diff -urN linux-2.4.25/CREDITS linux-2.4.26/CREDITS --- linux-2.4.25/CREDITS 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/CREDITS 2004-04-14 06:05:21.000000000 -0700 @@ -3386,9 +3386,9 @@ W: http://www.yoshifuji.org/~hideaki/ P: 1024D/E0620EEA 9022 65EB 1ECF 3AD1 0BDF 80D8 4807 F894 E062 0EEA D: IPv6 and other networking related stuff -D: USAGI/WIDE Project, The University of Tokyo -S: Green House #102, 1-15-5, Nishikata, -S: Bunkyo, Tokyo 113-0024 +D: USAGI/WIDE Project, Keio University +S: Jeunet Palace Kawasaki #1-201, 10-2, Furukawa-cho, Saiwai-ku +S: Kawasaki, Kanagawa 212-0025 S: Japan N: Eric Youngdale diff -urN linux-2.4.25/Documentation/Configure.help linux-2.4.26/Documentation/Configure.help --- linux-2.4.25/Documentation/Configure.help 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/Documentation/Configure.help 2004-04-14 06:05:24.000000000 -0700 @@ -1159,6 +1159,14 @@ This effect can be also invoked by calling "idex=ata66" If unsure, say N. +ATI IXP chipset IDE support +CONFIG_BLK_DEV_ATIIXP + This driver adds explicit support for ATI IXP chipset. + This allows the kernel to change PIO, DMA and UDMA speeds + and to configure the chip to optimum performance. + + Say Y here if you have an ATI IXP chipset IDE controller. + CMD64X/CMD680 chipset support CONFIG_BLK_DEV_CMD64X Say Y here if you have an IDE controller which uses any of these @@ -2085,6 +2093,40 @@ If you choose to compile this as a module, the module will be called hptraid.o. +CMD/Silicon Image Medley Software RAID +CONFIG_BLK_DEV_ATARAID_MEDLEY + Say Y or M if you have a Silicon Image 3112 SATA RAID controller, + a CMD680 based controller, or another IDE RAID controller that uses + CMD's Medley software RAID, and want Linux to use the software RAID + feature of this card. This driver uses /dev/ataraid/dXpY (X and Y + numbers) as device names. + + This driver currently only supports RAID0 (striped) mode, so if you + are using RAID1 (mirroring) this will not work for you. In that + case, you may want to try the Silicon Image Medley Software RAID + driver (below). + + Support for mirroring is planned in the future. + + If you choose to compile this as a module, the module will be called + medley.o. + +Silicon Image Medley Software RAID (old driver) +CONFIG_BLK_DEV_ATARAID_SII + Say Y or M if you have a Silicon Image SATARaid controller + and want Linux to use the softwareraid feature of this card. + This driver uses /dev/ataraid/dXpY (X and Y numbers) as device + names. + + This driver does not reliably detect all Medley RAID sets, and could + be dangerous if you have a striped set with disks of different size. + + You should use the new Medley RAID driver (above), unless you use + RAID1 (mirroring), which the new driver does not yet support. + + If you choose to compile this as a module, the module will be called + silraid.o. + Support for Acer PICA 1 chipset CONFIG_ACER_PICA_61 This is a machine with a R4400 133/150 MHz CPU. To compile a Linux @@ -6206,17 +6248,6 @@ If in doubt, say N. -SCTP: Use old checksum (Adler-32) -CONFIG_SCTP_ADLER32 - RCF2960 currently specifies the Adler-32 checksum algorithm for SCTP. - This has been deprecated and replaced by an algorithm now referred - to as crc32c. - - If you say Y, this will use the Adler-32 algorithm, this might be - useful for interoperation with downlevel peers. - - If unsure, say N. - SCTP: Debug messages CONFIG_SCTP_DBG_MSG If you say Y, this will enable verbose debugging messages. @@ -6234,6 +6265,29 @@ If unsure, say N +#choice +SCTP: HMAC algorithm +CONFIG_SCTP_HMAC_NONE + Choose an HMAC algorithm to be used during association establishment. + It can be one of SHA1, MD5 or NONE. It is advised to use either HMAC-MD5 + or HMAC-SHA1. + See configuration for Cryptographic API and enable these algorithms + to make usable by SCTP. + +SCTP: SHA1 HMAC algorithm +CONFIG_SCTP_HMAC_SHA1 + Enable the use of HMAC-SHA1 during association establishment. It + is advised to use either HMAC-MD5 or HMAC-SHA1. + See configuration for Cryptographic API and enable these algorithms + to make usable by SCTP. + +SCTP: MD5 HMAC algorithm +config SCTP_HMAC_MD5 + Enable the use of HMAC-MD5 during association establishment. It is + advised to use either HMAC-MD5 or HMAC-SHA1. + See configuration for Cryptographic API and enable these algorithms + to make usable by SCTP. + Kernel httpd acceleration CONFIG_KHTTPD The kernel httpd acceleration daemon (kHTTPd) is a (limited) web @@ -7001,8 +7055,11 @@ Packet socket: mmapped IO CONFIG_PACKET_MMAP - If you say Y here, the Packet protocol driver will use an IO - mechanism that results in faster communication. + If you say Y here, the Packet protocol driver can use a faster and + more efficient capture method. This feature also allows bigger + receive buffers. To take advantage of this method who have to use + a libpcap library that supports it. For more info see + . If unsure, say N. @@ -10237,6 +10294,19 @@ say M here and read . The module will be called airo_cs.o. +Atmel at76c502/at76c504 PCMCIA cards +CONFIG_PCMCIA_ATMEL + A driver for PCMCIA 802.11 wireless cards based on the + Atmel fast-vnet chips. This driver supports standard + Linux wireless extensions. + + Many cards based on this chipset do not have flash memory + and need their firmware loaded at start-up. If yours is + one of these, you will need to provide a firmware image + to be loaded into the card by the driver. The Atmel + firmware package can be downloaded from + http://www.thekelleys.org.uk/atmel/atmel_firmware.tar.gz + Aviator/Raytheon 2.4MHz wireless support CONFIG_PCMCIA_RAYCS Say Y here if you intend to attach an Aviator/Raytheon PCMCIA @@ -10770,6 +10840,14 @@ whenever you want). If you want to compile it as a module, say M here and read . +Network delay simualtor +CONFIG_NET_SCH_DELAY + Say Y if you want to delay packets by a fixed amount of + time. This is often useful to simulate network delay when + testing applications or protocols. + + This code is also available as a module called sch_delay.o + Ingress Qdisc CONFIG_NET_SCH_INGRESS If you say Y here, you will be able to police incoming bandwidth @@ -12358,6 +12436,16 @@ . The module will be called b44. +nForce Ethernet support (EXPERIMENTAL) +CONFIG_FORCEDETH + If you have a network (Ethernet) controller of this type, say Y and + read the Ethernet-HOWTO, available from + . + + To compile this driver as a module, choose M here and read + . The module will be + called forcedeth.o. + CS89x0 support (Daynaport CS and LC cards) CONFIG_CS89x0 Support for CS89x0 chipset based Ethernet cards. If you have a @@ -19919,14 +20007,6 @@ of verbosity. Saying Y enables these statements. This will increase your kernel size by around 50K. -ACPI Relaxed AML Checking -CONFIG_ACPI_RELAXED_AML - If you say `Y' here, the ACPI interpreter will relax its checking - for valid AML and will ignore some AML mistakes, such as off-by-one - errors in region sizes. Some laptops may require this option. In - particular, many Toshiba laptops require this for correct operation - of the AC module. - ACPI Button CONFIG_ACPI_BUTTON This driver registers for events based on buttons, such as the @@ -23541,7 +23621,7 @@ If you have the BSC Oktagon SCSI disk controller for the Amiga, say Y to this question. If you're in doubt about whether you have one, see the picture at - . + . Atari native SCSI support CONFIG_ATARI_SCSI @@ -28701,6 +28781,13 @@ The CAST6 encryption algorithm (synonymous with CAST-256) is described in RFC2612. +CONFIG_CRYPTO_ARC4 + ARC4 cipher algorithm. + + This is a stream cipher using keys ranging from 8 bits to 2048 + bits in length. ARC4 is commonly used in protocols such as WEP + and SSL. + CONFIG_CRYPTO_DEFLATE This is the Deflate algorithm (RFC1951), specified for use in IPSec with the IPCOMP protocol (RFC3173, RFC2394). diff -urN linux-2.4.25/Documentation/crypto/api-intro.txt linux-2.4.26/Documentation/crypto/api-intro.txt --- linux-2.4.25/Documentation/crypto/api-intro.txt 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/Documentation/crypto/api-intro.txt 2004-04-14 06:05:24.000000000 -0700 @@ -185,6 +185,8 @@ Matthew Skala (Twofish) Dag Arne Osvik (Serpent) Brian Gladman (AES) + Kartikey Mahendra Bhatt (CAST6) + Jon Oberheide (ARC4) SHA1 algorithm contributors: Jean-Francois Dive diff -urN linux-2.4.25/Documentation/kernel-parameters.txt linux-2.4.26/Documentation/kernel-parameters.txt --- linux-2.4.25/Documentation/kernel-parameters.txt 2003-11-28 10:26:19.000000000 -0800 +++ linux-2.4.26/Documentation/kernel-parameters.txt 2004-04-14 06:05:24.000000000 -0700 @@ -73,16 +73,21 @@ off Disable ACPI ht Limit ACPI to boot-time LAPIC enumeration for HT, disabling the run-time AML interpreter. + strict Be less tolerant of platforms that are not + strictly ACPI specification compliant. - acpi_pic_sci= [HW,ACPI] ACPI System Conrol Interrupt trigger mode - level Force PIC-mode SCI to Level Trigger (default) - edge Force PIC-mode SCI to Edge Trigger + acpi_sci= [HW,ACPI] ACPI System Control Interrupt trigger mode + Format: { level | edge | high | low } acpi_irq_balance ACPI will balance active IRQs acpi_irq_nobalance ACPI will not move active IRQs acpi_irq_pci= If irq_balance, Clear listed IRQs for use by PCI acpi_irq_isa= If irq_balance, Mark listed IRQs used by ISA + acpi_osi= [HW,ACPI] empty param disables _OSI + + acpi_serialize [HW,ACPI] force serialization of AML methods + ad1816= [HW,SOUND] ad1848= [HW,SOUND] diff -urN linux-2.4.25/Documentation/networking/bonding.txt linux-2.4.26/Documentation/networking/bonding.txt --- linux-2.4.25/Documentation/networking/bonding.txt 2003-11-28 10:26:19.000000000 -0800 +++ linux-2.4.26/Documentation/networking/bonding.txt 2004-04-14 06:05:25.000000000 -0700 @@ -21,7 +21,7 @@ Table of Contents ================= - + Installation Bond Configuration Module Parameters @@ -31,6 +31,7 @@ Frequently Asked Questions High Availability Promiscuous Sniffing notes +8021q VLAN support Limitations Resources and Links @@ -66,7 +67,7 @@ /usr/include/linux. To install ifenslave.c, do: - # gcc -Wall -Wstrict-prototypes -O -I/usr/src/linux/include ifenslave.c -o ifenslave + # gcc -Wall -Wstrict-prototypes -O -I/usr/src/linux/include ifenslave.c -o ifenslave # cp ifenslave /sbin/ifenslave @@ -74,10 +75,10 @@ ================== You will need to add at least the following line to /etc/modules.conf -so the bonding driver will automatically load when the bond0 interface is -configured. Refer to the modules.conf manual page for specific modules.conf -syntax details. The Module Parameters section of this document describes each -bonding driver parameter. +so the bonding driver will automatically load when the bond0 interface is +configured. Refer to the modules.conf manual page for specific modules.conf +syntax details. The Module Parameters section of this document describes each +bonding driver parameter. alias bond0 bonding @@ -113,7 +114,7 @@ network interface be a slave of bond1. Restart the networking subsystem or just bring up the bonding device if your -administration tools allow it. Otherwise, reboot. On Red Hat distros you can +administration tools allow it. Otherwise, reboot. On Red Hat distros you can issue `ifup bond0' or `/etc/rc.d/init.d/network restart'. If the administration tools of your distribution do not support @@ -128,30 +129,26 @@ (use appropriate values for your network above) -You can then create a script containing these commands and place it in the +You can then create a script containing these commands and place it in the appropriate rc directory. If you specifically need all network drivers loaded before the bonding driver, -adding the following line to modules.conf will cause the network driver for +adding the following line to modules.conf will cause the network driver for eth0 and eth1 to be loaded before the bonding driver. probeall bond0 eth0 eth1 bonding -Be careful not to reference bond0 itself at the end of the line, or modprobe +Be careful not to reference bond0 itself at the end of the line, or modprobe will die in an endless recursive loop. -To have device characteristics (such as MTU size) propagate to slave devices, -set the bond characteristics before enslaving the device. The characteristics -are propagated during the enslave process. - -If running SNMP agents, the bonding driver should be loaded before any network -drivers participating in a bond. This requirement is due to the the interface -index (ipAdEntIfIndex) being associated to the first interface found with a -given IP address. That is, there is only one ipAdEntIfIndex for each IP -address. For example, if eth0 and eth1 are slaves of bond0 and the driver for -eth0 is loaded before the bonding driver, the interface for the IP address -will be associated with the eth0 interface. This configuration is shown below, -the IP address 192.168.1.1 has an interface index of 2 which indexes to eth0 +If running SNMP agents, the bonding driver should be loaded before any network +drivers participating in a bond. This requirement is due to the the interface +index (ipAdEntIfIndex) being associated to the first interface found with a +given IP address. That is, there is only one ipAdEntIfIndex for each IP +address. For example, if eth0 and eth1 are slaves of bond0 and the driver for +eth0 is loaded before the bonding driver, the interface for the IP address +will be associated with the eth0 interface. This configuration is shown below, +the IP address 192.168.1.1 has an interface index of 2 which indexes to eth0 in the ifDescr table (ifDescr.2). interfaces.ifTable.ifEntry.ifDescr.1 = lo @@ -189,10 +186,10 @@ Module Parameters ================= -Optional parameters for the bonding driver can be supplied as command line -arguments to the insmod command. Typically, these parameters are specified in -the file /etc/modules.conf (see the manual page for modules.conf). The -available bonding driver parameters are listed below. If a parameter is not +Optional parameters for the bonding driver can be supplied as command line +arguments to the insmod command. Typically, these parameters are specified in +the file /etc/modules.conf (see the manual page for modules.conf). The +available bonding driver parameters are listed below. If a parameter is not specified the default value is used. When initially configuring a bond, it is recommended "tail -f /var/log/messages" be run in a separate window to watch for bonding driver error messages. @@ -202,19 +199,19 @@ during link failures. arp_interval - - Specifies the ARP monitoring frequency in milli-seconds. - If ARP monitoring is used in a load-balancing mode (mode 0 or 2), the - switch should be configured in a mode that evenly distributes packets - across all links - such as round-robin. If the switch is configured to - distribute the packets in an XOR fashion, all replies from the ARP - targets will be received on the same link which could cause the other + + Specifies the ARP monitoring frequency in milli-seconds. + If ARP monitoring is used in a load-balancing mode (mode 0 or 2), the + switch should be configured in a mode that evenly distributes packets + across all links - such as round-robin. If the switch is configured to + distribute the packets in an XOR fashion, all replies from the ARP + targets will be