|
|
|
@33540
|
14 years |
vboxsync |
*: spelling fixes, thanks Timeless!
|
|
|
|
@32872
|
14 years |
vboxsync |
Wrong PD type (triggers assertion in debug build; otherwise harmless)
|
|
|
|
@32516
|
14 years |
vboxsync |
Removed double invalidate.
|
|
|
|
@32036
|
14 years |
vboxsync |
Removed X86_PTE_PAE_PG_MASK, renamed X86_PTE_PAE_PG_MASK_FULL to …
|
|
|
|
@32009
|
14 years |
vboxsync |
Removed GST_PDPE_PG_MASK and renamed GST_PDPE_PG_MASK_FULL to …
|
|
|
|
@32005
|
14 years |
vboxsync |
Changed all X86_PDPE_PG_MASK references to X86_PDPE_PG_MASK_FULL.
|
|
|
|
@32004
|
14 years |
vboxsync |
pgmShwSyncPaePDPtr: Only sync X86_PDPE_P and X86_PDPE_A since most of …
|
|
|
|
@32000
|
14 years |
vboxsync |
x86.h,*: Eliminated X86_PML4E_PG_MASK and renamed …
|
|
|
|
@31998
|
14 years |
vboxsync |
Changed the remaining X86_PML4E_PG_MASK uses to X86_PML4E_PG_MASK_FULL.
|
|
|
|
@31997
|
14 years |
vboxsync |
PGM: Don't shadow any extra bits in long mode PDPEs and PML4Es.
|
|
|
|
@31996
|
14 years |
vboxsync |
Mostly safe X86_PTE_PAE_PG_MASK -> X86_PTE_PAE_PG_MASK_FULL conversions.
|
|
|
|
@31994
|
14 years |
vboxsync |
Safe X86_PDPE_PG_MASK -> X86_PDPE_PG_MASK_FULL conversions.
|
|
|
|
@31993
|
14 years |
vboxsync |
Safe X86_PML4E_PG_MASK -> X86_PML4E_PG_MASK_FULL conversions.
|
|
|
|
@31870
|
14 years |
vboxsync |
PGM: Don't sync unnecessary PTE bits.
|
|
|
|
@31849
|
14 years |
vboxsync |
PGM: Don't shadow PDE bits 62/3:52 (NXE=1/0), only shadow the bits we …
|
|
|
|
@31780
|
14 years |
vboxsync |
PGM: Addressed a fixme. logging and minor cleanup.
|
|
|
|
@31636
|
14 years |
vboxsync |
EM: Addressed VBOXSTRICTRC todo from r64673. Decided to only use …
|
|
|
|
@31565
|
14 years |
vboxsync |
PGM,HWACCM: MMIO optimizations - coding in progress.
|
|
|
|
@31402
|
14 years |
vboxsync |
PGM: Replaced the hazzardous raw-mode context dynamic mapping code …
|
|
|
|
@31170
|
14 years |
vboxsync |
PGM: More inline cleanup (prep for tracking dynamic mappings in raw-mode).
|
|
|
|
@31167
|
14 years |
vboxsync |
PGM: Pass pVCpu instead of pPGM (PPGMCPU) and eliminate …
|
|
|
|
@31123
|
14 years |
vboxsync |
PGM: Moved the PGM stats out of the VM structure. Reduces the size of …
|
|
|
|
@31081
|
14 years |
vboxsync |
PGM: Use GstWalk in the #PF, part 1.
|
|
|
|
@31080
|
14 years |
vboxsync |
PGM: Micro optimizations.
|
|
|
|
@31067
|
14 years |
vboxsync |
PGM: A couple of simplifications and optimizations. -assertions
|
|
|
|
@31066
|
14 years |
vboxsync |
PGM: A couple of simplifications and optimizations.
|
|
|
|
@31054
|
14 years |
vboxsync |
Added PGMCPU::fNoExecutionEnabled.
|
|
|
|
@30889
|
14 years |
vboxsync |
PGM: Cleanups related to pending MMIO/#PF optimizations. Risky.
