|
|
|
@49270
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix incorrect masking of TPR bits with TPR-shadowing.
|
|
|
|
@49269
|
11 years |
vboxsync |
VMM/HMVMXR0: More paranoid assertions cannot hurt.
|
|
|
|
@49258
|
11 years |
vboxsync |
VMM/HMVMXR0: Introduced HMVMX_ALWAYS_FLUSH_TLB debug switch.
|
|
|
|
@49257
|
11 years |
vboxsync |
VMM/HMVMXR0: INS/OUTS with REP prefix update RFLAGS. Fix incorrect …
|
|
|
|
@49227
|
11 years |
vboxsync |
VMM/HMVMXR0: Adding functions for dynamic MSR swapping.
|
|
|
|
@49209
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix MSR_TSC_AUX, restore host MSR.
|
|
|
|
@49207
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix MSR_TSC_AUX, use the right check to be doubly sure.
|
|
|
|
@49204
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix MSR_TSC_AUX auto-load/store when not using TSC …
|
|
|
|
@49186
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix MSR_TSC_AUX auto-load/store when not using TSC …
|
|
|
|
@49152
|
11 years |
vboxsync |
HMR0VMX.cpp: Clear the TF bit in the single step loop, instead on …
|
|
|
|
@49085
|
11 years |
vboxsync |
VMM/HMVMXR0: Partially revert r89778. Back to disassembling and …
|
|
|
|
@49026
|
11 years |
vboxsync |
VMM: Some @thread doxygen corrections.
|
|
|
|
@49019
|
11 years |
vboxsync |
VMM: FPU cleanup.
|
|
|
|
@49004
|
11 years |
vboxsync |
VMM/HMVMXR0: Comment update.
|
|
|
|
@49003
|
11 years |
vboxsync |
VMM/HMVMXR0, HMSVMR0: Comment out unused code paths in TLB shootdown.
|
|
|
|
@49002
|
11 years |
vboxsync |
VMM/HMVMXR0: Use instruction info. for string IO VM-exits on CPUs that …
|
|
|
|
@49000
|
11 years |
vboxsync |
VMM: IntrInfo to IntInfo renaming.
|
|
|
|
@48998
|
11 years |
vboxsync |
VMM/HMVMXR0: Propagate all unexpected exits to release log, slight …
|
|
|
|
@48995
|
11 years |
vboxsync |
VMM/HMVMXR0: Make sure host segments are present in the LDT if we're …
|
|
|
|
@48936
|
11 years |
vboxsync |
VMM: Whitespace cleanups by scm.
|
|
|
|
@48885
|
11 years |
vboxsync |
VMM/HMVMXR0: Don't assume CR8 load/store exiting is available on …
|
|
|
|
@48700
|
11 years |
vboxsync |
VMM/HMVMXR0, HMSVMR0: Alignment and assert.
|
|
|
|
@48651
|
11 years |
vboxsync |
VMM/HMVMXR0: Checking this once outside the loop is sufficient.
|
|
|
|
@48649
|
11 years |
vboxsync |
VMM/HMVMXR0: VMCS size is bits 44:32 not 43:32. Assert what the Intel …
|
|
|
|
@48648
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix switcher verification bits to be compiled to match …
|
|
|
|
@48624
|
11 years |
vboxsync |
VMM/HMVMXR0, HMSVMR0: Use HMCF macros.
|
|
|
|
@48621
|
11 years |
vboxsync |
VMM/VMMR0: Don't disable interrupts for a long time when disabling …
|
|
|
|
@48570
|
11 years |
vboxsync |
VMM/HMVMXR0, HMSVMR0: Restore hyper/guest DR7 in accordance with what …
|
|
|
|
@48565
|
11 years |
vboxsync |
VMM/HM: Added total VM-exits STAM.
|
|
|
|
@48552
|
11 years |
vboxsync |
VMM/HMVMXR0, HMSVMR0: Fixes for shared FPU/debug state handling with …
|
|
|
|
@48478
|
11 years |
vboxsync |
HMVMX: Look at the right guest long mode indicator.
|
|
|
|
@48477
|
11 years |
vboxsync |
VMM/HMVMXR0: Debug macro switch HMVMX_ALWAYS_SWAP_FPU_STATE.
|
|
|
|
@48476
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix assertions and stale comments.
