|
|
@15374
|
16 years |
vboxsync |
Scratch pad
|
|
|
@15371
|
16 years |
vboxsync |
More paranoia
|
|
|
@15368
|
16 years |
vboxsync |
Paranoia
|
|
|
@15364
|
16 years |
vboxsync |
Cleanup + extra check
|
|
|
@15363
|
16 years |
vboxsync |
Type corrections for logging.
|
|
|
@15362
|
16 years |
vboxsync |
Don't use RTCCUINTREG.
|
|
|
@15361
|
16 years |
vboxsync |
Wrong stack position
|
|
|
@15360
|
16 years |
vboxsync |
Comment
|
|
|
@15359
|
16 years |
vboxsync |
Makes no difference.
|
|
|
@15358
|
16 years |
vboxsync |
Resync the whole guest state after each world switch.
|
|
|
@15354
|
16 years |
vboxsync |
Flush the VMCS write cache first (before any other vmreads/vmwrites!)
|
|
|
@15349
|
16 years |
vboxsync |
VMM: Fixed linked list bug responsible for #3379.
|
|
|
@15348
|
16 years |
vboxsync |
#3202: Optimized PGMPOOL_PAGE_2_PTR for darwin/R0 and */RC.
|
|
|
@15347
|
16 years |
vboxsync |
PGMR0DynMap: Fixed testcase (missing migration).
|
|
|
@15346
|
16 years |
vboxsync |
Avoid a few calls to RTMpCpuId() and RTMCpuIdToSetIndex().
|
|
|
@15344
|
16 years |
vboxsync |
#3202: Optimizations of the dynamic page mapping code (ring-0). Do …
|
|
|
@15332
|
16 years |
vboxsync |
Messed up return code.
|
|
|
@15331
|
16 years |
vboxsync |
More fixes
|
|
|
@15328
|
16 years |
vboxsync |
VT-x switcher updates
|
|
|
@15317
|
16 years |
vboxsync |
Removed VMR3GetGuestBitness.
|
|
|
@15307
|
16 years |
vboxsync |
VT-x switcher update
|
|
|
@15306
|
16 years |
vboxsync |
Fixed VMCSREAD macro
|
|
|
@15303
|
16 years |
vboxsync |
REM: actually ask for guest bitness when loading apropriate implmentation
|
|
|
@15297
|
16 years |
vboxsync |
Activate VMX_USE_CACHED_VMCS_ACCESSES
|
|
|
@15296
|
16 years |
vboxsync |
Update the 64 bits variant too
|
|
|
@15295
|
16 years |
vboxsync |
Update
|
|
|
@15294
|
16 years |
vboxsync |
Write order is important.
|
|
|
@15292
|
16 years |
vboxsync |
better assertion
|
|
|
@15291
|
16 years |
vboxsync |
Flush pending writes when leaving ring 0.
|
|
|
@15289
|
16 years |
vboxsync |
Flush the queued writes first before checking the values. (debug only)
|
|
|
@15288
|
16 years |
vboxsync |
Exclusive
|
|
|
@15284
|
16 years |
vboxsync |
PGM, REM: Virtual address in TLB - this is what I meant…
|
|
|
@15276
|
16 years |
vboxsync |
Fix
|
|
|
@15275
|
16 years |
vboxsync |
Fixes
|
|
|
@15273
|
16 years |
vboxsync |
Missing setup
|
|
|
@15265
|
16 years |
vboxsync |
Wrong operand order
|
|
|
@15262
|
16 years |
vboxsync |
Bug fixes
|
|
|
@15258
|
16 years |
vboxsync |
Don't cache 64 bits read and writes for now (the _FULL fields).
|
|
|
@15257
|
16 years |
vboxsync |
PGMR0DynMap: Two more parenthesis.
|
|
|
@15255
|
16 years |
vboxsync |
Compile fixes
|
|
|
@15254
|
16 years |
vboxsync |
Bugfix
|
|
|
@15253
|
16 years |
vboxsync |
Fixed wrong opcodes
|
|
|
@15250
|
16 years |
vboxsync |
Duplicate index
|
|
|
@15249
|
16 years |
vboxsync |
More VMCS access caching work.
|
|
|
@15246
|
16 years |
vboxsync |
More VMCS read/write caching.
|
|
|
@15236
|
16 years |
vboxsync |
Started with VMCS read/write cache.
|
|
|
@15228
|
16 years |
vboxsync |
backed out 40461. (PGMAllBth.h)
|
|
|
@15227
|
16 years |
vboxsync |
PGMAllBth: Fixed typo in CalcKind (harmless), did some predicting and …
|
|
|
@15226
|
16 years |
vboxsync |
PGM: Inlined PGMDynMapHCPageOff (get rid of it perhaps?).
|
|
|
@15225
|
16 years |
vboxsync |
PGMPool: typo in stat description.
|
|
|
@15224
|
16 years |
vboxsync |
PGMR0DynMap: Silly silly silly silly bug, mapping were mapped write …
|
|
|
@15218
|
16 years |
vboxsync |
HWACCM: some temporary profiling of sub-parts of SwitchFromGC_2.
