|
|
@20981
|
15 years |
vboxsync |
Backed out 49187; toxic
|
|
|
@20979
|
15 years |
vboxsync |
Cpu poke never worked in the VT-x/AMD-V case, because pVCpu->idHostCpu …
|
|
|
@20132
|
16 years |
vboxsync |
HWACCM: Finished (I hope) the VBOX_WITH_VMMR0_DISABLE_PREEMPTION code.
|
|
|
@19360
|
16 years |
vboxsync |
Split up GVM and introduced GVMCPU.
|
|
|
@19227
|
16 years |
vboxsync |
Implemented VMMGetCpu in ring 0. (SMP guests)
|
|
|
@19141
|
16 years |
vboxsync |
Action flags breakup.
Fixed PGM saved state loading of 2.2.2 images. …
|
|
|
@19123
|
16 years |
vboxsync |
VMMR0: Too chatty/messy in dmesg on darwin.
|
|
|
@18984
|
16 years |
vboxsync |
Autoset does belong in PGMCPU
|
|
|
@18977
|
16 years |
vboxsync |
More compile fixes
|
|
|
@18927
|
16 years |
vboxsync |
Big step to separate VMM data structures for guest SMP. (pgm, em)
|
|
|
@18008
|
16 years |
vboxsync |
Some extra checks
|
|
|
@17916
|
16 years |
vboxsync |
VT-x init: some BIOSes forget to set the locked bit.
|
|
|
@17246
|
16 years |
vboxsync |
Allow mixing of VT-x and software virtualization. (untested so far)
|
|
|
@16119
|
16 years |
vboxsync |
Clear CPUM_SYNC_FPU_STATE in CPUMR0SaveGuestFPU.
|
|
|
@15989
|
16 years |
vboxsync |
Fixed clearing properly
|
|
|
@15988
|
16 years |
vboxsync |
Restore previous EFER state while checking for SVM presence.
|
|
|
@15797
|
16 years |
vboxsync |
Redid r41365.
|
|
|
@15789
|
16 years |
vboxsync |
Protect code that relies on not being rescheduled to another cpu. …
|
|
|
@15701
|
16 years |
vboxsync |
fixed build
|
|
|
@15695
|
16 years |
vboxsync |
Compile fix
|
|
|
@15694
|
16 years |
vboxsync |
Profiling of the 32/64 switcher.
|
|
|
@15439
|
16 years |
vboxsync |
Enable 64 bits guest support on 32 bits hosts. Only use rem64 if the …
|
|
|
@15414
|
16 years |
vboxsync |
Corrected VBOX_WITH_HYBIRD_32BIT_KERNEL to …
|
|
|
@15409
|
16 years |
vboxsync |
Made exitting on the wrong cpu fatal in strict builds but not when …
|
|
|
@15404
|
16 years |
vboxsync |
#3202: 64-bit guest support on the mac.
|
|
|
@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 …
|
|
|
@14903
|
16 years |
vboxsync |
HWACCMR0: Try use SUPR0EnableVTx. (#3202)
|
|
|
@14899
|
16 years |
vboxsync |
Wrote testcase for the new switcher.
|
|
|
@14875
|
16 years |
vboxsync |
More switcher updates
|
|
|
@14870
|
16 years |
vboxsync |
Cleaning up.
|
|
|
@14859
|
16 years |
vboxsync |
More updates for 32/64.
|
|
|
@14845
|
16 years |
vboxsync |
Switcher updates
|
|
|
@14804
|
16 years |
vboxsync |
#3202: Got long mode darwin host running.
|
|
|
@14658
|
16 years |
vboxsync |
HWACCMR0: Added PGMDynMap*AutoSet calls upon entry and exit (darwin only).
|
|
|
@14606
|
16 years |
vboxsync |
HWACCMR0.cpp: partly enabled the code on the mac.
|
|
|
@14533
|
16 years |
vboxsync |
missing bits from r39820
|
|
|
@14532
|
16 years |
vboxsync |
Compile fix
|
|
|
@13960
|
16 years |
vboxsync |
Moved guest and host CPU contexts into per-VCPU array.
|
|
|
@13898
|
16 years |
vboxsync |
Moved more data to VMCPU.
|
|
|
@13883
|
16 years |
vboxsync |
Moved more data around.
|
|
|
@13879
|
16 years |
vboxsync |
SMP updates for VT-x/AMD-V.
|
|
|
@13873
|
16 years |
vboxsync |
Updates
|
|
|
@13872
|
16 years |
vboxsync |
Pass the VMCPU id on to all hwaccm functions.
|
|
|
@13825
|
16 years |
vboxsync |
VMM: %VX64 -> %RX64
|
|
|
@13816
|
16 years |
vboxsync |
VMM: VBOX_SUCCESS -> RT_SUCCESS, VBOX_FAILURE -> RT_FAILURE.
|
|
|
@13533
|
16 years |
vboxsync |
Extra assertions to check for unexpected use conditions.
|
|
|
@13532
|
16 years |
vboxsync |
CPUMQueryGuestCtxPtr doesn't need to return a status. It can never fail.
|
|
|
@13517
|
16 years |
vboxsync |
Refined suspend state testing.
