Gabe Black [Fri, 27 Feb 2009 17:26:09 +0000 (09:26 -0800)]
X86: Don't treat the REX prefixes as prefixes in 32 bit modes. These are inc/dec instructions.
Gabe Black [Fri, 27 Feb 2009 17:26:01 +0000 (09:26 -0800)]
X86: Set address size to 64 bits when generating addresses internally.
Gabe Black [Fri, 27 Feb 2009 17:25:51 +0000 (09:25 -0800)]
X86: Add a vsyscall page for 32 bit processes to use.
Gabe Black [Fri, 27 Feb 2009 17:25:43 +0000 (09:25 -0800)]
X86: Implement sysenter as a system call interface.
Gabe Black [Fri, 27 Feb 2009 17:25:33 +0000 (09:25 -0800)]
X86: Add a 32 bit mmap2 system call.
Gabe Black [Fri, 27 Feb 2009 17:25:26 +0000 (09:25 -0800)]
X86: Install a 32 bit fstat64 system call.
Gabe Black [Fri, 27 Feb 2009 17:25:16 +0000 (09:25 -0800)]
X86: Take address size into account when computing an effective address.
Gabe Black [Fri, 27 Feb 2009 17:25:02 +0000 (09:25 -0800)]
X86: Make instructions that use intseg preserve all 8 bytes of their addresses.
Gabe Black [Fri, 27 Feb 2009 17:24:10 +0000 (09:24 -0800)]
X86: Fix a decoder bug and add in some missing instructions.
Gabe Black [Fri, 27 Feb 2009 17:23:58 +0000 (09:23 -0800)]
X86: Respect segment override prefixes even when there's no ModRM byte.
Gabe Black [Fri, 27 Feb 2009 17:23:50 +0000 (09:23 -0800)]
X86: Fix segment limit checks.
Gabe Black [Fri, 27 Feb 2009 17:23:42 +0000 (09:23 -0800)]
X86: Implement the 32 bit set_thread_area system call.
Gabe Black [Fri, 27 Feb 2009 17:23:27 +0000 (09:23 -0800)]
X86: Set an initial value for the LDT selector.
Gabe Black [Fri, 27 Feb 2009 17:23:17 +0000 (09:23 -0800)]
X86: Set up a space for a GDT in SE so we can set up TLS or LDT segments.
Gabe Black [Fri, 27 Feb 2009 17:23:00 +0000 (09:23 -0800)]
X86: Compute shift instruction flags correctly.
Gabe Black [Fri, 27 Feb 2009 17:22:50 +0000 (09:22 -0800)]
X86: Install some 32 bit system calls.
Gabe Black [Fri, 27 Feb 2009 17:22:30 +0000 (09:22 -0800)]
X86: Handle 32 bit system call arguments.
Gabe Black [Fri, 27 Feb 2009 17:22:14 +0000 (09:22 -0800)]
Processes: Make getting and setting system call arguments part of a process object.
Gabe Black [Fri, 27 Feb 2009 17:21:58 +0000 (09:21 -0800)]
X86: Implement the int system call interface in the decoder.
Gabe Black [Fri, 27 Feb 2009 17:21:36 +0000 (09:21 -0800)]
X86: Distinguish the width of values on the stack between 32 and 64 bit processes.
Gabe Black [Fri, 27 Feb 2009 17:21:14 +0000 (09:21 -0800)]
X86: Add a class to support 32 bit x86 linux process.
Ali Saidi [Fri, 27 Feb 2009 00:29:17 +0000 (19:29 -0500)]
CPA: Add annotations to IGbE and CopyEngine device models.
Ali Saidi [Fri, 27 Feb 2009 00:29:17 +0000 (19:29 -0500)]
CPA: Add code to automatically record function symbols as CPU executes.
Ali Saidi [Fri, 27 Feb 2009 00:29:17 +0000 (19:29 -0500)]
CPA: Add new object for gathering critical path annotations.
Ali Saidi [Fri, 27 Feb 2009 00:29:16 +0000 (19:29 -0500)]
CPA: Add m5ops for critical path annotation work.
Ali Saidi [Fri, 27 Feb 2009 00:29:16 +0000 (19:29 -0500)]
Trace: fix the --trace-start option
Gabe Black [Wed, 25 Feb 2009 18:22:49 +0000 (10:22 -0800)]
Devices: Make the RTC device reflect the use of BCD in its status registers.