|
|
|
@15217
|
16 years |
vboxsync |
HWACCM: describe the exit reason stats.
|
|
|
@15214
|
16 years |
vboxsync |
HWACCMA.asm: code alignment, avoid stack.
|
|
|
@15213
|
16 years |
vboxsync |
HWACCMA.asm: code alignment.
|
|
|
@15211
|
16 years |
vboxsync |
VMXR0SaveHostState: Assert on bad cs and ss.
|
|
|
@15199
|
16 years |
vboxsync |
HWACCMR0A.asm: trimmed down VMXR0StartVM32 without any real effect. :/
|
|
|
@15198
|
16 years |
vboxsync |
HWACCMR0A.asm: retf -> far jmps for 64->32 thunking on darwin.
|
|
|
@15197
|
16 years |
vboxsync |
HWACCM: split up the SwitchFromGC (aka StatExit) stats into two parts …
|
|
|
@15196
|
16 years |
vboxsync |
PGMR0DynMap: profiling the whole shebang.
|
|
|
@15189
|
16 years |
vboxsync |
VMXR0RunGuestCode: profiling fixes.
|
|
|
@15188
|
16 years |
vboxsync |
Some typos corrected.
|
|
|
@15187
|
16 years |
vboxsync |
Compile fix
|
|
|
@15186
|
16 years |
vboxsync |
Fixed fpu and debug state syncing.
|
|
|
@15184
|
16 years |
vboxsync |
typos
|
|
|
@15183
|
16 years |
vboxsync |
Duh
|
|
|
@15182
|
16 years |
vboxsync |
Argh
|
|
|
@15181
|
16 years |
vboxsync |
Restrict instruction emulation for 64 bits guests on 32 bits hosts.
|
|
|
@15177
|
16 years |
vboxsync |
Fix for darwin assertion.
|
|
|
@15174
|
16 years |
vboxsync |
#1865: don't ever return invalid ring-0 address on 2x4G systems, …
|
|
|
@15172
|
16 years |
vboxsync |
Shadow paging fixes for amd64 on 32 bits hosts.
|
|
|
@15167
|
16 years |
vboxsync |
HWACCMGetShwPagingMode change backed out.
|
|
|
@15162
|
16 years |
vboxsync |
Compile fix
|
|
|
@15161
|
16 years |
vboxsync |
Backed out accidental commit 40567
|
|
|
@15160
|
16 years |
vboxsync |
Compile fix
|
|
|
@15159
|
16 years |
vboxsync |
Set the correct shadow paging mode for AMD-V nested paging.
|
|
|
@15155
|
16 years |
vboxsync |
Removed wrong assertion
|
|
|
@15154
|
16 years |
vboxsync |
Always use amd64 paging if the guest is in amd64 mode (nested paging).
|
|
|
@15153
|
16 years |
vboxsync |
Always use amd64 paging if the guest is in amd64 mode (nested paging).
|
|
|
@15151
|
16 years |
vboxsync |
PGMMODE_AMD64 guest mode always implied PGMMODE_AMD64 shadow mode.
|
|
|
@15150
|
16 years |
vboxsync |
Wrong handler
|
|
|
@15148
|
16 years |
vboxsync |
Update
|
|
|
@15147
|
16 years |
vboxsync |
Wrong push order
|
|
|
@15144
|
16 years |
vboxsync |
Oops
|
|
|
@15142
|
16 years |
vboxsync |
Compile fixes
|
|
|
@15141
|
16 years |
vboxsync |
Cleaned up
|
|
|
@15134
|
16 years |
vboxsync |
HWACCMR0: Don't register power notification when using SUPR0EnableVTx …
|
|
|
@15129
|
16 years |
vboxsync |
PDMDevHlp: RT_BIT_32
|
|
|
@15127
|
16 years |
vboxsync |
grr
|
|
|
@15126
|
16 years |
vboxsync |
pdmR3DevHlp_PCIIORegionRegister: make too big hurt.
|
|
|
@15111
|
16 years |
vboxsync |
Fixed offset overflow bug (#3357).
|
|
|
@15100
|
16 years |
vboxsync |
PCI device size sanity check
|
|
|
@15099
|
16 years |
vboxsync |
this applies to PCI I/O memory as well
|
|
|
@15097
|
16 years |
vboxsync |
don't allow to register PCI memory regions with a size != 2n
|
|
|
@15096
|
16 years |
vboxsync |
typo
|
|
|
@15072
|
16 years |
vboxsync |
Compile fixes
|
|
|
@15071
|
16 years |
vboxsync |
Deal with 64 bits address flushes in 32 bits host mode. (flush the …
|
|
|
@15063
|
16 years |
vboxsync |
Unbreak the old recompiler
|
|
|
@15046
|
16 years |
vboxsync |
No need to restore CR2 for AMD-V.
|
|
|
@15045
|
16 years |
vboxsync |
VT-x 64 bits switcher handler updates
|
|
|