_retrans, TCP_SKB_CB(skb)->ack_seq + tp->reordering * - tp->mss_cache_std))) { + tp->mss_cache))) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); @@ -1957,15 +1957,6 @@ static inline void tcp_ack_packets_out(struct sock *sk, struct tcp_sock *tp) } } -/* There is one downside to this scheme. Although we keep the - * ACK clock ticking, adjusting packet counters and advancing - * congestion window, we do not liberate socket send buffer - * space. - * - * Mucking with skb->truesize and sk->sk_wmem_alloc et al. - * then making a write space wakeup callback is a possible - * future enhancement. WARNING: it is not trivial to make. - */ static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb, __u32 now, __s32 *seq_rtt) { @@ -2047,7 +2038,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p, s32 *seq_usrtt * the other end. */ if (after(scb->end_seq, tp->snd_una)) { - if (tcp_skb_pcount(skb) > 1) + if (tcp_skb_pcount(skb) > 1 && + after(tp->snd_una, scb->seq)) acked |= tcp_tso_acked(sk, skb, now, &seq_rtt); break; @@ -2810,7 +2802,7 @@ static void tcp_sack_remove(struct tcp_sock *tp) int this_sack; /* Empty ofo queue, hence, all the SACKs are eaten. Clear. */ - if (skb_queue_len(&tp->out_of_order_queue) == 0) { + if (skb_queue_empty(&tp->out_of_order_queue)) { tp->rx_opt.num_sacks = 0; tp->rx_opt.eff_sacks = tp->rx_opt.dsack; return; @@ -2943,13 +2935,13 @@ queue_and_out: if(th->fin) tcp_fin(skb, sk, th); - if (skb_queue_len(&tp->out_of_order_queue)) { + if (!skb_queue_empty(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); /* RFC2581. 4.2. SHOULD send immediate ACK, when * gap in queue is filled. */ - if (!skb_queue_len(&tp->out_of_order_queue)) + if (skb_queue_empty(&tp->out_of_order_queue)) tp->ack.pingpong = 0; } @@ -3257,9 +3249,8 @@ static int tcp_prune_queue(struct sock *sk) * This must not ever occur. */ /* First, purge the out_of_order queue. */ - if (skb_queue_len(&tp->out_of_order_queue)) { - NET_ADD_STATS_BH(LINUX_MIB_OFOPRUNED, - skb_queue_len(&tp->out_of_order_queue)); + if (!skb_queue_empty(&tp->out_of_order_queue)) { + NET_INC_STATS_BH(LINUX_MIB_OFOPRUNED); __skb_queue_purge(&tp->out_of_order_queue); /* Reset SACK state. A conforming SACK implementation will @@ -3308,6 +3299,28 @@ void tcp_cwnd_application_limited(struct sock *sk) tp->snd_cwnd_stamp = tcp_time_stamp; } +static inline int tcp_should_expand_sndbuf(struct sock *sk, struct tcp_sock *tp) +{ + /* If the user specified a specific send buffer setting, do + * not modify it. + */ + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return 0; + + /* If we are under global TCP memory pressure, do not expand. */ + if (tcp_memory_pressure) + return 0; + + /* If we are under soft global TCP memory pressure, do not expand. */ + if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) + return 0; + + /* If we filled the congestion window, do not expand. */ + if (tp->packets_out >= tp->snd_cwnd) + return 0; + + return 1; +} /* When incoming ACK allowed to free some skb from write_queue, * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket @@ -3319,11 +3332,8 @@ static void tcp_new_space(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - if (tp->packets_out < tp->snd_cwnd && - !(sk->sk_userlocks & SOCK_SNDBUF_LOCK) && - !tcp_memory_pressure && - atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { - int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache_std) + + if (tcp_should_expand_sndbuf(sk, tp)) { + int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff), demanded = max_t(unsigned int, tp->snd_cwnd, tp->reordering + 1); @@ -3346,22 +3356,9 @@ static inline void tcp_check_space(struct sock *sk) } } -static void __tcp_data_snd_check(struct sock *sk, struct sk_buff *skb) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (after(TCP_SKB_CB(skb)->end_seq, tp->snd_una + tp->snd_wnd) || - tcp_packets_in_flight(tp) >= tp->snd_cwnd || - tcp_write_xmit(sk, tp->nonagle)) - tcp_check_probe_timer(sk, tp); -} - -static __inline__ void tcp_data_snd_check(struct sock *sk) +static __inline__ void tcp_data_snd_check(struct sock *sk, struct tcp_sock *tp) { - struct sk_buff *skb = sk->sk_send_head; - - if (skb != NULL) - __tcp_data_snd_check(sk, skb); + tcp_push_pending_frames(sk, tp); tcp_check_space(sk); } @@ -3655,7 +3652,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, */ tcp_ack(sk, skb, 0); __kfree_skb(skb); - tcp_data_snd_check(sk); + tcp_data_snd_check(sk, tp); return 0; } else { /* Header too small */ TCP_INC_STATS_BH(TCP_MIB_INERRS); @@ -3721,7 +3718,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) { /* Well, only one small jumplet in fast path... */ tcp_ack(sk, skb, FLAG_DATA); - tcp_data_snd_check(sk); + tcp_data_snd_check(sk, tp); if (!tcp_ack_scheduled(tp)) goto no_ack; } @@ -3799,7 +3796,7 @@ step5: /* step 7: process the segment text */ tcp_data_queue(sk, skb); - tcp_data_snd_check(sk); + tcp_data_snd_check(sk, tp); tcp_ack_snd_check(sk); return 0; @@ -4109,7 +4106,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* Do step6 onward by hand. */ tcp_urg(sk, skb, th); __kfree_skb(skb); - tcp_data_snd_check(sk); + tcp_data_snd_check(sk, tp); return 0; } @@ -4300,7 +4297,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* tcp_data could move socket to TIME-WAIT */ if (sk->sk_state != TCP_CLOSE) { - tcp_data_snd_check(sk); + tcp_data_snd_check(sk, tp); tcp_ack_snd_check(sk); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ebf112347a97..62f62bb05c2a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2045,7 +2045,7 @@ static int tcp_v4_init_sock(struct sock *sk) */ tp->snd_ssthresh = 0x7fffffff; /* Infinity */ tp->snd_cwnd_clamp = ~0; - tp->mss_cache_std = tp->mss_cache = 536; + tp->mss_cache = 536; tp->reordering = sysctl_tcp_reordering; tp->ca_ops = &tcp_init_congestion_ops; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0e17c244875c..e3f8ea1bfa9c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -49,7 +49,7 @@ int sysctl_tcp_retrans_collapse = 1; * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ -int sysctl_tcp_tso_win_divisor = 8; +int sysctl_tcp_tso_win_divisor = 3; static inline void update_send_head(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb) @@ -140,11 +140,11 @@ static inline void tcp_event_data_sent(struct tcp_sock *tp, tp->ack.pingpong = 1; } -static __inline__ void tcp_event_ack_sent(struct sock *sk) +static __inline__ void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) { struct tcp_sock *tp = tcp_sk(sk); - tcp_dec_quickack_mode(tp); + tcp_dec_quickack_mode(tp, pkts); tcp_clear_xmit_timer(sk, TCP_TIME_DACK); } @@ -355,7 +355,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb) tp->af_specific->send_check(sk, th, skb->len, skb); if (tcb->flags & TCPCB_FLAG_ACK) - tcp_event_ack_sent(sk); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); if (skb->len != tcp_header_size) tcp_event_data_sent(tp, skb, sk); @@ -403,42 +403,11 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) sk->sk_send_head = skb; } -static inline void tcp_tso_set_push(struct sk_buff *skb) -{ - /* Force push to be on for any TSO frames to workaround - * problems with busted implementations like Mac OS-X that - * hold off socket receive wakeups until push is seen. - */ - if (tcp_skb_pcount(skb) > 1) - TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; -} - -/* Send _single_ skb sitting at the send head. This function requires - * true push pending frames to setup probe timer etc. - */ -void tcp_push_one(struct sock *sk, unsigned cur_mss) +static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = sk->sk_send_head; - if (tcp_snd_test(sk, skb, cur_mss, TCP_NAGLE_PUSH)) { - /* Send it out now. */ - TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_tso_set_push(skb); - if (!tcp_transmit_skb(sk, skb_clone(skb, sk->sk_allocation))) { - sk->sk_send_head = NULL; - tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; - tcp_packets_out_inc(sk, tp, skb); - return; - } - } -} - -void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (skb->len <= tp->mss_cache_std || + if (skb->len <= tp->mss_cache || !(sk->sk_route_caps & NETIF_F_TSO)) { /* Avoid the costly divide in the normal * non-TSO case. @@ -448,10 +417,10 @@ void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb) } else { unsigned int factor; - factor = skb->len + (tp->mss_cache_std - 1); - factor /= tp->mss_cache_std; + factor = skb->len + (tp->mss_cache - 1); + factor /= tp->mss_cache; skb_shinfo(skb)->tso_segs = factor; - skb_shinfo(skb)->tso_size = tp->mss_cache_std; + skb_shinfo(skb)->tso_size = tp->mss_cache; } } @@ -537,6 +506,7 @@ static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len) } /* Link BUFF into the send queue. */ + skb_header_release(buff); __skb_append(skb, buff); return 0; @@ -657,7 +627,7 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ tp->pmtu_cookie = pmtu; - tp->mss_cache = tp->mss_cache_std = mss_now; + tp->mss_cache = mss_now; return mss_now; } @@ -669,57 +639,316 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) * cannot be large. However, taking into account rare use of URG, this * is not a big flaw. */ - -unsigned int tcp_current_mss(struct sock *sk, int large) +unsigned int tcp_current_mss(struct sock *sk, int large_allowed) { struct tcp_sock *tp = tcp_sk(sk); struct dst_entry *dst = __sk_dst_get(sk); - unsigned int do_large, mss_now; + u32 mss_now; + u16 xmit_size_goal; + int doing_tso = 0; + + mss_now = tp->mss_cache; + + if (large_allowed && + (sk->sk_route_caps & NETIF_F_TSO) && + !tp->urg_mode) + doing_tso = 1; - mss_now = tp->mss_cache_std; if (dst) { u32 mtu = dst_mtu(dst); if (mtu != tp->pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } - do_large = (large && - (sk->sk_route_caps & NETIF_F_TSO) && - !tp->urg_mode); + if (tp->rx_opt.eff_sacks) + mss_now -= (TCPOLEN_SACK_BASE_ALIGNED + + (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK)); - if (do_large) { - unsigned int large_mss, factor, limit; + xmit_size_goal = mss_now; - large_mss = 65535 - tp->af_specific->net_header_len - + if (doing_tso) { + xmit_size_goal = 65535 - + tp->af_specific->net_header_len - tp->ext_header_len - tp->tcp_header_len; - if (tp->max_window && large_mss > (tp->max_window>>1)) - large_mss = max((tp->max_window>>1), - 68U - tp->tcp_header_len); + if (tp->max_window && + (xmit_size_goal > (tp->max_window >> 1))) + xmit_size_goal = max((tp->max_window >> 1), + 68U - tp->tcp_header_len); + + xmit_size_goal -= (xmit_size_goal % mss_now); + } + tp->xmit_size_goal = xmit_size_goal; - factor = large_mss / mss_now; + return mss_now; +} - /* Always keep large mss multiple of real mss, but - * do not exceed 1/tso_win_divisor of the congestion window - * so we can keep the ACK clock ticking and minimize - * bursting. - */ - limit = tp->snd_cwnd; - if (sysctl_tcp_tso_win_divisor) - limit /= sysctl_tcp_tso_win_divisor; - limit = max(1U, limit); - if (factor > limit) - factor = limit; +/* Congestion window validation. (RFC2861) */ - tp->mss_cache = mss_now * factor; +static inline void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp) +{ + __u32 packets_out = tp->packets_out; + + if (packets_out >= tp->snd_cwnd) { + /* Network is feed fully. */ + tp->snd_cwnd_used = 0; + tp->snd_cwnd_stamp = tcp_time_stamp; + } else { + /* Network starves. */ + if (tp->packets_out > tp->snd_cwnd_used) + tp->snd_cwnd_used = tp->packets_out; - mss_now = tp->mss_cache; + if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= tp->rto) + tcp_cwnd_application_limited(sk); } +} - if (tp->rx_opt.eff_sacks) - mss_now -= (TCPOLEN_SACK_BASE_ALIGNED + - (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK)); - return mss_now; +static unsigned int tcp_window_allows(struct tcp_sock *tp, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd) +{ + u32 window, cwnd_len; + + window = (tp->snd_una + tp->snd_wnd - TCP_SKB_CB(skb)->seq); + cwnd_len = mss_now * cwnd; + return min(window, cwnd_len); +} + +/* Can at least one segment of SKB be sent right now, according to the + * congestion window rules? If so, return how many segments are allowed. + */ +static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *skb) +{ + u32 in_flight, cwnd; + + /* Don't be strict about the congestion window for the final FIN. */ + if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) + return 1; + + in_flight = tcp_packets_in_flight(tp); + cwnd = tp->snd_cwnd; + if (in_flight < cwnd) + return (cwnd - in_flight); + + return 0; +} + +/* This must be invoked the first time we consider transmitting + * SKB onto the wire. + */ +static inline int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb) +{ + int tso_segs = tcp_skb_pcount(skb); + + if (!tso_segs) { + tcp_set_skb_tso_segs(sk, skb); + tso_segs = tcp_skb_pcount(skb); + } + return tso_segs; +} + +static inline int tcp_minshall_check(const struct tcp_sock *tp) +{ + return after(tp->snd_sml,tp->snd_una) && + !after(tp->snd_sml, tp->snd_nxt); +} + +/* Return 0, if packet can be sent now without violation Nagle's rules: + * 1. It is full sized. + * 2. Or it contains FIN. (already checked by caller) + * 3. Or TCP_NODELAY was set. + * 4. Or TCP_CORK is not set, and all sent packets are ACKed. + * With Minshall's modification: all sent small packets are ACKed. + */ + +static inline int tcp_nagle_check(const struct tcp_sock *tp, + const struct sk_buff *skb, + unsigned mss_now, int nonagle) +{ + return (skb->len < mss_now && + ((nonagle&TCP_NAGLE_CORK) || + (!nonagle && + tp->packets_out && + tcp_minshall_check(tp)))); +} + +/* Return non-zero if the Nagle test allows this packet to be + * sent now. + */ +static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb, + unsigned int cur_mss, int nonagle) +{ + /* Nagle rule does not apply to frames, which sit in the middle of the + * write_queue (they have no chances to get new data). + * + * This is implemented in the callers, where they modify the 'nonagle' + * argument based upon the location of SKB in the send queue. + */ + if (nonagle & TCP_NAGLE_PUSH) + return 1; + + /* Don't use the nagle rule for urgent data (or for the final FIN). */ + if (tp->urg_mode || + (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)) + return 1; + + if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) + return 1; + + return 0; +} + +/* Does at least the first segment of SKB fit into the send window? */ +static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, unsigned int cur_mss) +{ + u32 end_seq = TCP_SKB_CB(skb)->end_seq; + + if (skb->len > cur_mss) + end_seq = TCP_SKB_CB(skb)->seq + cur_mss; + + return !after(end_seq, tp->snd_una + tp->snd_wnd); +} + +/* This checks if the data bearing packet SKB (usually sk->sk_send_head) + * should be put on the wire right now. If so, it returns the number of + * packets allowed by the congestion window. + */ +static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb, + unsigned int cur_mss, int nonagle) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned int cwnd_quota; + + tcp_init_tso_segs(sk, skb); + + if (!tcp_nagle_test(tp, skb, cur_mss, nonagle)) + return 0; + + cwnd_quota = tcp_cwnd_test(tp, skb); + if (cwnd_quota && + !tcp_snd_wnd_test(tp, skb, cur_mss)) + cwnd_quota = 0; + + return cwnd_quota; +} + +static inline int tcp_skb_is_last(const struct sock *sk, + const struct sk_buff *skb) +{ + return skb->next == (struct sk_buff *)&sk->sk_write_queue; +} + +int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp) +{ + struct sk_buff *skb = sk->sk_send_head; + + return (skb && + tcp_snd_test(sk, skb, tcp_current_mss(sk, 1), + (tcp_skb_is_last(sk, skb) ? + TCP_NAGLE_PUSH : + tp->nonagle))); +} + +/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet + * which is put after SKB on the list. It is very much like + * tcp_fragment() except that it may make several kinds of assumptions + * in order to speed up the splitting operation. In particular, we + * know that all the data is in scatter-gather pages, and that the + * packet has never been sent out before (and thus is not cloned). + */ +static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len) +{ + struct sk_buff *buff; + int nlen = skb->len - len; + u16 flags; + + /* All of a TSO frame must be composed of paged data. */ + BUG_ON(skb->len != skb->data_len); + + buff = sk_stream_alloc_pskb(sk, 0, 0, GFP_ATOMIC); + if (unlikely(buff == NULL)) + return -ENOMEM; + + buff->truesize = nlen; + skb->truesize -= nlen; + + /* Correct the sequence numbers. */ + TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; + TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; + TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; + + /* PSH and FIN should only be set in the second packet. */ + flags = TCP_SKB_CB(skb)->flags; + TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH); + TCP_SKB_CB(buff)->flags = flags; + + /* This packet was never sent out yet, so no SACK bits. */ + TCP_SKB_CB(buff)->sacked = 0; + + buff->ip_summed = skb->ip_summed = CHECKSUM_HW; + skb_split(skb, buff, len); + + /* Fix up tso_factor for both original and new SKB. */ + tcp_set_skb_tso_segs(sk, skb); + tcp_set_skb_tso_segs(sk, buff); + + /* Link BUFF into the send queue. */ + skb_header_release(buff); + __skb_append(skb, buff); + + return 0; +} + +/* Try to defer sending, if possible, in order to minimize the amount + * of TSO splitting we do. View it as a kind of TSO Nagle test. + * + * This algorithm is from John Heffner. + */ +static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb) +{ + u32 send_win, cong_win, limit, in_flight; + + if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) + return 0; + + if (tp->ca_state != TCP_CA_Open) + return 0; + + in_flight = tcp_packets_in_flight(tp); + + BUG_ON(tcp_skb_pcount(skb) <= 1 || + (tp->snd_cwnd <= in_flight)); + + send_win = (tp->snd_una + tp->snd_wnd) - TCP_SKB_CB(skb)->seq; + + /* From in_flight test above, we know that cwnd > in_flight. */ + cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache; + + limit = min(send_win, cong_win); + + /* If sk_send_head can be sent fully now, just do it. */ + if (skb->len <= limit) + return 0; + + if (sysctl_tcp_tso_win_divisor) { + u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); + + /* If at least some fraction of a window is available, + * just use it. + */ + chunk /= sysctl_tcp_tso_win_divisor; + if (limit >= chunk) + return 0; + } else { + /* Different approach, try not to defer past a single + * ACK. Receiver should ACK every other full sized + * frame, so if we have space for more than 3 frames + * then send now. + */ + if (limit > tcp_max_burst(tp) * tp->mss_cache) + return 0; + } + + /* Ok, it looks like it is advisable to defer. */ + return 1; } /* This routine writes packets to the network. It advances the @@ -729,57 +958,158 @@ unsigned int tcp_current_mss(struct sock *sk, int large) * Returns 1, if no segments are in flight and we have queued segments, but * cannot send anything now because of SWS or another problem. */ -int tcp_write_xmit(struct sock *sk, int nonagle) +static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) { struct tcp_sock *tp = tcp_sk(sk); - unsigned int mss_now; + struct sk_buff *skb; + unsigned int tso_segs, sent_pkts; + int cwnd_quota; /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and all * will be happy. */ - if (sk->sk_state != TCP_CLOSE) { - struct sk_buff *skb; - int sent_pkts = 0; + if (unlikely(sk->sk_state == TCP_CLOSE)) + return 0; + + skb = sk->sk_send_head; + if (unlikely(!skb)) + return 0; + + tso_segs = tcp_init_tso_segs(sk, skb); + cwnd_quota = tcp_cwnd_test(tp, skb); + if (unlikely(!cwnd_quota)) + goto out; + + sent_pkts = 0; + while (likely(tcp_snd_wnd_test(tp, skb, mss_now))) { + BUG_ON(!tso_segs); + + if (tso_segs == 1) { + if (unlikely(!tcp_nagle_test(tp, skb, mss_now, + (tcp_skb_is_last(sk, skb) ? + nonagle : TCP_NAGLE_PUSH)))) + break; + } else { + if (tcp_tso_should_defer(sk, tp, skb)) + break; + } - /* Account for SACKS, we may need to fragment due to this. - * It is just like the real MSS changing on us midstream. - * We also handle things correctly when the user adds some - * IP options mid-stream. Silly to do, but cover it. - */ - mss_now = tcp_current_mss(sk, 1); - - while ((skb = sk->sk_send_head) && - tcp_snd_test(sk, skb, mss_now, - tcp_skb_is_last(sk, skb) ? nonagle : - TCP_NAGLE_PUSH)) { - if (skb->len > mss_now) { - if (tcp_fragment(sk, skb, mss_now)) + if (tso_segs > 1) { + u32 limit = tcp_window_allows(tp, skb, + mss_now, cwnd_quota); + + if (skb->len < limit) { + unsigned int trim = skb->len % mss_now; + + if (trim) + limit = skb->len - trim; + } + if (skb->len > limit) { + if (tso_fragment(sk, skb, limit)) break; } - - TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_tso_set_push(skb); - if (tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC))) + } else if (unlikely(skb->len > mss_now)) { + if (unlikely(tcp_fragment(sk, skb, mss_now))) break; + } - /* Advance the send_head. This one is sent out. - * This call will increment packets_out. - */ - update_send_head(sk, tp, skb); + TCP_SKB_CB(skb)->when = tcp_time_stamp; + + if (unlikely(tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC)))) + break; + + /* Advance the send_head. This one is sent out. + * This call will increment packets_out. + */ + update_send_head(sk, tp, skb); + + tcp_minshall_update(tp, mss_now, skb); + sent_pkts++; + + /* Do not optimize this to use tso_segs. If we chopped up + * the packet above, tso_segs will no longer be valid. + */ + cwnd_quota -= tcp_skb_pcount(skb); + + BUG_ON(cwnd_quota < 0); + if (!cwnd_quota) + break; + + skb = sk->sk_send_head; + if (!skb) + break; + tso_segs = tcp_init_tso_segs(sk, skb); + } + + if (likely(sent_pkts)) { + tcp_cwnd_validate(sk, tp); + return 0; + } +out: + return !tp->packets_out && sk->sk_send_head; +} + +/* Push out any pending frames which were held back due to + * TCP_CORK or attempt at coalescing tiny packets. + * The socket must be locked by the caller. + */ +void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp, + unsigned int cur_mss, int nonagle) +{ + struct sk_buff *skb = sk->sk_send_head; - tcp_minshall_update(tp, mss_now, skb); - sent_pkts = 1; + if (skb) { + if (tcp_write_xmit(sk, cur_mss, nonagle)) + tcp_check_probe_timer(sk, tp); + } +} + +/* Send _single_ skb sitting at the send head. This function requires + * true push pending frames to setup probe timer etc. + */ +void tcp_push_one(struct sock *sk, unsigned int mss_now) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb = sk->sk_send_head; + unsigned int tso_segs, cwnd_quota; + + BUG_ON(!skb || skb->len < mss_now); + + tso_segs = tcp_init_tso_segs(sk, skb); + cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH); + + if (likely(cwnd_quota)) { + BUG_ON(!tso_segs); + + if (tso_segs > 1) { + u32 limit = tcp_window_allows(tp, skb, + mss_now, cwnd_quota); + + if (skb->len < limit) { + unsigned int trim = skb->len % mss_now; + + if (trim) + limit = skb->len - trim; + } + if (skb->len > limit) { + if (unlikely(tso_fragment(sk, skb, limit))) + return; + } + } else if (unlikely(skb->len > mss_now)) { + if (unlikely(tcp_fragment(sk, skb, mss_now))) + return; } - if (sent_pkts) { + /* Send it out now. */ + TCP_SKB_CB(skb)->when = tcp_time_stamp; + + if (likely(!tcp_transmit_skb(sk, skb_clone(skb, sk->sk_allocation)))) { + update_send_head(sk, tp, skb); tcp_cwnd_validate(sk, tp); - return 0; + return; } - - return !tp->packets_out && sk->sk_send_head; } - return 0; } /* This function returns the amount that we can raise the @@ -1039,7 +1369,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (sk->sk_route_caps & NETIF_F_TSO) { sk->sk_route_caps &= ~NETIF_F_TSO; sock_set_flag(sk, SOCK_NO_LARGESEND); - tp->mss_cache = tp->mss_cache_std; } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) @@ -1101,7 +1430,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) * is still in somebody's hands, else make a clone. */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_tso_set_push(skb); err = tcp_transmit_skb(sk, (skb_cloned(skb) ? pskb_copy(skb, GFP_ATOMIC): @@ -1285,7 +1613,7 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by draft-ietf-tcpimpl-prob-03.txt section 3.10. -DaveM */ -void tcp_send_active_reset(struct sock *sk, int priority) +void tcp_send_active_reset(struct sock *sk, unsigned int __nocast priority) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -1670,14 +1998,12 @@ int tcp_write_wakeup(struct sock *sk) if (sk->sk_route_caps & NETIF_F_TSO) { sock_set_flag(sk, SOCK_NO_LARGESEND); sk->sk_route_caps &= ~NETIF_F_TSO; - tp->mss_cache = tp->mss_cache_std; } } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(sk, skb); TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_tso_set_push(skb); err = tcp_transmit_skb(sk, skb_clone(skb, GFP_ATOMIC)); if (!err) { update_send_head(sk, tp, skb); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b127b4498565..0084227438c2 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -231,11 +231,10 @@ static void tcp_delack_timer(unsigned long data) } tp->ack.pending &= ~TCP_ACK_TIMER; - if (skb_queue_len(&tp->ucopy.prequeue)) { + if (!skb_queue_empty(&tp->ucopy.prequeue)) { struct sk_buff *skb; - NET_ADD_STATS_BH(LINUX_MIB_TCPSCHEDULERFAILED, - skb_queue_len(&tp->ucopy.prequeue)); + NET_INC_STATS_BH(LINUX_MIB_TCPSCHEDULERFAILED); while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) sk->sk_backlog_rcv(sk, skb); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index e66ca9381cfd..95163cd52ae0 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -1,6 +1,26 @@ # # IPv6 configuration -# +# + +# IPv6 as module will cause a CRASH if you try to unload it +config IPV6 + tristate "The IPv6 protocol" + default m + select CRYPTO if IPV6_PRIVACY + select CRYPTO_MD5 if IPV6_PRIVACY + ---help--- + This is complemental support for the IP version 6. + You will still be able to do traditional IPv4 networking as well. + + For general information about IPv6, see + <http://playground.sun.com/pub/ipng/html/ipng-main.html>. + For Linux IPv6 development information, see <http://www.linux-ipv6.org>. + For specific information about IPv6 under Linux, read the HOWTO at + <http://www.bieringer.de/linux/IPv6/>. + + To compile this protocol support as a module, choose M here: the + module will be called ipv6. + config IPV6_PRIVACY bool "IPv6: Privacy Extensions (RFC 3041) support" depends on IPV6 diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2b193e3df49a..28d9bcab0970 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -774,7 +774,6 @@ static int __init inet6_init(void) if (if6_proc_init()) goto proc_if6_fail; #endif - ipv6_packet_init(); ip6_route_init(); ip6_flowlabel_init(); err = addrconf_init(); @@ -791,6 +790,8 @@ static int __init inet6_init(void) /* Init v6 transport protocols. */ udpv6_init(); tcpv6_init(); + + ipv6_packet_init(); err = 0; out: return err; @@ -798,7 +799,6 @@ out: addrconf_fail: ip6_flowlabel_cleanup(); ip6_route_cleanup(); - ipv6_packet_cleanup(); #ifdef CONFIG_PROC_FS if6_proc_exit(); proc_if6_fail: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 06e7cdaeedc5..1f2c2f9e353f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -465,7 +465,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; - to->security = from->security; dst_release(to->dst); to->dst = dst_clone(from->dst); to->dev = from->dev; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 562fcd14fdea..29fed6e58d0a 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -281,7 +281,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, struct in6_addr *addr) } write_unlock_bh(&ipv6_sk_mc_lock); - return -ENOENT; + return -EADDRNOTAVAIL; } static struct inet6_dev *ip6_mc_find_dev(struct in6_addr *group, int ifindex) @@ -386,12 +386,16 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (ipv6_addr_equal(&pmc->addr, group)) break; } - if (!pmc) /* must have a prior join */ + if (!pmc) { /* must have a prior join */ + err = -EINVAL; goto done; + } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { - if (pmc->sfmode != omode) + if (pmc->sfmode != omode) { + err = -EINVAL; goto done; + } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip6_mc_add_src(idev, group, omode, 0, NULL, 0); @@ -402,7 +406,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, psl = pmc->sflist; if (!add) { if (!psl) - goto done; + goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i=0; i<psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], source, @@ -411,7 +415,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, break; } if (rv) /* source not found */ - goto done; + goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { @@ -488,6 +492,7 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; + int leavegroup = 0; int i, err; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; @@ -503,7 +508,12 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) if (!idev) return -ENODEV; dev = idev->dev; - err = -EADDRNOTAVAIL; + + err = 0; + if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { + leavegroup = 1; + goto done; + } for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { if (pmc->ifindex != gsf->gf_interface) @@ -511,8 +521,10 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) if (ipv6_addr_equal(&pmc->addr, group)) break; } - if (!pmc) /* must have a prior join */ + if (!pmc) { /* must have a prior join */ + err = -EINVAL; goto done; + } if (gsf->gf_numsrc) { newpsl = (struct ip6_sf_socklist *)sock_kmalloc(sk, IP6_SFLSIZE(gsf->gf_numsrc), GFP_ATOMIC); @@ -544,10 +556,13 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) (void) ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sflist = newpsl; pmc->sfmode = gsf->gf_fmode; + err = 0; done: read_unlock_bh(&idev->lock); in6_dev_put(idev); dev_put(dev); + if (leavegroup) + err = ipv6_sock_mc_drop(sk, gsf->gf_interface, group); return err; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9dac7fdf4726..f6e288dc116e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2018,7 +2018,7 @@ static int tcp_v6_init_sock(struct sock *sk) */ tp->snd_ssthresh = 0x7fffffff; tp->snd_cwnd_clamp = ~0; - tp->mss_cache_std = tp->mss_cache = 536; + tp->mss_cache = 536; tp->reordering = sysctl_tcp_reordering; diff --git a/net/ipx/Kconfig b/net/ipx/Kconfig index a16237c0e783..980a826f5d02 100644 --- a/net/ipx/Kconfig +++ b/net/ipx/Kconfig @@ -1,6 +1,39 @@ # # IPX configuration # +config IPX + tristate "The IPX protocol" + select LLC + ---help--- + This is support for the Novell networking protocol, IPX, commonly + used for local networks of Windows machines. You need it if you + want to access Novell NetWare file or print servers using the Linux + Novell client ncpfs (available from + <ftp://platan.vc.cvut.cz/pub/linux/ncpfs/>) or from + within the Linux DOS emulator DOSEMU (read the DOSEMU-HOWTO, + available from <http://www.tldp.org/docs.html#howto>). In order + to do the former, you'll