Gabe Black [Wed, 25 Feb 2009 18:22:43 +0000 (10:22 -0800)]
X86: Implement IST stack switching.
Gabe Black [Wed, 25 Feb 2009 18:22:36 +0000 (10:22 -0800)]
CPU: Only look up the nearest symbol in the kernel if you're actually in kernel code.
Gabe Black [Wed, 25 Feb 2009 18:22:31 +0000 (10:22 -0800)]
ISA: Get rid of the get*RegName functions.
Gabe Black [Wed, 25 Feb 2009 18:22:25 +0000 (10:22 -0800)]
SPARC: Get rid of the state keeping track of register frames.
Gabe Black [Wed, 25 Feb 2009 18:22:17 +0000 (10:22 -0800)]
ISA: Set up common trace flags for tracing registers.
Gabe Black [Wed, 25 Feb 2009 18:22:09 +0000 (10:22 -0800)]
ISA: Get rid of FlattenIntIndex function.
Gabe Black [Wed, 25 Feb 2009 18:21:59 +0000 (10:21 -0800)]
SPARC: Get rid of flattenIndex in the int register file.
Gabe Black [Wed, 25 Feb 2009 18:21:52 +0000 (10:21 -0800)]
ISA: Use the "Stack" traceflag for DPRINTFs about the initial stack frame.
Gabe Black [Wed, 25 Feb 2009 18:21:46 +0000 (10:21 -0800)]
SPARC: Get rid of the setGlobals function.
Gabe Black [Wed, 25 Feb 2009 18:21:40 +0000 (10:21 -0800)]
SPARC: Get rid of the setCWP function.
Gabe Black [Wed, 25 Feb 2009 18:21:33 +0000 (10:21 -0800)]
SPARC: Add a traceflag for register windows.
Gabe Black [Wed, 25 Feb 2009 18:21:27 +0000 (10:21 -0800)]
X86: Implement the lldt instruction.
Gabe Black [Wed, 25 Feb 2009 18:21:21 +0000 (10:21 -0800)]
X86: Add segmentation checks for ldt related descriptors and selectors.
Gabe Black [Wed, 25 Feb 2009 18:21:14 +0000 (10:21 -0800)]
X86: Make the TSS type check actually return a fault if it fails.
Gabe Black [Wed, 25 Feb 2009 18:21:08 +0000 (10:21 -0800)]
X86: Make rdcr use merge and the mov to control register instructions use the right operand size.
Gabe Black [Wed, 25 Feb 2009 18:21:02 +0000 (10:21 -0800)]
X86: Implement CLTS.
Gabe Black [Wed, 25 Feb 2009 18:20:47 +0000 (10:20 -0800)]
X86: Make the segment register reading microops use merge.
Gabe Black [Wed, 25 Feb 2009 18:20:42 +0000 (10:20 -0800)]
X86: Implement the mov to debug register intructions.
Gabe Black [Wed, 25 Feb 2009 18:20:30 +0000 (10:20 -0800)]
X86: Rename oszForPseudoDesc maxOsz to reflect its more general use.
Gabe Black [Wed, 25 Feb 2009 18:20:25 +0000 (10:20 -0800)]
X86: Add code to interpret debug register values.
Gabe Black [Wed, 25 Feb 2009 18:20:19 +0000 (10:20 -0800)]
X86: Fix a few bugs with the segment register instructions in real mode.
Fix a few instances where the register form of zext was used where zexti was
intended. Also get rid of the 64 bit only rip relative addressed version since
64 bit and real mode are mutually exclusive.
Gabe Black [Wed, 25 Feb 2009 18:20:10 +0000 (10:20 -0800)]
X86: Do a merge for the zero extension microop.
Gabe Black [Wed, 25 Feb 2009 18:20:01 +0000 (10:20 -0800)]
X86: Add microops for reading/writing debug registers.
Gabe Black [Wed, 25 Feb 2009 18:19:54 +0000 (10:19 -0800)]
X86: Add classes that break out the bits of the DR6 and DR7 registers.
Gabe Black [Wed, 25 Feb 2009 18:19:47 +0000 (10:19 -0800)]
X86: Check src1 for illegal values since that's the index we actually use.
Gabe Black [Wed, 25 Feb 2009 18:19:41 +0000 (10:19 -0800)]
X86: Implement the fence instructions. These are not microcoded.