|
|
|
|
@30861
|
14 years |
vboxsync |
VMM,REM: Replumbled the MSR updating and reading so that PGM can …
|
|
|
|
@30831
|
14 years |
vboxsync |
Another Mac compile fix
|
|
|
|
@30830
|
14 years |
vboxsync |
Mac compile fixes
|
|
|
|
@30824
|
14 years |
vboxsync |
Must also deal with zero cr3 translation ptrs in ring 0.
|
|
|
|
@30326
|
15 years |
vboxsync |
PGM: PGMShwModifyPage/PGMShwSetPage -> PGMShwMakePageWritable, …
|
|
|
|
@29250
|
15 years |
vboxsync |
iprt/asm*.h: split out asm-math.h, don't include asm-*.h from asm.h, …
|
|
|
|
@28800
|
15 years |
vboxsync |
Automated rebranding to Oracle copyright/license strings via filemuncher
|
|
|
|
@28754
|
15 years |
vboxsync |
Backed out 60634
|
|
|
|
@28752
|
15 years |
vboxsync |
Always overwrite old PML4E or PDPTE.
|
|
|
|
@27816
|
15 years |
vboxsync |
PGMSyncCR3: Go back to ring 3 if a pgm pool sync is again pending.
|
|
|
|
@27814
|
15 years |
vboxsync |
Backed out part of r59436
|
|
|
|
@27813
|
15 years |
vboxsync |
Backed out r59424
|
|
|
|
@27784
|
15 years |
vboxsync |
PGMSyncCR3: pgmPoolResetDirtyPages must be called before pgmPoolSyncCR3
|
|
|
|
@27778
|
15 years |
vboxsync |
Must take the pgm lock during PGMSyncCR3; guest SMP can cause an …
|
|
|
|
@27408
|
15 years |
vboxsync |
Logging fix
|
|
|
|
@27390
|
15 years |
vboxsync |
Tweaked previous fix
|
|
|
|
@27378
|
15 years |
vboxsync |
pgmPoolMonitorModifiedClearAll can cause a pgm pool flush (dirty page …
|
|
|
|
@27371
|
15 years |
vboxsync |
Don't always change back the cr3
|
|
|
|
@27370
|
15 years |
vboxsync |
Logging
|
|
|
|
@27369
|
15 years |
vboxsync |
Make sure we check for pending pgm pool syncs as we clear …
|
|
|
|
@26685
|
15 years |
vboxsync |
Large page changes
|
|
|
|
@26277
|
15 years |
vboxsync |
VMM: more RC/GC warnings - CSAMDoesPageNeedScanning and CSAMMarkPage …
|
|
|
|
@26202
|
15 years |
vboxsync |
Broke up guest page fault and dirty page checking to avoid taking the …
|
|
|
|
@26180
|
15 years |
vboxsync |
*: The rest of the %V* format specifiers are history.
|
|
|
|
@26150
|
15 years |
vboxsync |
PGM: Split out the inlined code from PGMInternal.h and into …
|
|
|
|
@25958
|
15 years |
vboxsync |
REMNotifyInvalidatePage never rails; drop the return code
|
|
|
|
@25935
|
15 years |
vboxsync |
PGM,CPUM: Be more careful and flexible with guest mappings on restore. …
|
|
|
|
@25915
|
15 years |
vboxsync |
PGMInvalidatePage: invalidate the TLB entry; might already be done by …
|
|
|
|
@25912
|
15 years |
vboxsync |
Ignore all irrelevant error codes out non-present pages/pds etc in …
|
|
|
|
@25866
|
15 years |
vboxsync |
VMM: More micro optimizations.
|
|
|
|
@25537
|
15 years |
vboxsync |
Removed all inactive PGM pool code.
|
|
|
|
@24764
|
15 years |
vboxsync |
Handle missing page inconsistency with guest smp (instruction emulation)
|
|
|
|
@24206
|
15 years |
vboxsync |
No #ifdefs
|
|
|
|
@24201
|
15 years |
vboxsync |
Compile fix
|
|
|
|
@24197
|
15 years |
vboxsync |
Introducing PGMHasDirtyPages
|
|
|
|
@23087
|
15 years |
vboxsync |
Added comment
|
|
|
|
@23086
|
15 years |
vboxsync |
Check for more invalid rcs (4064)
|
|
|
|
@23085
|
15 years |
vboxsync |
The VERR_PAGE_TABLE_NOT_PRESENT problem occurs on uniprocessor VMs …
|
|
|
|
@22890
|
15 years |
vboxsync |
VM::cCPUs -> VM::cCpus so it matches all the other cCpus and aCpus members.
