Age | Commit message (Collapse) | Author | |
---|---|---|---|
2009-08-01 | Clean up some inconsistencies with Request flags. | Steve Reinhardt | |
2009-07-08 | Registers: Eliminate the ISA defined floating point register file. | Gabe Black | |
2009-07-08 | Registers: Add an ISA object which replaces the MiscRegFile. | Gabe Black | |
This object encapsulates (or will eventually) the identity and characteristics of the ISA in the CPU. | |||
2009-04-26 | X86: Split out the internal memory space from the regular translate() and ↵ | Gabe Black | |
precompute mode. | |||
2009-04-23 | X86: Put the StoreCheck flag with the others, and don't collide with other ↵ | Gabe Black | |
flags. | |||
2009-04-19 | X86: Fix how the TLB handles the storecheck flag. | Gabe Black | |
2009-04-19 | X86: Some segment selectors can be used when "NULL". | Gabe Black | |
2009-04-08 | tlb: More fixing of unified TLB | Nathan Binkert | |
2009-04-08 | tlb: Don't separate the TLB classes into an instruction TLB and a data TLB | Gabe Black | |
2009-02-27 | quell gcc 4.3 warning | Nathan Binkert | |
2009-02-27 | X86: Fix segment limit checks. | Gabe Black | |
2009-02-25 | X86: Actually check page protections. | Gabe Black | |
2009-02-25 | X86: Add a flag to force memory accesses to happen at CPL 0. | Gabe Black | |
2009-02-25 | X86: Make the X86 TLB take advantage of delayed translations, and get rid of ↵ | Gabe Black | |
the fake TLB miss faults. | |||
2009-02-25 | CPU: Implement translateTiming which defers to translateAtomic, and convert ↵ | Gabe Black | |
the timing simple CPU to use it. | |||
2009-02-25 | ISA: Replace the translate functions in the TLBs with translateAtomic. | Gabe Black | |
2009-02-23 | X86: Pass whether an access was a read/write/fetch so faults can behave ↵ | Gabe Black | |
accordingly. | |||
2009-02-01 | X86: Compute PCI config addresses correctly. | Gabe Black | |
2008-11-10 | mem: update stuff for changes to Packet and Request | Nathan Binkert | |
2008-11-02 | Add in Context IDs to the simulator. From now on, cpuId is almost never used, | Lisa Hsu | |
the primary identifier for a hardware context should be contextId(). The concept of threads within a CPU remains, in the form of threadId() because sometimes you need to know which context within a cpu to manipulate. | |||
2008-11-02 | make BaseCPU the provider of _cpuId, and cpuId() instead of being scattered | Lisa Hsu | |
across the subclasses. generally make it so that member data is _cpuId and accessor functions are cpuId(). The ID val comes from the python (default -1 if none provided), and if it is -1, the index of cpuList will be given. this has passed util/regress quick and se.py -n4 and fs.py -n4 as well as standard switch. | |||
2008-10-12 | X86: Make the local APIC accessible through the memory system directly, and ↵ | Gabe Black | |
make the timer work. | |||
2008-10-12 | Turn Interrupts objects into SimObjects. Also, move local APIC state into ↵ | Gabe Black | |
x86's Interrupts object. | |||
2008-06-12 | X86: Rename the divide count register to divide configuration. | Gabe Black | |
2008-06-12 | X86: Change how segment loading is performed. | Gabe Black | |
2008-06-12 | X86: In non 64bit mode, throw a fault when a NULL segment is accessed. | Gabe Black | |
2008-06-12 | X86: Have all 8 machine check registers since the kernel assumes they're there. | Gabe Black | |
2008-06-12 | X86: Bypass unaligned access support for register addressed MSRs. | Gabe Black | |
2008-06-12 | X86: Remove enforcement of APIC register access alignment. Panic if more ↵ | Gabe Black | |
than one register is accessed at a time. | |||
2008-03-01 | X86: Don't map the local APIC into the physical address space in SE mode. | Gabe Black | |
