Commit Graph

2480 Commits

Author SHA1 Message Date
Stanislav Shwartsman
314171bb56 fixed compilation w/o AVX 2011-10-09 13:56:39 +00:00
Stanislav Shwartsman
71cbff104b fixing xsave/xrstor flows with AVX 2011-10-09 09:19:49 +00:00
Stanislav Shwartsman
8ada4ce5e4 added to cpudb: Intel(R) Core(TM) i5 M 520 (Arrandale) - based on Westmere arch 2011-10-07 19:32:44 +00:00
Stanislav Shwartsman
2580d8c46d added FMA4 AMD instructions support, fixed mem access length for Intel scalar FMA instructions 2011-10-07 14:09:35 +00:00
Stanislav Shwartsman
aad57310c2 disasm for FMA4, better dbg print SSE rounding control with MXCSR 2011-10-06 20:33:10 +00:00
Stanislav Shwartsman
8a9b8f4622 MXCSR.FUZ is ignoired for F16 instructions 2011-10-03 15:08:22 +00:00
Stanislav Shwartsman
e282b5e88d Move DAZ handling into softfloat library (for float16, float32 and float64 only) and cleanup SSE and AVX code
Fix decoding of opcodes with VEX.W=1 in 32-bit mode (AVX2, FMA)
2011-10-01 15:40:36 +00:00
Stanislav Shwartsman
f425400af5 fixed warnings from compilation with mingw-gcc 4.6.1 2011-09-30 20:38:18 +00:00
Stanislav Shwartsman
e5d0540365 commit new added files 2011-09-29 22:38:38 +00:00
Stanislav Shwartsman
6751af5d8e added AVX FMA extensions support. The implementation is based on QEMU patch by Peter Maydell (fixed) 2011-09-29 22:20:56 +00:00
Stanislav Shwartsman
275194fb32 #GP on reading VMX_EPT_VPID_CAP MSR when EPT and VPID disabled 2011-09-26 20:36:26 +00:00
Stanislav Shwartsman
f0d9f8fab7 added some comments 2011-09-26 20:10:15 +00:00
Stanislav Shwartsman
0547c8823e compilation w/o x86-64 2011-09-26 19:48:58 +00:00
Stanislav Shwartsman
12ad45395b enable Penryn VMX capabilities with VMX=1, VMX=2 is required for EPT and heavier stuff 2011-09-26 19:36:20 +00:00
Stanislav Shwartsman
54d1d8aa55 added new assertion to generic cpuid 2011-09-26 18:47:47 +00:00
Stanislav Shwartsman
aa96ecd98a compilation fix 2011-09-26 18:18:10 +00:00
Stanislav Shwartsman
0aadf88c07 more polishing for vmx configurability 2011-09-26 18:08:31 +00:00
Stanislav Shwartsman
c28c7f6a06 Supply real VMX capabilities together with the CPU MODEL .bochsrc option.
So now the same single option will choose not only the CPUID flags but also VMX capabilities matching real HW machine.

Removed cpuid of core2_extreme_x9770 from the cpudb. I don't remember its VMX capabilities anyway.
There is another Penryn model in the cpudb - core2_penryn_t9600.
2011-09-26 12:31:40 +00:00
Stanislav Shwartsman
8d95830562 first step to configuration of VMX through cpuid_t class 2011-09-25 19:04:55 +00:00
Stanislav Shwartsman
b66feecc86 move common instrumentation constants (valid for all stubs) to cpu.h 2011-09-25 17:38:54 +00:00
Stanislav Shwartsman
62d0c8abf7 - Now you could disable x86-64 from .bochsrc so now it is possible to emulate
32-bit CPU using Bochs binary compiled with x86-64 support.

The commit also fixes some init.cc issues with initialization of SYSCALL/SYSRET MSR in AMD hosts and also includes code reorg.
2011-09-25 17:36:20 +00:00
Stanislav Shwartsman
2b7894de7b fixed dbg print mentioned in SF bug 3029271 2011-09-22 22:08:18 +00:00
Stanislav Shwartsman
1b9f286945 - New way of CPUs scheduling in SMP mode brings up to 50% speedup to the
SMP emulation. New implementation uses dynamic CPU quantum value and takes
   full advantage of the trace cache. Each emulated processor will execute
   the whole trace before switching to the next processor.
 * It is also safe to use large (up to 16 instructions) quantum values for
   the SMP emulation now and improve performance even further.

