the PAT MSR on guest exit/entry. This workaround was done for a beta release
of VMware Fusion 5 but is no longer needed in later versions.
All Intel CPUs since Nehalem have supported saving and restoring MSR_PAT
in the VM exit and entry controls.
Discussed with: grehan
- Host registers are now stored on the stack instead of a per-cpu host context.
- Host %FS and %GS selectors are not saved and restored across VMRUN.
- Restoring the %FS/%GS selectors was futile anyways since that only updates
the low 32 bits of base address in the hidden descriptor state.
- GS.base is properly updated via the MSR_GSBASE on return from svm_launch().
- FS.base is not used while inside the kernel so it can be safely ignored.
- Add function prologue/epilogue so svm_launch() can be traced with Dtrace's
FBT entry/exit probes. They also serve to save/restore the host %rbp across
VMRUN.
Reviewed by: grehan
Discussed with: Anish Gupta (akgupt3@gmail.com)
As of git submit e179f6914152eca9, the Linux kernel does a simple
probe of the PIC by writing a pattern to the IMR and then reading it
back, prior to the init sequence of ICW words.
The bhyve PIC emulation wasn't allowing the IMR to be read until
the ICW sequence was complete. This limitation isn't required so
relax the test.
With this change, Linux kernels 3.15-rc2 and later won't hang
on boot when calibrating the local APIC.
Reviewed by: tychon
MFC after: 3 days
- CR2
- CR0, CR3, CR4 and EFER
- GDT/IDT base/limit fields
- CS/DS/ES/SS selector/base/limit/attrib fields
The caching can be further restricted via the tunable 'hw.vmm.svm.vmcb_clean'.
Restructure the code such that the fields above are only modified in a single
place. This makes it easy to invalidate the VMCB cache when any of these fields
is modified.
behavior was changed in r271888 so update the comment block to reflect this.
MSR_KGSBASE is accessible from the guest without triggering a VM-exit. The
permission bitmap for MSR_KGSBASE is modified by vmx_msr_guest_init() so get
rid of redundant code in vmx_vminit().
code. There are only a handful of MSRs common between the two so there isn't
too much duplicate functionality.
The VT-x code has the following types of MSRs:
- MSRs that are unconditionally saved/restored on every guest/host context
switch (e.g., MSR_GSBASE).
- MSRs that are restored to guest values on entry to vmx_run() and saved
before returning. This is an optimization for MSRs that are not used in
host kernel context (e.g., MSR_KGSBASE).
- MSRs that are emulated and every access by the guest causes a trap into
the hypervisor (e.g., MSR_IA32_MISC_ENABLE).
Reviewed by: grehan
Keep track of NMI blocking by enabling the IRET intercept on a successful
vNMI injection. The NMI blocking condition is cleared when the handler
executes an IRET and traps back into the hypervisor.
Don't inject NMI if the processor is in an interrupt shadow to preserve the
atomic nature of "STI;HLT". Take advantage of this and artificially set the
interrupt shadow to prevent NMI injection when restarting the "iret".
Reviewed by: Anish Gupta (akgupt3@gmail.com), grehan
Get rid of unused 'svm_feature' from the softc.
Get rid of the redundant 'vcpu_cnt' checks in svm.c. There is a similar check
in vmm.c against 'vm->active_cpus' before the AMD-specific code is called.
Submitted by: Anish Gupta (akgupt3@gmail.com)
processor. Briefly, the hypervisor sets V_INTR_VECTOR to the APIC vector
and sets V_IRQ to 1 to indicate a pending interrupt. The hardware then takes
care of injecting this vector when the guest is able to receive it.
Legacy PIC interrupts are still delivered via the event injection mechanism.
This is because the vector injected by the PIC must reflect the state of its
pins at the time the CPU is ready to accept the interrupt.
Accesses to the TPR via %CR8 are handled entirely in hardware. This requires
that the emulated TPR must be synced to V_TPR after a #VMEXIT.
The guest can also modify the TPR via the memory mapped APIC. This requires
that the V_TPR must be synced with the emulated TPR before a VMRUN.
Reviewed by: Anish Gupta (akgupt3@gmail.com)
VM-exit and ultimately on whether nRIP is valid. This allows us to update
the %rip after the emulation is finished so any exceptions triggered during
the emulation will point to the right instruction.
