summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2008-07-16mem: use single BadAddr responder per system.Steve Reinhardt
Previously there was one per bus, which caused some coherence problems when more than one decided to respond. Now there is just one on the main memory bus. The default bus responder on all other buses is now the downstream cache's cpu_side port. Caches no longer need to do address range filtering; instead, we just have a simple flag to prevent snoops from propagating to the I/O bus.
2009-04-21Automated merge with ssh://m5sim.org//repo/m5Nathan Binkert
2009-04-21pseudo: only include kernel stats if FULL_SYSTEM.Nathan Binkert
2009-04-21arm: include missing file for armNathan Binkert
2009-04-21arm: Unify the ARM tlb. We forgot about this when we did the rest.Nathan Binkert
This code compiles, but there are no tests still
2009-04-21syscall_emul: style fixes (mostly wrapping overly long lines)Steve Reinhardt
2009-04-21syscall: Resolve conflicts between m5threads and Gabe's recent SE changes.Steve Reinhardt
2009-04-21Commit m5threads package.Daniel Sanchez
This patch adds limited multithreading support in syscall-emulation mode, by using the clone system call. The clone system call works for Alpha, SPARC and x86, and multithreaded applications run correctly in Alpha and SPARC.
2009-04-21SCons: Export export_vars so SConsopts files can add to themNathan Binkert
2009-04-21Minor tweaks for future Ruby compatibility.Steve Reinhardt
2009-04-21request: add PREFETCH flag.Steve Reinhardt
2009-04-20request: rename INST_READ to INST_FETCH.Steve Reinhardt
2009-04-20request: split public and private flags into separate fields.Steve Reinhardt
This frees up needed space for more public flags. Also: - remove unused Request accessor methods - make Packet use public Request accessors, so it need not be a friend
2009-04-19Mem: Fill out the comment that describes the LOCKED request flag.Gabe Black
2009-04-19Mem: Change isLlsc to isLLSC.Gabe Black
2009-04-19X86: Fix the functions that manipulate large bit arrays in the local APIC.Gabe Black
2009-04-19X86: Fix up a copyright.Gabe Black
2009-04-19X86: Fix how the TLB handles the storecheck flag.Gabe Black
2009-04-19X86: Recognize and handle the lock legacy prefix.Gabe Black
2009-04-19X86: Implement a locking version of XADD.Gabe Black
2009-04-19X86: Implement a locking version of BTC.Gabe Black
2009-04-19X86: Implement a locking version of BTR.Gabe Black
2009-04-19X86: Implement a locking version of CMPXCHG.Gabe Black
2009-04-19X86: Implement a locking version of BTS.Gabe Black
2009-04-19X86: Implement a locking version of DEC.Gabe Black
2009-04-19X86: Implement a locking version of INC.Gabe Black
2009-04-19X86: Implement a locking version of NEG.Gabe Black
2009-04-19X86: Implement a locking version of NOT.Gabe Black
2009-04-19X86: Implement a locking version of XCHG.Gabe Black
2009-04-19X86: Implement a locking version of XOR.Gabe Black
2009-04-19X86: Implement a locking version of SUB.Gabe Black
2009-04-19X86: Implement a locking version of AND.Gabe Black
2009-04-19X86: Implement a locking version of SBB.Gabe Black
2009-04-19X86: Implement a locking version of ADC.Gabe Black
2009-04-19X86: Implement a locking version of OR.Gabe Black
2009-04-19X86: Implement a locking version of ADD.Gabe Black
2009-04-19X86: Implement the stul microop.Gabe Black
This microop does a store and unlocks the requested address. The RISC86 microop ISA doesn't seem to have an equivalent to this, so I'm guessing that the store following an ldstl is automatically unlocking. We don't do it this way for performance reasons since the behavior is the same.
2009-04-19X86: Implement the ldstl microop.Gabe Black
This microop does a load, checks that a store would succeed, and locks the requested address.
2009-04-19CPUs: Make the atomic CPU support locked memory accesses.Gabe Black
2009-04-19Memory: Add a LOCKED flag back in for x86 style locking.Gabe Black
2009-04-19Memory: Rename LOCKED for load locked store conditional to LLSC.Gabe Black
2009-04-19SE mode: Make keeping track of the number of syscalls less hacky.Gabe Black
2009-04-19X86: Mask the PIC at startup to avoid a glitch which causes an NMI.Gabe Black
2009-04-19X86: Actually handle 16 bit mode modrm.Gabe Black
2009-04-19X86: Make the TEST instruction set all the flags it's supposed to.Gabe Black
2009-04-19X86: Implement broadcast IPIs.Gabe Black
2009-04-19X86: Fix the ordering of the vendor string reported by CPUID.Gabe Black
2009-04-19X86: Keep track of what the initial count value was in the LAPIC timer.Gabe Black
2009-04-19X86: Only recognize the first startup IPI after INIT or reset.Gabe Black
2009-04-19X86: Use recvResponse to implement the idle bit in the Local APIC ICR.Gabe Black