also have to say Y to "NCP file system + support", below. + + IPX is similar in scope to IP, while SPX, which runs on top of IPX, + is similar to TCP. There is also experimental support for SPX in + Linux (see "SPX networking", below). + + To turn your Linux box into a fully featured NetWare file server and + IPX router, say Y here and fetch either lwared from + <ftp://ibiblio.org/pub/Linux/system/network/daemons/> or + mars_nwe from <ftp://www.compu-art.de/mars_nwe/>. For more + information, read the IPX-HOWTO available from + <http://www.tldp.org/docs.html#howto>. + + General information about how to connect Linux, Windows machines and + Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. + + The IPX driver would enlarge your kernel by about 16 KB. To compile + this driver as a module, choose M here: the module will be called ipx. + Unless you want to integrate your Linux box with a local Novell + network, say N. + config IPX_INTERN bool "IPX: Full internal IPX network" depends on IPX diff --git a/net/irda/irlap.c b/net/irda/irlap.c index 046ad0750e48..7029618f5719 100644 --- a/net/irda/irlap.c +++ b/net/irda/irlap.c @@ -445,9 +445,8 @@ void irlap_disconnect_request(struct irlap_cb *self) IRDA_ASSERT(self->magic == LAP_MAGIC, return;); /* Don't disconnect until all data frames are successfully sent */ - if (skb_queue_len(&self->txq) > 0) { + if (!skb_queue_empty(&self->txq)) { self->disconnect_pending = TRUE; - return; } diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c index 1cd89f5f3b75..a505b5457608 100644 --- a/net/irda/irlap_event.c +++ b/net/irda/irlap_event.c @@ -191,7 +191,7 @@ static void irlap_start_poll_timer(struct irlap_cb *self, int timeout) * Send out the RR frames faster if our own transmit queue is empty, or * if the peer is busy. The effect is a much faster conversation */ - if ((skb_queue_len(&self->txq) == 0) || (self->remote_busy)) { + if (skb_queue_empty(&self->txq) || self->remote_busy) { if (self->fast_RR == TRUE) { /* * Assert that the fast poll timer has not reached the @@ -263,7 +263,7 @@ void irlap_do_event(struct irlap_cb *self, IRLAP_EVENT event, IRDA_DEBUG(2, "%s() : queue len = %d\n", __FUNCTION__, skb_queue_len(&self->txq)); - if (skb_queue_len(&self->txq)) { + if (!skb_queue_empty(&self->txq)) { /* Prevent race conditions with irlap_data_request() */ self->local_busy = TRUE; @@ -1074,7 +1074,7 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event, #else /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* Window has been adjusted for the max packet * size, so much simpler... - Jean II */ - nextfit = (skb_queue_len(&self->txq) > 0); + nextfit = !skb_queue_empty(&self->txq); #endif /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* * Send data with poll bit cleared only if window > 1 @@ -1814,7 +1814,7 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event, #else /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* Window has been adjusted for the max packet * size, so much simpler... - Jean II */ - nextfit = (skb_queue_len(&self->txq) > 0); + nextfit = !skb_queue_empty(&self->txq); #endif /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* * Send data with final bit cleared only if window > 1 @@ -1937,7 +1937,7 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event, irlap_data_indication(self, skb, FALSE); /* Any pending data requests? */ - if ((skb_queue_len(&self->txq) > 0) && + if (!skb_queue_empty(&self->txq) && (self->window > 0)) { self->ack_required = TRUE; @@ -2038,7 +2038,7 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event, /* * Any pending data requests? */ - if ((skb_queue_len(&self->txq) > 0) && + if (!skb_queue_empty(&self->txq) && (self->window > 0) && !self->remote_busy) { irlap_data_indication(self, skb, TRUE); @@ -2069,7 +2069,7 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event, */ nr_status = irlap_validate_nr_received(self, info->nr); if (nr_status == NR_EXPECTED) { - if ((skb_queue_len( &self->txq) > 0) && + if (!skb_queue_empty(&self->txq) && (self->window > 0)) { self->remote_busy = FALSE; diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c index 040abe714aa3..6dafbb43b529 100644 --- a/net/irda/irlap_frame.c +++ b/net/irda/irlap_frame.c @@ -1018,11 +1018,10 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command) /* * We can now fill the window with additional data frames */ - while (skb_queue_len( &self->txq) > 0) { + while (!skb_queue_empty(&self->txq)) { IRDA_DEBUG(0, "%s(), sending additional frames!\n", __FUNCTION__); - if ((skb_queue_len( &self->txq) > 0) && - (self->window > 0)) { + if (self->window > 0) { skb = skb_dequeue( &self->txq); IRDA_ASSERT(skb != NULL, return;); @@ -1031,8 +1030,7 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command) * bit cleared */ if ((self->window > 1) && - skb_queue_len(&self->txq) > 0) - { + !skb_queue_empty(&self->txq)) { irlap_send_data_primary(self, skb); } else { irlap_send_data_primary_poll(self, skb); diff --git a/net/irda/irttp.c b/net/irda/irttp.c index d091ccf773b3..6602d901f8b1 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -1513,7 +1513,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata, /* * Check if there is still data segments in the transmit queue */ - if (skb_queue_len(&self->tx_queue) > 0) { + if (!skb_queue_empty(&self->tx_queue)) { if (priority == P_HIGH) { /* * No need to send the queued data, if we are diff --git a/net/lapb/Kconfig b/net/lapb/Kconfig new file mode 100644 index 000000000000..f0b5efb31a00 --- /dev/null +++ b/net/lapb/Kconfig @@ -0,0 +1,22 @@ +# +# LAPB Data Link Drive +# + +config LAPB + tristate "LAPB Data Link Driver (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + Link Access Procedure, Balanced (LAPB) is the data link layer (i.e. + the lower) part of the X.25 protocol. It offers a reliable + connection service to exchange data frames with one other host, and + it is used to transport higher level protocols (mostly X.25 Packet + Layer, the higher part of X.25, but others are possible as well). + Usually, LAPB is used with specialized X.21 network cards, but Linux + currently supports LAPB only over Ethernet connections. If you want + to use LAPB connections over Ethernet, say Y here and to "LAPB over + Ethernet driver" below. Read + <file:Documentation/networking/lapb-module.txt> for technical + details. + + To compile this driver as a module, choose M here: the + module will be called lapb. If unsure, say N. diff --git a/net/llc/llc_c_ev.c b/net/llc/llc_c_ev.c index cd130c3b72bc..d5bdb53a348f 100644 --- a/net/llc/llc_c_ev.c +++ b/net/llc/llc_c_ev.c @@ -84,7 +84,7 @@ static u16 llc_util_nr_inside_tx_window(struct sock *sk, u8 nr) if (llc->dev->flags & IFF_LOOPBACK) goto out; rc = 1; - if (!skb_queue_len(&llc->pdu_unack_q)) + if (skb_queue_empty(&llc->pdu_unack_q)) goto out; skb = skb_peek(&llc->pdu_unack_q); pdu = llc_pdu_sn_hdr(skb); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fc456a7aaec3..3405fdf41b93 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -858,7 +858,7 @@ static inline void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); - if (!skb_queue_len(&sk->sk_receive_queue)) + if (skb_queue_empty(&sk->sk_receive_queue)) clear_bit(0, &nlk->state); if (!test_bit(0, &nlk->state)) wake_up_interruptible(&nlk->wait); diff --git a/net/packet/Kconfig b/net/packet/Kconfig new file mode 100644 index 000000000000..34ff93ff894d --- /dev/null +++ b/net/packet/Kconfig @@ -0,0 +1,26 @@ +# +# Packet configuration +# + +config PACKET + tristate "Packet socket" + ---help--- + The Packet protocol is used by applications which communicate + directly with network devices without an intermediate network + protocol implemented in the kernel, e.g. tcpdump. If you want them + to work, choose Y. + + To compile this driver as a module, choose M here: the module will + be called af_packet. + + If unsure, say Y. + +config PACKET_MMAP + bool "Packet socket: mmapped IO" + depends on PACKET + help + If you say Y here, the Packet protocol driver will use an IO + mechanism that results in faster communication. + + If unsure, say N. + diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0269616e75a1..c9d5980aa4de 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -274,6 +274,9 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct dst_release(skb->dst); skb->dst = NULL; + /* drop conntrack reference */ + nf_reset(skb); + spkt = (struct sockaddr_pkt*)skb->cb; skb_push(skb, skb->data-skb->mac.raw); @@ -517,6 +520,9 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packe dst_release(skb->dst); skb->dst = NULL; + /* drop conntrack reference */ + nf_reset(skb); + spin_lock(&sk->sk_receive_queue.lock); po->stats.tp_packets++; __skb_queue_tail(&sk->sk_receive_queue, skb); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 7bac249258e3..59d3e71f8b85 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -1,6 +1,43 @@ # # Traffic control configuration. # + +menuconfig NET_SCHED + bool "QoS and/or fair queueing" + ---help--- + When the kernel has several packets to send out over a network + device, it has to decide which ones to send first, which ones to + delay, and which ones to drop. This is the job of the packet + scheduler, and several different algorithms for how to do this + "fairly" have been proposed. + + If you say N here, you will get the standard packet scheduler, which + is a FIFO (first come, first served). If you say Y here, you will be + able to choose from among several alternative algorithms which can + then be attached to different network devices. This is useful for + example if some of your network devices are real time devices that + need a certain minimum data flow rate, or if you need to limit the + maximum data flow rate for traffic which matches specified criteria. + This code is considered to be experimental. + + To administer these schedulers, you'll need the user-level utilities + from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>. + That package also contains some documentation; for more, check out + <http://snafu.freedom.org/linux2.2/iproute-notes.html>. + + This Quality of Service (QoS) support will enable you to use + Differentiated Services (diffserv) and Resource Reservation Protocol + (RSVP) on your Linux router if you also say Y to "QoS