Don't attempt to handle INS/OUTS VM-exits unless the DecodeAssist capability
is available. The effective segment field in EXITINFO1 is not valid without
this capability.
Add VM_EXITCODE_SVM to flag SVM VM-exits that cannot be handled. Provide the
VMCB fields exitinfo1 and exitinfo2 as collateral to help with debugging.
Provide a SVM VM-exit handler to dump the exitcode, exitinfo1 and exitinfo2
fields in bhyve(8).
Reviewed by: Anish Gupta (akgupt3@gmail.com)
Reviewed by: grehan
- Don't enable the HLT intercept by default. It will be enabled by bhyve(8)
if required. Prior to this change HLT exiting was always enabled making
the "-H" option to bhyve(8) meaningless.
- Recognize a VM exit triggered by a non-maskable interrupt. Prior to this
change the exit would be punted to userspace and the virtual machine would
terminate.
instruction bytes in the VMCB on a nested page fault. This is useful because
it saves having to walk the guest page tables to fetch the instruction.
vie_init() now takes two additional parameters 'inst_bytes' and 'inst_len'
that map directly to 'vie->inst[]' and 'vie->num_valid'.
The instruction emulation handler skips calling 'vmm_fetch_instruction()'
if 'vie->num_valid' is non-zero.
The use of this capability can be turned off by setting the sysctl/tunable
'hw.vmm.svm.disable_npf_assist' to '1'.
Reviewed by: Anish Gupta (akgupt3@gmail.com)
Discussed with: grehan
by explicitly moving it out of the interrupt shadow. The hypervisor is done
"executing" the HLT and by definition this moves the vcpu out of the
1-instruction interrupt shadow.
Prior to this change the interrupt would be held pending because the VMCS
guest-interruptibility-state would indicate that "blocking by STI" was in
effect. This resulted in an unnecessary round trip into the guest before
the pending interrupt could be injected.
Reviewed by: grehan
window exiting. This simply involves setting V_IRQ and enabling the VINTR
intercept. This instructs the CPU to trap back into the hypervisor as soon
as an interrupt can be injected into the guest. The pending interrupt is
then injected via the traditional event injection mechanism.
Rework vcpu interrupt injection so that Linux guests now idle with host cpu
utilization close to 0%.
Reviewed by: Anish Gupta (earlier version)
Discussed with: grehan
Provide APIs svm_enable_intercept()/svm_disable_intercept() to add/delete
VMCB intercepts. These APIs ensure that the VMCB state cache is invalidated
when intercepts are modified.
Each intercept is identified as a (index,bitmask) tuple. For e.g., the
VINTR intercept is identified as (VMCB_CTRL1_INTCPT,VMCB_INTCPT_VINTR).
The first 20 bytes in control area that are used to enable intercepts
are represented as 'uint32_t intercept[5]' in 'struct vmcb_ctrl'.
Modify svm_setcap() and svm_getcap() to use the new APIs.
Discussed with: Anish Gupta (akgupt3@gmail.com)
Prior to this change an ASID was hard allocated to a guest and shared by all
its vcpus. The meant that the number of VMs that could be created was limited
to the number of ASIDs supported by the CPU. It was also inefficient because
it forced a TLB flush on every VMRUN.
With this change the number of guests that can be created is independent of
the number of available ASIDs. Also, the TLB is flushed only when a new ASID
is allocated.
Discussed with: grehan
Reviewed by: Anish Gupta (akgupt3@gmail.com)
function restore_host_tss().
Don't bother to restore MSR_KGSBASE after a #VMEXIT since it is not used in
the kernel. It will be restored on return to userspace.
Discussed with: Anish Gupta (akgupt3@gmail.com)
proper constraint for 'x'. The "+r" constraint indicates that 'x' is an
input and output register operand.
While here generate code for different variants of getcc() using a macro
GETCC(sz) where 'sz' indicates the operand size.
Update the status bits in %rflags when emulating AND and OR opcodes.
Reviewed by: grehan
shadow, so move the check for pending exception before bailing out due to
an interrupt shadow.
Change return type of 'vmcb_eventinject()' to a void and convert all error
returns into KASSERTs.
Fix VMCB_EXITINTINFO_EC(x) and VMCB_EXITINTINFO_TYPE(x) to do the shift
before masking the result.