|
|
|
|
@48474
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix invalid assertion on 32-bit hosts.
|
|
|
|
@48473
|
11 years |
vboxsync |
VMM/HMVMXR0: Try restore state properly on assertions in longjmps …
|
|
|
|
@48457
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix check in hmR0VmxCheckGuestState(), CR0.PE MB1 unless …
|
|
|
|
@48456
|
11 years |
vboxsync |
Build fix.
|
|
|
|
@48455
|
11 years |
vboxsync |
VMM/HMVMXR0: Nits.
|
|
|
|
@48454
|
11 years |
vboxsync |
VMM/HMVMXR0: oops.
|
|
|
|
@48453
|
11 years |
vboxsync |
VMM/HMVMXR0: Check VMCS values rather than fudged pCtx values in …
|
|
|
|
@48443
|
11 years |
vboxsync |
VMM/HMVMXR0: Leave VT-x properly for VERR_VMX_INVALID_GUEST_STATE and …
|
|
|
|
@48436
|
11 years |
vboxsync |
VMM/HMVMXR0: Temporary workaround, intercept CR0.PE changes with UX.
|
|
|
|
@48426
|
11 years |
vboxsync |
VMM: Fixed strict build assertion assumption with thread-context …
|
|
|
|
@48421
|
11 years |
vboxsync |
VMM/HMVMXR0: Clear interrupt-window exiting control on premature …
|
|
|
|
@48407
|
11 years |
vboxsync |
VMM/HMVMXR0: Attempt to fix guru in the switcher case with MOV DRx …
|
|
|
|
@48404
|
11 years |
vboxsync |
debug build fix.
|
|
|
|
@48402
|
11 years |
vboxsync |
VMM/HMVMXR0: Assertion.
|
|
|
|
@48394
|
11 years |
vboxsync |
VMM/HMVMXR0: Address possible deadlock situation with the PGM lock. …
|
|
|
|
@48370
|
11 years |
vboxsync |
EM,HM: MWait fix, clearing the active bit too early.
|
|
|
|
@48369
|
11 years |
vboxsync |
VMM/HMVMXR0: Nits.
|
|
|
|
@48362
|
11 years |
vboxsync |
VMM/HMVMXR0: Clarify that it's guest-CPU context CR0 and not VMCS CR0.
|
|
|
|
@48361
|
11 years |
vboxsync |
VMM/HMVMXR0: comment cosmetic.
|
|
|
|
@48360
|
11 years |
vboxsync |
HMVMXR0.cpp: Made hmR0VmxSetupVMRunHandler trigger the necessary host …
|
|
|
|
@48347
|
11 years |
vboxsync |
HMVMXR0.cpp: Only the 64 -> 32 needs the exit controls update, I believe.
|
|
|
|
@48344
|
11 years |
vboxsync |
VMM/HMVMXR0: No need to ask VMX exit ctls to be reloaded when we're …
|
|
|
|
@48329
|
11 years |
vboxsync |
VMM: nits.
|
|
|
|
@48326
|
11 years |
vboxsync |
VMM: Nits.
|
|
|
|
@48284
|
11 years |
vboxsync |
VMM/HMVMXR0: Avoid calling PGM twice for reading just 4 consecutive bytes.
|
|
|
|
@48262
|
11 years |
vboxsync |
VMM/HM: Preempt stats and minor optimizations to VT-x when …
|
|
|
|
@48256
|
11 years |
vboxsync |
VMM: More descriptive host-NMI stat name.
|
|
|
|
@48250
|
11 years |
vboxsync |
VMM/HMVMXR0: Undo injected event on premature returns to ring-3. …
|
|
|
|
@48248
|
11 years |
vboxsync |
Comments.
|
|
|
|
@48240
|
11 years |
vboxsync |
More paranoia regarding pfnStartVM changes on 32-bit hosts (doesn't help).
|
|
|
|
@48237
|
11 years |
vboxsync |
VMM/HMVMXR0: Nits.
|
|
|
|
@48230
|
11 years |
vboxsync |
VMM: Propagate errors properly while leaving HM context.
|
|
|
|
@48227
|
11 years |
vboxsync |
VMM: Ensure longjmps after hmR0[Vmx|Svm]LeaveSession() don't happen.