support", + "Packet classifier API" and to some classifiers below. Documentation + and software is at <http://diffserv.sourceforge.net/>. + + If you say Y here and to "/proc file system" below, you will be able + to read status information about packet schedulers from the file + /proc/net/psched. + + The available schedulers are listed in the following questions; you + can say Y to as many as you like. If unsure, say N now. + choice prompt "Packet scheduler clock source" depends on NET_SCHED diff --git a/net/sched/Makefile b/net/sched/Makefile index 8f58cecd6266..e48d0d456b3e 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -4,7 +4,7 @@ obj-y := sch_generic.o -obj-$(CONFIG_NET_SCHED) += sch_api.o sch_fifo.o +obj-$(CONFIG_NET_SCHED) += sch_api.o sch_fifo.o sch_blackhole.o obj-$(CONFIG_NET_CLS) += cls_api.o obj-$(CONFIG_NET_CLS_ACT) += act_api.o obj-$(CONFIG_NET_ACT_POLICE) += police.o diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 48bb23c2a35a..53d98f8d3d80 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -205,11 +205,6 @@ META_COLLECTOR(int_protocol) dst->value = skb->protocol; } -META_COLLECTOR(int_security) -{ - dst->value = skb->security; -} - META_COLLECTOR(int_pkttype) { dst->value = skb->pkt_type; @@ -524,7 +519,6 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { [META_ID(REALDEV)] = META_FUNC(int_realdev), [META_ID(PRIORITY)] = META_FUNC(int_priority), [META_ID(PROTOCOL)] = META_FUNC(int_protocol), - [META_ID(SECURITY)] = META_FUNC(int_security), [META_ID(PKTTYPE)] = META_FUNC(int_pkttype), [META_ID(PKTLEN)] = META_FUNC(int_pktlen), [META_ID(DATALEN)] = META_FUNC(int_datalen), diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 05e6e0a799da..b9a069af4a02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -399,10 +399,8 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) { int err; struct rtattr *kind = tca[TCA_KIND-1]; - void *p = NULL; struct Qdisc *sch; struct Qdisc_ops *ops; - int size; ops = qdisc_lookup_ops(kind); #ifdef CONFIG_KMOD @@ -437,64 +435,55 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) if (ops == NULL) goto err_out; - /* ensure that the Qdisc and the private data are 32-byte aligned */ - size = ((sizeof(*sch) + QDISC_ALIGN_CONST) & ~QDISC_ALIGN_CONST); - size += ops->priv_size + QDISC_ALIGN_CONST; - - p = kmalloc(size, GFP_KERNEL); - err = -ENOBUFS; - if (!p) + sch = qdisc_alloc(dev, ops); + if (IS_ERR(sch)) { + err = PTR_ERR(sch); goto err_out2; - memset(p, 0, size); - sch = (struct Qdisc *)(((unsigned long)p + QDISC_ALIGN_CONST) - & ~QDISC_ALIGN_CONST); - sch->padded = (char *)sch - (char *)p; - - INIT_LIST_HEAD(&sch->list); - skb_queue_head_init(&sch->q); + } - if (handle == TC_H_INGRESS) + if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; - - sch->ops = ops; - sch->enqueue = ops->enqueue; - sch->dequeue = ops->dequeue; - sch->dev = dev; - dev_hold(dev); - atomic_set(&sch->refcnt, 1); - sch->stats_lock = &dev->queue_lock; - if (handle == 0) { + handle = TC_H_MAKE(TC_H_INGRESS, 0); + } else if (handle == 0) { handle = qdisc_alloc_handle(dev); err = -ENOMEM; if (handle == 0) goto err_out3; } - if (handle == TC_H_INGRESS) - sch->handle =TC_H_MAKE(TC_H_INGRESS, 0); - else - sch->handle = handle; + sch->handle = handle; if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS-1])) == 0) { +#ifdef CONFIG_NET_ESTIMATOR + if (tca[TCA_RATE-1]) { + err = gen_new_estimator(&sch->bstats, &sch->rate_est, + sch->stats_lock, + tca[TCA_RATE-1]); + if (err) { + /* + * Any broken qdiscs that would require + * a ops->reset() here? The qdisc was never + * in action so it shouldn't be necessary. + */ + if (ops->destroy) + ops->destroy(sch); + goto err_out3; + } + } +#endif qdisc_lock_tree(dev); list_add_tail(&sch->list, &dev->qdisc_list); qdisc_unlock_tree(dev); -#ifdef CONFIG_NET_ESTIMATOR - if (tca[TCA_RATE-1]) - gen_new_estimator(&sch->bstats, &sch->rate_est, - sch->stats_lock, tca[TCA_RATE-1]); -#endif return sch; } err_out3: dev_put(dev); + kfree((char *) sch - sch->padded); err_out2: module_put(ops->owner); err_out: *errp = err; - if (p) - kfree(p); return NULL; } diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c new file mode 100644 index 000000000000..81f0b8346d17 --- /dev/null +++ b/net/sched/sch_blackhole.c @@ -0,0 +1,54 @@ +/* + * net/sched/sch_blackhole.c Black hole queue + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Thomas Graf <tgraf@suug.ch> + * + * Note: Quantum tunneling is not supported. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/pkt_sched.h> + +static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + qdisc_drop(skb, sch); + return NET_XMIT_SUCCESS; +} + +static struct sk_buff *blackhole_dequeue(struct Qdisc *sch) +{ + return NULL; +} + +static struct Qdisc_ops blackhole_qdisc_ops = { + .id = "blackhole", + .priv_size = 0, + .enqueue = blackhole_enqueue, + .dequeue = blackhole_dequeue, + .owner = THIS_MODULE, +}; + +static int __init blackhole_module_init(void) +{ + return register_qdisc(&blackhole_qdisc_ops); +} + +static void __exit blackhole_module_exit(void) +{ + unregister_qdisc(&blackhole_qdisc_ops); +} + +module_init(blackhole_module_init) +module_exit(blackhole_module_exit) + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 7683b34dc6a9..73e218e646ac 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -395,24 +395,23 @@ static struct Qdisc_ops pfifo_fast_ops = { .owner = THIS_MODULE, }; -struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops) +struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops) { void *p; struct Qdisc *sch; - int size; + unsigned int size; + int err = -ENOBUFS; /* ensure that the Qdisc and the private data are 32-byte aligned */ - size = ((sizeof(*sch) + QDISC_ALIGN_CONST) & ~QDISC_ALIGN_CONST); - size += ops->priv_size + QDISC_ALIGN_CONST; + size = QDISC_ALIGN(sizeof(*sch)); + size += ops->priv_size + (QDISC_ALIGNTO - 1); p = kmalloc(size, GFP_KERNEL); if (!p) - return NULL; + goto errout; memset(p, 0, size); - - sch = (struct Qdisc *)(((unsigned long)p + QDISC_ALIGN_CONST) - & ~QDISC_ALIGN_CONST); - sch->padded = (char *)sch - (char *)p; + sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); + sch->padded = (char *) sch - (char *) p; INIT_LIST_HEAD(&sch->list); skb_queue_head_init(&sch->q); @@ -423,11 +422,24 @@ struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops) dev_hold(dev); sch->stats_lock = &dev->queue_lock; atomic_set(&sch->refcnt, 1); + + return sch; +errout: + return ERR_PTR(-err); +} + +struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops) +{ + struct Qdisc *sch; + + sch = qdisc_alloc(dev, ops); + if (IS_ERR(sch)) + goto errout; + if (!ops->init || ops->init(sch, NULL) == 0) return sch; - dev_put(dev); - kfree(p); +errout: return NULL; } @@ -591,6 +603,7 @@ EXPORT_SYMBOL(__netdev_watchdog_up); EXPORT_SYMBOL(noop_qdisc); EXPORT_SYMBOL(noop_qdisc_ops); EXPORT_SYMBOL(qdisc_create_dflt); +EXPORT_SYMBOL(qdisc_alloc); EXPORT_SYMBOL(qdisc_destroy); EXPORT_SYMBOL(qdisc_reset); EXPORT_SYMBOL(qdisc_restart); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 664d0e47374f..7845d045eec4 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -385,7 +385,7 @@ static int red_change(struct Qdisc *sch, struct rtattr *opt) memcpy(q->Stab, RTA_DATA(tb[TCA_RED_STAB-1]), 256); q->qcount = -1; - if (skb_queue_len(&sch->q) == 0) + if (skb_queue_empty(&sch->q)) PSCHED_SET_PASTPERFECT(q->qidlestart); sch_tree_unlock(sch); return 0; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 7ae6aa772dab..5b24ae0650d3 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -71,7 +71,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a const struct sctp_endpoint *ep, const struct sock *sk, sctp_scope_t scope, - int gfp) + unsigned int __nocast gfp) { struct sctp_sock *sp; int i; @@ -203,7 +203,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a */ asoc->addip_serial = asoc->c.initial_tsn; - skb_queue_head_init(&asoc->addip_chunks); + INIT_LIST_HEAD(&asoc->addip_chunk_list); /* Make an empty list of remote transport addresses. */ INIT_LIST_HEAD(&asoc->peer.transport_addr_list); @@ -272,7 +272,8 @@ fail_init: /* Allocate and initialize a new association */ struct sctp_association *sctp_association_new(const struct sctp_endpoint *ep, const struct sock *sk, - sctp_scope_t scope, int gfp) + sctp_scope_t scope, + unsigned int __nocast gfp) { struct sctp_association *asoc; @@ -478,7 +479,7 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, /* Add a transport address to an association. */ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, const union sctp_addr *addr, - const int gfp, + const unsigned int __nocast gfp, const int peer_state) { struct sctp_transport *peer; @@ -1229,7 +1230,8 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned len) /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. */ -int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, int gfp) +int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, + unsigned int __nocast gfp) { sctp_scope_t scope; int flags; @@ -1251,7 +1253,8 @@ int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, int gfp) /* Build the association's bind address list from the cookie. */ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc, - struct sctp_cookie *cookie, int gfp) + struct sctp_cookie *cookie, + unsigned int __nocast gfp) { int var_size2 = ntohs(cookie->peer_init->chunk_hdr.length); int var_size3 = cookie->raw_addr_list_len; diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index f90eadfb60a2..f71549710f2e 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -53,7 +53,8 @@ /* Forward declarations for internal helpers. */ static int sctp_copy_one_addr(struct sctp_bind_addr *, union sctp_addr *, - sctp_scope_t scope, int gfp, int flags); + sctp_scope_t scope, unsigned int __nocast gfp, + int flags); static void sctp_bind_addr_clean(struct sctp_bind_addr *); /* First Level Abstractions. */ @@ -63,7 +64,8 @@ static void sctp_bind_addr_clean(struct sctp_bind_addr *); */ int sctp_bind_addr_copy(struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, - sctp_scope_t scope, int gfp, int flags) + sctp_scope_t scope, unsigned int __nocast gfp, + int flags) { struct sctp_sockaddr_entry *addr; struct list_head *pos; @@ -144,7 +146,7 @@ void sctp_bind_addr_free(struct sctp_bind_addr *bp) /* Add