The same merge also completely fixes SF bug :
  [3312237] stepN command might be not working properly

Handlers chaining speedups are also supported with SMP emulation now.
2011-09-22 19:38:52 +00:00
Stanislav Shwartsman
f81589c5d6 Don't allow traces longer than cpu_loop can execute 2011-09-21 20:28:29 +00:00
Stanislav Shwartsman
c6d07ae1b5 store modrm() for x87 in Ib() byte because x87 have no Ib() 2011-09-20 06:02:27 +00:00
Stanislav Shwartsman
2583f8549a small code duplication fix 2011-09-19 20:47:59 +00:00
Stanislav Shwartsman
d489ba3d37 generic cpuid: automatically enable lzcnt of bmi is enabled; sse4a support in cpuid 2011-09-18 18:17:34 +00:00
Stanislav Shwartsman
6fb673b9fa change BX_PANIC to BX_ERROR 2011-09-18 17:36:54 +00:00
Stanislav Shwartsman
50207eeb90 - Added support for AMD SSE4A emulation, the instructions can be enabled
using .bochsrc CPUID option.
2011-09-18 16:18:22 +00:00
Stanislav Shwartsman
efc588cf1e rename avx2_gather.cc -> gather.cc 2011-09-16 20:59:57 +00:00
Stanislav Shwartsman
ea54f40361 keep global pages when needed in INVPCID/INVVPID 2011-09-16 20:52:38 +00:00
Stanislav Shwartsman
3632340dac improve bochs exit dump in long64 mode 2011-09-16 20:25:05 +00:00
Stanislav Shwartsman
88a58b3781 fixed compilation with x86-64=0 2011-09-16 20:12:36 +00:00
Stanislav Shwartsman
330bf62f61 added INVPCID instruction support 2011-09-16 20:06:23 +00:00
Stanislav Shwartsman
e2f0880f1c support more than 32-bit cpu features vector 2011-09-14 20:22:24 +00:00
Stanislav Shwartsman
d5fcfabb38 bugfix + update changes 2011-09-13 19:38:09 +00:00
Stanislav Shwartsman
f4dbaf1cd8 re-shuffle macros, no impact in general 2011-09-13 17:55:36 +00:00
Stanislav Shwartsman
02e1a0f23c Merge lazy flags optimization by Darek Mihocka.
I measure slight but consistent speedup of ~1-3% for all guests.
Tested: Windows XP/7 boot 32/64 bit, various Linux live CD
2011-09-12 19:36:53 +00:00
Stanislav Shwartsman
9f1f4781b3 fixed Sandy Bridge name in err message - it is Core i7 and not Core2 2011-09-06 19:49:22 +00:00
Stanislav Shwartsman
939aee87c9 handle special case - BSF/BSR vs TZCNT/LZCNT 2011-09-06 19:18:21 +00:00
Stanislav Shwartsman
184837e0ed fixed compilation err with no handlers chaining enabled 2011-09-06 15:41:52 +00:00
Stanislav Shwartsman
96cedbc756 continue handlers-chaining optimization: update time once per trace and not for every instruction 2011-09-06 15:35:39 +00:00
Stanislav Shwartsman
e000b61cfd make RDTSC 'end of trace' instruction - guarantee that any pair ot RDTSC/RDTSCP on same CPU do not belong to same trace (and therefore will always update time and etc) - required for Win7 Thin 2011-09-06 14:13:39 +00:00
Stanislav Shwartsman
5a350143a5 bug fixes 2011-09-06 13:09:45 +00:00
Stanislav Shwartsman
c67338203c small fixups, code cleanup and reorganization 2011-09-05 17:14:49 +00:00
Stanislav Shwartsman
41f9b25777 fixed avx2 gather instructions 2011-09-04 19:50:18 +00:00
Stanislav Shwartsman
c0f5919787 small optimization 2011-09-03 15:36:40 +00:00
Stanislav Shwartsman
8099fd9efd implemented alternative access to CR8: AMD feature. Lock CR0 -> CR8 2011-09-03 15:22:56 +00:00
Stanislav Shwartsman
cf56ffb6e0 BSF/BSR should stay, only F3 prefix change opcode 2011-08-31 21:13:50 +00:00
Stanislav Shwartsman
9d18af1207 fixed compilation for AVX OFF 2011-08-31 20:52:53 +00:00