|
|
|
|
@48220
|
11 years |
vboxsync |
HMVMXR0.cpp: When the guest switches from long mode to one of the …
|
|
|
|
@48219
|
11 years |
vboxsync |
VMM/HMVMXR0: Hungarian.
|
|
|
|
@48218
|
11 years |
vboxsync |
VMM: Addressed a rare corner case stale TLB entry issue.
|
|
|
|
@48216
|
11 years |
vboxsync |
VMM/HM: Cleanup.
|
|
|
|
@48215
|
11 years |
vboxsync |
VMM/HMVMXR0: Cleanup.
|
|
|
|
@48212
|
11 years |
vboxsync |
VMM/HM: Naming fixes.
|
|
|
|
@48205
|
11 years |
vboxsync |
VMM/HMVMXR0: Make code more robust regarding longjmps in awkward places.
|
|
|
|
@48194
|
11 years |
vboxsync |
VMM/HMVMXR0: Even without preemption hooks, we can now load the …
|
|
|
|
@48174
|
11 years |
vboxsync |
HM: Adjusted some CPUMIsXxxDebugStateActive() assertion for …
|
|
|
|
@48156
|
11 years |
vboxsync |
VMM/HMVMXR0: Update comment and add assertion. We no longer have gaps …
|
|
|
|
@48153
|
11 years |
vboxsync |
VMM/HM: More dead code path elimination.
|
|
|
|
@48140
|
11 years |
vboxsync |
VMM/HMVMXR0: Safer longjmp coverage, only restore host state when …
|
|
|
|
@48135
|
11 years |
vboxsync |
VMM/HM: Eliminate dead code paths.
|
|
|
|
@48132
|
11 years |
vboxsync |
VMM: Ditch VBOX_WITH_VMMR0_DISABLE_PREEMPTION.
|
|
|
|
@48130
|
11 years |
vboxsync |
VMM: Enable thread-context hooks. Reimplemented event injection logic …
|
|
|
|
@48082
|
11 years |
vboxsync |
VMM/HMVMXR0: Fix invalid VMCS launch-state when thread-context hooks …
|
|
|
|
@48060
|
11 years |
vboxsync |
VMM/HMVMXR0: Comments.
|
|
|
|
@48044
|
11 years |
vboxsync |
VMM/HM: Thread-context hooks, disable preemption while touching host …
|
|
|
|
@48041
|
11 years |
vboxsync |
VMM/HMVMXR0: Don't play safe when we have assertions to catch things.
|
|
|
|
@48040
|
11 years |
vboxsync |
VMM/HMVMXR0: Avoid loading the host state earlier when we can get …
|
|
|
|
@48039
|
11 years |
vboxsync |
VMM/HMVMXR0: Burn fix.
|
|
|
|
@48038
|
11 years |
vboxsync |
VMM/VMMR0, HMVMXR0: Minor fixes relating to error paths.
|
|
|
|
@48037
|
11 years |
vboxsync |
VMM/HM: Preemption hooks, work in progress. Hopefully I didn't break …
|
|
|
|
@48029
|
11 years |
vboxsync |
VMM/HMVMXR0: More log adjustments.
|
|
|
|
@48027
|
11 years |
vboxsync |
HMVMX: Log a bit more.
|
|
|
|
@48025
|
11 years |
vboxsync |
VMM/HMVMXR0: Asserted by the caller, don't re-assert here.
|
|
|
|
@48023
|
11 years |
vboxsync |
VMM/HMVMXR0: Additional logging to track VMCS state changes.
|
|
|
|
@47999
|
11 years |
vboxsync |
VMM/HM: Better error reporting for unsupported VT-x feature combos.
|
|
|
|
@47997
|
11 years |
vboxsync |
VMM/HMVMXR0: Try fix stale VMCS launch state while getting preempted.
|
|
|
|
@47989
|
11 years |
vboxsync |
VMM/VMMR0: Preemption hooks implemented and enabled for Solaris and …
|
|
|
|
@47844
|
11 years |
vboxsync |
VMM: X2APIC + NMI. Only tested on AMD64.
|
|
|
|
@47803
|
11 years |
vboxsync |
VMM/HM: Preemption hoooks, work in progress.
|
|
|
|
@47802
|
11 years |
vboxsync |
VMM/HM: Redundant updates of flags is not necessary.
|
|
|
|
@47776
|
11 years |
vboxsync |
Warnings and space.
|
|
|
|