received on the same link which could cause the other team members to fail. ARP monitoring should not be used in conjunction - with miimon. A value of 0 disables ARP monitoring. The default value + with miimon. A value of 0 disables ARP monitoring. The default value is 0. - + arp_ip_target - + Specifies the ip addresses to use when arp_interval is > 0. These are the targets of the ARP request sent to determine the health of the link to the targets. Specify these values in ddd.ddd.ddd.ddd @@ -223,8 +220,8 @@ maximum number of targets that can be specified is set at 16. downdelay - - Specifies the delay time in milli-seconds to disable a link after a + + Specifies the delay time in milli-seconds to disable a link after a link failure has been detected. This should be a multiple of miimon value, otherwise the value will be rounded. The default value is 0. @@ -247,7 +244,7 @@ and bond2 will be created. The default value is 1. miimon - + Specifies the frequency in milli-seconds that MII link monitoring will occur. A value of zero disables MII link monitoring. A value of 100 is a good starting point. See High Availability section for @@ -258,7 +255,7 @@ Specifies one of the bonding policies. The default is round-robin (balance-rr). Possible values are (you can use either the text or numeric option): - + balance-rr or 0 Round-robin policy: Transmit in a sequential order @@ -273,7 +270,7 @@ externally visible on only one port (network adapter) to avoid confusing the switch. This mode provides fault tolerance. - + balance-xor or 2 XOR policy: Transmit based on [(source MAC address @@ -293,7 +290,7 @@ groups that share the same speed and duplex settings. Transmits and receives on all slaves in the active aggregator. - + Pre-requisites: 1. Ethtool support in the base drivers for retrieving the @@ -317,7 +314,7 @@ Ethtool support in the base drivers for retrieving the speed of each slave. - balance-alb or 6 + balance-alb or 6 Adaptive load balancing: includes balance-tlb + receive load balancing (rlb) for IPV4 traffic and does not require @@ -327,7 +324,7 @@ overwrites the src hw address with the unique hw address of one of the slaves in the bond such that different clients use different hw addresses for the server. - + Receive traffic from connections created by the server is also balanced. When the server sends an ARP Request the bonding driver copies and saves the client's IP information @@ -363,25 +360,11 @@ 2. Base driver support for setting the hw address of a device also when it is open. This is required so that there will always be one slave in the team using the bond hw - address (the current_slave) while having a unique hw - address for each slave in the bond. If the current_slave - fails it's hw address is swapped with the new current_slave + address (the curr_active_slave) while having a unique hw + address for each slave in the bond. If the curr_active_slave + fails it's hw address is swapped with the new curr_active_slave that was chosen. -multicast - - Option specifying the mode of operation for multicast support. - Possible values are: - - disabled or 0 - Disabled (no multicast support) - - active or 1 - Enabled on active slave only, useful in active-backup mode - - all or 2 - Enabled on all slaves, this is the default - primary A string (eth0, eth2, etc) to equate to a primary device. If this @@ -397,11 +380,11 @@ primary is only valid in active-backup mode. updelay - - Specifies the delay time in milli-seconds to enable a link after a + + Specifies the delay time in milli-seconds to enable a link after a link up status has been detected. This should be a multiple of miimon value, otherwise the value will be rounded. The default value is 0. - + use_carrier Specifies whether or not miimon should use MII or ETHTOOL @@ -529,20 +512,20 @@ ---------------------------- The bonding driver information files reside in the /proc/net/bonding directory. -Sample contents of /proc/net/bonding/bond0 after the driver is loaded with +Sample contents of /proc/net/bonding/bond0 after the driver is loaded with parameters of mode=0 and miimon=1000 is shown below. - + Bonding Mode: load balancing (round-robin) Currently Active Slave: eth0 MII Status: up MII Polling Interval (ms): 1000 Up Delay (ms): 0 Down Delay (ms): 0 - + Slave Interface: eth1 MII Status: up Link Failure Count: 1 - + Slave Interface: eth0 MII Status: up Link Failure Count: 1 @@ -550,34 +533,34 @@ 2) Network verification ----------------------- The network configuration can be verified using the ifconfig command. In -the example below, the bond0 interface is the master (MASTER) while eth0 and -eth1 are slaves (SLAVE). Notice all slaves of bond0 have the same MAC address +the example below, the bond0 interface is the master (MASTER) while eth0 and +eth1 are slaves (SLAVE). Notice all slaves of bond0 have the same MAC address (HWaddr) as bond0 for all modes except TLB and ALB that require a unique MAC address for each slave. [root]# /sbin/ifconfig -bond0 Link encap:Ethernet HWaddr 00:C0:F0:1F:37:B4 +bond0 Link encap:Ethernet HWaddr 00:C0:F0:1F:37:B4 inet addr:XXX.XXX.XXX.YYY Bcast:XXX.XXX.XXX.255 Mask:255.255.252.0 UP BROADCAST RUNNING MASTER MULTICAST MTU:1500 Metric:1 RX packets:7224794 errors:0 dropped:0 overruns:0 frame:0 TX packets:3286647 errors:1 dropped:0 overruns:1 carrier:0 - collisions:0 txqueuelen:0 + collisions:0 txqueuelen:0 -eth0 Link encap:Ethernet HWaddr 00:C0:F0:1F:37:B4 +eth0 Link encap:Ethernet HWaddr 00:C0:F0:1F:37:B4 inet addr:XXX.XXX.XXX.YYY Bcast:XXX.XXX.XXX.255 Mask:255.255.252.0 UP BROADCAST RUNNING SLAVE MULTICAST MTU:1500 Metric:1 RX packets:3573025 errors:0 dropped:0 overruns:0 frame:0 TX packets:1643167 errors:1 dropped:0 overruns:1 carrier:0 - collisions:0 txqueuelen:100 - Interrupt:10 Base address:0x1080 + collisions:0 txqueuelen:100 + Interrupt:10 Base address:0x1080 -eth1 Link encap:Ethernet HWaddr 00:C0:F0:1F:37:B4 +eth1 Link encap:Ethernet HWaddr 00:C0:F0:1F:37:B4 inet addr:XXX.XXX.XXX.YYY Bcast:XXX.XXX.XXX.255 Mask:255.255.252.0 UP BROADCAST RUNNING SLAVE MULTICAST MTU:1500 Metric:1 RX packets:3651769 errors:0 dropped:0 overruns:0 frame:0 TX packets:1643480 errors:0 dropped:0 overruns:0 carrier:0 - collisions:0 txqueuelen:100 - Interrupt:9 Base address:0x1400 + collisions:0 txqueuelen:100 + Interrupt:9 Base address:0x1400 Frequently Asked Questions @@ -605,9 +588,9 @@ 5. What happens when a slave link dies? - If your ethernet cards support MII or ETHTOOL link status monitoring - and the MII monitoring has been enabled in the driver (see description - of module parameters), there will be no adverse consequences. This + If your ethernet cards support MII or ETHTOOL link status monitoring + and the MII monitoring has been enabled in the driver (see description + of module parameters), there will be no adverse consequences. This release of the bonding driver knows how to get the MII information and enables or disables its slaves according to their link status. See section on High Availability for additional information. @@ -615,15 +598,15 @@ For ethernet cards not supporting MII status, the arp_interval and arp_ip_target parameters must be specified for bonding to work correctly. If packets have not been sent or received during the - specified arp_interval durration, an ARP request is sent to the + specified arp_interval duration, an ARP request is sent to the targets to generate send and receive traffic. If after this interval, either the successful send and/or receive count has not incremented, the next slave in the sequence will become the active slave. If neither mii_monitor and arp_interval is configured, the bonding - driver will not handle this situation very well. The driver will - continue to send packets but some packets will be lost. Retransmits + driver will not handle this situation very well. The driver will + continue to send packets but some packets will be lost. Retransmits will cause serious degradation of performance (in the case when one of two slave links fails, 50% packets will be lost, which is a serious problem for both TCP and UDP). @@ -636,9 +619,9 @@ 7. Which switches/systems does it work with? - In round-robin and XOR mode, it works with systems that support + In round-robin and XOR mode, it works with systems that support trunking: - + * Many Cisco switches and routers (look for EtherChannel support). * SunTrunking software. * Alteon AceDirector switches / WebOS (use Trunks). @@ -646,7 +629,7 @@ models (450) can define trunks between ports on different physical units. * Linux bonding, of course ! - + In 802.3ad mode, it works with with systems that support IEEE 802.3ad Dynamic Link Aggregation: @@ -667,32 +650,24 @@ is then passed to all following slaves and remains persistent (even if the the first slave is removed) until the bonding device is brought down or reconfigured. - + If you wish to change the MAC address, you can set it with ifconfig: # ifconfig bond0 hw ether 00:11:22:33:44:55 The MAC address can be also changed by bringing down/up the device and then changing its slaves (or their order): - + # ifconfig bond0 down ; modprobe -r bonding # ifconfig bond0 .... up # ifenslave bond0 eth... This method will automatically take the address from the next slave that will be added. - - To restore your slaves' MAC addresses, you need to detach them - from the bond (`ifenslave -d bond0 eth0'), set them down - (`ifconfig eth0 down'), unload the drivers (`rmmod 3c59x', for - example) and reload them to get the MAC addresses from their - eeproms. If the driver is shared by several devices, you need - to turn them all down. Another solution is to look for the MAC - address at boot time (dmesg or tail /var/log/messages) and to - reset it by hand with ifconfig : - # ifconfig eth0 down - # ifconfig eth0 hw ether 00:20:40:60:80:A0 + To restore your slaves' MAC addresses, you need to detach them + from the bond (`ifenslave -d bond0 eth0'). The bonding driver will then + restore the MAC addresses that the slaves had before they were enslaved. 9. Which transmit polices can be used? @@ -729,27 +704,27 @@ ================= To implement high availability using the bonding driver, the driver needs to be -compiled as a module, because currently it is the only way to pass parameters +compiled as a module, because currently it is the only way to pass parameters to the driver. This may change in the future. -High availability is achieved by using MII or ETHTOOL status reporting. You -need to verify that all your interfaces support MII or ETHTOOL link status -reporting. On Linux kernel 2.2.17, all the 100 Mbps capable drivers and -yellowfin gigabit driver support MII. To determine if ETHTOOL link reporting -is available for interface eth0, type "ethtool eth0" and the "Link detected:" -line should contain the correct link status. If your system has an interface -that does not support MII or ETHTOOL status reporting, a failure of its link -will not be detected! A message indicating MII and ETHTOOL is not supported by -a network driver is logged when the bonding driver is loaded with a non-zero +High availability is achieved by using MII or ETHTOOL status reporting. You +need to verify that all your interfaces support MII or ETHTOOL link status +reporting. On Linux kernel 2.2.17, all the 100 Mbps capable drivers and +yellowfin gigabit driver support MII. To determine if ETHTOOL link reporting +is available for interface eth0, type "ethtool eth0" and the "Link detected:" +line should contain the correct link status. If your system has an interface +that does not support MII or ETHTOOL status reporting, a failure of its link +will not be detected! A message indicating MII and ETHTOOL is not supported by +a network driver is logged when the bonding driver is loaded with a non-zero miimon value. The bonding driver can regularly check all its slaves links using the ETHTOOL -IOCTL (ETHTOOL_GLINK command) or by checking the MII status registers. The -check interval is specified by the module argument "miimon" (MII monitoring). -It takes an integer that represents the checking time in milliseconds. It -should not come to close to (1000/HZ) (10 milli-seconds on i386) because it -may then reduce the system interactivity. A value of 100 seems to be a good -starting point. It means that a dead link will be detected at most 100 +IOCTL (ETHTOOL_GLINK command) or by checking the MII status registers. The +check interval is specified by the module argument "miimon" (MII monitoring). +It takes an integer that represents the checking time in milliseconds. It +should not come to close to (1000/HZ) (10 milli-seconds on i386) because it +may then reduce the system interactivity. A value of 100 seems to be a good +starting point. It means that a dead link will be detected at most 100 milli-seconds after it goes down. Example: @@ -761,7 +736,7 @@ alias bond0 bonding options bond0 miimon=100 -There are currently two policies for high availability. They are dependent on +There are currently two policies for high availability. They are dependent on whether: a) hosts are connected to a single host or switch that support trunking @@ -811,7 +786,7 @@ # ifenslave bond0 eth0 eth1 -2) High Availability on two or more switches (or a single switch without +2) High Availability on two or more switches (or a single switch without trunking support) --------------------------------------------------------------------------- This mode is more problematic because it relies on the fact that there @@ -857,7 +832,7 @@ In this configuration, there is an ISL - Inter Switch Link (could be a trunk), several servers (host1, host2 ...) attached to both switches each, and one or -more ports to the outside world (port3...). One an only one slave on each host +more ports to the outside world (port3...). One and only one slave on each host is active at a time, while all links are still monitored (the system can detect a failure of active and backup links). @@ -870,10 +845,10 @@ connected to one switch and host2's to the other. Such system will survive a failure of a single host, cable, or switch. The worst thing that may happen in the case of a switch failure is that half of the hosts will be temporarily -unreachable until the other switch expires its tables. +unreachable until the other switch expires its tables. Example 2: Using multiple ethernet cards connected to a switch to configure - NIC failover (switch is not required to support trunking). + NIC failover (switch is not required to support trunking). +----------+ +----------+ @@ -947,6 +922,41 @@ just ignore all the warnings it emits. +8021q VLAN support +================== + +It is possible to configure VLAN devices over a bond interface using the 8021q +driver. However, only packets coming from the 8021q driver and passing through +bonding will be tagged by default. Self generated packets, like bonding's +learning packets or ARP packets generated by either ALB mode or the ARP +monitor mechanism, are tagged internally by bonding itself. As a result, +bonding has to "learn" what VLAN IDs are configured on top of it, and it uses +those IDs to tag self generated packets. + +For simplicity reasons, and to support the use of adapters that can do VLAN +hardware acceleration offloding, the bonding interface declares itself as +fully hardware