Reviewed by: Anish Gupta (akgupt3@gmail.com)
tunables to modify the default cpu topology advertised by bhyve.
Also add a tunable "hw.vmm.topology.cpuid_leaf_b" to disable the CPUID
leaf 0xb. This is intended for testing guest behavior when it falls back
on using CPUID leaf 0x4 to deduce CPU topology.
The default behavior is to advertise each vcpu as a core in a separate soket.
the vcpu had no caches at all. This causes problems when executing applications
in the guest compiled with the Intel compiler.
Submitted by: Mark Hill (mark.hill@tidalscale.com)
Add the ACPI MCFG table to advertise the extended config memory window.
Introduce a new flag MEM_F_IMMUTABLE for memory ranges that cannot be deleted
or moved in the guest's address space. The PCI extended config space is an
example of an immutable memory range.
Add emulation for the "movzw" instruction. This instruction is used by FreeBSD
to read a 16-bit extended config space register.
CR: https://phabric.freebsd.org/D505
Reviewed by: jhb, grehan
Requested by: tychon
features. If bootverbose is enabled, a detailed list is provided;
otherwise, a single-line summary is displayed.
- Add read-only sysctls for optional VT-x capabilities used by bhyve
under a new hw.vmm.vmx.cap node. Move a few exiting sysctls that
indicate the presence of optional capabilities under this node.
CR: https://phabric.freebsd.org/D498
Reviewed by: grehan, neel
MFC after: 1 week
forever in vm_handle_hlt().
This is usually not an issue as long as one of the other vcpus properly resets
or powers off the virtual machine. However, if the bhyve(8) process is killed
with a signal the halted vcpu cannot be woken up because it's sleep cannot be
interrupted.
Fix this by waking up periodically and returning from vm_handle_hlt() if
TDF_ASTPENDING is set.
Reported by: Leon Dang
Sponsored by: Nahanni Systems
It is not possible to PUSH a 32-bit operand on the stack in 64-bit mode. The
default operand size for PUSH is 64-bits and the operand size override prefix
changes that to 16-bits.
vm_copy_setup() can return '1' if it encounters a fault when walking the
guest page tables. This is a guest issue and is now handled properly by
resuming the guest to handle the fault.
The faulting instruction needs to be restarted when the exception handler
is done handling the fault. bhyve now does this correctly by setting
'vmexit[vcpu].inst_length' to zero so the %rip is not advanced.
A minor complication is that the fault injection APIs are used by instruction
emulation code that is shared by vmm.ko and bhyve. Thus the argument that
refers to 'struct vm *' in kernel or 'struct vmctx *' in userspace needs to
be loosely typed as a 'void *'.
A nested exception condition arises when a second exception is triggered while
delivering the first exception. Most nested exceptions can be handled serially
but some are converted into a double fault. If an exception is generated during
delivery of a double fault then the virtual machine shuts down as a result of
a triple fault.
vm_exit_intinfo() is used to record that a VM-exit happened while an event was
being delivered through the IDT. If an exception is triggered while handling
the VM-exit it will be treated like a nested exception.
vm_entry_intinfo() is used by processor-specific code to get the event to be
injected into the guest on the next VM-entry. This function is responsible for
deciding the disposition of nested exceptions.
instruction emulation [1].
Fix bug in emulation of opcode 0x8A where the destination is a legacy high
byte register and the guest vcpu is in 32-bit mode. Prior to this change
instead of modifying %ah, %bh, %ch or %dh the emulation would end up
modifying %spl, %bpl, %sil or %dil instead.
Add support for moffsets by treating it as a 2, 4 or 8 byte immediate value
during instruction decoding.
Fix bug in verify_gla() where the linear address computed after decoding
the instruction was not being truncated to the effective address size [2].