Gabe Black [Wed, 25 Feb 2009 18:19:33 +0000 (10:19 -0800)]
CPU: Add a flag to identify a read barrier to the static inst class.
Gabe Black [Wed, 25 Feb 2009 18:19:28 +0000 (10:19 -0800)]
X86: Update stats now that prefetch is implemented.
Gabe Black [Wed, 25 Feb 2009 18:19:22 +0000 (10:19 -0800)]
X86: Implement a basic prefetch instruction.
Gabe Black [Wed, 25 Feb 2009 18:19:14 +0000 (10:19 -0800)]
X86: Use the right portion of a register for stores.
Gabe Black [Wed, 25 Feb 2009 18:19:06 +0000 (10:19 -0800)]
X86: Add IRQ4 to the Intel MP tables.
Gabe Black [Wed, 25 Feb 2009 18:18:58 +0000 (10:18 -0800)]
X86: Actually check page protections.
Gabe Black [Wed, 25 Feb 2009 18:18:51 +0000 (10:18 -0800)]
X86: Update CS later so stack accesses have the right permission checks.
Gabe Black [Wed, 25 Feb 2009 18:18:45 +0000 (10:18 -0800)]
CPU: Update stats now that there's no fetch in the middle of macroops.
Gabe Black [Wed, 25 Feb 2009 18:18:36 +0000 (10:18 -0800)]
CPU: Don't fetch when executing a macroop.
If the CPL changes mid macroop, the end of the instruction might not be
priveleged enough to execute the beginning.
Gabe Black [Wed, 25 Feb 2009 18:18:29 +0000 (10:18 -0800)]
X86: Use atCPL0 for accesses that are part of CPU machinery.
Gabe Black [Wed, 25 Feb 2009 18:18:22 +0000 (10:18 -0800)]
X86: Add a flag to force memory accesses to happen at CPL 0.
Gabe Black [Wed, 25 Feb 2009 18:18:16 +0000 (10:18 -0800)]
X86: Move where CS is set so CPL checks work out.
Gabe Black [Wed, 25 Feb 2009 18:18:06 +0000 (10:18 -0800)]
X86: Implement inUserMode for x86.
Gabe Black [Wed, 25 Feb 2009 18:17:59 +0000 (10:17 -0800)]
X86: Add a trace flag for tracing faults.
Gabe Black [Wed, 25 Feb 2009 18:17:54 +0000 (10:17 -0800)]
X86: Implement the sysret instruction in long mode.
Gabe Black [Wed, 25 Feb 2009 18:17:49 +0000 (10:17 -0800)]
X86: Implement the longmode versions of the syscall instruction.
Gabe Black [Wed, 25 Feb 2009 18:17:43 +0000 (10:17 -0800)]
X86: Make the microcode assembler recognize r8-r15.
Gabe Black [Wed, 25 Feb 2009 18:17:38 +0000 (10:17 -0800)]
X86: Add a wrattr microop.
Gabe Black [Wed, 25 Feb 2009 18:17:27 +0000 (10:17 -0800)]
X86: Add a trace flag for the page table walker.
Gabe Black [Wed, 25 Feb 2009 18:17:19 +0000 (10:17 -0800)]
X86: Make exceptions handle stack switching.
Gabe Black [Wed, 25 Feb 2009 18:17:14 +0000 (10:17 -0800)]
X86: Implement the LTR instruction.
Gabe Black [Wed, 25 Feb 2009 18:17:08 +0000 (10:17 -0800)]
X86: Fix segment limit checking.
Gabe Black [Wed, 25 Feb 2009 18:17:02 +0000 (10:17 -0800)]
X86: Add a check to chks to verify a task state segment descriptor.
Gabe Black [Wed, 25 Feb 2009 18:16:54 +0000 (10:16 -0800)]
X86: Add a check to chks which raises #GP(selector) if selector is NULL or not in the GDT.
Gabe Black [Wed, 25 Feb 2009 18:16:43 +0000 (10:16 -0800)]
X86: Add makeAtomicResponse to the read/write functions of x86 devices.
Gabe Black [Wed, 25 Feb 2009 18:16:34 +0000 (10:16 -0800)]
X86: Fix the timing mode of the page table walker.
Gabe Black [Wed, 25 Feb 2009 18:16:29 +0000 (10:16 -0800)]
X86: Update stats for in place TLB miss handling.