offloaing capable, it gets the add_vid/kill_vid notifications +to gather the necessary information, and it propagates those actions to the +slaves. +In case of mixed adapter types, hardware accelerated tagged packets that should +go through an adapter that is not offloading capable are "un-accelerated" by the +bonding driver so the VLAN tag sits in the regular location. + +VLAN interfaces *must* be added on top of a bonding interface only after +enslaving at least one slave. This is because until the first slave is added the +bonding interface has a HW address of 00:00:00:00:00:00, which will be copied by +the VLAN interface when it is created. + +Notice that a problem would occur if all slaves are released from a bond that +still has VLAN interfaces on top of it. When later coming to add new slaves, the +bonding interface would get a HW address from the first slave, which might not +match that of the VLAN interfaces. It is recommended that either all VLANs are +removed and then re-added, or to manually set the bonding interface's HW +address so it matches the VLAN's. (Note: changing a VLAN interface's HW address +would set the underlying device -- i.e. the bonding interface -- to promiscouos +mode, which might not be what you want). + + Limitations =========== The main limitations are : @@ -957,7 +967,7 @@ servers, but may be useful when the front switches send multicast information on their links (e.g. VRRP), or even health-check the servers. Use the arp_interval/arp_ip_target parameters to count incoming/outgoing - frames. + frames. diff -urN linux-2.4.25/Documentation/networking/ifenslave.c linux-2.4.26/Documentation/networking/ifenslave.c --- linux-2.4.25/Documentation/networking/ifenslave.c 2003-11-28 10:26:19.000000000 -0800 +++ linux-2.4.26/Documentation/networking/ifenslave.c 2004-04-14 06:05:25.000000000 -0700 @@ -4,8 +4,6 @@ * This program controls the Linux implementation of running multiple * network interfaces in parallel. * - * Usage: ifenslave [-v] master-interface < slave-interface [metric ] > ... - * * Author: Donald Becker * Copyright 1994-1996 Donald Becker * @@ -90,24 +88,30 @@ * - For opt_c: slave should not be set to the master's setting * while it is running. It was already set during enslave. To * simplify things, it is now handeled separately. + * + * - 2003/12/01 - Shmulik Hen + * - Code cleanup and style changes + * set version to 1.1.0 */ -#define APP_VERSION "1.0.12" -#define APP_RELDATE "June 30, 2003" +#define APP_VERSION "1.1.0" +#define APP_RELDATE "December 1, 2003" #define APP_NAME "ifenslave" static char *version = -APP_NAME ".c:v" APP_VERSION " (" APP_RELDATE ") " "\nDonald Becker (becker@cesdis.gsfc.nasa.gov).\n" -"detach support added on 2000/10/02 by Willy Tarreau (willy at meta-x.org).\n" -"2.4 kernel support added on 2001/02/16 by Chad N. Tindel (ctindel at ieee dot org.\n"; +APP_NAME ".c:v" APP_VERSION " (" APP_RELDATE ")\n" +"o Donald Becker (becker@cesdis.gsfc.nasa.gov).\n" +"o Detach support added on 2000/10/02 by Willy Tarreau (willy at meta-x.org).\n" +"o 2.4 kernel support added on 2001/02/16 by Chad N. Tindel\n" +" (ctindel at ieee dot org).\n"; static const char *usage_msg = -"Usage: ifenslave [-adfrvVh] < [metric ] > ...\n" -" ifenslave -c master-interface slave-if\n"; +"Usage: ifenslave [-f] [...]\n" +" ifenslave -d [...]\n" +" ifenslave -c \n" +" ifenslave --help\n"; -static const char *howto_msg = -"Usage: ifenslave [-adfrvVh] < [metric ] > ...\n" -" ifenslave -c master-interface slave-if\n" +static const char *help_msg = "\n" " To create a bond device, simply follow these three steps :\n" " - ensure that the required drivers are properly loaded :\n" @@ -115,18 +119,32 @@ " - assign an IP address to the bond device :\n" " # ifconfig bond0 netmask broadcast \n" " - attach all the interfaces you need to the bond device :\n" -" # ifenslave bond0 eth0 eth1 eth2\n" +" # ifenslave [{-f|--force}] bond0 eth0 [eth1 [eth2]...]\n" " If bond0 didn't have a MAC address, it will take eth0's. Then, all\n" " interfaces attached AFTER this assignment will get the same MAC addr.\n" -"\n" -" To detach a dead interface without setting the bond device down :\n" -" # ifenslave -d bond0 eth1\n" +" (except for ALB/TLB modes)\n" "\n" " To set the bond device down and automatically release all the slaves :\n" " # ifconfig bond0 down\n" "\n" +" To detach a dead interface without setting the bond device down :\n" +" # ifenslave {-d|--detach} bond0 eth0 [eth1 [eth2]...]\n" +"\n" " To change active slave :\n" -" # ifenslave -c bond0 eth0\n" +" # ifenslave {-c|--change-active} bond0 eth0\n" +"\n" +" To show master interface info\n" +" # ifenslave bond0\n" +"\n" +" To show all interfaces info\n" +" # ifenslave {-a|--all-interfaces}\n" +"\n" +" To be more verbose\n" +" # ifenslave {-v|--verbose} ...\n" +"\n" +" # ifenslave {-u|--usage} Show usage\n" +" # ifenslave {-V|--version} Show version\n" +" # ifenslave {-h|--help} This message\n" "\n"; #include @@ -153,476 +171,332 @@ #include struct option longopts[] = { - /* { name has_arg *flag val } */ - {"all-interfaces", 0, 0, 'a'}, /* Show all interfaces. */ - {"force", 0, 0, 'f'}, /* Force the operation. */ - {"help", 0, 0, '?'}, /* Give help */ - {"howto", 0, 0, 'h'}, /* Give some more help */ - {"receive-slave", 0, 0, 'r'}, /* Make a receive-only slave. */ - {"verbose", 0, 0, 'v'}, /* Report each action taken. */ - {"version", 0, 0, 'V'}, /* Emit version information. */ - {"detach", 0, 0, 'd'}, /* Detach a slave interface. */ - {"change-active", 0, 0, 'c'}, /* Change the active slave. */ - { 0, 0, 0, 0 } + /* { name has_arg *flag val } */ + {"all-interfaces", 0, 0, 'a'}, /* Show all interfaces. */ + {"change-active", 0, 0, 'c'}, /* Change the active slave. */ + {"detach", 0, 0, 'd'}, /* Detach a slave interface. */ + {"force", 0, 0, 'f'}, /* Force the operation. */ + {"help", 0, 0, 'h'}, /* Give help */ + {"usage", 0, 0, 'u'}, /* Give usage */ + {"verbose", 0, 0, 'v'}, /* Report each action taken. */ + {"version", 0, 0, 'V'}, /* Emit version information. */ + { 0, 0, 0, 0} }; /* Command-line flags. */ unsigned int -opt_a = 0, /* Show-all-interfaces flag. */ -opt_f = 0, /* Force the operation. */ -opt_r = 0, /* Set up a Rx-only slave. */ -opt_d = 0, /* detach a slave interface. */ -opt_c = 0, /* change-active-slave flag. */ -verbose = 0, /* Verbose flag. */ -opt_version = 0, -opt_howto = 0; -int skfd = -1; /* AF_INET socket for ioctl() calls. */ +opt_a = 0, /* Show-all-interfaces flag. */ +opt_c = 0, /* Change-active-slave flag. */ +opt_d = 0, /* Detach a slave interface. */ +opt_f = 0, /* Force the operation. */ +opt_h = 0, /* Help */ +opt_u = 0, /* Usage */ +opt_v = 0, /* Verbose flag. */ +opt_V = 0; /* Version */ + +int skfd = -1; /* AF_INET socket for ioctl() calls.*/ +int abi_ver = 0; /* userland - kernel ABI version */ +int hwaddr_set = 0; /* Master's hwaddr is set */ +int saved_errno; + +struct ifreq master_mtu, master_flags, master_hwaddr; +struct ifreq slave_mtu, slave_flags, slave_hwaddr; + +struct dev_ifr { + struct ifreq *req_ifr; + char *req_name; + int req_type; +}; + +struct dev_ifr master_ifra[] = { + {&master_mtu, "SIOCGIFMTU", SIOCGIFMTU}, + {&master_flags, "SIOCGIFFLAGS", SIOCGIFFLAGS}, + {&master_hwaddr, "SIOCGIFHWADDR", SIOCGIFHWADDR}, + {NULL, "", 0} +}; + +struct dev_ifr slave_ifra[] = { + {&slave_mtu, "SIOCGIFMTU", SIOCGIFMTU}, + {&slave_flags, "SIOCGIFFLAGS", SIOCGIFFLAGS}, + {&slave_hwaddr, "SIOCGIFHWADDR", SIOCGIFHWADDR}, + {NULL, "", 0} +}; static void if_print(char *ifname); -static int get_abi_ver(char *master_ifname); +static int get_drv_info(char *master_ifname); +static int get_if_settings(char *ifname, struct dev_ifr ifra[]); +static int get_slave_flags(char *slave_ifname); +static int set_master_hwaddr(char *master_ifname, struct sockaddr *hwaddr); +static int set_slave_hwaddr(char *slave_ifname, struct sockaddr *hwaddr); +static int set_slave_mtu(char *slave_ifname, int mtu); +static int set_if_flags(char *ifname, short flags); +static int set_if_up(char *ifname, short flags); +static int set_if_down(char *ifname, short flags); +static int clear_if_addr(char *ifname); +static int set_if_addr(char *master_ifname, char *slave_ifname); +static int change_active(char *master_ifname, char *slave_ifname); +static int enslave(char *master_ifname, char *slave_ifname); +static int release(char *master_ifname, char *slave_ifname); +#define v_print(fmt, args...) \ + if (opt_v) \ + fprintf(stderr, fmt, ## args ) -int -main(int argc, char **argv) +int main(int argc, char *argv[]) { - struct ifreq ifr2, if_hwaddr, if_ipaddr, if_metric, if_mtu, if_dstaddr; - struct ifreq if_netmask, if_brdaddr, if_flags; - int rv, goterr = 0; - int c, errflag = 0; - sa_family_t master_family; char **spp, *master_ifname, *slave_ifname; - int hwaddr_notset; - int abi_ver = 0; + int c, i, rv; + int res = 0; + int exclusive = 0; - while ((c = getopt_long(argc, argv, "acdfrvV?h", longopts, 0)) != EOF) + while ((c = getopt_long(argc, argv, "acdfhuvV", longopts, 0)) != EOF) { switch (c) { - case 'a': opt_a++; break; - case 'f': opt_f++; break; - case 'r': opt_r++; break; - case 'd': opt_d++; break; - case 'c': opt_c++; break; - case 'v': verbose++; break; - case 'V': opt_version++; break; - case 'h': opt_howto++; break; - case '?': errflag++; - } + case 'a': opt_a++; exclusive++; break; + case 'c': opt_c++; exclusive++; break; + case 'd': opt_d++; exclusive++; break; + case 'f': opt_f++; exclusive++; break; + case 'h': opt_h++; exclusive++; break; + case 'u': opt_u++; exclusive++; break; + case 'v': opt_v++; break; + case 'V': opt_V++; exclusive++; break; - /* option check */ - if (opt_c) - if(opt_a || opt_f || opt_r || opt_d || verbose || opt_version || - opt_howto || errflag ) { + case '?': fprintf(stderr, usage_msg); - return 2; + res = 2; + goto out; } + } - if (errflag) { + /* options check */ + if (exclusive > 1) { fprintf(stderr, usage_msg); - return 2; + res = 2; + goto out; } - if (opt_howto) { - fprintf(stderr, howto_msg); - return 0; + if (opt_v || opt_V) { + printf(version); + if (opt_V) { + res = 0; + goto out; + } } - if (verbose || opt_version) { - printf(version); - if (opt_version) - exit(0); + if (opt_u) { + printf(usage_msg); + res = 0; + goto out; } - /* Open a basic socket. */ - if ((skfd = socket(AF_INET, SOCK_DGRAM,0)) < 0) { - perror("socket"); - exit(-1); + if (opt_h) { + printf(usage_msg); + printf(help_msg); + res = 0; + goto out; } - if (verbose) - fprintf(stderr, "DEBUG: argc=%d, optind=%d and argv[optind] is %s.\n", - argc, optind, argv[optind]); + /* Open a basic socket */ + if ((skfd = socket(AF_INET, SOCK_DGRAM, 0)) < 0) { + perror("socket"); + res = 1; + goto out; + } - /* No remaining args means show all interfaces. */ - if (optind == argc) { - if_print((char *)NULL); - (void) close(skfd); - exit(0); + if (opt_a) { + if (optind == argc) { + /* No remaining args */ + /* show all interfaces */ + if_print((char *)NULL); + goto out; + } else { + /* Just show usage */ + fprintf(stderr, usage_msg); + res = 2; + goto out; + } } - /* Copy the interface name. */ + /* Copy the interface name */ spp = argv + optind; master_ifname = *spp++; - slave_ifname = *spp++; - /* Check command line. */ - if (opt_c) { - char **tempp = spp; - if ((master_ifname == NULL)||(slave_ifname == NULL)||(*tempp++ != NULL)) { - fprintf(stderr, usage_msg); - (void) close(skfd); - return 2; - } + if (master_ifname == NULL) { + fprintf(stderr, usage_msg); + res = 2; + goto out; } - /* A single args means show the configuration for this interface. */ - if (slave_ifname == NULL) { - if_print(master_ifname); - (void) close(skfd); - exit(0); + /* exchange abi version with bonding module */ + res = get_drv_info(master_ifname); + if (res) { + fprintf(stderr, + "Master '%s': Error: handshake with driver failed. " + "Aborting\n", + master_ifname); + goto out; } - /* exchange abi version with bonding driver */ - abi_ver = get_abi_ver(master_ifname); - if (abi_ver < 0) { - (void) close(skfd); - exit(1); - } - - /* Get the vitals from the master interface. */ - { - struct ifreq *ifra[7] = { &if_ipaddr, &if_mtu, &if_dstaddr, - &if_brdaddr, &if_netmask, &if_flags, - &if_hwaddr }; - const char *req_name[7] = { - "IP address", "MTU", "destination address", - "broadcast address", "netmask", "status flags", - "hardware address" }; - const int ioctl_req_type[7] = { - SIOCGIFADDR, SIOCGIFMTU, SIOCGIFDSTADDR, - SIOCGIFBRDADDR, SIOCGIFNETMASK, SIOCGIFFLAGS, - SIOCGIFHWADDR }; - int i; - - for (i = 0; i < 7; i++) { - strncpy(ifra[i]->ifr_name, master_ifname, IFNAMSIZ); - if (ioctl(skfd, ioctl_req_type[i], ifra[i]) < 0) { - fprintf(stderr, - "Something broke getting the master's %s: %s.\n", - req_name[i], strerror(errno)); - } - } - - /* check if master is up; if not then fail any operation */ - if (!(if_flags.ifr_flags & IFF_UP)) { - fprintf(stderr, "Illegal operation; the specified master interface '%s' is not up.\n", master_ifname); - (void) close(skfd); - exit (1); - } + slave_ifname = *spp++; - hwaddr_notset = 1; /* assume master's address not set yet */ - for (i = 0; hwaddr_notset && (i < 6); i++) { - hwaddr_notset &= ((unsigned char *)if_hwaddr.ifr_hwaddr.sa_data)[i] == 0; + if (slave_ifname == NULL) { + if (opt_d || opt_c) { + fprintf(stderr, usage_msg); + res = 2; + goto out; } - /* The family '1' is ARPHRD_ETHER for ethernet. */ - if (if_hwaddr.ifr_hwaddr.sa_family != 1 && !opt_f) { - fprintf(stderr, "The specified master interface '%s' is not" - " ethernet-like.\n This program is designed to work" - " with ethernet-like network interfaces.\n" - " Use the '-f' option to force the operation.\n", - master_ifname); - (void) close(skfd); - exit (1); - } - master_family = if_hwaddr.ifr_hwaddr.sa_family; - if (verbose) { - unsigned char *hwaddr = (unsigned char *)if_hwaddr.ifr_hwaddr.sa_data; - printf("The current hardware address (SIOCGIFHWADDR) of %s is type %d " - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", master_ifname, - if_hwaddr.ifr_hwaddr.sa_family, hwaddr[0], hwaddr[1], - hwaddr[2], hwaddr[3], hwaddr[4], hwaddr[5]); - } + /* A single arg means show the + * configuration for this interface + */ + if_print(master_ifname); + goto out; } + res = get_if_settings(master_ifname, master_ifra); + if (res) { + /* Probably a good reason not to go on */ + fprintf(stderr, + "Master '%s': Error: get settings failed: %s. " + "Aborting\n", + master_ifname, strerror(res)); + goto out; + } - /* do this when enslaving interfaces */ - do { - if (opt_d) { /* detach a slave interface from the master */ - strncpy(if_flags.ifr_name, master_ifname, IFNAMSIZ); - strncpy(if_flags.ifr_slave, slave_ifname, IFNAMSIZ); - if ((ioctl(skfd, SIOCBONDRELEASE, &if_flags) < 0) && - (ioctl(skfd, BOND_RELEASE_OLD, &if_flags) < 0)) { - fprintf(stderr, "SIOCBONDRELEASE: cannot detach %s from %s. errno=%s.\n", - slave_ifname, master_ifname, strerror(errno)); - } - else if (abi_ver < 1) { - /* The driver is using an old ABI, so we'll set the interface - * down to avoid any conflicts due to same IP/MAC - */ - strncpy(ifr2.ifr_name, slave_ifname, IFNAMSIZ); - if (ioctl(skfd, SIOCGIFFLAGS, &ifr2) < 0) { - int saved_errno = errno; - fprintf(stderr, "SIOCGIFFLAGS on %s failed: %s\n", slave_ifname, - strerror(saved_errno)); - } - else { - ifr2.ifr_flags &= ~(IFF_UP | IFF_RUNNING); - if (ioctl(skfd, SIOCSIFFLAGS, &ifr2) < 0) { - int saved_errno = errno; - fprintf(stderr, "Shutting down interface %s failed: %s\n", - slave_ifname, strerror(saved_errno)); - } - } - } - } else if (opt_c) { /* change primary slave */ - strncpy(if_flags.ifr_name, master_ifname, IFNAMSIZ); - strncpy(if_flags.ifr_slave, slave_ifname, IFNAMSIZ); - if ((ioctl(skfd, SIOCBONDCHANGEACTIVE, &if_flags) < 0) && - (ioctl(skfd, BOND_CHANGE_ACTIVE_OLD, &if_flags) < 0)) { - fprintf(stderr, "SIOCBONDCHANGEACTIVE: %s.