Tested by: Leon Dang [1]
Reported by: Peter Grehan [2]
Sponsored by: Nahanni Systems
These changes prevent sysctl(8) from returning proper output,
such as:
1) no output from sysctl(8)
2) erroneously returning ENOMEM with tools like truss(1)
or uname(1)
truss: can not get etype: Cannot allocate memory
there is an environment variable which shall initialize the SYSCTL
during early boot. This works for all SYSCTL types both statically and
dynamically created ones, except for the SYSCTL NODE type and SYSCTLs
which belong to VNETs. A new flag, CTLFLAG_NOFETCH, has been added to
be used in the case a tunable sysctl has a custom initialisation
function allowing the sysctl to still be marked as a tunable. The
kernel SYSCTL API is mostly the same, with a few exceptions for some
special operations like iterating childrens of a static/extern SYSCTL
node. This operation should probably be made into a factored out
common macro, hence some device drivers use this. The reason for
changing the SYSCTL API was the need for a SYSCTL parent OID pointer
and not only the SYSCTL parent OID list pointer in order to quickly
generate the sysctl path. The motivation behind this patch is to avoid
parameter loading cludges inside the OFED driver subsystem. Instead of
adding special code to the OFED driver subsystem to post-load tunables
into dynamically created sysctls, we generalize this in the kernel.
Other changes:
- Corrected a possibly incorrect sysctl name from "hw.cbb.intr_mask"
to "hw.pcic.intr_mask".
- Removed redundant TUNABLE statements throughout the kernel.
- Some minor code rewrites in connection to removing not needed
TUNABLE statements.
- Added a missing SYSCTL_DECL().
- Wrapped two very long lines.
- Avoid malloc()/free() inside sysctl string handling, in case it is
called to initialize a sysctl from a tunable, hence malloc()/free() is
not ready when sysctls from the sysctl dataset are registered.
- Bumped FreeBSD version to indicate SYSCTL API change.
MFC after: 2 weeks
Sponsored by: Mellanox Technologies
This is different than the amount shown for the process e.g. by
/usr/bin/top - that is the mappings faulted in by the mmap'd region
of guest memory.
The values can be fetched with bhyvectl
# bhyvectl --get-stats --vm=myvm
...
Resident memory 413749248
Wired memory 0
...
vmm_stat.[ch] -
Modify the counter code in bhyve to allow direct setting of a counter
as opposed to incrementing, and providing a callback to fetch a
counter's value.
Reviewed by: neel
is sampled "atomically". Any interrupts after this point will be held pending
by the CPU until the guest starts executing and will immediately trigger a
#VMEXIT.
Reviewed by: Anish Gupta (akgupt3@gmail.com)
injected into the guest. This allows the hypervisor to inject another
ExtINT or APIC vector as soon as the guest is able to process interrupts.
This change is not to address any correctness issue but to guarantee that
any pending APIC vector that was preempted by the ExtINT will be injected
as soon as possible. Prior to this change such pending interrupts could be
delayed until the next VM exit.
Handle ExtINT injection for SVM. The HPET emulation
will inject a legacy interrupt at startup, and if this
isn't handled, will result in the HLT-exit code assuming
there are outstanding ExtINTs and return without sleeping.
svm_inj_interrupts() needs more changes to bring it up
to date with the VT-x version: these are forthcoming.
Reviewed by: neel
Linux guests accept the values in this register, while *BSD
guests reprogram it. Default values of zero correspond to
PAT_UNCACHEABLE, resulting in glacial performance.
Thanks to Willem Jan Withagen for first reporting this and
helping out with the investigation.
Remove CR2 save/restore - the guest restore/save is done
in hardware, and there is no need to save/restore the host
version (same as VT-x).
Submitted by: neel (SVM segment descriptor 'P' bit code)
Reviewed by: neel
- use the new virtual APIC page
- update to current bhyve APIs
Tested by Anish with multiple FreeBSD SMP VMs on a Phenom,
and verified by myself with light FreeBSD VM testing
on a Sempron 3850 APU.
The issues reported with Linux guests are very likely to still
be here, but this sync eliminates the skew between the
project branch and CURRENT, and should help to determine
the causes.
Some follow-on commits will fix minor cosmetic issues.
Submitted by: Anish Gupta (akgupt3@gmail.com)
it implicitly in vmm.ko.
Add ioctl VM_GET_CPUS to get the current set of 'active' and 'suspended' cpus
and display them via /usr/sbin/bhyvectl using the "--get-active-cpus" and
"--get-suspended-cpus" options.
This is in preparation for being able to reset virtual machine state without
having to destroy and recreate it.
guest for which the rules regarding xsetbv emulation are known. In
particular future extensions like AVX-512 have interdependencies among
feature bits that could allow a guest to trigger a GP# in the host with
the current approach of allowing anything the host supports.