Gabe Black [Wed, 25 Feb 2009 18:16:21 +0000 (10:16 -0800)]
X86: Make the X86 TLB take advantage of delayed translations, and get rid of the fake TLB miss faults.
Gabe Black [Wed, 25 Feb 2009 18:16:15 +0000 (10:16 -0800)]
CPU: Implement translateTiming which defers to translateAtomic, and convert the timing simple CPU to use it.
Gabe Black [Wed, 25 Feb 2009 18:16:04 +0000 (10:16 -0800)]
SPARC: Adjust a few instructions to not write registers in initiateAcc.
Gabe Black [Wed, 25 Feb 2009 18:15:56 +0000 (10:15 -0800)]
X86: Make the stupd microop not update registers in initiateAcc.
Gabe Black [Wed, 25 Feb 2009 18:15:44 +0000 (10:15 -0800)]
ISA: Replace the translate functions in the TLBs with translateAtomic.
Gabe Black [Wed, 25 Feb 2009 18:15:34 +0000 (10:15 -0800)]
CPU: Get rid of translate... functions from various interface classes.
Nathan Binkert [Mon, 23 Feb 2009 20:22:19 +0000 (12:22 -0800)]
stats: reorganize how parameters are stored and accessed.
Nathan Binkert [Mon, 23 Feb 2009 20:22:18 +0000 (12:22 -0800)]
stats: move the limits stuff into the types.hh file
Nathan Binkert [Mon, 23 Feb 2009 20:22:17 +0000 (12:22 -0800)]
stats: get rid of the convoluted 'database' code.
Just use the stuff directly and things ought to be more clear
Nathan Binkert [Mon, 23 Feb 2009 20:22:15 +0000 (12:22 -0800)]
stats: Try to make the names of things more intuitive.
Basically, this means renaming several things called data to info, which
is information about the statistics. Things that are named data now are
actual data stored for the statistic.
Nathan Binkert [Mon, 23 Feb 2009 20:04:52 +0000 (12:04 -0800)]
stats: clean up the statistics unittest
Nathan Binkert [Mon, 23 Feb 2009 20:04:50 +0000 (12:04 -0800)]
stats: fix text printout for distributions
Nathan Binkert [Mon, 23 Feb 2009 20:03:06 +0000 (12:03 -0800)]
stats: cleanup static stats to make startup work.
This is mainly to allow the unit test to run without requiring the standard
M5 stats from being initialized (e.g. sim_seconds, sim_ticks, host_seconds)
Nathan Binkert [Mon, 23 Feb 2009 19:48:40 +0000 (11:48 -0800)]
debug: Move debug_break into src/base
Gabe Black [Mon, 23 Feb 2009 08:20:34 +0000 (00:20 -0800)]
X86: Pass whether an access was a read/write/fetch so faults can behave accordingly.
Korey Sewell [Fri, 20 Feb 2009 16:02:48 +0000 (11:02 -0500)]
Remove unnecessary building of FreeList/RenameMap in InOrder. Clean-up comments and O3 extensions InOrder Thread Context
Nathan Binkert [Wed, 18 Feb 2009 18:00:15 +0000 (10:00 -0800)]
events: Make trace events happen at the right priority.
Also, while we're at it, remember that priorities are in the Event class
and add a disable method to disable tracing.
Steve Reinhardt [Wed, 18 Feb 2009 03:24:46 +0000 (19:24 -0800)]
Make etherdump timestamps zero-based.
We previously used the actual wall time for the base timestamps,
making etherdumps non-deterministic. This fixes that problem and
gets rid of the "malformed packet" at the front that we needed to
provide the right base timestamp to wireshark/tcpdump.
Lisa Hsu [Mon, 16 Feb 2009 22:47:39 +0000 (17:47 -0500)]
sycalls: implement mremap() and add DATA flag for getrlimit(). mremap has been tested on Alpha, compiles for the rest but not tested. I don't see why it wouldn't work though.
Steve Reinhardt [Mon, 16 Feb 2009 17:09:45 +0000 (12:09 -0500)]
Update stats for new prefetching fixes.
Prefetching is not enabled in any of our regressions, so no significant
stat values have changed, but zero-valued prefetch stats no longer
show up when prefetching is disabled so there are noticable changes
in the reference stat files anyway.