\n", strerror(errno)); - } - } else { /* attach a slave interface to the master */ - - strncpy(ifr2.ifr_name, slave_ifname, IFNAMSIZ); - if (ioctl(skfd, SIOCGIFFLAGS, &ifr2) < 0) { - int saved_errno = errno; - fprintf(stderr, "SIOCGIFFLAGS on %s failed: %s\n", slave_ifname, - strerror(saved_errno)); - (void) close(skfd); - return 1; - } - - if ((ifr2.ifr_flags & IFF_SLAVE) && !opt_r) { - fprintf(stderr, "%s is already a slave\n", slave_ifname); - (void) close(skfd); - return 1; - } - - /* if hwaddr_notset, assign the slave hw address to the master */ - if (hwaddr_notset) { - /* assign the slave hw address to the - * master since it currently does not - * have one; otherwise, slaves may - * have different hw addresses in - * active-backup mode as seen when enslaving - * using "ifenslave bond0 eth0 eth1" because - * hwaddr_notset is set outside this loop. - * TODO: put this and the "else" portion in - * a function. - */ - /* get the slaves MAC address */ - strncpy(if_hwaddr.ifr_name, slave_ifname, - IFNAMSIZ); - rv = ioctl(skfd, SIOCGIFHWADDR, &if_hwaddr); - if (-1 == rv) { - fprintf(stderr, "Could not get MAC " - "address of %s: %s\n", - slave_ifname, - strerror(errno)); - strncpy(if_hwaddr.ifr_name, - master_ifname, IFNAMSIZ); - goterr = 1; - } - - if (!goterr) { - if (abi_ver < 1) { - /* In ABI versions older than 1, the - * master's set_mac routine couldn't - * work if it was up, because it - * used the default ethernet set_mac - * function. - */ - /* bring master down */ - if_flags.ifr_flags &= ~IFF_UP; - if (ioctl(skfd, SIOCSIFFLAGS, - &if_flags) < 0) { - goterr = 1; - fprintf(stderr, - "Shutting down " - "interface %s failed: " - "%s\n", - master_ifname, - strerror(errno)); - } - } - - strncpy(if_hwaddr.ifr_name, - master_ifname, IFNAMSIZ); - if (ioctl(skfd, SIOCSIFHWADDR, - &if_hwaddr) < 0) { - fprintf(stderr, - "Could not set MAC " - "address of %s: %s\n", - master_ifname, - strerror(errno)); - goterr=1; - } else { - hwaddr_notset = 0; - } - - if (abi_ver < 1) { - /* bring master back up */ - if_flags.ifr_flags |= IFF_UP; - if (ioctl(skfd, SIOCSIFFLAGS, - &if_flags) < 0) { - fprintf(stderr, - "Bringing up interface " - "%s failed: %s\n", - master_ifname, - strerror(errno)); - } - } - } - } else if (abi_ver < 1) { /* if (hwaddr_notset) */ - - /* The driver is using an old ABI, so we'll set the interface - * down and assign the master's hwaddr to it - */ - if (ifr2.ifr_flags & IFF_UP) { - ifr2.ifr_flags &= ~IFF_UP; - if (ioctl(skfd, SIOCSIFFLAGS, &ifr2) < 0) { - int saved_errno = errno; - fprintf(stderr, "Shutting down interface %s failed: %s\n", - slave_ifname, strerror(saved_errno)); - } - } - - strncpy(if_hwaddr.ifr_name, slave_ifname, IFNAMSIZ); - if (ioctl(skfd, SIOCSIFHWADDR, &if_hwaddr) < 0) { - int saved_errno = errno; - fprintf(stderr, "SIOCSIFHWADDR on %s failed: %s\n", if_hwaddr.ifr_name, - strerror(saved_errno)); - if (saved_errno == EBUSY) - fprintf(stderr, " The slave device %s is busy: it must be" - " idle before running this command.\n", slave_ifname); - else if (saved_errno == EOPNOTSUPP) - fprintf(stderr, " The slave device you specified does not support" - " setting the MAC address.\n Your kernel likely does not" - " support slave devices.\n"); - else if (saved_errno == EINVAL) - fprintf(stderr, " The slave device's address type does not match" - " the master's address type.\n"); - } else { - if (verbose) { - unsigned char *hwaddr = if_hwaddr.ifr_hwaddr.sa_data; - printf("Slave's (%s) hardware address set to " - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", slave_ifname, - hwaddr[0], hwaddr[1], hwaddr[2], hwaddr[3], hwaddr[4], hwaddr[5]); - } - } - } + /* check if master is indeed a master; + * if not then fail any operation + */ + if (!(master_flags.ifr_flags & IFF_MASTER)) { + fprintf(stderr, + "Illegal operation; the specified interface '%s' " + "is not a master. Aborting\n", + master_ifname); + res = 1; + goto out; + } - if (*spp && !strcmp(*spp, "metric")) { - if (*++spp == NULL) { - fprintf(stderr, usage_msg); - (void) close(skfd); - exit(2); - } - if_metric.ifr_metric = atoi(*spp); - strncpy(if_metric.ifr_name, slave_ifname, IFNAMSIZ); - if (ioctl(skfd, SIOCSIFMETRIC, &if_metric) < 0) { - fprintf(stderr, "SIOCSIFMETRIC on %s: %s\n", slave_ifname, - strerror(errno)); - goterr = 1; - } - spp++; - } + /* check if master is up; if not then fail any operation */ + if (!(master_flags.ifr_flags & IFF_UP)) { + fprintf(stderr, + "Illegal operation; the specified master interface " + "'%s' is not up.\n", + master_ifname); + res = 1; + goto out; + } - if (strncpy(if_ipaddr.ifr_name, slave_ifname, IFNAMSIZ) <= 0 - || ioctl(skfd, SIOCSIFADDR, &if_ipaddr) < 0) { - fprintf(stderr, - "Something broke setting the slave's address: %s.\n", - strerror(errno)); - } else { - if (verbose) { - unsigned char *ipaddr = if_ipaddr.ifr_addr.sa_data; - printf("Set the slave's (%s) IP address to %d.%d.%d.%d.\n", - slave_ifname, ipaddr[0], ipaddr[1], ipaddr[2], ipaddr[3]); - } - } + /* Only for enslaving */ + if (!opt_c && !opt_d) { + sa_family_t master_family = master_hwaddr.ifr_hwaddr.sa_family; + unsigned char *hwaddr = + (unsigned char *)master_hwaddr.ifr_hwaddr.sa_data; - if (strncpy(if_mtu.ifr_name, slave_ifname, IFNAMSIZ) <= 0 - || ioctl(skfd, SIOCSIFMTU, &if_mtu) < 0) { - fprintf(stderr, "Something broke setting the slave MTU: %s.\n", - strerror(errno)); - } else { - if (verbose) - printf("Set the slave's (%s) MTU to %d.\n", slave_ifname, if_mtu.ifr_mtu); - } + /* The family '1' is ARPHRD_ETHER for ethernet. */ + if (master_family != 1 && !opt_f) { + fprintf(stderr, + "Illegal operation: The specified master " + "interface '%s' is not ethernet-like.\n " + "This program is designed to work with " + "ethernet-like network interfaces.\n " + "Use the '-f' option to force the " + "operation.\n", + master_ifname); + res = 1; + goto out; + } - if (strncpy(if_dstaddr.ifr_name, slave_ifname, IFNAMSIZ) <= 0 - || ioctl(skfd, SIOCSIFDSTADDR, &if_dstaddr) < 0) { - fprintf(stderr, "Error setting the slave (%s) with SIOCSIFDSTADDR: %s.\n", - slave_ifname, strerror(errno)); - } else { - if (verbose) { - unsigned char *ipaddr = if_dstaddr.ifr_dstaddr.sa_data; - printf("Set the slave's (%s) destination address to %d.%d.%d.%d.\n", - slave_ifname, ipaddr[0], ipaddr[1], ipaddr[2], ipaddr[3]); - } + /* Check master's hw addr */ + for (i = 0; i < 6; i++) { + if (hwaddr[i] != 0) { + hwaddr_set = 1; + break; } + } - if (strncpy(if_brdaddr.ifr_name, slave_ifname, IFNAMSIZ) <= 0 - || ioctl(skfd, SIOCSIFBRDADDR, &if_brdaddr) < 0) { - fprintf(stderr, - "Something broke setting the slave (%s) broadcast address: %s.\n", - slave_ifname, strerror(errno)); - } else { - if (verbose) { - unsigned char *ipaddr = if_brdaddr.ifr_broadaddr.sa_data; - printf("Set the slave's (%s) broadcast address to %d.%d.%d.%d.\n", - slave_ifname, ipaddr[0], ipaddr[1], ipaddr[2], ipaddr[3]); - } - } + if (hwaddr_set) { + v_print("current hardware address of master '%s' " + "is %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x, " + "type %d\n", + master_ifname, + hwaddr[0], hwaddr[1], + hwaddr[2], hwaddr[3], + hwaddr[4], hwaddr[5], + master_family); + } + } - if (strncpy(if_netmask.ifr_name, slave_ifname, IFNAMSIZ) <= 0 - || ioctl(skfd, SIOCSIFNETMASK, &if_netmask) < 0) { - fprintf(stderr, - "Something broke setting the slave (%s) netmask: %s.\n", - slave_ifname, strerror(errno)); - } else { - if (verbose) { - unsigned char *ipaddr = if_netmask.ifr_netmask.sa_data; - printf("Set the slave's (%s) netmask to %d.%d.%d.%d.\n", - slave_ifname, ipaddr[0], ipaddr[1], ipaddr[2], ipaddr[3]); + /* Accepts only one slave */ + if (opt_c) { + /* change active slave */ + res = get_slave_flags(slave_ifname); + if (res) { + fprintf(stderr, + "Slave '%s': Error: get flags failed. " + "Aborting\n", + slave_ifname); + goto out; + } + res = change_active(master_ifname, slave_ifname); + if (res) { + fprintf(stderr, + "Master '%s', Slave '%s': Error: " + "Change active failed\n", + master_ifname, slave_ifname); + } + } else { + /* Accept multiple slaves */ + do { + if (opt_d) { + /* detach a slave interface from the master */ + rv = get_slave_flags(slave_ifname); + if (rv) { + /* Can't work with this slave. */ + /* remember the error and skip it*/ + fprintf(stderr, + "Slave '%s': Error: get flags " + "failed. Skipping\n", + slave_ifname); + res = rv; + continue; } - } - - if (abi_ver < 1) { - - /* The driver is using an old ABI, so we'll set the interface - * up before enslaving it - */ - ifr2.ifr_flags |= IFF_UP; - if ((ifr2.ifr_flags &= ~(IFF_SLAVE | IFF_MASTER)) == 0 - || strncpy(ifr2.ifr_name, slave_ifname, IFNAMSIZ) <= 0 - || ioctl(skfd, SIOCSIFFLAGS, &ifr2) < 0) { - fprintf(stderr, - "Something broke setting the slave (%s) flags: %s.\n", - slave_ifname, strerror(errno)); - } else { - if (verbose) - printf("Set the slave's (%s) flags %4.4x.\n", - slave_ifname, if_flags.ifr_flags); + rv = release(master_ifname, slave_ifname); + if (rv) { + fprintf(stderr, + "Master '%s', Slave '%s': Error: " + "Release failed\n", + master_ifname, slave_ifname); + res = rv; } } else { - /* the bonding module takes care of setting the slave's mac address - * and opening its interface - */ - if (ifr2.ifr_flags & IFF_UP) { /* the interface will need to be down */ - ifr2.ifr_flags &= ~IFF_UP; - if (ioctl(skfd, SIOCSIFFLAGS, &ifr2) < 0) { - int saved_errno = errno; - fprintf(stderr, "Shutting down interface %s failed: %s\n", - slave_ifname, strerror(saved_errno)); - } + /* attach a slave interface to the master */ + rv = get_if_settings(slave_ifname, slave_ifra); + if (rv) { + /* Can't work with this slave. */ + /* remember the error and skip it*/ + fprintf(stderr, + "Slave '%s': Error: get " + "settings failed: %s. " + "Skipping\n", + slave_ifname, strerror(rv)); + res = rv; + continue; } - } - - /* Do the real thing */ - if (!opt_r) { - strncpy(if_flags.ifr_name, master_ifname, IFNAMSIZ); - strncpy(if_flags.ifr_slave, slave_ifname, IFNAMSIZ); - if ((ioctl(skfd, SIOCBONDENSLAVE, &if_flags) < 0) && - (ioctl(skfd, BOND_ENSLAVE_OLD, &if_flags) < 0)) { - fprintf(stderr, "SIOCBONDENSLAVE: %s.\n", strerror(errno)); + rv = enslave(master_ifname, slave_ifname); + if (rv) { + fprintf(stderr, + "Master '%s', Slave '%s': Error: " + "Enslave failed\n", + master_ifname, slave_ifname); + res = rv; } } - } - } while ( (slave_ifname = *spp++) != NULL); + } while ((slave_ifname = *spp++) != NULL); + } - /* Close the socket. */ - (void) close(skfd); +out: + if (skfd >= 0) { + close(skfd); + } - return(goterr); + return res; } static short mif_flags; @@ -631,35 +505,34 @@ static int if_getconfig(char *ifname) { struct ifreq ifr; - int metric, mtu; /* Parameters of the master interface. */ + int metric, mtu; /* Parameters of the master interface. */ struct sockaddr dstaddr, broadaddr, netmask; + unsigned char *hwaddr; strcpy(ifr.ifr_name, ifname); if (ioctl(skfd, SIOCGIFFLAGS, &ifr) < 0) return -1; mif_flags = ifr.ifr_flags; printf("The result of SIOCGIFFLAGS on %s is %x.\n", - ifname, ifr.ifr_flags); + ifname, ifr.ifr_flags); strcpy(ifr.ifr_name, ifname); if (ioctl(skfd, SIOCGIFADDR, &ifr) < 0) return -1; printf("The result of SIOCGIFADDR is %2.2x.%2.2x.%2.2x.%2.2x.\n", - ifr.ifr_addr.sa_data[0], ifr.ifr_addr.sa_data[1], - ifr.ifr_addr.sa_data[2], ifr.ifr_addr.sa_data[3]); + ifr.ifr_addr.sa_data[0], ifr.ifr_addr.sa_data[1], + ifr.ifr_addr.sa_data[2], ifr.ifr_addr.sa_data[3]); strcpy(ifr.ifr_name, ifname); if (ioctl(skfd, SIOCGIFHWADDR, &ifr) < 0) return -1; - { - /* Gotta convert from 'char' to unsigned for printf(). */ - unsigned char *hwaddr = (unsigned char *)ifr.ifr_hwaddr.sa_data; - printf("The result of SIOCGIFHWADDR is type %d " - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", - ifr.ifr_hwaddr.sa_family, hwaddr[0], hwaddr[1], - hwaddr[2], hwaddr[3], hwaddr[4], hwaddr[5]); - } + /* Gotta convert from 'char' to unsigned for printf(). */ + hwaddr = (unsigned char *)ifr.ifr_hwaddr.sa_data; + printf("The result of SIOCGIFHWADDR is type %d " + "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", + ifr.ifr_hwaddr.sa_family, hwaddr[0], hwaddr[1], + hwaddr[2], hwaddr[3], hwaddr[4], hwaddr[5]); strcpy(ifr.ifr_name, ifname); if (ioctl(skfd, SIOCGIFMETRIC, &ifr) < 0) { @@ -691,7 +564,7 @@ } else netmask = ifr.ifr_netmask; - return(0); + return 0; } static void if_print(char *ifname) @@ -705,15 +578,16 @@ ifc.ifc_len = sizeof(buff); ifc.ifc_buf = buff; if (ioctl(skfd, SIOCGIFCONF, &ifc) < 0) { - fprintf(stderr, "SIOCGIFCONF: %s\n", strerror(errno)); + perror("SIOCGIFCONF failed"); return; } ifr = ifc.ifc_req; for (i = ifc.ifc_len / sizeof(struct ifreq); --i >= 0; ifr++) { if (if_getconfig(ifr->ifr_name) < 0) { - fprintf(stderr, "%s: unknown interface.\n", - ifr->ifr_name); + fprintf(stderr, + "%s: unknown interface.\n", + ifr->ifr_name); continue; } @@ -721,16 +595,18 @@ /*ife_print(&ife);*/ } } else { - if (if_getconfig(ifname) < 0) - fprintf(stderr, "%s: unknown interface.\n", ifname); + if (if_getconfig(ifname) < 0) { + fprintf(stderr, + "%s: unknown interface.\n", ifname); + } } } -static int get_abi_ver(char *master_ifname) +static int get_drv_info(char *master_ifname) { struct ifreq ifr; struct ethtool_drvinfo info; - int abi_ver = 0; + char *endptr; memset(&ifr, 0, sizeof(ifr)); strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); @@ -739,24 +615,487 @@ info.cmd = ETHTOOL_GDRVINFO; strncpy(info.driver, "ifenslave", 32); snprintf(info.fw_version, 32, "%d", BOND_ABI_VERSION); - if (ioctl(skfd, SIOCETHTOOL, &ifr) >= 0) { - char *endptr; - abi_ver = strtoul(info.fw_version, &endptr, 0); - if (*endptr) { - fprintf(stderr, "Error: got invalid string as an ABI " - "version from the bonding module\n"); - return -1; + if (ioctl(skfd, SIOCETHTOOL, &ifr) < 0) { + if (errno == EOPNOTSUPP) { + goto out; } + + saved_errno = errno; + v_print("Master '%s': Error: get bonding info failed %s\n", + master_ifname, strerror(saved_errno)); + return 1; } - if (verbose) { - printf("ABI ver is %d\n", abi_ver); + abi_ver = strtoul(info.fw_version, &endptr, 0); + if (*endptr) { + v_print("Master '%s': Error: got invalid string as an ABI " + "version from the bonding module\n", + master_ifname); + return 1; } - return abi_ver; + +out: + v_print("ABI ver is %d\n", abi_ver); + + return 0; } +static int change_active(char *master_ifname, char *slave_ifname) +{ + struct ifreq ifr; + int res = 0; + if (!