|
|
|
|
@22545
|
15 years |
vboxsync |
Update
|
|
|
|
@22544
|
15 years |
vboxsync |
Moved locking inside #ifdef
|
|
|
|
@22473
|
15 years |
vboxsync |
Disabled experiment with optimized dirty PTs.
|
|
|
|
@21059
|
15 years |
vboxsync |
LogRel -> Log
|
|
|
|
@21057
|
15 years |
vboxsync |
Correction
|
|
|
|
@21056
|
15 years |
vboxsync |
Workaround for difficult to reproduce problem (invalid …
|
|
|
|
@20874
|
15 years |
vboxsync |
VMMR0CallHost -> VMMRZCallRing3[NoCpu]; VMMCALLHOST -> VMMCALLRING3.
|
|
|
|
@20873
|
15 years |
vboxsync |
VMMGCCallHost -> VMMRZCallRing3[NoCpu].
|
|
|
|
@20795
|
15 years |
vboxsync |
VMM: Fixed guest PAE issues on the mac.
|
|
|
|
@20767
|
15 years |
vboxsync |
Locking paranoia
|
|
|
|
@20762
|
15 years |
vboxsync |
More PGM locking
|
|
|
|
@20671
|
16 years |
vboxsync |
Bigger lock for the pagefault handler.
Avoid deadlocks when syncing …
|
|
|
|
@20567
|
16 years |
vboxsync |
DevATA,ATAController: Do not use MMGCRamReadNoTrapHandler nor …
|
|
|
|
@20151
|
16 years |
vboxsync |
Handle pgm pool flushes a bit differently.
|
|
|
|
@20068
|
16 years |
vboxsync |
Trying to get rid of annoying assertions
|
|
|
|
@20008
|
16 years |
vboxsync |
PDMCritSect: rewrite, ring-0 unlocking not yet enabled.
|
|
|
|
@19874
|
16 years |
vboxsync |
Protect PGMShwModifyPage
|
|
|
|
@19833
|
16 years |
vboxsync |
PGM_INVL_GUEST_TLBS -> PGM_INVL_VCPU_TLBS
|
|
|
|
@19808
|
16 years |
vboxsync |
Invalidate is per VCPU.
|
|
|
|
@19790
|
16 years |
vboxsync |
Protect InvalidatePage with the pgm lock.
|
|
|
|
@19682
|
16 years |
vboxsync |
Try to cleanup after one VCPU goes into guru meditation mode. Release …
|
|
|
|
@19516
|
16 years |
vboxsync |
Always call pgmPoolSyncCR3 from PGMSyncCR3 (regardless of guest paging …
|
|
|
|
@19474
|
16 years |
vboxsync |
MMIO locking
|
|
|
|
@19471
|
16 years |
vboxsync |
Added PGMIsLocked & PDMCritSectIsLocked
|
|
|
|
@19329
|
16 years |
vboxsync |
Removed pgmPoolGetPageByHCPhys.
|
|
|
|
@19141
|
16 years |
vboxsync |
Action flags breakup.
Fixed PGM saved state loading of 2.2.2 images. …
|
|
|
|
@18992
|
16 years |
vboxsync |
More PGM api changes
|
|
|
|
@18988
|
16 years |
vboxsync |
PGM api changes
|
|
|
|
@18958
|
16 years |
vboxsync |
Extra compile check
|
|
|
|
@18957
|
16 years |
vboxsync |
Fixed locked array size (was too small) and caused corruption.
|
|
|
|
@18949
|
16 years |
vboxsync |
Bug fix
|
|
|
|
@18943
|
16 years |
vboxsync |
Mac build fix
|
|
|
|
@18927
|
16 years |
vboxsync |
Big step to separate VMM data structures for guest SMP. (pgm, em)
|
|
|
|