an address to the bind address list in the SCTP_bind_addr structure. */ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, - int gfp) + unsigned int __nocast gfp) { struct sctp_sockaddr_entry *addr; @@ -197,7 +199,8 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) * The second argument is the return value for the length. */ union sctp_params sctp_bind_addrs_to_raw(const struct sctp_bind_addr *bp, - int *addrs_len, int gfp) + int *addrs_len, + unsigned int __nocast gfp) { union sctp_params addrparms; union sctp_params retval; @@ -249,7 +252,7 @@ end_raw: * address parameters). */ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list, - int addrs_len, __u16 port, int gfp) + int addrs_len, __u16 port, unsigned int __nocast gfp) { union sctp_addr_param *rawaddr; struct sctp_paramhdr *param; @@ -347,7 +350,8 @@ union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, /* Copy out addresses from the global local address list. */ static int sctp_copy_one_addr(struct sctp_bind_addr *dest, union sctp_addr *addr, - sctp_scope_t scope, int gfp, int flags) + sctp_scope_t scope, unsigned int __nocast gfp, + int flags) { int error = 0; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 0c2ab7885058..61da2937e641 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -62,7 +62,7 @@ static void sctp_datamsg_init(struct sctp_datamsg *msg) } /* Allocate and initialize datamsg. */ -SCTP_STATIC struct sctp_datamsg *sctp_datamsg_new(int gfp) +SCTP_STATIC struct sctp_datamsg *sctp_datamsg_new(unsigned int __nocast gfp) { struct sctp_datamsg *msg; msg = kmalloc(sizeof(struct sctp_datamsg), gfp); diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index c44bf4165c6e..e47ac0d1a6d6 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -67,7 +67,8 @@ static void sctp_endpoint_bh_rcv(struct sctp_endpoint *ep); * Initialize the base fields of the endpoint structure. */ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, - struct sock *sk, int gfp) + struct sock *sk, + unsigned int __nocast gfp) { struct sctp_sock *sp = sctp_sk(sk); memset(ep, 0, sizeof(struct sctp_endpoint)); @@ -137,7 +138,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Create a sctp_endpoint with all that boring stuff initialized. * Returns NULL if there isn't enough memory. */ -struct sctp_endpoint *sctp_endpoint_new(struct sock *sk, int gfp) +struct sctp_endpoint *sctp_endpoint_new(struct sock *sk, + unsigned int __nocast gfp) { struct sctp_endpoint *ep; diff --git a/net/sctp/input.c b/net/sctp/input.c index 339f7acfdb64..5e085e041a6e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -115,6 +115,17 @@ static void sctp_rcv_set_owner_r(struct sk_buff *skb, struct sock *sk) atomic_add(sizeof(struct sctp_chunk),&sk->sk_rmem_alloc); } +struct sctp_input_cb { + union { + struct inet_skb_parm h4; +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + struct inet6_skb_parm h6; +#endif + } header; + struct sctp_chunk *chunk; +}; +#define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) + /* * This is the routine which IP calls when receiving an SCTP packet. */ @@ -243,6 +254,7 @@ int sctp_rcv(struct sk_buff *skb) ret = -ENOMEM; goto discard_release; } + SCTP_INPUT_CB(skb)->chunk = chunk; sctp_rcv_set_owner_r(skb,sk); @@ -265,9 +277,9 @@ int sctp_rcv(struct sk_buff *skb) sctp_bh_lock_sock(sk); if (sock_owned_by_user(sk)) - sk_add_backlog(sk, (struct sk_buff *) chunk); + sk_add_backlog(sk, skb); else - sctp_backlog_rcv(sk, (struct sk_buff *) chunk); + sctp_backlog_rcv(sk, skb); /* Release the sock and any reference counts we took in the * lookup calls. @@ -302,14 +314,8 @@ discard_release: */ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - struct sctp_chunk *chunk; - struct sctp_inq *inqueue; - - /* One day chunk will live inside the skb, but for - * now this works. - */ - chunk = (struct sctp_chunk *) skb; - inqueue = &chunk->rcvr->inqueue; + struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; + struct sctp_inq *inqueue = &chunk->rcvr->inqueue; sctp_inq_push(inqueue, chunk); return 0; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index cedf4351556c..2d33922c044b 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -50,7 +50,7 @@ /* Initialize an SCTP inqueue. */ void sctp_inq_init(struct sctp_inq *queue) { - skb_queue_head_init(&queue->in); + INIT_LIST_HEAD(&queue->in_chunk_list); queue->in_progress = NULL; /* Create a task for delivering data. */ @@ -62,11 +62,13 @@ void sctp_inq_init(struct sctp_inq *queue) /* Release the memory associated with an SCTP inqueue. */ void sctp_inq_free(struct sctp_inq *queue) { - struct sctp_chunk *chunk; + struct sctp_chunk *chunk, *tmp; /* Empty the queue. */ - while ((chunk = (struct sctp_chunk *) skb_dequeue(&queue->in)) != NULL) + list_for_each_entry_safe(chunk, tmp, &queue->in_chunk_list, list) { + list_del_init(&chunk->list); sctp_chunk_free(chunk); + } /* If there is a packet which is currently being worked on, * free it as well. @@ -92,7 +94,7 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *packet) * Eventually, we should clean up inqueue to not rely * on the BH related data structures. */ - skb_queue_tail(&(q->in), (struct sk_buff *) packet); + list_add_tail(&packet->list, &q->in_chunk_list); q->immediate.func(q->immediate.data); } @@ -131,12 +133,16 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) /* Do we need to take the next packet out of the queue to process? */ if (!chunk) { + struct list_head *entry; + /* Is the queue empty? */ - if (skb_queue_empty(&queue->in)) + if (list_empty(&queue->in_chunk_list)) return NULL; + entry = queue->in_chunk_list.next; chunk = queue->in_progress = - (struct sctp_chunk *) skb_dequeue(&queue->in); + list_entry(entry, struct sctp_chunk, list); + list_del_init(entry); /* This is the first chunk in the packet. */ chunk->singleton = 1; diff --git a/net/sctp/output.c b/net/sctp/output.c index 84b5b370b09d..931371633464 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -108,7 +108,7 @@ struct sctp_packet *sctp_packet_init(struct sctp_packet *packet, packet->transport = transport; packet->source_port = sport; packet->destination_port = dport; - skb_queue_head_init(&packet->chunks); + INIT_LIST_HEAD(&packet->chunk_list); if (asoc) { struct sctp_sock *sp = sctp_sk(asoc->base.sk); overhead = sp->pf->af->net_header_len; @@ -129,12 +129,14 @@ struct sctp_packet *sctp_packet_init(struct sctp_packet *packet, /* Free a packet. */ void sctp_packet_free(struct sctp_packet *packet) { - struct sctp_chunk *chunk; + struct sctp_chunk *chunk, *tmp; SCTP_DEBUG_PRINTK("%s: packet:%p\n", __FUNCTION__, packet); - while ((chunk = (struct sctp_chunk *)__skb_dequeue(&packet->chunks)) != NULL) + list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { + list_del_init(&chunk->list); sctp_chunk_free(chunk); + } if (packet->malloced) kfree(packet); @@ -276,7 +278,7 @@ append: packet->has_sack = 1; /* It is OK to send this chunk. */ - __skb_queue_tail(&packet->chunks, (struct sk_buff *)chunk); + list_add_tail(&chunk->list, &packet->chunk_list); packet->size += chunk_len; chunk->transport = packet->transport; finish: @@ -295,7 +297,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) struct sctphdr *sh; __u32 crc32; struct sk_buff *nskb; - struct sctp_chunk *chunk; + struct sctp_chunk *chunk, *tmp; struct sock *sk; int err = 0; int padding; /* How much padding do we need? */ @@ -305,11 +307,11 @@ int sctp_packet_transmit(struct sctp_packet *packet) SCTP_DEBUG_PRINTK("%s: packet:%p\n", __FUNCTION__, packet); /* Do NOT generate a chunkless packet. */ - chunk = (struct sctp_chunk *)skb_peek(&packet->chunks); - if (unlikely(!chunk)) + if (list_empty(&packet->chunk_list)) return err; /* Set up convenience variables... */ + chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list); sk = chunk->skb->sk; /* Allocate the new skb. */ @@ -370,7 +372,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) * [This whole comment explains WORD_ROUND() below.] */ SCTP_DEBUG_PRINTK("***sctp_transmit_packet***\n"); - while ((chunk = (struct sctp_chunk *)__skb_dequeue(&packet->chunks)) != NULL) { + list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { + list_del_init(&chunk->list); if (sctp_chunk_is_data(chunk)) { if (!chunk->has_tsn) { @@ -511,7 +514,8 @@ err: * will get resent or dropped later. */ - while ((chunk = (struct sctp_chunk *)__skb_dequeue(&packet->chunks)) != NULL) { + list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { + list_del_init(&chunk->list); if (!sctp_chunk_is_data(chunk)) sctp_chunk_free(chunk); } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 4eb81a1407b7..efb72faba20c 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -75,7 +75,7 @@ static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); static inline void sctp_outq_head_data(struct sctp_outq *q, struct sctp_chunk *ch) { - __skb_queue_head(&q->out, (struct sk_buff *)ch); + list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; return; } @@ -83,17 +83,22 @@ static inline void sctp_outq_head_data(struct sctp_outq *q, /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { - struct sctp_chunk *ch; - ch = (struct sctp_chunk *)__skb_dequeue(&q->out); - if (ch) + struct sctp_chunk *ch = NULL; + + if (!list_empty(&q->out_chunk_list)) { + struct list_head *entry = q->out_chunk_list.next; + + ch = list_entry(entry, struct sctp_chunk, list); + list_del_init(entry); q->out_qlen -= ch->skb->len; + } return ch; } /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { - __skb_queue_tail(&q->out, (struct sk_buff *)ch); + list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; return; } @@ -197,8 +202,8 @@ static inline int sctp_cacc_skip(struct sctp_transport *primary, void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) { q->asoc = asoc; - skb_queue_head_init(&q->out); - skb_queue_head_init(&q->control); + INIT_LIST_HEAD(&q->out_chunk_list); + INIT_LIST_HEAD(&q->control_chunk_list); INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); @@ -217,7 +222,7 @@ void sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *pos, *temp; - struct sctp_chunk *chunk; + struct sctp_chunk *chunk, *tmp; /* Throw away unacknowledged chunks. */ list_for_each(pos, &q->asoc->peer.transport_addr_list) { @@ -269,8 +274,10 @@ void sctp_outq_teardown(struct sctp_outq *q) q->error = 