(slave_flags.ifr_flags & IFF_SLAVE)) { + fprintf(stderr, + "Illegal operation: The specified slave interface " + "'%s' is not a slave\n", + slave_ifname); + return 1; + } + + strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); + strncpy(ifr.ifr_slave, slave_ifname, IFNAMSIZ); + if ((ioctl(skfd, SIOCBONDCHANGEACTIVE, &ifr) < 0) && + (ioctl(skfd, BOND_CHANGE_ACTIVE_OLD, &ifr) < 0)) { + saved_errno = errno; + v_print("Master '%s': Error: SIOCBONDCHANGEACTIVE failed: " + "%s\n", + master_ifname, strerror(saved_errno)); + res = 1; + } + + return res; +} + +static int enslave(char *master_ifname, char *slave_ifname) +{ + struct ifreq ifr; + int res = 0; + + if (slave_flags.ifr_flags & IFF_SLAVE) { + fprintf(stderr, + "Illegal operation: The specified slave interface " + "'%s' is already a slave\n", + slave_ifname); + return 1; + } + + res = set_if_down(slave_ifname, slave_flags.ifr_flags); + if (res) { + fprintf(stderr, + "Slave '%s': Error: bring interface down failed\n", + slave_ifname); + return res; + } + + if (abi_ver < 2) { + /* Older bonding versions would panic if the slave has no IP + * address, so get the IP setting from the master. + */ + res = set_if_addr(master_ifname, slave_ifname); + if (res) { + fprintf(stderr, + "Slave '%s': Error: set address failed\n", + slave_ifname); + return res; + } + } else { + res = clear_if_addr(slave_ifname); + if (res) { + fprintf(stderr, + "Slave '%s': Error: clear address failed\n", + slave_ifname); + return res; + } + } + + if (master_mtu.ifr_mtu != slave_mtu.ifr_mtu) { + res = set_slave_mtu(slave_ifname, master_mtu.ifr_mtu); + if (res) { + fprintf(stderr, + "Slave '%s': Error: set MTU failed\n", + slave_ifname); + return res; + } + } + + if (hwaddr_set) { + /* Master already has an hwaddr + * so set it's hwaddr to the slave + */ + if (abi_ver < 1) { + /* The driver is using an old ABI, so + * the application sets the slave's + * hwaddr + */ + res = set_slave_hwaddr(slave_ifname, + &(master_hwaddr.ifr_hwaddr)); + if (res) { + fprintf(stderr, + "Slave '%s': Error: set hw address " + "failed\n", + slave_ifname); + goto undo_mtu; + } + + /* For old ABI the application needs to bring the + * slave back up + */ + res = set_if_up(slave_ifname, slave_flags.ifr_flags); + if (res) { + fprintf(stderr, + "Slave '%s': Error: bring interface " + "down failed\n", + slave_ifname); + goto undo_slave_mac; + } + } + /* The driver is using a new ABI, + * so the driver takes care of setting + * the slave's hwaddr and bringing + * it up again + */ + } else { + /* No hwaddr for master yet, so + * set the slave's hwaddr to it + */ + if (abi_ver < 1) { + /* For old ABI, the master needs to be + * down before setting it's hwaddr + */ + res = set_if_down(master_ifname, master_flags.ifr_flags); + if (res) { + fprintf(stderr, + "Master '%s': Error: bring interface " + "down failed\n", + master_ifname); + goto undo_mtu; + } + } + + res = set_master_hwaddr(master_ifname, + &(slave_hwaddr.ifr_hwaddr)); + if (res) { + fprintf(stderr, + "Master '%s': Error: set hw address " + "failed\n", + master_ifname); + goto undo_mtu; + } + + if (abi_ver < 1) { + /* For old ABI, bring the master + * back up + */ + res = set_if_up(master_ifname, master_flags.ifr_flags); + if (res) { + fprintf(stderr, + "Master '%s': Error: bring interface " + "up failed\n", + master_ifname); + goto undo_master_mac; + } + } + + hwaddr_set = 1; + } + + /* Do the real thing */ + strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); + strncpy(ifr.ifr_slave, slave_ifname, IFNAMSIZ); + if ((ioctl(skfd, SIOCBONDENSLAVE, &ifr) < 0) && + (ioctl(skfd, BOND_ENSLAVE_OLD, &ifr) < 0)) { + saved_errno = errno; + v_print("Master '%s': Error: SIOCBONDENSLAVE failed: %s\n", + master_ifname, strerror(saved_errno)); + res = 1; + } + + if (res) { + goto undo_master_mac; + } + + return 0; + +/* rollback (best effort) */ +undo_master_mac: + set_master_hwaddr(master_ifname, &(master_hwaddr.ifr_hwaddr)); + hwaddr_set = 0; + goto undo_mtu; +undo_slave_mac: + set_slave_hwaddr(slave_ifname, &(slave_hwaddr.ifr_hwaddr)); +undo_mtu: + set_slave_mtu(slave_ifname, slave_mtu.ifr_mtu); + return res; +} + +static int release(char *master_ifname, char *slave_ifname) +{ + struct ifreq ifr; + int res = 0; + + if (!(slave_flags.ifr_flags & IFF_SLAVE)) { + fprintf(stderr, + "Illegal operation: The specified slave interface " + "'%s' is not a slave\n", + slave_ifname); + return 1; + } + + strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); + strncpy(ifr.ifr_slave, slave_ifname, IFNAMSIZ); + if ((ioctl(skfd, SIOCBONDRELEASE, &ifr) < 0) && + (ioctl(skfd, BOND_RELEASE_OLD, &ifr) < 0)) { + saved_errno = errno; + v_print("Master '%s': Error: SIOCBONDRELEASE failed: %s\n", + master_ifname, strerror(saved_errno)); + return 1; + } else if (abi_ver < 1) { + /* The driver is using an old ABI, so we'll set the interface + * down to avoid any conflicts due to same MAC/IP + */ + res = set_if_down(slave_ifname, slave_flags.ifr_flags); + if (res) { + fprintf(stderr, + "Slave '%s': Error: bring interface " + "down failed\n", + slave_ifname); + } + } + + /* set to default mtu */ + set_slave_mtu(slave_ifname, 1500); + + return res; +} + +static int get_if_settings(char *ifname, struct dev_ifr ifra[]) +{ + int i; + int res = 0; + + for (i = 0; ifra[i].req_ifr; i++) { + strncpy(ifra[i].req_ifr->ifr_name, ifname, IFNAMSIZ); + res = ioctl(skfd, ifra[i].req_type, ifra[i].req_ifr); + if (res < 0) { + saved_errno = errno; + v_print("Interface '%s': Error: %s failed: %s\n", + ifname, ifra[i].req_name, + strerror(saved_errno)); + + return saved_errno; + } + } + + return 0; +} + +static int get_slave_flags(char *slave_ifname) +{ + int res = 0; + + strncpy(slave_flags.ifr_name, slave_ifname, IFNAMSIZ); + res = ioctl(skfd, SIOCGIFFLAGS, &slave_flags); + if (res < 0) { + saved_errno = errno; + v_print("Slave '%s': Error: SIOCGIFFLAGS failed: %s\n", + slave_ifname, strerror(saved_errno)); + } else { + v_print("Slave %s: flags %04X.\n", + slave_ifname, slave_flags.ifr_flags); + } + + return res; +} + +static int set_master_hwaddr(char *master_ifname, struct sockaddr *hwaddr) +{ + unsigned char *addr = (unsigned char *)hwaddr->sa_data; + struct ifreq ifr; + int res = 0; + + strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); + memcpy(&(ifr.ifr_hwaddr), hwaddr, sizeof(struct sockaddr)); + res = ioctl(skfd, SIOCSIFHWADDR, &ifr); + if (res < 0) { + saved_errno = errno; + v_print("Master '%s': Error: SIOCSIFHWADDR failed: %s\n", + master_ifname, strerror(saved_errno)); + return res; + } else { + v_print("Master '%s': hardware address set to " + "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", + master_ifname, addr[0], addr[1], addr[2], + addr[3], addr[4], addr[5]); + } + + return res; +} + +static int set_slave_hwaddr(char *slave_ifname, struct sockaddr *hwaddr) +{ + unsigned char *addr = (unsigned char *)hwaddr->sa_data; + struct ifreq ifr; + int res = 0; + + strncpy(ifr.ifr_name, slave_ifname, IFNAMSIZ); + memcpy(&(ifr.ifr_hwaddr), hwaddr, sizeof(struct sockaddr)); + res = ioctl(skfd, SIOCSIFHWADDR, &ifr); + if (res < 0) { + saved_errno = errno; + + v_print("Slave '%s': Error: SIOCSIFHWADDR failed: %s\n", + slave_ifname, strerror(saved_errno)); + + if (saved_errno == EBUSY) { + v_print(" The device is busy: it must be idle " + "before running this command.\n"); + } else if (saved_errno == EOPNOTSUPP) { + v_print(" The device does not support setting " + "the MAC address.\n" + " Your kernel likely does not support slave " + "devices.\n"); + } else if (saved_errno == EINVAL) { + v_print(" The device's address type does not match " + "the master's address type.\n"); + } + return res; + } else { + v_print("Slave '%s': hardware address set to " + "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x.\n", + slave_ifname, addr[0], addr[1], addr[2], + addr[3], addr[4], addr[5]); + } + + return res; +} + +static int set_slave_mtu(char *slave_ifname, int mtu) +{ + struct ifreq ifr; + int res = 0; + + ifr.ifr_mtu = mtu; + strncpy(ifr.ifr_name, slave_ifname, IFNAMSIZ); + + res = ioctl(skfd, SIOCSIFMTU, &ifr); + if (res < 0) { + saved_errno = errno; + v_print("Slave '%s': Error: SIOCSIFMTU failed: %s\n", + slave_ifname, strerror(saved_errno)); + } else { + v_print("Slave '%s': MTU set to %d.\n", slave_ifname, mtu); + } + + return res; +} + +static int set_if_flags(char *ifname, short flags) +{ + struct ifreq ifr; + int res = 0; + + ifr.ifr_flags = flags; + strncpy(ifr.ifr_name, ifname, IFNAMSIZ); + + res = ioctl(skfd, SIOCSIFFLAGS, &ifr); + if (res < 0) { + saved_errno = errno; + v_print("Interface '%s': Error: SIOCSIFFLAGS failed: %s\n", + ifname, strerror(saved_errno)); + } else { + v_print("Interface '%s': flags set to %04X.\n", ifname, flags); + } + + return res; +} + +static int set_if_up(char *ifname, short flags) +{ + return set_if_flags(ifname, flags | IFF_UP); +} + +static int set_if_down(char *ifname, short flags) +{ + return set_if_flags(ifname, flags & ~IFF_UP); +} + +static int clear_if_addr(char *ifname) +{ + struct ifreq ifr; + int res = 0; + + strncpy(ifr.ifr_name, ifname, IFNAMSIZ); + ifr.ifr_addr.sa_family = AF_INET; + memset(ifr.ifr_addr.sa_data, 0, sizeof(ifr.ifr_addr.sa_data)); + + res = ioctl(skfd, SIOCSIFADDR, &ifr); + if (res < 0) { + saved_errno = errno; + v_print("Interface '%s': Error: SIOCSIFADDR failed: %s\n", + ifname, strerror(saved_errno)); + } else { + v_print("Interface '%s': address cleared\n", ifname); + } + + return res; +} + +static int set_if_addr(char *master_ifname, char *slave_ifname) +{ + struct ifreq ifr; + int res; + unsigned char *ipaddr; + int i; + struct { + char *req_name; + char *desc; + int g_ioctl; + int s_ioctl; + } ifra[] = { + {"IFADDR", "addr", SIOCGIFADDR, SIOCSIFADDR}, + {"DSTADDR", "destination addr", SIOCGIFDSTADDR, SIOCSIFDSTADDR}, + {"BRDADDR", "broadcast addr", SIOCGIFBRDADDR, SIOCSIFBRDADDR}, + {"NETMASK", "netmask", SIOCGIFNETMASK, SIOCSIFNETMASK}, + {NULL, NULL, 0, 0}, + }; + + for (i = 0; ifra[i].req_name; i++) { + strncpy(ifr.ifr_name, master_ifname, IFNAMSIZ); + res = ioctl(skfd, ifra[i].g_ioctl, &ifr); + if (res < 0) { + int saved_errno = errno; + + v_print("Interface '%s': Error: SIOCG%s failed: %s\n", + master_ifname, ifra[i].req_name, + strerror(saved_errno)); + + ifr.ifr_addr.sa_family = AF_INET; + memset(ifr.ifr_addr.sa_data, 0, + sizeof(ifr.ifr_addr.sa_data)); + } + + strncpy(ifr.ifr_name, slave_ifname, IFNAMSIZ); + res = ioctl(skfd, ifra[i].s_ioctl, &ifr); + if (res < 0) { + int saved_errno = errno; + + v_print("Interface '%s': Error: SIOCS%s failed: %s\n", + slave_ifname, ifra[i].req_name, + strerror(saved_errno)); + + return res; + } + + ipaddr = ifr.ifr_addr.sa_data; + v_print("Interface '%s': set IP %s to %d.%d.%d.%d\n", + slave_ifname, ifra[i].desc, + ipaddr[0], ipaddr[1], ipaddr[2], ipaddr[3]); + } + + return 0; +} /* * Local variables: @@ -768,3 +1107,4 @@ * compile-command: "gcc -Wall -Wstrict-prototypes -O -I/usr/src/linux/include ifenslave.c -o ifenslave" * End: */ + diff -urN linux-2.4.25/Documentation/networking/ip-sysctl.txt linux-2.4.26/Documentation/networking/ip-sysctl.txt --- linux-2.4.25/Documentation/networking/ip-sysctl.txt 2003-06-13 07:51:29.000000000 -0700 +++ linux-2.4.26/Documentation/networking/ip-sysctl.txt 2004-04-14 06:05:25.000000000 -0700 @@ -481,6 +481,55 @@ conf/{all,interface}/arp_filter is set to TRUE, it will be disabled otherwise +arp_announce - INTEGER + Define different restriction levels for announcing the local + source IP address from IP packets in ARP requests sent on + interface: + 0 - (default) Use any local address, configured on any interface + 1 - Try to avoid local addresses that are not in the target's + subnet for this interface. This mode is useful when target + hosts reachable via this interface require the source IP + address in ARP requests to be part of their logical network + configured on the receiving interface. When we generate the + request we will check all our subnets that include the + target IP and will preserve the source address if it is from + such subnet. If there is no such subnet we select source + address according to the rules for level 2. + 2 - Always use the best local address for this target. + In this mode we ignore the source address in the IP packet + and try to select local address that we prefer for talks with + the target host. Such local address is selected by looking + for primary IP addresses on all our subnets on the outgoing + interface that include the target IP address. If no suitable + local address is found we select the first local address + we have on the outgoing interface or on all other interfaces, + with the hope we will receive reply for our request and + even sometimes no matter the source IP address we announce. + + The max value from conf/{all,interface}/arp_announce is used. + + Increasing the restriction level gives more chance for + receiving answer from the resolved target while decreasing + the level announces more valid sender's information. + +arp_ignore - INTEGER + Define different modes for sending replies in response to + received ARP requests that resolve local target IP addresses: + 0 - (default): reply for any local target IP address, configured + on any interface + 1 - reply only if the target IP address is local address + configured on the incoming interface + 2 - reply only if the target IP address is local address + configured on the incoming interface and both with the + sender's IP address are part from same subnet on this interface + 3 - do not reply for local addresses configured with scope host, + only resolutions for global and link addresses are replied + 4-7 - reserved + 8 - do not reply for all local addresses + + The max value from conf/{all,interface}/arp_ignore is used + when ARP request is received on the {interface} + tag - INTEGER Allows you to write a number, which can be used as required. Default value is 0. diff -urN linux-2.4.25/Documentation/networking/packet_mmap.txt linux-2.4.26/Documentation/networking/packet_mmap.txt --- linux-2.4.25/Documentation/networking/packet_mmap.txt 1969-12-31 16:00:00.000000000 -0800 +++ linux-2.4.26/Documentation/networking/packet_mmap.txt 2004-04-14 06:05:25.000000000 -0700 @@ -0,0 +1,412 @@ + +DaveM: + +If you agree with it I will send two small patches to modify +kernel's configure help. + + Ulisses + +-------------------------------------------------------------------------------- ++ ABSTRACT +-------------------------------------------------------------------------------- + +This file documents the CONFIG_PACKET_MMAP option available with the PACKET +socket interface on 2.4 and 2.6 kernels. This type of sockets is used for +capture network traffic with utilities like tcpdump or any other that uses +the libpcap library. + +You can find the latest version of this document at + + http://pusa.uv.es/~ulisses/packet_mmap/ + +Please send me your comments to + + Ulisses Alonso Camaró + +------------------------------------------------------------------------------- ++ Why use PACKET_MMAP +-------------------------------------------------------------------------------- + +In Linux 2.4/2.6 if PACKET_MMAP is not enabled, the capture process is very +inefficient. It uses very limited buffers and requires one system call +to capture each packet, it requires two if you want to get packet's +timestamp (like libpcap always does). + +In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size +configurable circular buffer mapped in user space. This way reading packets just +needs to wait for them, most of the time there is no need to issue a single +system call. By using a shared buffer between the kernel and the user +also has the benefit of minimizing packet copies. + +It's fine to use PACKET_MMAP to improve the performance of the