summaryrefslogtreecommitdiff
path: root/dev
AgeCommit message (Expand)Author
2004-10-25Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5-smpAli Saidi
2004-10-25changes to make interrupts part of the platform rather than tsunamiAli Saidi
2004-10-23flesh out the TCP/IP/Ethernet supportNathan Binkert
2004-10-23get rid of some unused variablesNathan Binkert
2004-10-23get rid of pmap.h and make things variables and inlineNathan Binkert
2004-10-22Clean up the Range class and associated usages. The code wasNathan Binkert
2004-10-19Clean up/standardize handling of various output files.Steve Reinhardt
2004-10-16Fixes for bigendian platformsAli Saidi
2004-09-21a bit more cleaning of the network header wrappers.Nathan Binkert
2004-09-20Clean up network header stuff and make it more generic. UseNathan Binkert
2004-08-31Updates to make SMP work.Ali Saidi
2004-08-20Fixup interrupting of the ethernet device.Nathan Binkert
2004-08-11cleanup interrupt code for gigabit deviceNathan Binkert
2004-08-11std::Nathan Binkert
2004-07-30better debuggingNathan Binkert
2004-07-30Fix a few bugs in the receive state machine. In doing back to trackingNathan Binkert
2004-07-30make all ethernet dma use the new interfaceNathan Binkert
2004-07-30better debugging of DMA operationsNathan Binkert
2004-07-26styleNathan Binkert
2004-07-23When a packet has finished transmitting, kick the stateNathan Binkert
2004-07-23notify the transmitter when the packet has finished transmitting.Nathan Binkert
2004-07-22Add support to store less than the full packet in an etherdumpNathan Binkert
2004-07-21Wrap tracing stuff in #if TRACING_ON to avoid compile errorNathan Binkert
2004-07-14Fix serialization when a tx interrupt isn't scheduledErik Hallnor
2004-07-14Fix infinite loop in ns_gige stat machineNathan Binkert
2004-07-12make the cache access latency a parameter that is based on busNathan Binkert
2004-07-12make tx/rx fifo size a param, also fix the empty dma problem by adjusting the...Lisa Hsu
2004-07-09Remove second pciToDma translation on current PRD address pointer b/cAndrew Schultz
2004-07-09Merge zizzer.eecs.umich.edu:/bk/m5Lisa Hsu
2004-07-09when you add caches, dma commands within the state machine are delayed and ca...Lisa Hsu
2004-07-08store the checkpoint to the proper directoryNathan Binkert
2004-07-06tag each mem_req as coming from the nic if it is DMA'd from the NIC. the NIC...Lisa Hsu
2004-07-05these changes are an undo from my last changeset. these are meant for later.Lisa Hsu
2004-07-04almost forgot to do this - hope it doesn't mess up schedule.Lisa Hsu
2004-06-30Merge zizzer.eecs.umich.edu:/bk/m5Lisa Hsu
2004-06-30fix transmit side checksum offloading to not generate a pseudo header.Lisa Hsu
2004-06-29Another fix for the too much work problem in 2.6. This should do it.Ali Saidi
2004-06-28With the new uart code 300 cycles isn't quite enough, 350 seems toAli Saidi
2004-06-28Don't serialize the absolute path so we can move checkpoints around.Nathan Binkert
2004-06-27allow the use of old console code and update elf_object not to rely on EM_ALP...Ali Saidi
2004-06-26rewrote uart and renamed console.cc to simconsole to reduce confusionAli Saidi
2004-06-23minor changes to endian code so that it runs on x86 linuxAli Saidi
2004-06-23Merge zizzer:/bk/linux into zeep.eecs.umich.edu:/z/saidi/work/m5-endianAli Saidi
2004-06-23Fix to properly shadow the DEV bit in the Drive/Head register so otherAndrew Schultz
2004-06-23more modifications for cross-endian support. linux now gets to pciconfigAli Saidi
2004-06-21lLisa Hsu
2004-06-21Merge saidi@zizzer.eecs.umich.edu:/bk/linuxAli Saidi
2004-06-21start towards getting m5 endian compliantAli Saidi
2004-06-17Fixes to IDE disk to fix serialization. Now passes simple CPU serializeAndrew Schultz
2004-06-16Fix serialize/unserialize of the timers and RTC eventsAndrew Schultz