|
|
|
@13516
|
16 years |
vboxsync |
Protection against touching VT-x/AMD-V after the suspend signal has …
|
|
|
@13514
|
16 years |
vboxsync |
Enabled power notification callbacks to disable VT-x/AMD-V before …
|
|
|
@13025
|
16 years |
vboxsync |
Updates for EPT.
|
|
|
@12989
|
16 years |
vboxsync |
VMM + VBox/cdefs.h: consolidated all the XYZ*DECLS of the VMM into …
|
|
|
@12892
|
16 years |
vboxsync |
AssertMsgRC
|
|
|
@12702
|
16 years |
vboxsync |
#1865: HWACCM - alignment fix+check for 32-bit gcc, doxygen.
|
|
|
@12657
|
16 years |
vboxsync |
#1865: CPUM. Also added missing aliasing for DR4&5 to the guest DRx …
|
|
|
@12600
|
16 years |
vboxsync |
Turned dr0..dr7 into an array.
|
|
|
@12578
|
16 years |
vboxsync |
Enable hardware breakpoint support for VT-x and AMD-V.
|
|
|
@12554
|
16 years |
vboxsync |
Some debug register statistics added.
|
|
|
@12225
|
16 years |
vboxsync |
VMM: X86_DR7_ENABLED_MASK should not include GD, because it isn't a …
|
|
|
@12162
|
16 years |
vboxsync |
VMM: Assert that we don't change CPU unexpectedly while executing in …
|
|
|
@12121
|
16 years |
vboxsync |
Committed hardware breakpoint support for VT-x and AMD-V. Untested and …
|
|
|
@12090
|
16 years |
vboxsync |
Started with hardware debug register support.
Fixed out of sync …
|
|
|
@11311
|
16 years |
vboxsync |
VMM: ELEMENTS -> RT_ELEMENTS.
|
|
|
@11133
|
16 years |
vboxsync |
compiler warnings
|
|
|
@10817
|
16 years |
vboxsync |
Started with EPT support.
|
|
|
@10687
|
16 years |
vboxsync |
Save the FPU control word and MXCSR on entry and restore them …
|
|
|
@10683
|
16 years |
vboxsync |
Backed out 33399; must save the host context on entry due to long …
|
|
|
@10682
|
16 years |
vboxsync |
Saving of the host state is done correctly already for VT-x. (not …
|
|
|
@10672
|
16 years |
vboxsync |
Added a comment about the fact that we trash our own FPU state. Could …
|
|
|
@10647
|
16 years |
vboxsync |
Manual saving of XMM registers.
Use new FPU/MMX/XMM state saving for …
|
|
|
@10572
|
16 years |
vboxsync |
Use NIL_RTR0MEMOBJ and ASMMemZeroPage.
|
|
|
@10537
|
16 years |
vboxsync |
Updated HWACCMDumpRegs
|
|
|
@10502
|
16 years |
vboxsync |
Take precautions for being rescheduled to a different cpu due to long …
|
|
|
@10489
|
16 years |
vboxsync |
AMD-V: Always flush the TLB the first time a cpu is used.
|
|
|
@10465
|
16 years |
vboxsync |
Cleaned up
|
|
|
@10301
|
16 years |
vboxsync |
Wrong place for the assertion
|
|
|
@10297
|
16 years |
vboxsync |
More assertions.
|
|
|
@9669
|
17 years |
vboxsync |
warnings
|
|
|
@9421
|
17 years |
vboxsync |
64 bits hidden selector base.
|
|
|
@9414
|
17 years |
vboxsync |
macro
|
|
|
@9413
|
17 years |
vboxsync |
Compile fixes
|
|
|
@9412
|
17 years |
vboxsync |
use macros to access base, limit of a descriptor and offset of an IDT entry
|
|
|
@9411
|
17 years |
vboxsync |
Use a union for esp & rsp, so they are in-sync.
|
|
|
@9409
|
17 years |
vboxsync |
Probably caused the testbox failures.
|
|
|
@9407
|
17 years |
vboxsync |
HWACCM updates.
|
|
|
@9008
|
17 years |
vboxsync |
Changes for proper flushing of the TLB for physical registration changes.
|
|
|
@8879
|
17 years |
vboxsync |
Init idCpu
|
|
|
@8878
|
17 years |
vboxsync |
Don't automatically flush the TLB when we remain on the same cpu (on …
|
|
|
@8876
|
17 years |
vboxsync |
ASID based TLB flushing
|
|
|
@8873
|
17 years |
vboxsync |
Fetch the SVM features too and write them to the release log
|
|
|
@8853
|
17 years |
vboxsync |
Manual page invalidation or TLB flush is required for AMD-V.
|
|
|
@8554
|
17 years |
vboxsync |
Always refuse to load if the cpu is in vmx root mode (32 bits to PAE …
|
|
|
@8553
|
17 years |
vboxsync |
Moved VMX root mode check around.
|
|
|
@8550
|
17 years |
vboxsync |
Corrected the KVM presence check
|
|
|
@8155
|
17 years |
vboxsync |
The Big Sun Rebranding Header Change
|
|
|
@8115
|
17 years |
vboxsync |
Don't assert if RTMpOnAll returns VERR_NOT_SUPPORTED!
|
|
|
@7574
|
17 years |
vboxsync |
And again
|
|
|
@7573
|
17 years |
vboxsync |
Correction
|
|
|