capture process, +but it isn't everything. At least, if you are capturing at high speeds (this +is relative to the cpu speed), you should check if the device driver of your +network interface card supports some sort of interrupt load mitigation or +(even better) if it supports NAPI, also make sure it is enabled. + +-------------------------------------------------------------------------------- ++ How to use CONFIG_PACKET_MMAP +-------------------------------------------------------------------------------- + +From the user standpoint, you should use the higher level libpcap library, wich +is a de facto standard, portable across nearly all operating systems +including Win32. + +Said that, at time of this writing, official libpcap 0.8.1 is out and doesn't include +support for PACKET_MMAP, and also probably the libpcap included in your distribution. + +I'm aware of two implementations of PACKET_MMAP in libpcap: + + http://pusa.uv.es/~ulisses/packet_mmap/ (by Simon Patarin, based on libpcap 0.6.2) + http://public.lanl.gov/cpw/ (by Phil Wood, based on lastest libpcap) + +The rest of this document is intended for people who want to understand +the low level details or want to improve libpcap by including PACKET_MMAP +support. + +-------------------------------------------------------------------------------- ++ How to use CONFIG_PACKET_MMAP directly +-------------------------------------------------------------------------------- + +From the system calls stand point, the use of PACKET_MMAP involves +the following process: + + +[setup] socket() -------> creation of the capture socket + setsockopt() ---> allocation of the circular buffer (ring) + mmap() ---------> maping of the allocated buffer to the + user process + +[capture] poll() ---------> to wait for incoming packets + +[shutdown] close() --------> destruction of the capture socket and + deallocation of all associated + resources. + + +socket creation and destruction is straight forward, and is done +the same way with or without PACKET_MMAP: + +int fd; + +fd= socket(PF_PACKET, mode, htons(ETH_P_ALL)) + +where mode is SOCK_RAW for the raw interface were link level +information can be captured or SOCK_DGRAM for the cooked +interface where link level information capture is not +supported and a link level pseudo-header is provided +by the kernel. + +The destruction of the socket and all associated resources +is done by a simple call to close(fd). + +Next I will describe PACKET_MMAP settings and it's constraints, +also the maping of the circular buffer in the user process and +the use of this buffer. + +-------------------------------------------------------------------------------- ++ PACKET_MMAP settings +-------------------------------------------------------------------------------- + + +To setup PACKET_MMAP from user level code is done with a call like + + setsockopt(fd, SOL_PACKET, PACKET_RX_RING, (void *) &req, sizeof(req)) + +The most significant argument in the previous call is the req parameter, +this parameter must to have the following structure: + + struct tpacket_req + { + unsigned int tp_block_size; /* Minimal size of contiguous block */ + unsigned int tp_block_nr; /* Number of blocks */ + unsigned int tp_frame_size; /* Size of frame */ + unsigned int tp_frame_nr; /* Total number of frames */ + }; + +This structure is defined in /usr/include/linux/if_packet.h and establishes a +circular buffer (ring) of unswappable memory mapped in the capture process. +Being mapped in the capture process allows reading the captured frames and +related meta-information like timestamps without requiring a system call. + +Captured frames are grouped in blocks. Each block is a physically contiguous +region of memory and holds tp_block_size/tp_frame_size frames. The total number +of blocks is tp_block_nr. Note that tp_frame_nr is a redundant parameter because + + frames_per_block = tp_block_size/tp_frame_size + +indeed, packet_set_ring checks that the following condition is true + + frames_per_block * tp_block_nr == tp_frame_nr + + +Lets see an example, with the following values: + + tp_block_size= 4096 + tp_frame_size= 2048 + tp_block_nr = 4 + tp_frame_nr = 8 + +we will get the following buffer structure: + + block #1 block #2 ++---------+---------+ +---------+---------+ +| frame 1 | frame 2 | | frame 3 | frame 4 | ++---------+---------+ +---------+---------+ + + block #3 block #4 ++---------+---------+ +---------+---------+ +| frame 5 | frame 6 | | frame 7 | frame 8 | ++---------+---------+ +---------+---------+ + +A frame can be of any size with the only condition it can fit in a block. A block +can only hold an integer number of frames, or in other words, a frame cannot +be spawn accross two blocks so there are some datails you have to take into +account when choosing the frame_size. See "Maping and use of the circular +buffer (ring)". + + +-------------------------------------------------------------------------------- ++ PACKET_MMAP setting constraints +-------------------------------------------------------------------------------- + +In kernel versions prior to 2.4.26 (for the 2.4 branch) and 2.6.5 (2.6 branch), +the PACKET_MMAP buffer could hold only 32768 frames in a 32 bit architecture or +16384 in a 64 bit architecture. For information on these kernel versions +see http://pusa.uv.es/~ulisses/packet_mmap/packet_mmap.pre-2.4.26_2.6.5.txt + + Block size limit +------------------ + +As stated earlier, each block is a contiguous physical region of memory. These +memory regions are allocated with calls to the __get_free_pages() function. As +the name indicates, this function allocates pages of memory, and the second +argument is "order" or a power of two number of pages, that is +(for PAGE_SIZE == 4096) order=0 ==> 4096 bytes, order=1 ==> 8192 bytes, +order=2 ==> 16384 bytes, etc. The maximum size of a +region allocated by __get_free_pages is determined by the MAX_ORDER macro. More +precisely the limit can be calculated as: + + PAGE_SIZE << MAX_ORDER + + In a i386 architecture PAGE_SIZE is 4096 bytes + In a 2.4/i386 kernel MAX_ORDER is 10 + In a 2.6/i386 kernel MAX_ORDER is 11 + +So get_free_pages can allocate as much as 4MB or 8MB in a 2.4/2.6 kernel +respectively, with an i386 architecture. + +User space programs can include /usr/include/sys/user.h and +/usr/include/linux/mmzone.h to get PAGE_SIZE MAX_ORDER declarations. + +The pagesize can also be determined dynamically with the getpagesize (2) +system call. + + + Block number limit +-------------------- + +To understand the constraints of PACKET_MMAP, we have to see the structure +used to hold the pointers to each block. + +Currently, this structure is a dynamically allocated vector with kmalloc +called pg_vec, its size limits the number of blocks that can be allocated. + + +---+---+---+---+ + | x | x | x | x | + +---+---+---+---+ + | | | | + | | | v + | | v block #4 + | v block #3 + v block #2 + block #1 + + +kmalloc allocates any number of bytes of phisically contiguous memory from +a pool of pre-determined sizes. This pool of memory is mantained by the slab +allocator wich is at the end the responsible for doing the allocation and +hence wich imposes the maximum memory that kmalloc can allocate. + +In a 2.4/2.6 kernel and the i386 architecture, the limit is 131072 bytes. The +predetermined sizes that kmalloc uses can be checked in the "size-" +entries of /proc/slabinfo + +In a 32 bit architecture, pointers are 4 bytes long, so the total number of +pointers to blocks is + + 131072/4 = 32768 blocks + + + PACKET_MMAP buffer size calculator +------------------------------------ + +Definitions: + + : is the maximum size of allocable with kmalloc (see /proc/slabinfo) +: depends on the architecture -- sizeof(void *) + : depends on the architecture -- PAGE_SIZE or getpagesize (2) + : is the value defined with MAX_ORDER + : it's an upper bound of frame's capture size (more on this later) + +from these definitions we will derive + + = / + = << + +so, the max buffer size is + + * + +and, the number of frames be + + * / + +Suposse the following parameters, wich apply for 2.6 kernel and an +i386 architecture: + + = 131072 bytes + = 4 bytes + = 4096 bytes + = 11 + +and a value for of 2048 byteas. These parameters will yield + + = 131072/4 = 32768 blocks + = 4096 << 11 = 8 MiB. + +and hence the buffer will have a 262144 MiB size. So it can hold +262144 MiB / 2048 bytes = 134217728 frames + + +Actually, this buffer size is not possible with an i386 architecture. +Remember that the memory is allocated in kernel space, in the case of +an i386 kernel's memory size is limited to 1GiB. + +All memory allocations are not freed until the socket is closed. The memory +allocations are done with GFP_KERNEL priority, this basically means that +the allocation can wait and swap other process' memory in order to allocate +the nececessary memory, so normally limits can be reached. + + Other constraints +------------------- + +If you check the source code you will see that what I draw here as a frame +is not only the link level frame. At the begining of each frame there is a +header called struct tpacket_hdr used in PACKET_MMAP to hold link level's frame +meta information like timestamp. So what we draw here a frame it's really +the following (from include/linux/if_packet.h): + +/* + Frame structure: + + - Start. Frame must be aligned to TPACKET_ALIGNMENT=16 + - struct tpacket_hdr + - pad to TPACKET_ALIGNMENT=16 + - struct sockaddr_ll + - Gap, chosen so that packet data (Start+tp_net) alignes to + TPACKET_ALIGNMENT=16 + - Start+tp_mac: [ Optional MAC header ] + - Start+tp_net: Packet data, aligned to TPACKET_ALIGNMENT=16. + - Pad to align to TPACKET_ALIGNMENT=16 + */ + + + The following are conditions that are checked in packet_set_ring + + tp_block_size must be a multiple of PAGE_SIZE (1) + tp_frame_size must be greater than TPACKET_HDRLEN (obvious) + tp_frame_size must be a multiple of TPACKET_ALIGNMENT + tp_frame_nr must be exactly frames_per_block*tp_block_nr + +Note that tp_block_size should be choosed to be a power of two or there will +be a waste of memory. + +-------------------------------------------------------------------------------- ++ Maping and use of the circular buffer (ring) +-------------------------------------------------------------------------------- + +The maping of the buffer in the user process is done with the conventional +mmap function. Even the circular buffer is compound of several physically +discontiguous blocks of memory, they are contiguous to the user space, hence +just one call to mmap is needed: + + mmap(0, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); + +If tp_frame_size is a divisor of tp_block_size frames will be +contiguosly spaced by tp_frame_size bytes. If not, each +tp_block_size/tp_frame_size frames there will be a gap between +the frames. This is because a frame cannot be spawn across two +blocks. + +At the beginning of each frame there is an status field (see +struct tpacket_hdr). If this field is 0 means that the frame is ready +to be used for the kernel, If not, there is a frame the user can read +and the following flags apply: + + from include/linux/if_packet.h + + #define TP_STATUS_COPY 2 + #define TP_STATUS_LOSING 4 + #define TP_STATUS_CSUMNOTREADY 8 + + +TP_STATUS_COPY : This flag indicates that the frame (and associated + meta information) has been truncated because it's + larger than tp_frame_size. This packet can be + read entirely with recvfrom(). + + In order to make this work it must to be + enabled previously with setsockopt() and + the PACKET_COPY_THRESH option. + + The number of frames than can be buffered to + be read with recvfrom is limited like a normal socket. + See the SO_RCVBUF option in the socket (7) man page. + +TP_STATUS_LOSING : indicates there were packet drops from last time + statistics where checked with getsockopt() and + the PACKET_STATISTICS option. + +TP_STATUS_CSUMNOTREADY: currently it's used for outgoing IP packets wich + it's checksum will be done in hardware. So while + reading the packet we should not try to check the + checksum. + +for convenience there are also the following defines: + + #define TP_STATUS_KERNEL 0 + #define TP_STATUS_USER 1 + +The kernel initializes all frames to TP_STATUS_KERNEL, when the kernel +receives a packet it puts in the buffer and updates the status with +at least the TP_STATUS_USER flag. Then the user can read the packet, +once the packet is read the user must zero the status field, so the kernel +can use again that frame buffer. + +The user can use poll (any other variant should apply too) to check if new +packets are in the ring: + + struct pollfd pfd; + + pfd.fd = fd; + pfd.revents = 0; + pfd.events = POLLIN|POLLRDNORM|POLLERR; + + if (status == TP_STATUS_KERNEL) + retval = poll(&pfd, 1, timeout); + +It doesn't incur in a race condition to first check the status value and +then poll for frames. + +-------------------------------------------------------------------------------- ++ THANKS +-------------------------------------------------------------------------------- + + Jesse Brandeburg, for fixing my grammathical/spelling errors + +>>> EOF +- +To unsubscribe from this list: send the line "unsubscribe linux-net" in +the body of a message to majordomo@vger.kernel.org +More majordomo info at http://vger.kernel.org/majordomo-info.html \ No newline at end of file diff -urN linux-2.4.25/MAINTAINERS linux-2.4.26/MAINTAINERS --- linux-2.4.25/MAINTAINERS 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/MAINTAINERS 2004-04-14 06:05:25.000000000 -0700 @@ -166,7 +166,7 @@ P: Len Brown M: len.brown@intel.com L: acpi-devel@lists.sourceforge.net -W: http://sf.net/projects/acpi/ +W: http://acpi.sourceforge.net/ S: Maintained AD1816 SOUND DRIVER @@ -1081,8 +1081,8 @@ P: Andrew Stanley-Jones M: asj@lanmedia.com W: http://www.lanmedia.com/ -S: Supported - +S: Orphan + LAPB module P: Henner Eisen M: eis@baty.hanse.de @@ -1456,9 +1456,9 @@ PERMEDIA 3 FRAMEBUFFER DRIVER P: Romain Dolbeau -M: dolbeau@irisa.fr +M: dolbeau@caps-entreprise.com L: linux-fbdev-devel@lists.sourceforge.net -W: http://www.irisa.fr/prive/dolbeau/pm3fb/pm3fb.html +W: http://www.caps-entreprise.com/private/dolbeau/pm3fb/pm3fb.html S: Maintained PHILIPS NINO PALM PC @@ -1626,6 +1626,12 @@ L: linux-scsi@vger.kernel.org S: Maintained +SCTP PROTOCOL +P: Sridhar Samudrala +M: sri@us.ibm.com +L: lksctp-developers@lists.sourceforge.net +S: Supported + SCx200 CPU SUPPORT P: Christer Weinigel M: christer@weinigel.se @@ -2067,8 +2073,8 @@ S: Maintained USB SUBSYSTEM -P: Greg Kroah-Hartman -M: greg@kroah.com +P: Pete Zaitcev +M: zaitcev@redhat.com L: linux-usb-users@lists.sourceforge.net L: linux-usb-devel@lists.sourceforge.net W: http://www.linux-usb.org @@ -2104,7 +2110,6 @@ VIA 82Cxxx AUDIO DRIVER P: Jeff Garzik -L: linux-via@gtf.org S: Odd fixes VIA RHINE NETWORK DRIVER diff -urN linux-2.4.25/Makefile linux-2.4.26/Makefile --- linux-2.4.25/Makefile 2004-02-18 05:36:32.000000000 -0800 +++ linux-2.4.26/Makefile 2004-04-14 06:05:41.000000000 -0700 @@ -1,6 +1,6 @@ VERSION = 2 PATCHLEVEL = 4 -SUBLEVEL = 25 +SUBLEVEL = 26 EXTRAVERSION = KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION) @@ -223,7 +223,8 @@ drivers/tc/lk201-map.c \ net/khttpd/make_times_h \ net/khttpd/times.h \ - submenu* + submenu* \ + drivers/ieee1394/oui.c # directories removed with 'make clean' CLEAN_DIRS = \ modules diff -urN linux-2.4.25/arch/alpha/lib/ev6-stxncpy.S linux-2.4.26/arch/alpha/lib/ev6-stxncpy.S --- linux-2.4.25/arch/alpha/lib/ev6-stxncpy.S 2003-08-25 04:44:39.000000000 -0700 +++ linux-2.4.26/arch/alpha/lib/ev6-stxncpy.S 2004-04-14 06:05:25.000000000 -0700 @@ -365,7 +365,7 @@ andnot t2, t6, t12 # E : dest mask for a single word copy or t8, t10, t5 # E : test for end-of-count too - cmpbge zero, t2, t3 # E : + cmpbge zero, t12, t3 # E : cmoveq a2, t5, t8 # E : Latency=2, extra map slot nop # E : keep with cmoveq andnot t8, t3, t8 # E : (stall) diff -urN linux-2.4.25/arch/alpha/lib/stxncpy.S linux-2.4.26/arch/alpha/lib/stxncpy.S --- linux-2.4.25/arch/alpha/lib/stxncpy.S 2003-08-25 04:44:39.000000000 -0700 +++ linux-2.4.26/arch/alpha/lib/stxncpy.S 2004-04-14 06:05:25.000000000 -0700 @@ -317,7 +317,7 @@ cmpbge zero, t1, t8 # .. e1 : is there a zero? andnot t2, t6, t12 # e0 : dest mask for a single word copy or t8, t10, t5 # .. e1 : test for end-of-count too - cmpbge zero, t2, t3 # e0 : + cmpbge zero, t12, t3 # e0 : cmoveq a2, t5, t8 # .. e1 : andnot t8, t3, t8 # e0 : beq t8, $u_head # .. e1 (zdb) diff -urN linux-2.4.25/arch/i386/defconfig linux-2.4.26/arch/i386/defconfig --- linux-2.4.25/arch/i386/defconfig 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/arch/i386/defconfig 2004-04-14 06:05:25.000000000 -0700 @@ -2,7 +2,6 @@ # Automatically generated make config: don't edit # CONFIG_X86=y -CONFIG_ISA=y # CONFIG_SBUS is not set CONFIG_UID16=y @@ -31,12 +30,14 @@ # CONFIG_MPENTIUM4 is not set # CONFIG_MK6 is not set # CONFIG_MK7 is not set +# CONFIG_MK8 is not set # CONFIG_MELAN is not set # CONFIG_MCRUSOE is not set # CONFIG_MWINCHIPC6 is not set # CONFIG_MWINCHIP2 is not set # CONFIG_MWINCHIP3D is not set # CONFIG_MCYRIXIII is not set +# CONFIG_MVIAC3_2 is not set CONFIG_X86_WP_WORKS_OK=y CONFIG_X86_INVLPG=y CONFIG_X86_CMPXCHG=y @@ -46,26 +47,29 @@ # CONFIG_RWSEM_GENERIC_SPINLOCK is not set CONFIG_RWSEM_XCHGADD_ALGORITHM=y CONFIG_X86_L1_CACHE_SHIFT=5 -CONFIG_X86_TSC=y +CONFIG_X86_HAS_TSC=y CONFIG_X86_GOOD_APIC=y CONFIG_X86_PGE=y CONFIG_X86_USE_PPRO_CHECKSUM=y +CONFIG_X86_F00F_WORKS_OK=y CONFIG_X86_MCE=y # CONFIG_TOSHIBA is not set # CONFIG_I8K is not set # CONFIG_MICROCODE is not set # CONFIG_X86_MSR is not set # CONFIG_X86_CPUID is not set -# CONFIG_EDD is not set CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set +# CONFIG_HIGHMEM is not set # CONFIG_MATH_EMULATION is not set # CONFIG_MTRR is not set CONFIG_SMP=y -# CONFIG_MULTIQUAD is not set -CONFIG_HAVE_DEC_LOCK=y CONFIG_NR_CPUS=32 +# CONFIG_X86_NUMA is not set +# CONFIG_X86_TSC_DISABLE is not set +CONFIG_X86_TSC=y +CONFIG_HAVE_DEC_LOCK=y # # General setup @@ -79,6 +83,7 @@ CONFIG_PCI_GOANY=y CONFIG_PCI_BIOS=y CONFIG_PCI_DIRECT=y +CONFIG_ISA=y CONFIG_PCI_NAMES=y # CONFIG_EISA is not set # CONFIG_MCA is not set @@ -100,7 +105,6 @@ # CONFIG_HOTPLUG_PCI_COMPAQ is not set # CONFIG_HOTPLUG_PCI_COMPAQ_NVRAM is not set # CONFIG_HOTPLUG_PCI_IBM is not set -# CONFIG_HOTPLUG_PCI_ACPI is not set CONFIG_SYSVIPC=y # CONFIG_BSD_PROCESS_ACCT is not set CONFIG_SYSCTL=y @@ -109,10 +113,17 @@ CONFIG_BINFMT_AOUT=y CONFIG_BINFMT_ELF=y CONFIG_BINFMT_MISC=y +# CONFIG_OOM_KILLER is not set CONFIG_PM=y # CONFIG_APM is not set # +# ACPI Support +# +# CONFIG_ACPI is not set +CONFIG_ACPI_BOOT=y + +# # Memory Technology Devices (MTD) # # CONFIG_MTD is not set @@ -137,12 +148,14 @@ # CONFIG_BLK_CPQ_DA is not set # CONFIG_BLK_CPQ_CISS_DA is not set # CONFIG_CISS_SCSI_TAPE is not set +# CONFIG_CISS_MONITOR_THREAD is not set # CONFIG_BLK_DEV_DAC960 is not set # CONFIG_BLK_DEV_UMEM is not set # CONFIG_BLK_DEV_LOOP is not set # CONFIG_BLK_DEV_NBD is not set # CONFIG_BLK_DEV_RAM is not set # CONFIG_BLK_DEV_INITRD is not set +# CONFIG_BLK_STATS is not set # # Multi-device support (RAID and LVM) @@ -224,15 +237,6 @@ CONFIG_BLK_DEV_IDEDISK=y CONFIG_IDEDISK_MULTI_MODE=y # CONFIG_IDEDISK_STROKE is not set -# CONFIG_BLK_DEV_IDEDISK_VENDOR is not set -# CONFIG_BLK_DEV_IDEDISK_FUJITSU is not set -# CONFIG_BLK_DEV_IDEDISK_IBM is not set -# CONFIG_BLK_DEV_IDEDISK_MAXTOR is not set -# CONFIG_BLK_DEV_IDEDISK_QUANTUM is not set -# CONFIG_BLK_DEV_IDEDISK_SEAGATE is not set -# CONFIG_BLK_DEV_IDEDISK_WD is not set -# CONFIG_BLK_DEV_COMMERIAL is not set -# CONFIG_BLK_DEV_TIVO is not set # CONFIG_BLK_DEV_IDECS is not set CONFIG_BLK_DEV_IDECD=y # CONFIG_BLK_DEV_IDETAPE is not set @@ -246,8 +250,8 @@ CONFIG_BLK_DEV_CMD640=y # CONFIG_BLK_DEV_CMD640_ENHANCED is not set # CONFIG_BLK_DEV_ISAPNP is not set -CONFIG_BLK_DEV_RZ1000=y CONFIG_BLK_DEV_IDEPCI=y +# CONFIG_BLK_DEV_GENERIC is not set CONFIG_IDEPCI_SHARE_IRQ=y CONFIG_BLK_DEV_IDEDMA_PCI=y # CONFIG_BLK_DEV_OFFBOARD is not set @@ -256,30 +260,29 @@ # CONFIG_IDEDMA_ONLYDISK is not set CONFIG_BLK_DEV_IDEDMA=y # CONFIG_IDEDMA_PCI_WIP is not set -# CONFIG_BLK_DEV_IDEDMA_TIMEOUT is not set -# CONFIG_IDEDMA_NEW_DRIVE_LISTINGS is not set -CONFIG_BLK_DEV_ADMA=y +# CONFIG_BLK_DEV_ADMA100 is not set # CONFIG_BLK_DEV_AEC62XX is not set -# CONFIG_AEC62XX_TUNING is not set # CONFIG_BLK_DEV_ALI15X3 is not set # CONFIG_WDC_ALI15X3 is not set # CONFIG_BLK_DEV_AMD74XX is not set # CONFIG_AMD74XX_OVERRIDE is not set # CONFIG_BLK_DEV_CMD64X is not set -# CONFIG_BLK_DEV_CMD680 is not set +# CONFIG_BLK_DEV_TRIFLEX is not set # CONFIG_BLK_DEV_CY82C693 is not set # CONFIG_BLK_DEV_CS5530 is not set # CONFIG_BLK_DEV_HPT34X is not set # CONFIG_HPT34X_AUTODMA is not set # CONFIG_BLK_DEV_HPT366 is not set CONFIG_BLK_DEV_PIIX=y -CONFIG_PIIX_TUNING=y # CONFIG_BLK_DEV_NS87415 is not set # CONFIG_BLK_DEV_OPTI621 is not set -# CONFIG_BLK_DEV_PDC202XX is not set +# CONFIG_BLK_DEV_PDC202XX_OLD is not set # CONFIG_PDC202XX_BURST is not set -# CONFIG_PDC202XX_FORCE is not set +# CONFIG_BLK_DEV_PDC202XX_NEW is not set +CONFIG_BLK_DEV_RZ1000=y +# CONFIG_BLK_DEV_SC1200 is not set # CONFIG_BLK_DEV_SVWKS is not set +# CONFIG_BLK_DEV_SIIMAGE is not set # CONFIG_BLK_DEV_SIS5513 is not set # CONFIG_BLK_DEV_SLC90E66 is not set # CONFIG_BLK_DEV_TRM290 is not set @@ -291,6 +294,7 @@ # CONFIG_BLK_DEV_ATARAID is not set # CONFIG_BLK_DEV_ATARAID_PDC is not set # CONFIG_BLK_DEV_ATARAID_HPT is not set +# CONFIG_BLK_DEV_ATARAID_SII is not set # # SCSI support @@ -325,12 +329,14 @@ # CONFIG_SCSI_AHA1542 is not set # CONFIG_SCSI_AHA1740 is not set # CONFIG_SCSI_AIC7XXX is not set +# CONFIG_SCSI_AIC79XX is not set # CONFIG_SCSI_AIC7XXX_OLD is not set # CONFIG_SCSI_DPT_I2O is not set # CONFIG_SCSI_ADVANSYS is not set # CONFIG_SCSI_IN2000 is not set # CONFIG_SCSI_AM53C974 is not set # CONFIG_SCSI_MEGARAID is not set +# CONFIG_SCSI_MEGARAID2 is not set # CONFIG_SCSI_BUSLOGIC is not set # CONFIG_SCSI_CPQFCTS is not set # CONFIG_SCSI_DMX3191D is not set @@ -370,6 +376,7 @@ # CONFIG_SCSI_T128 is not set # CONFIG_SCSI_U14_34F is not set # CONFIG_SCSI_ULTRASTOR is not set +# CONFIG_SCSI_NSP32 is not set # # PCMCIA SCSI adapter support @@ -429,16 +436,19 @@ # CONFIG_NET_ISA is not set CONFIG_NET_PCI=y # CONFIG_PCNET32 is not set +# CONFIG_AMD8111_ETH is not set # CONFIG_ADAPTEC_STARFIRE is not set # CONFIG_AC3200 is not set # CONFIG_APRICOT is not set +# CONFIG_B44 is not set # CONFIG_CS89x0 is not set # CONFIG_TULIP is not set -# CONFIG_TC35815 is not set # CONFIG_DE4X5 is not set # CONFIG_DGRS is not set # CONFIG_DM9102 is not set CONFIG_EEPRO100=y +# CONFIG_EEPRO100_PIO is not set +# CONFIG_E100 is not set # CONFIG_LNE390 is not set # CONFIG_FEALNX is not set # CONFIG_NATSEMI is not set @@ -450,10 +460,11 @@ # CONFIG_8139TOO_PIO is not set # CONFIG_8139TOO_TUNE_TWISTER is not set # CONFIG_8139TOO_8129 is not set -# CONFIG_8139_NEW_RX_RESET is not set +# CONFIG_8139_OLD_RX_RESET is not set # CONFIG_SIS900 is not set # CONFIG_EPIC100 is not set # CONFIG_SUNDANCE is not set +# CONFIG_SUNDANCE_MMIO is not set # CONFIG_TLAN is not set # CONFIG_VIA_RHINE is not set # CONFIG_VIA_RHINE_MMIO is not set @@ -465,10 +476,12 @@ # # CONFIG_ACENIC is not set # CONFIG_DL2K is not set +# CONFIG_E1000 is not set # CONFIG_MYRI_SBUS is not set # CONFIG_NS83820 is not set # CONFIG_HAMACHI is not set # CONFIG_YELLOWFIN is not set +# CONFIG_R8169 is not set # CONFIG_SK98LIN is not set # CONFIG_TIGON3 is not set # CONFIG_FDDI is not set @@ -542,6 +555,7 @@ # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_JOYDEV is not set # CONFIG_INPUT_EVDEV is not set +# CONFIG_INPUT_UINPUT is not set # # Character devices @@ -583,13 +597,22 @@ # Input core support is needed for joysticks # # CONFIG_QIC02_TAPE is not set +# CONFIG_IPMI_HANDLER is not set +# CONFIG_IPMI_PANIC_EVENT is not set +# CONFIG_IPMI_DEVICE_INTERFACE is not set +# CONFIG_IPMI_KCS is not set +# CONFIG_IPMI_WATCHDOG is not set # # Watchdog Cards # # CONFIG_WATCHDOG is not set +# CONFIG_SCx200 is not set +# CONFIG_SCx200_GPIO is not set # CONFIG_AMD_RNG is not set # CONFIG_INTEL_RNG is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_AMD_PM768 is not set # CONFIG_NVRAM is not set # CONFIG_RTC is not set # CONFIG_DTLK is not set @@ -605,9 +628,16 @@ CONFIG_AGP_I810=y CONFIG_AGP_VIA=y CONFIG_AGP_AMD=y +# CONFIG_AGP_AMD_K8 is not set CONFIG_AGP_SIS=y CONFIG_AGP_ALI=y # CONFIG_AGP_SWORKS is not set +# CONFIG_AGP_NVIDIA is not set +# CONFIG_AGP_ATI is not set + +# +# Direct Rendering Manager (XFree86 DRI support) +# CONFIG_DRM=y # CONFIG_DRM_OLD is not set @@ -616,10 +646,12 @@ # CONFIG_DRM_NEW=y CONFIG_DRM_TDFX=y +# CONFIG_DRM_GAMMA is not set # CONFIG_DRM_R128 is not set CONFIG_DRM_RADEON=y CONFIG_DRM_I810=y CONFIG_DRM_I810_XFREE_41=y +# CONFIG_DRM_I830 is not set # CONFIG_DRM_MGA is not set # CONFIG_DRM_SIS is not set @@ -627,7 +659,9 @@ # PCMCIA character devices # # CONFIG_PCMCIA_SERIAL_CS is not set +# CONFIG_SYNCLINK_CS is not set # CONFIG_MWAVE is not set +# CONFIG_OBMOUSE is not set # # Multimedia devices @@ -638,6 +672,7 @@ # File systems # # CONFIG_QUOTA is not set +# CONFIG_QFMT_V2 is not set # CONFIG_AUTOFS_FS is not set CONFIG_AUTOFS4_FS=y # CONFIG_REISERFS_FS is not set @@ -647,6 +682,9 @@ # CONFIG_ADFS_FS_RW is not set # CONFIG_AFFS_FS is not set # CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BEFS_DEBUG is not set # CONFIG_BFS_FS is not set # CONFIG_EXT3_FS is not set # CONFIG_JBD is not set @@ -664,6 +702,9 @@ CONFIG_ISO9660_FS=y # CONFIG_JOLIET is not set # CONFIG_ZISOFS is not set +# CONFIG_JFS_FS is not set +# CONFIG_JFS_DEBUG is not set +# CONFIG_JFS_STATISTICS is not set # CONFIG_MINIX_FS is not set # CONFIG_VXFS_FS is not set # CONFIG_NTFS_FS is not set @@ -683,6 +724,11 @@ # CONFIG_UDF_RW is not set # CONFIG_UFS_FS is not set # CONFIG_UFS_FS_WRITE is not set +# CONFIG_XFS_FS is not set +# CONFIG_XFS_QUOTA is not set +# CONFIG_XFS_RT is not set +# CONFIG_XFS_TRACE is not set +# CONFIG_XFS_DEBUG is not set # # Network File Systems @@ -691,9 +737,11 @@ # CONFIG_INTERMEZZO_FS is not set CONFIG_NFS_FS=y # CONFIG_NFS_V3 is not set +# CONFIG_NFS_DIRECTIO is not set # CONFIG_ROOT_NFS is not set CONFIG_NFSD=y # CONFIG_NFSD_V3 is not set +# CONFIG_NFSD_TCP is not set CONFIG_SUNRPC=y CONFIG_LOCKD=y # CONFIG_SMB_FS is not set @@ -707,7 +755,6 @@ # CONFIG_NCPFS_NLS is not set # CONFIG_NCPFS_EXTRAS is not set # CONFIG_ZISOFS_FS is not set -# CONFIG_ZLIB_FS_INFLATE is not set # # Partition Types @@ -727,6 +774,7 @@ # Sound # CONFIG_SOUND=y +# CONFIG_SOUND_ALI5455 is not set # CONFIG_SOUND_BT878 is not set # CONFIG_SOUND_CMPCI is not set # CONFIG_SOUND_EMU10K1 is not set @@ -738,6 +786,7 @@ # CONFIG_SOUND_ESSSOLO1 is not set # CONFIG_SOUND_MAESTRO is not set # CONFIG_SOUND_MAESTRO3 is not set +# CONFIG_SOUND_FORTE is not set # CONFIG_SOUND_ICH is not set # CONFIG_SOUND_RME96XX is not set # CONFIG_SOUND_SONICVIBES is not set @@ -748,6 +797,8 @@ # CONFIG_MIDI_VIA82CXXX is not set # CONFIG_SOUND_OSS is not set # CONFIG_SOUND_TVMIXER is not set +# CONFIG_SOUND_AD1980 is not set +# CONFIG_SOUND_WM97XX is not set # # USB support @@ -760,7 +811,6 @@ # # CONFIG_USB_DEVICEFS is not set # CONFIG_USB_BANDWIDTH is not set -# CONFIG_USB_LONG_TIMEOUT is not set # # USB Host Controller Drivers @@ -768,13 +818,15 @@ # CONFIG_USB_EHCI_HCD is not set CONFIG_USB_UHCI_ALT=y # CONFIG_USB_OHCI is not set +# CONFIG_USB_SL811HS_ALT is not set +# CONFIG_USB_SL811HS is not set # # USB Device Class drivers # # CONFIG_USB_AUDIO is not set # CONFIG_USB_EMI26 is not set -# CONFIG_USB_BLUETOOTH is not set +# CONFIG_USB_MIDI is not set CONFIG_USB_STORAGE=y # CONFIG_USB_STORAGE_DEBUG is not set # CONFIG_USB_STORAGE_DATAFAB is not set @@ -783,6 +835,7 @@ # CONFIG_USB_STORAGE_DPCM is not set # CONFIG_USB_STORAGE_HP8200e is not set # CONFIG_USB_STORAGE_SDDR09 is not set +# CONFIG_USB_STORAGE_SDDR55 is not set # CONFIG_USB_STORAGE_JUMPSHOT is not set # CONFIG_USB_ACM is not set # CONFIG_USB_PRINTER is not set @@ -799,7 +852,10 @@ # CONFIG_USB_HIDDEV is not set # CONFIG_USB_KBD is not set # CONFIG_USB_MOUSE is not set +# CONFIG_USB_AIPTEK is not set # CONFIG_USB_WACOM is not set +# CONFIG_USB_KBTAB is not set +# CONFIG_USB_POWERMATE is not set # # USB Imaging devices @@ -837,39 +893,20 @@ # USB Serial Converter support # # CONFIG_USB_SERIAL is not set -# CONFIG_USB_SERIAL_GENERIC is not set -# CONFIG_USB_SERIAL_BELKIN is not set -# CONFIG_USB_SERIAL_WHITEHEAT is not set -# CONFIG_USB_SERIAL_DIGI_ACCELEPORT is not set -# CONFIG_USB_SERIAL_EMPEG is not set -# CONFIG_USB_SERIAL_FTDI_SIO is not set -# CONFIG_USB_SERIAL_VISOR is not set -# CONFIG_USB_SERIAL_IPAQ is not set -# CONFIG_USB_SERIAL_IR is not set -# CONFIG_USB_SERIAL_EDGEPORT is not set -# CONFIG_USB_SERIAL_KEYSPAN_PDA is not set -# CONFIG_USB_SERIAL_KEYSPAN is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28 is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28X is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28XA is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28XB is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA19 is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA18X is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA19W is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA49W is not set -# CONFIG_USB_SERIAL_MCT_U232 is not set -# CONFIG_USB_SERIAL_KLSI is not set -# CONFIG_USB_SERIAL_PL2303 is not set -# CONFIG_USB_SERIAL_CYBERJACK is not set -# CONFIG_USB_SERIAL_XIRCOM is not set -# CONFIG_USB_SERIAL_OMNINET is not set # # USB Miscellaneous drivers # # CONFIG_USB_RIO500 is not set # CONFIG_USB_AUERSWALD is not set +# CONFIG_USB_TIGL is not set # CONFIG_USB_BRLVGER is not set +# CONFIG_USB_LCD is not set + +# +# Support for USB gadgets +# +# CONFIG_USB_GADGET is not set # # Bluetooth support @@ -880,3 +917,16 @@ # Kernel hacking # # CONFIG_DEBUG_KERNEL is not set +CONFIG_LOG_BUF_SHIFT=0 + +# +# Cryptographic options +# +# CONFIG_CRYPTO is not set + +# +# Library routines +# +CONFIG_CRC32=y +# CONFIG_ZLIB_INFLATE is not set +# CONFIG_ZLIB_DEFLATE is not set diff -urN linux-2.4.25/arch/i386/kernel/acpi.c linux-2.4.26/arch/i386/kernel/acpi.c --- linux-2.4.25/arch/i386/kernel/acpi.c 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/arch/i386/kernel/acpi.c 2004-04-14 06:05:25.000000000 -0700 @@ -49,14 +49,16 @@ #define PREFIX "ACPI: " -int acpi_lapic = 0; -int acpi_ioapic = 0; +int acpi_lapic; +int acpi_ioapic; +int acpi_strict; +acpi_interrupt_flags acpi_sci_flags __initdata; +int acpi_sci_override_gsi __initdata; /* -------------------------------------------------------------------------- Boot-time Configuration -------------------------------------------------------------------------- */ -#ifdef CONFIG_ACPI_BOOT int acpi_noirq __initdata = 0; /* skip ACPI IRQ initialization */ int acpi_ht __initdata = 1; /* enable HT */ @@ -214,6 +216,59 @@ return 0; } +/* + * Parse Interrupt Source Override for the ACPI SCI + */ +static void +acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger) +{ + if (trigger == 0) /* compatible SCI trigger is level */ + trigger = 3; + + if (polarity == 0) /* compatible SCI polarity is low */ + polarity = 3; + + /* Command-line over-ride via acpi_sci= */ + if (acpi_sci_flags.trigger) + trigger = acpi_sci_flags.trigger; + + if (acpi_sci_flags.polarity) + polarity = acpi_sci_flags.polarity; + + /* + * mp_config_acpi_legacy_irqs() already setup IRQs < 16 + * If GSI is < 16, this will update its flags, + * else it will create a new mp_irqs[] entry. + */ + mp_override_legacy_irq(gsi, polarity, trigger, gsi); + + /* + * stash over-ride to indicate we've been here + * and for later update of acpi_fadt + */ + acpi_sci_override_gsi = gsi; + return; +} + +static int __init +acpi_parse_fadt(unsigned long phys, unsigned long size) +{ + struct fadt_descriptor_rev2 *fadt =0; + + fadt = (struct fadt_descriptor_rev2*) __acpi_map_table(phys,size); + if (!fadt) { + printk(KERN_WARNING PREFIX "Unable to map FADT\n"); + return 0; + } + +#ifdef CONFIG_ACPI_INTERPRETER + /* initialize sci_int early for INT_SRC_OVR MADT parsing */ + acpi_fadt.sci_int = fadt->sci_int; +#endif + + return 0; +} + static int __init acpi_parse_int_src_ovr ( @@ -227,6 +282,12 @@ acpi_table_print_madt_entry(header); + if (intsrc->bus_irq == acpi_fadt.sci_int) { + acpi_sci_ioapic_setup(intsrc->global_irq, + intsrc->flags.polarity, intsrc->flags.trigger); + return 0; + } + mp_override_legacy_irq ( intsrc->bus_irq, intsrc->flags.polarity, @@ -307,7 +368,7 @@ * acpi_lapic = 1 if LAPIC found * acpi_ioapic = 1 if IOAPIC found * if (acpi_lapic && acpi_ioapic) smp_found_config = 1; - * if acpi_blacklisted() acpi_disabled = 1; + * if acpi_blacklisted() disable_acpi() * acpi_irq_model=... * ... * @@ -334,14 +395,14 @@ */ result = acpi_table_init(); if (result) { - acpi_disabled = 1; + disable_acpi(); return result; } result = acpi_blacklisted(); if (result) { printk(KERN_NOTICE PREFIX "BIOS listed in blacklist, disabling ACPI support\n"); - acpi_disabled = 1; + disable_acpi(); return result; } @@ -444,6 +505,9 @@ /* Build a default routing table for legacy (ISA) interrupts. */ mp_config_acpi_legacy_irqs(); + /* Record sci_int for use when looking for MADT sci_int override */ + acpi_table_parse(ACPI_FADT, acpi_parse_fadt); + result = acpi_table_parse_madt(ACPI_MADT_INT_SRC_OVR, acpi_parse_int_src_ovr); if (result < 0) { printk(KERN_ERR PREFIX "Error parsing interrupt source overrides entry\n"); @@ -451,6 +515,13 @@ return result; } + /* + * If BIOS did not supply an INT_SRC_OVR for the SCI + * pretend we got one so we can set the SCI flags. + */ + if (!acpi_sci_override_gsi) + acpi_sci_ioapic_setup(acpi_fadt.sci_int, 0, 0); + result = acpi_table_parse_madt(ACPI_MADT_NMI_SRC, acpi_parse_nmi_src); if (result < 0) { printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n"); @@ -472,17 +543,15 @@ return 0; } -#endif /*CONFIG_ACPI_BOOT*/ #ifdef CONFIG_ACPI_BUS /* - * "acpi_pic_sci=level" (current default) - * programs the PIC-mode SCI to Level Trigger. - * (NO-OP if the BIOS set Level Trigger already) - * - * If a PIC-mode SCI is not recogznied or gives spurious IRQ7's - * it may require Edge Trigger -- use "acpi_pic_sci=edge" - * (NO-OP if the BIOS set Edge Trigger already) + * acpi_pic_sci_set_trigger() + * + * use ELCR to set PIC-mode trigger type for SCI + * + * If a PIC-mode SCI is not recognized or gives spurious IRQ7's + * it may require Edge Trigger -- use "acpi_sci=edge" * * Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers * for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge. @@ -490,56 +559,41 @@ * ECLR2 is IRQ's 8-15 (IRQ 8, 13 must be 0) */ -static __initdata int acpi_pic_sci_trigger; /* 0: level, 1: edge */ - void __init -acpi_pic_sci_set_trigger(unsigned int irq) +acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) { unsigned char mask = 1 << (irq & 7); unsigned int port = 0x4d0 + (irq >> 3); unsigned char val = inb(port); - + printk(PREFIX "IRQ%d SCI:", irq); if (!(val & mask)) { printk(" Edge"); - if (!acpi_pic_sci_trigger) { + if (trigger == 3) { printk(" set to Level"); outb(val | mask, port); } } else { printk(" Level"); - if (acpi_pic_sci_trigger) { + if (trigger == 1) { printk(" set to Edge"); - outb(val | mask, port); + outb(val & ~mask, port); } } printk(" Trigger.\n"); } -int __init -acpi_pic_sci_setup(char *str) -{ - while (str && *str) { - if (strncmp(str, "level", 5) == 0) - acpi_pic_sci_trigger = 0; /* force level trigger */ - if (strncmp(str, "edge", 4) == 0) - acpi_pic_sci_trigger = 1; /* force edge trigger */ - str = strchr(str, ','); - if (str) - str += strspn(str, ", \t"); - } - return 1; -} - -__setup("acpi_pic_sci=", acpi_pic_sci_setup); - #endif /* CONFIG_ACPI_BUS */ +#ifndef __HAVE_ARCH_CMPXCHG +#warning ACPI uses CMPXCHG, i486 and later hardware +#endif + /* -------------------------------------------------------------------------- Low-Level Sleep Support -------------------------------------------------------------------------- */ @@ -656,7 +710,8 @@ void __init acpi_reserve_bootmem(void) { acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE); - printk(KERN_DEBUG "ACPI: have wakeup address 0x%8.8lx\n", acpi_wakeup_address); + if (!acpi_wakeup_address) + printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n"); } void do_suspend_lowlevel_s4bios(int resume) diff -urN linux-2.4.25/arch/i386/kernel/dmi_scan.c linux-2.4.26/arch/i386/kernel/dmi_scan.c --- linux-2.4.25/arch/i386/kernel/dmi_scan.c 2003-11-28 10:26:19.000000000 -0800 +++ linux-2.4.26/arch/i386/kernel/dmi_scan.c 2004-04-14 06:05:25.000000000 -0700 @@ -482,13 +482,13 @@ #ifdef CONFIG_ACPI_BOOT -extern int acpi_disabled, acpi_force, acpi_ht; +extern int acpi_force; -static __init __attribute__((unused)) int acpi_disable(struct dmi_blacklist *d) +static __init __attribute__((unused)) int dmi_disable_acpi(struct dmi_blacklist *d) { if (!acpi_force) { printk(KERN_NOTICE "%s detected: acpi off\n",d->ident); - acpi_disabled = 1; + disable_acpi(); } else { printk(KERN_NOTICE "Warning: DMI blacklist says broken, but acpi forced\n"); @@ -504,7 +504,7 @@ { if (!acpi_force) { printk(KERN_NOTICE "%s detected: force use of acpi=ht\n", d->ident); - acpi_disabled = 1; + disable_acpi(); acpi_ht = 1; } else { printk(KERN_NOTICE @@ -839,7 +839,7 @@ * Boxes that need ACPI disabled */ - { acpi_disable, "IBM Thinkpad", { + { dmi_disable_acpi, "IBM Thinkpad", { MATCH(DMI_BOARD_VENDOR, "IBM"), MATCH(DMI_BOARD_NAME, "2629H1G"), NO_MATCH, NO_MATCH }}, @@ -968,8 +968,7 @@ if (disable && !acpi_force) { printk(KERN_NOTICE "ACPI disabled because your bios is from %s and too old\n", s); printk(KERN_NOTICE "You can enable it with acpi=force\n"); - acpi_disabled = 1; - acpi_ht = 0; + disable_acpi(); } } } diff -urN linux-2.4.25/arch/i386/kernel/i386_ksyms.c linux-2.4.26/arch/i386/kernel/i386_ksyms.c --- linux-2.4.25/arch/i386/kernel/i386_ksyms.c 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/arch/i386/kernel/i386_ksyms.c 2004-04-14 06:05:25.000000000 -0700 @@ -146,6 +146,10 @@ /* TLB flushing */ EXPORT_SYMBOL(flush_tlb_page); + +/* HT support */ +EXPORT_SYMBOL(smp_num_siblings); +EXPORT_SYMBOL(cpu_sibling_map); #endif #ifdef CONFIG_X86_IO_APIC diff -urN linux-2.4.25/arch/i386/kernel/io_apic.c linux-2.4.26/arch/i386/kernel/io_apic.c --- linux-2.4.25/arch/i386/kernel/io_apic.c 2003-11-28 10:26:19.000000000 -0800 +++ linux-2.4.26/arch/i386/kernel/io_apic.c 2004-04-14 06:05:25.000000000 -0700 @@ -1864,7 +1864,11 @@ entry.trigger = edge_level; entry.polarity = active_high_low; - add_pin_to_irq(irq, ioapic, pin); + /* + * IRQs < 16 are already in the irq_2_pin[] map + */ + if (irq >= 16) + add_pin_to_irq(irq, ioapic, pin); entry.vector = assign_irq_vector(irq); diff -urN linux-2.4.25/arch/i386/kernel/microcode.c linux-2.4.26/arch/i386/kernel/microcode.c --- linux-2.4.25/arch/i386/kernel/microcode.c 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/arch/i386/kernel/microcode.c 2004-04-14 06:05:25.000000000 -0700 @@ -1,7 +1,7 @@ /* * Intel CPU Microcode Update driver for Linux * - * Copyright (C) 2000 Tigran Aivazian + * Copyright (C) 2000-2004 Tigran Aivazian * * This driver allows to upgrade microcode on Intel processors * belonging to IA-32 family - PentiumPro, Pentium II, @@ -64,6 +64,10 @@ * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl * because we no longer hold a copy of applied microcode * in kernel memory. + * 1.14 23 Feb 2004 Tigran Aivazian + * Restored devfs regular file entry point which was + * accidentally removed when back-porting changes from the 2.6 + * version of the driver. */ @@ -73,6 +77,7 @@ #include #include #include +#include #include #include @@ -84,8 +89,8 @@ MODULE_AUTHOR("Tigran Aivazian "); MODULE_LICENSE("GPL"); -#define MICROCODE_VERSION "1.13" -#define MICRO_DEBUG 1 +#define MICROCODE_VERSION "1.14" +#define MICRO_DEBUG 0 #if MICRO_DEBUG #define dprintk(x...) printk(KERN_INFO x) #else @@ -470,6 +475,7 @@ return -EINVAL; } +/* shared between misc device and devfs regular file */ static struct file_operations microcode_fops = { .owner = THIS_MODULE, .write = microcode_write, @@ -483,29 +489,38 @@ .fops = µcode_fops, }; +static devfs_handle_t devfs_handle; + static int __init microcode_init (void) { int error; error = misc_register(µcode_dev); - if (error) { + if (error) printk(KERN_ERR "microcode: can't misc_register on minor=%d\n", MICROCODE_MINOR); - return error; + devfs_handle = devfs_register(NULL, "cpu/microcode", + DEVFS_FL_DEFAULT, 0, 0, S_IFREG | S_IRUSR | S_IWUSR, + µcode_fops, NULL); + if (devfs_handle == NULL && error) { + printk(KERN_ERR "microcode: failed to devfs_register()\n"); + goto out; } - + error = 0; printk(KERN_INFO - "IA-32 Microcode Update Driver: v%s \n", - MICROCODE_VERSION); - return 0; + "IA-32 Microcode Update Driver: v" + MICROCODE_VERSION " \n"); +out: + return error; } static void __exit microcode_exit (void) { misc_deregister(µcode_dev); - printk(KERN_INFO "IA-32 Microcode Update Driver v%s unregistered\n", - MICROCODE_VERSION); + devfs_unregister(devfs_handle); + printk(KERN_INFO "IA-32 Microcode Update Driver v" + MICROCODE_VERSION " unregistered\n"); } module_init(microcode_init) diff -urN linux-2.4.25/arch/i386/kernel/mpparse.c linux-2.4.26/arch/i386/kernel/mpparse.c --- linux-2.4.25/arch/i386/kernel/mpparse.c 2004-02-18 05:36:30.000000000 -0800 +++ linux-2.4.26/arch/i386/kernel/mpparse.c 2004-04-14 06:05:25.000000000 -0700 @@ -34,6 +34,9 @@ /* Have we found an MP table */ int smp_found_config; +#ifdef CONFIG_SMP +extern unsigned int max_cpus; +#endif /* * Various Linux-internal data structures created from the @@ -229,11 +232,19 @@ boot_cpu_logical_apicid = logical_apicid; } - if (num_processors >= NR_CPUS){ - printk(KERN_WARNING "NR_CPUS limit of %i reached. Cannot " - "boot CPU(apicid 0x%x).\n", NR_CPUS, m->mpc_apicid); +#ifdef CONFIG_SMP + if (num_processors >= NR_CPUS) { + printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." + " Processor ignored.\n", NR_CPUS); + return; + } + if (num_processors >= max_cpus) { + printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." + " Processor ignored.\n", max_cpus); return; } +#endif + num_processors++; if (m->mpc_apicid > MAX_APICS) { @@ -1118,7 +1129,7 @@ * erroneously sets the trigger to level, resulting in a HUGE * increase of timer interrupts! */ - if ((bus_irq == 0) && (global_irq == 2) && (trigger == 3)) + if ((bus_irq == 0) && (trigger == 3)) trigger = 1; intsrc.mpc_type = MP_INTSRC; @@ -1139,7 +1150,7 @@ * Otherwise create a new entry (e.g. global_irq == 2). */ for (i = 0; i < mp_irq_entries; i++) { - if ((mp_irqs[i].mpc_dstapic == intsrc.mpc_dstapic) + if ((mp_irqs[i].mpc_srcbus == intsrc.mpc_srcbus) && (mp_irqs[i].mpc_srcbusirq == intsrc.mpc_srcbusirq)) { mp_irqs[i] = intsrc; found = 1; @@ -1200,13 +1211,14 @@ */ for (i = 0; i < 16; i++) { - if (i == 2) continue; /* Don't connect IRQ2 */ + if (i == 2) + continue; /* Don't connect IRQ2 */ mp_irqs[mp_irq_entries].mpc_type = MP_INTSRC; mp_irqs[mp_irq_entries].mpc_irqflag = 0; /* Conforming */ mp_irqs[mp_irq_entries].mpc_srcbus = MP_ISA_BUS; mp_irqs[mp_irq_entries].mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; - mp_irqs[mp_irq_entries].mpc_irqtype = i ? mp_INT : mp_ExtINT; /* 8259A to #0 */ + mp_irqs[mp_irq_entries].mpc_irqtype = mp_INT; mp_irqs[mp_irq_entries].mpc_srcbusirq = i; /* Identity mapped */ mp_irqs[mp_irq_entries].mpc_dstirq = i; @@ -1227,70 +1239,6 @@ extern FADT_DESCRIPTOR acpi_fadt; -void __init mp_config_ioapic_for_sci(int irq) -{ - int ioapic; - int ioapic_pin; - struct acpi_table_madt* madt; - struct acpi_table_int_src_ovr *entry = NULL; - acpi_interrupt_flags flags; - void *madt_end; - acpi_status status; - - /* - * Ensure that if there is an interrupt source override entry - * for the ACPI SCI, we leave it as is. Unfortunately this involves - * walking the MADT again. - */ - status = acpi_get_firmware_table("APIC", 1, ACPI_LOGICAL_ADDRESSING, - (struct acpi_table_header **) &madt); - if (ACPI_SUCCESS(status)) { - madt_end = (void *) (unsigned long)madt + madt->header.length; - - entry = (struct acpi_table_int_src_ovr *) - ((unsigned long) madt + sizeof(struct acpi_table_madt)); - - while ((void *) entry < madt_end) { - if (entry->header.type == ACPI_MADT_INT_SRC_OVR && - acpi_fadt.sci_int == entry->bus_irq) - goto found; - - entry = (struct acpi_table_int_src_ovr *) - ((unsigned long) entry + entry->header.length); - } - } - /* - * Although the ACPI spec says that the SCI should be level/low - * don't reprogram it unless there is an explicit MADT OVR entry - * instructing us to do so -- otherwise we break Tyan boards which - * have the SCI wired edge/high but no MADT OVR. - */ - return; - -found: - /* - * See the note at the end of ACPI 2.0b section - * 5.2.10.8 for what this is about. - */ - flags = entry->flags; - acpi_fadt.sci_int = entry->global_irq; - irq = entry->global_irq; - - ioapic = mp_find_ioapic(irq); - - ioapic_pin = irq - mp_ioapic_routing[ioapic].irq_start; - - /* - * MPS INTI flags: - * trigger: 0=default, 1=edge, 3=level - * polarity: 0=default, 1=high, 3=low - * Per ACPI spec, default for SCI means level/low. - */ - io_apic_set_pci_routing(ioapic, ioapic_pin, irq, - (flags.trigger == 1 ? 0 : 1), (flags.polarity == 1 ? 0 : 1)); -} - - #ifdef CONFIG_ACPI_PCI void __init mp_parse_prt (void) @@ -1349,7 +1297,7 @@ continue; } if ((1<irq = irq; continue; diff -urN linux-2.4.25/arch/i386/kernel/pci-irq.c linux-2.4.26/arch/i386/kernel/pci-irq.c --- linux-2.4.25/arch/i386/kernel/pci-irq.c 2003-11-28 10:26:19.000000000 -0800 +++ linux-2.4.26/arch/i386/kernel/pci-irq.c 2004-04-14 06:05:25.000000000 -0700 @@ -595,6 +595,7 @@ case PCI_DEVICE_ID_INTEL_82801E_0: case PCI_DEVICE_ID_INTEL_82801EB_0: case PCI_DEVICE_ID_INTEL_ESB_0: + case PCI_DEVICE_ID_INTEL_ICH6_0: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff -urN linux-2.4.25/arch/