- Add proper checking of Intel MPX and AVX-512 XSAVE features in the
xsetbv emulation and allow these features to be exposed to the guest if
they are enabled in the host.
- Expose a subset of known-safe features from leaf 0 of the structured
extended features to guests if they are supported on the host including
RDFSBASE/RDGSBASE, BMI1/2, AVX2, AVX-512, HLE, ERMS, and RTM. Aside
from AVX-512, these features are all new instructions available for use
in ring 3 with no additional hypervisor changes needed.
Reviewed by: neel
API function 'vie_calculate_gla()'.
While the current implementation is simplistic it forms the basis of doing
segmentation checks if the guest is in 32-bit protected mode.
of the guest linear address space. These APIs in turn use a new ioctl
'VM_GLA2GPA' to convert the guest linear address to guest physical.
Use the new copyin/copyout APIs when emulating ins/outs instruction in
bhyve(8).
'struct vm_guest_paging'.
Check for canonical addressing in vmm_gla2gpa() and inject a protection
fault into the guest if a violation is detected.
If the page table walk is restarted in vmm_gla2gpa() then reset 'ptpphys' to
point to the root of the page tables.
indicate the faulting linear address.
If the guest PML4 entry has the PG_PS bit set then inject a page fault into
the guest with the PGEX_RSV bit set in the error_code.
Get rid of redundant checks for the PG_RW violations when walking the page
tables.
the UART FIFO.
The emulation is constrained in a number of ways: 64-bit only, doesn't check
for all exception conditions, limited to i/o ports emulated in userspace.
Some of these constraints will be relaxed in followup commits.
Requested by: grehan
Reviewed by: tychon (partially and a much earlier version)
the proper ICWx initialization sequence. It assumes, probably correctly, that
the boot firmware has done the 8259 initialization.
Since grub-bhyve does not initialize the 8259 this write to the mask register
takes a code path in which 'error' remains uninitialized (ready=0,icw_num=0).
Fix this by initializing 'error' at the start of the function.
Set the accessed and dirty bits in the page table entry. If it fails then
restart the page table walk from the beginning. This might happen if another
vcpu modifies the page tables simultaneously.
Reviewed by: alc, kib
to a guest physical address.
PG_PS (page size) field is valid only in a PDE or a PDPTE so it is now
checked only in non-terminal paging entries.
Ignore the upper 32-bits of the CR3 for PAE paging.
- inserting frame enter/leave sequences
- restructuring the vmx_enter_guest routine so that it subsumes
the vm_exit_guest block, which was the #vmexit RIP and not a
callable routine.
Reviewed by: neel
MFC after: 3 weeks
the legacy 8259A PICs.
- Implement an ICH-comptabile PCI interrupt router on the lpc device with
8 steerable pins configured via config space access to byte-wide
registers at 0x60-63 and 0x68-6b.
- For each configured PCI INTx interrupt, route it to both an I/O APIC
pin and a PCI interrupt router pin. When a PCI INTx interrupt is
asserted, ensure that both pins are asserted.
- Provide an initial routing of PCI interrupt router (PIRQ) pins to
8259A pins (ISA IRQs) and initialize the interrupt line config register
for the corresponding PCI function with the ISA IRQ as this matches
existing hardware.
- Add a global _PIC method for OSPM to select the desired interrupt routing
configuration.
- Update the _PRT methods for PCI bridges to provide both APIC and legacy
PRT tables and return the appropriate table based on the configured
routing configuration. Note that if the lpc device is not configured, no
routing information is provided.
- When the lpc device is enabled, provide ACPI PCI link devices corresponding
to each PIRQ pin.
- Add a VMM ioctl to adjust the trigger mode (edge vs level) for 8259A
pins via the ELCR.
- Mark the power management SCI as level triggered.
- Don't hardcode the number of elements in Packages in the source for
the DSDT. iasl(8) will fill in the actual number of elements, and
this makes it simpler to generate a Package with a variable number of
elements.
Reviewed by: tycho
to sleep permanently by executing a HLT with interrupts disabled.
When this condition is detected the guest with be suspended with a reason of
VM_SUSPEND_HALT and the bhyve(8) process will exit.
Tested by executing "halt" inside a RHEL7-beta guest.