0; /* Throw away any leftover control chunks. */ - while ((chunk = (struct sctp_chunk *) skb_dequeue(&q->control)) != NULL) + list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { + list_del_init(&chunk->list); sctp_chunk_free(chunk); + } } /* Free the outqueue structure and any related pending chunks. */ @@ -333,7 +340,7 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk) break; }; } else { - __skb_queue_tail(&q->control, (struct sk_buff *) chunk); + list_add_tail(&chunk->list, &q->control_chunk_list); SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); } @@ -650,10 +657,9 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) __u16 sport = asoc->base.bind_addr.port; __u16 dport = asoc->peer.port; __u32 vtag = asoc->peer.i.init_tag; - struct sk_buff_head *queue; struct sctp_transport *transport = NULL; struct sctp_transport *new_transport; - struct sctp_chunk *chunk; + struct sctp_chunk *chunk, *tmp; sctp_xmit_t status; int error = 0; int start_timer = 0; @@ -675,8 +681,9 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) * ... */ - queue = &q->control; - while ((chunk = (struct sctp_chunk *)skb_dequeue(queue)) != NULL) { + list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { + list_del_init(&chunk->list); + /* Pick the right transport to use. */ new_transport = chunk->transport; @@ -814,8 +821,6 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) /* Finally, transmit new packets. */ start_timer = 0; - queue = &q->out; - while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { /* RFC 2960 6.5 Every DATA chunk MUST carry a valid * stream identifier. @@ -1149,8 +1154,9 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_sackhdr *sack) /* See if all chunks are acked. * Make sure the empty queue handler will get run later. */ - q->empty = skb_queue_empty(&q->out) && skb_queue_empty(&q->control) && - list_empty(&q->retransmit); + q->empty = (list_empty(&q->out_chunk_list) && + list_empty(&q->control_chunk_list) && + list_empty(&q->retransmit)); if (!q->empty) goto finish; @@ -1679,9 +1685,9 @@ static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 ctsn) if (TSN_lte(tsn, ctsn)) { list_del_init(lchunk); if (!chunk->tsn_gap_acked) { - chunk->transport->flight_size -= - sctp_data_size(chunk); - q->outstanding_bytes -= sctp_data_size(chunk); + chunk->transport->flight_size -= + sctp_data_size(chunk); + q->outstanding_bytes -= sctp_data_size(chunk); } sctp_chunk_free(chunk); } else { @@ -1729,7 +1735,7 @@ static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 ctsn) nskips, &ftsn_skip_arr[0]); if (ftsn_chunk) { - __skb_queue_tail(&q->control, (struct sk_buff *)ftsn_chunk); + list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); } } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e7f37faba7c0..ce9245e71fca 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -219,7 +219,7 @@ static void sctp_free_local_addr_list(void) /* Copy the local addresses which are valid for 'scope' into 'bp'. */ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, - int gfp, int copy_flags) + unsigned int __nocast gfp, int copy_flags) { struct sctp_sockaddr_entry *addr; int error = 0; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5baed9bb7de5..00d32b7c8266 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -78,7 +78,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, static int sctp_process_param(struct sctp_association *asoc, union sctp_params param, const union sctp_addr *peer_addr, - int gfp); + unsigned int __nocast gfp); /* What was the inbound interface for this chunk? */ int sctp_chunk_iif(const struct sctp_chunk *chunk) @@ -174,7 +174,7 @@ void sctp_init_cause(struct sctp_chunk *chunk, __u16 cause_code, */ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, const struct sctp_bind_addr *bp, - int gfp, int vparam_len) + unsigned int __nocast gfp, int vparam_len) { sctp_inithdr_t init; union sctp_params addrs; @@ -261,7 +261,7 @@ nodata: struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, - int gfp, int unkparam_len) + unsigned int __nocast gfp, int unkparam_len) { sctp_inithdr_t initack; struct sctp_chunk *retval; @@ -1003,6 +1003,7 @@ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, SCTP_DEBUG_PRINTK("chunkifying skb %p w/o an sk\n", skb); } + INIT_LIST_HEAD(&retval->list); retval->skb = skb; retval->asoc = (struct sctp_association *)asoc; retval->resent = 0; @@ -1116,8 +1117,7 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk) /* Possibly, free the chunk. */ void sctp_chunk_free(struct sctp_chunk *chunk) { - /* Make sure that we are not on any list. */ - skb_unlink((struct sk_buff *) chunk); + BUG_ON(!list_empty(&chunk->list)); list_del_init(&chunk->transmitted_list); /* Release our reference on the message tracker. */ @@ -1233,7 +1233,8 @@ void sctp_chunk_assign_tsn(struct sctp_chunk *chunk) /* Create a CLOSED association to use with an incoming packet. */ struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *ep, - struct sctp_chunk *chunk, int gfp) + struct sctp_chunk *chunk, + unsigned int __nocast gfp) { struct sctp_association *asoc; struct sk_buff *skb; @@ -1348,7 +1349,7 @@ nodata: struct sctp_association *sctp_unpack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, - struct sctp_chunk *chunk, int gfp, + struct sctp_chunk *chunk, unsigned int __nocast gfp, int *error, struct sctp_chunk **errp) { struct sctp_association *retval = NULL; @@ -1812,7 +1813,7 @@ int sctp_verify_init(const struct sctp_association *asoc, */ int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid, const union sctp_addr *peer_addr, - sctp_init_chunk_t *peer_init, int gfp) + sctp_init_chunk_t *peer_init, unsigned int __nocast gfp) { union sctp_params param; struct sctp_transport *transport; @@ -1983,7 +1984,7 @@ nomem: static int sctp_process_param(struct sctp_association *asoc, union sctp_params param, const union sctp_addr *peer_addr, - int gfp) + unsigned int __nocast gfp) { union sctp_addr addr; int i; @@ -2739,8 +2740,12 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, asoc->addip_last_asconf = NULL; /* Send the next asconf chunk from the addip chunk queue. */ - asconf = (struct sctp_chunk *)__skb_dequeue(&asoc->addip_chunks); - if (asconf) { + if (!list_empty(&asoc->addip_chunk_list)) { + struct list_head *entry = asoc->addip_chunk_list.next; + asconf = list_entry(entry, struct sctp_chunk, list); + + list_del_init(entry); + /* Hold the chunk until an ASCONF_ACK is received. */ sctp_chunk_hold(asconf); if (sctp_primitive_ASCONF(asoc, asconf)) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 778639db125a..39c970b5b198 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -63,7 +63,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, void *event_arg, sctp_disposition_t status, sctp_cmd_seq_t *commands, - int gfp); + unsigned int __nocast gfp); static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, sctp_state_t state, struct sctp_endpoint *ep, @@ -71,7 +71,7 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, void *event_arg, sctp_disposition_t status, sctp_cmd_seq_t *commands, - int gfp); + unsigned int __nocast gfp); /******************************************************************** * Helper functions @@ -497,7 +497,8 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, static int sctp_cmd_process_init(sctp_cmd_seq_t *commands, struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_init_chunk_t *peer_init, int gfp) + sctp_init_chunk_t *peer_init, + unsigned int __nocast gfp) { int error; @@ -852,7 +853,7 @@ int sctp_do_sm(sctp_event_t event_type, sctp_subtype_t subtype, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, - int gfp) + unsigned int __nocast gfp) { sctp_cmd_seq_t commands; const sctp_sm_table_entry_t *state_fn; @@ -897,7 +898,7 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, void *event_arg, sctp_disposition_t status, sctp_cmd_seq_t *commands, - int gfp) + unsigned int __nocast gfp) { int error; @@ -985,7 +986,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, void *event_arg, sctp_disposition_t status, sctp_cmd_seq_t *commands, - int gfp) + unsigned int __nocast gfp) { int error = 0; int force; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index aad55dc3792b..091a66f06a35 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -406,7 +406,7 @@ static int sctp_send_asconf(struct sctp_association *asoc, * transmission. */ if (asoc->addip_last_asconf) { - __skb_queue_tail(&asoc->addip_chunks, (struct sk_buff *)chunk); + list_add_tail(&chunk->list, &asoc->addip_chunk_list); goto out; } diff --git a/net/sctp/ssnmap.c b/net/sctp/ssnmap.c index e627d2b451b6..25037daf3fa0 100644 --- a/net/sctp/ssnmap.c +++ b/net/sctp/ssnmap.c @@ -57,7 +57,8 @@ static inline size_t sctp_ssnmap_size(__u16 in, __u16 out) /* Create a new sctp_ssnmap. * Allocate room to store at least 'len' contiguous TSNs. */ -struct sctp_ssnmap *sctp_ssnmap_new(__u16 in, __u16 out, int gfp) +struct sctp_ssnmap *sctp_ssnmap_new(__u16 in, __u16 out, + unsigned int __nocast gfp) { struct sctp_ssnmap *retval; int size; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index a63b69179607..d2f04ebe5081 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -57,7 +57,7 @@ /* Initialize a new transport from provided memory. */ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, const union sctp_addr *addr, - int gfp) + unsigned int __nocast gfp) { /* Copy in the address. */ peer->ipaddr = *addr; @@ -121,7 +121,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, } /* Allocate and initialize a new transport. */ -struct sctp_transport *sctp_transport_new(const union sctp_addr *addr, int gfp) +struct sctp_transport *sctp_transport_new(const union sctp_addr *addr, + unsigned int __nocast gfp) { struct sctp_transport *transport; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 17d0ff534735..0abd5101107c 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -74,7 +74,7 @@ SCTP_STATIC void sctp_ulpevent_init(struct sctp_ulpevent *event, int msg_flags) /* Create a new sctp_ulpevent. */ SCTP_STATIC struct sctp_ulpevent *sctp_ulpevent_new(int size, int msg_flags, - int gfp) + unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sk_buff *skb; @@ -136,7 +136,7 @@ static inline void sctp_ulpevent_release_owner(struct sctp_ulpevent *event) struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( const struct sctp_association *asoc, __u16 flags, __u16 state, __u16 error, __u16 outbound, - __u16 inbound, int gfp) + __u16 inbound, unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_assoc_change *sac; @@ -237,7 +237,7 @@ fail: struct sctp_ulpevent *sctp_ulpevent_make_peer_addr_change( const struct sctp_association *asoc, const struct sockaddr_storage *aaddr, - int flags, int state, int error, int gfp) + int flags, int state, int error, unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_paddr_change *spc; @@ -350,7 +350,7 @@ fail: */ struct sctp_ulpevent *sctp_ulpevent_make_remote_error( const struct sctp_association *asoc, struct sctp_chunk *chunk, - __u16 flags, int gfp) + __u16 flags, unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_remote_error *sre; @@ -448,7 +448,7 @@ fail: */ struct sctp_ulpevent *sctp_ulpevent_make_send_failed( const struct sctp_association *asoc, struct sctp_chunk *chunk, - __u16 flags, __u32 error, int gfp) + __u16 flags, __u32 error, unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_send_failed *ssf; @@ -557,7 +557,7 @@ fail: */ struct sctp_ulpevent *sctp_ulpevent_make_shutdown_event( const struct sctp_association *asoc, - __u16 flags, int gfp) + __u16 flags, unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_shutdown_event *sse; @@ -620,7 +620,7 @@ fail: * 5.3.1.6 SCTP_ADAPTION_INDICATION */ struct sctp_ulpevent *sctp_ulpevent_make_adaption_indication( - const struct sctp_association *asoc, int gfp) + const struct sctp_association *asoc, unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_adaption_event *sai; @@ -657,7 +657,7 @@ fail: */ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, struct sctp_chunk *chunk, - int gfp) + unsigned int __nocast gfp) { struct sctp_ulpevent *event = NULL; struct sk_buff *skb; @@ -718,7 +718,8 @@ fail: * various events. */ struct sctp_ulpevent *sctp_ulpevent_make_pdapi( - const struct sctp_association *asoc, __u32 indication, int gfp) + const struct sctp_association *asoc, __u32 indication, + unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_pdapi_event *pd; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index d5dd2cf7ac4a..8bbc279d6c99 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -100,7 +100,7 @@ void sctp_ulpq_free(struct sctp_ulpq *ulpq) /* Process an incoming DATA chunk. */ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, - int gfp) + unsigned int __nocast gfp) { struct sk_buff_head temp; sctp_data_chunk_t *hdr; @@ -778,7 +778,8 @@ static __u16 sctp_ulpq_renege_frags(struct sctp_ulpq *ulpq, __u16 needed) /* Partial deliver the first message as there is pressure on rwnd. */ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq, - struct sctp_chunk *chunk, int gfp) + struct sctp_chunk *chunk, + unsigned int __nocast gfp) { struct sctp_ulpevent *event; struct sctp_association *asoc; @@ -802,7 +803,7 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq, /* Renege some packets to make room for an incoming chunk. */ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, - int gfp) + unsigned int __nocast gfp) { struct sctp_association *asoc; __u16 needed, freed; @@ -841,7 +842,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, /* Notify the application if an association is aborted and in * partial delivery mode. Send up any pending received messages. */ -void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, int gfp) +void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, unsigned int __nocast gfp) { struct sctp_ulpevent *ev = NULL; struct sock *sk; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 269f217918a3..3c654e06b084 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -145,8 +145,6 @@ __xprt_lock_write(struct rpc_xprt *xprt, struct rpc_task *task) if (test_and_set_bit(XPRT_LOCKED, &xprt->sockstate)) { if (task == xprt->snd_task) return 1; - if (task == NULL) - return 0; goto out_sleep; } if (xprt->nocong || __xprt_get_cong(xprt, task)) { diff --git a/net/unix/Kconfig b/net/unix/Kconfig new file mode 100644 index 000000000000..5a69733bcdad --- /dev/null +++ b/net/unix/Kconfig @@ -0,0 +1,21 @@ +# +# Unix Domain Sockets +# + +config UNIX + tristate "Unix domain sockets" + ---help--- + If you say Y here, you will include support for Unix domain sockets; + sockets are the standard Unix mechanism for establishing and + accessing network connections. Many commonly used programs such as + the X Window system and syslog use these sockets even if your + machine is not connected to any network. Unless you are working on + an embedded system or something similar, you therefore definitely + want to say Y here. + + To compile this driver as a module, choose M here: the module will be + called unix. Note that several important services won't work + correctly if you say M here and then neglect to load the module. + + Say Y unless you know what you are doing. + diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c420eba4876b..d403e34088ad 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -302,7 +302,7 @@ static void unix_write_space(struct sock *sk) * may receive messages only from that peer. */ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) { - if (skb_queue_len(&sk->sk_receive_queue)) { + if (!skb_queue_empty(&sk->sk_receive_queue)) { skb_queue_purge(&sk->sk_receive_queue); wake_up_interruptible_all(&unix_sk(sk)->peer_wait); @@ -1619,7 +1619,7 @@ static long unix_stream_data_wait(struct sock * sk, long timeo) for (;;) { prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); - if (skb_queue_len(&sk->sk_receive_queue) || + if (!skb_queue_empty(&sk->sk_receive_queue) || sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current) || diff --git a/net/wanrouter/Kconfig b/net/wanrouter/Kconfig new file mode 100644 index 000000000000..1debe1cb054e --- /dev/null +++ b/net/wanrouter/Kconfig @@ -0,0 +1,29 @@ +# +# Configuration for WAN router +# + +config WAN_ROUTER + tristate "WAN router" + depends on EXPERIMENTAL + ---help--- + Wide Area Networks (WANs), such as X.25, frame relay and leased + lines, are used to interconnect Local Area Networks (LANs) over vast + distances with data transfer rates significantly higher than those + achievable with commonly used asynchronous modem connections. + Usually, a quite expensive external device called a `WAN router' is + needed to connect to a WAN. + + As an alternative, WAN routing can be built into the Linux kernel. + With relatively inexpensive WAN interface cards available on the + market, a perfectly usable router can be built for less than half + the price of an external router. If you have one of those cards and + wish to use your Linux box as a WAN router, say Y here and also to + the WAN driver for your card, below. You will then need the + wan-tools package which is available from <ftp://ftp.sangoma.com/>. + Read <file:Documentation/networking/wan-router.txt> for more + information. + + To compile WAN routing support as a module, choose M here: the + module will be called wanrouter. + + If unsure, say N. diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index d6844ac226f5..13b650ad22e2 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -358,10 +358,10 @@ int wanrouter_encapsulate(struct sk_buff *skb, struct net_device *dev, */ -unsigned short wanrouter_type_trans(struct sk_buff *skb, struct net_device *dev) +__be16 wanrouter_type_trans(struct sk_buff *skb, struct net_device *dev) { int cnt = skb->data[0] ? 0 : 1; /* there may be a pad present */ - unsigned short ethertype; + __be16 ethertype; switch (skb->data[cnt]) { case NLPID_IP: /* IP datagramm */ @@ -379,7 +379,7 @@ unsigned short wanrouter_type_trans(struct sk_buff *skb, struct net_device *dev) skb->data[cnt+3], dev->name); return 0; } - ethertype = *((unsigned short*)&skb->data[cnt+4]); + ethertype = *((__be16*)&skb->data[cnt+4]); cnt += 6; break; diff --git a/net/x25/Kconfig b/net/x25/Kconfig new file mode 100644 index 000000000000..e6759c9660bb --- /dev/null +++ b/net/x25/Kconfig @@ -0,0 +1,36 @@ +# +# CCITT X.25 Packet Layer +# + +config X25 + tristate "CCITT X.25 Packet Layer (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + X.25 is a set of standardized network protocols, similar in scope to + frame relay; the one physical line from your box to the X.25 network + entry point can carry several logical point-to-point connections + (called "virtual circuits") to other computers connected to the X.25 + network. Governments, banks, and other organizations tend to use it + to connect to each other or to form Wide Area Networks (WANs). Many + countries have public X.25 networks. X.25 consists of two + protocols: the higher level Packet Layer Protocol (PLP) (say Y here + if you want that) and the lower level data link layer protocol LAPB + (say Y to "LAPB Data Link Driver" below if you want that). + + You can read more about X.25 at <http://www.sangoma.com/x25.htm> and + <http://www.cisco.com/univercd/cc/td/doc/product/software/ios11/cbook/cx25.htm>. + Information about X.25 for Linux is contained in the files + <file:Documentation/networking/x25.txt> and + <file:Documentation/networking/x25-iface.txt>. + + One connects to an X.25 network either with a dedicated network card + using the X.21 protocol (not yet supported by Linux) or one can do + X.25 over a standard telephone line using an ordinary modem (say Y + to "X.25 async driver" below) or over Ethernet using an ordinary + Ethernet card and the LAPB over Ethernet (say Y to "LAPB Data Link + Driver" and "LAPB over Ethernet driver" below). + + To compile this driver as a module, choose M here: the module + will be called x25. If unsure, say N. + + diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index 58ca6a972c48..0c1c04322baf 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -1,6 +1,10 @@ # # XFRM configuration # +config XFRM + bool + depends on NET + config XFRM_USER tristate "IPsec user configuration interface" depends on INET && XFRM @@ -10,3 +14,14 @@ config XFRM_USER If unsure, say Y. +config NET_KEY + tristate "PF_KEY sockets" + select XFRM + ---help--- + PF_KEYv2 socket family, compatible to KAME ones. + They are required if you are going to use IPsec tools ported + from KAME. + + Say Y unless you know what you are doing. + + |