--HG-- extra : convert_revision : b7103974b12130bbf43583c4cb5294b808add208 | |||
2008-02-26 | X86: Put in initial implementation of the local APIC. | Gabe Black | |
--HG-- extra : convert_revision : 1708a93d96b819e64ed456c75dbb5325ac8114a8 | |||
2008-02-26 | X86: Implement the INVLPG instruction and the TIA microop. | Gabe Black | |
--HG-- extra : convert_revision : 31db1ee082f6c3ca5443cba1eb335e408661ead2 | |||
2008-02-26 | TLB: Make a TLB base class and put a virtual demapPage function in it. | Gabe Black | |
--HG-- extra : convert_revision : cc0e62a5a337fd5bf332ad33bed61c0d505a936f | |||
2008-02-26 | X86: Get PCI config space to work, and adjust address space prefix numbering ↵ | Gabe Black | |
scheme. --HG-- extra : convert_revision : 2b382f478ee8cde3a35aa4c105196f200bc7afa6 | |||
2008-01-12 | X86: Make the IO ports work using extra physical address lines. Add a serial ↵ | Gabe Black | |
port. --HG-- extra : convert_revision : a14cb4fc9afedfc0ff58b11a7f8fb5516d462cc6 | |||
2007-12-01 | X86: Reorganize segmentation and implement segment selector movs. | Gabe Black | |
--HG-- extra : convert_revision : 553c3ffeda1f5312cf02493f602e7d4ba2fe66e8 | |||
2007-11-12 | X86: Separate out the page table walker into it's own cc and hh. | Gabe Black | |
--HG-- extra : convert_revision : cbc3af01ca3dc911a59224a574007c5c0bcf6042 | |||
2007-11-12 | X86: Fix a stupid typo where WRMSR and RDMSR were switched, and add a debug ↵ | Gabe Black | |
statement. --HG-- extra : convert_revision : f1eb17291f4c01f3c0fa8f99650bc1edf09d21de | |||
2007-11-12 | X86: Implement tlb invalidation and make it happen some of the times it should. | Gabe Black | |
--HG-- extra : convert_revision : 376516d33cd539fa526c834ef2b2c33069af3040 | |||
2007-11-12 | X86: Work on the page table walker, TLB, and related faults. | Gabe Black | |
--HG-- extra : convert_revision : 9edde958b7e571c07072785f18f9109f73b8059f | |||
2007-11-12 | X86: Implement a page table walker. | Gabe Black | |
--HG-- extra : convert_revision : 36bab5750100318faa9ba7178dc2e38590053aec | |||
2007-11-12 | X86: Various fixes to indexing segmentation related registers | Gabe Black | |
--HG-- extra : convert_revision : 3d45da3a3fb38327582cfdfb72cfc4ce1b1d31af | |||
2007-10-25 | TLB: Fix serialization issues with the tlb entries and make the page table ↵ | Gabe Black | |
store the process, not the system. --HG-- extra : convert_revision : 2421af11f62f60fb48faeee6bddadac2987df0e8 | |||
2007-10-12 | X86: Implement MSR reads and writes and the wrsmr and rdmsr instructions. | Gabe Black | |
There are no priviledge checks, so these instructions will all work in all modes. --HG-- extra : convert_revision : ff893eb569313d8aecbfffb47bcbd1c2d65cd393 | |||
2007-10-07 | X86: Work on the x86 tlb. | Gabe Black | |
--HG-- extra : convert_revision : a08a5cb049a6030ba9fd56a89383d56026238dbf | |||
2007-10-02 | Merge with head. | Gabe Black | |
--HG-- extra : convert_revision : 1aa0e4569a7c10e6a395c2c951ac29275b5bcf59 | |||
2007-10-02 | X86: Start implementing the x86 tlb which will handle segmentation ↵ | Gabe Black | |
permission and limit checks and paging. --HG-- extra : convert_revision : 6072f7d9eecbaa066d39d6da7f0180ea4a2615af | |||
2007-09-28 | Rename cycles() function to ticks() | Ali Saidi | |
--HG-- extra : convert_revision : 790eddb793d4f5ba35813d001037bd8601bd76a5 | |||
2007-09-24 | X86: Get X86_FS to compile. | Gabe Black | |
--HG-- extra : convert_revision : fb973bcf13648876d5691231845dd47a2be50f01 | |||
2007-08-31 | X86: Get x86 to compile again after the simobject constructor change. | Gabe Black | |
--HG-- extra : convert_revision : 17a3e16e849bee88892223f0c993b19c15daa554 |