Discussed with: grehan@
Reviewed by: jhb@, tychon@
the 'HLT' instruction. This condition was detected by 'vm_handle_hlt()' and
converted into the SPINDOWN_CPU exitcode . The bhyve(8) process would exit
the vcpu thread in response to a SPINDOWN_CPU and when the last vcpu was
spun down it would reset the virtual machine via vm_suspend(VM_SUSPEND_RESET).
This functionality was broken in r263780 in a way that made it impossible
to kill the bhyve(8) process because it would loop forever in
vm_handle_suspend().
Unbreak this by removing the code to spindown vcpus. Thus a 'halt' from
a Linux guest will appear to be hung but this is consistent with the
behavior on bare metal. The guest can be rebooted by using the bhyvectl
options '--force-reset' or '--force-poweroff'.
Reviewed by: grehan@
by adding an argument to the VM_SUSPEND ioctl that specifies how the virtual
machine should be suspended, viz. VM_SUSPEND_RESET or VM_SUSPEND_POWEROFF.
The disposition of VM_SUSPEND is also made available to the exit handler
via the 'u.suspended' member of 'struct vm_exit'.
This capability is exposed via the '--force-reset' and '--force-poweroff'
arguments to /usr/sbin/bhyvectl.
Discussed with: grehan@
Status and Control register at port 0x61.
Be more conservative about "catching up" callouts that were supposed
to fire in the past by skipping an interrupt if it was
scheduled too far in the past.
Restore the PIT ACPI DSDT entries and add an entry for NMISC too.
Approved by: neel (co-mentor)
'struct vmxctx'. It is preserved on the host stack across a guest entry
and exit and just restoring the host's '%rsp' is sufficient.
Pointed out by: grehan@
- remove redundant code
- remove erroneous setting of the error return
in vmmdev_ioctl()
- use style(9) initialization
- in vmx_inject_pir(), document the race condition
that the final conditional statement was detecting,
Tested with both gcc and clang builds.
Reviewed by: neel
correct for the pirbase test (since I'd have thought we'd need to do
something even when the offset is 0 and that test looks like a
misguided attempt to not use an uninitialized variable), but it is at
least the same as today.
My PCI RID changes somehow got intermixed with my PCI ARI patch when I
committed it. I may have accidentally applied a patch to a non-clean
working tree. Revert everything while I figure out what went wrong.
Pointy hat to: rstone
from any context i.e., it is not required to be called from a vcpu thread. The
ioctl simply sets a state variable 'vm->suspend' to '1' and returns.
The vcpus inspect 'vm->suspend' in the run loop and if it is set to '1' the
vcpu breaks out of the loop with a reason of 'VM_EXITCODE_SUSPENDED'. The
suspend handler waits until all 'vm->active_cpus' have transitioned to
'vm->suspended_cpus' before returning to userspace.
Discussed with: grehan
blocked on it.
This is done by issuing a wakeup after clearing the 'vcpuid' from 'active_cpus'.
Also, use CPU_CLR_ATOMIC() to guarantee visibility of the updated 'active_cpus'
across all host cpus.
attributed if an ExtINT arrives during interrupt injection.
Also, fix a spurious interrupt if the PIC tries to raise an interrupt
before the outstanding one is accepted.
Finally, improve the PIC interrupt latency when another interrupt is
raised immediately after the outstanding one is accepted by creating a
vmexit rather than waiting for one to occur by happenstance.
Approved by: neel (co-mentor)
New ioctls VM_ISA_ASSERT_IRQ, VM_ISA_DEASSERT_IRQ and VM_ISA_PULSE_IRQ
can be used to manipulate the pic, and optionally the ioapic, pin state.
Reviewed by: jhb, neel
Approved by: neel (co-mentor)
being updated outside of the vcpu_lock(). The race is benign and could
potentially result in a missed notification about a pending interrupt to
a vcpu. The interrupt would not be lost but rather delayed until the next
VM exit.
The vcpu's hostcpu is now updated concurrently with the vcpu state change.
When the vcpu transitions to the RUNNING state the hostcpu is set to 'curcpu'.
It is set to 'NOCPU' in all other cases.
Reviewed by: grehan
triggers a VM exit with the exit reason of an external interrupt but
without a valid interrupt set in the exit interrupt information.
Tested by: Michael Dexter
Reviewed by: neel
MFC after: 1 week
processor-specific VMCS or VMCB. The pending exception will be delivered right
before entering the guest.
The order of event injection into the guest is:
- hardware exception
- NMI
- maskable interrupt
In the Intel VT-x case, a pending NMI or interrupt will enable the interrupt
window-exiting and inject it as soon as possible after the hardware exception
is injected. Also since interrupts are inherently asynchronous, injecting
them after the hardware exception should not affect correctness from the
guest perspective.
Rename the unused ioctl VM_INJECT_EVENT to VM_INJECT_EXCEPTION and restrict
it to only deliver x86 hardware exceptions. This new ioctl is now used to
inject a protection fault when the guest accesses an unimplemented MSR.
Discussed with: grehan, jhb
Reviewed by: jhb
This brings in the "-w" option from bhyve to ignore unknown MSRs.
It will make debugging Linux guests a bit easier.
Suggested by: Willem Jan Withagen (wjw at digiware nl)
The vlapic.ops handler 'enable_x2apic_mode' is called when the vlapic mode
is switched to x2APIC. The VT-x implementation of this handler turns off the
APIC-access virtualization and enables the x2APIC virtualization in the VMCS.
The x2APIC virtualization is done by allowing guest read access to a subset
of MSRs in the x2APIC range. In non-root operation the processor will satisfy
an 'rdmsr' access to these MSRs by reading from the virtual APIC page instead.
The guest is also given write access to TPR, EOI and SELF_IPI MSRs which
get special treatment in non-root operation. This is documented in the
Intel SDM section titled "Virtualizing MSR-Based APIC Accesses".
Enforce that APIC-write and APIC-access VM-exits are handled only if
APIC-access virtualization is enabled. The one exception to this is
SELF_IPI virtualization which may result in an APIC-write VM-exit.
simplify the implementation of the x2APIC virtualization assist in VT-x.
Prior to this change the vlapic allowed the guest to change its mode from
xAPIC to x2APIC. We don't allow that any more and the vlapic mode is locked
when the virtual machine is created. This is not very constraining because
operating systems already have to deal with BIOS setting up the APIC in
x2APIC mode at boot.
Fix a bug in the CPUID emulation where the x2APIC capability was leaking
from the host to the guest.
Ignore MMIO reads and writes to the vlapic in x2APIC mode. Similarly, ignore
MSR accesses to the vlapic when it is in xAPIC mode.
The default configuration of the vlapic is xAPIC. The "-x" option to bhyve(8)
can be used to change the mode to x2APIC instead.
Discussed with: grehan@
emulated instructions.
- Add helper routines to inject interrupt information for a hardware
exception from the VM exit callback routines.
- Use the new routines to inject GP and UD exceptions for invalid
operations when emulating the xsetbv instruction.
- Don't directly manipulate the entry interrupt info when a user event
is injected. Instead, store the event info in the vmx state and
only apply it during a VM entry if a hardware exception or NMI is
not already pending.
- While here, use HANDLED/UNHANDLED instead of 1/0 in a couple of
routines.
Reviewed by: neel
in x2apic mode. Reads to this MSR are currently ignored but should cause a
general proctection exception to be injected into the vcpu.
All accesses to the corresponding offset in xAPIC mode are ignored.
Also, do not panic the host if there is mismatch between the trigger mode
programmed in the TMR and the actual interrupt being delivered. Instead the
anomaly is logged to aid debugging and to prevent a misbehaving guest from
panicking the host.
This is necessary because if the vlapic is configured in x2apic mode the
vioapic_process_eoi() function is called inside the critical section
established by vm_run().
XSAVE-enabled features like AVX.
- Store a per-cpu guest xcr0 register. When switching to the guest FPU
state, switch to the guest xcr0 value. Note that the guest FPU state is
saved and restored using the host's xcr0 value and xcr0 is saved/restored
"inside" of saving/restoring the guest FPU state.
- Handle VM exits for the xsetbv instruction by updating the guest xcr0.
- Expose the XSAVE feature to the guest only if the host has enabled XSAVE,
and only advertise XSAVE features enabled by the host to the guest.
This ensures that the guest will only adjust FPU state that is a subset
of the guest FPU state saved and restored by the host.
Reviewed by: grehan
If a VM-exit is caused by an NMI then "blocking by NMI" is in effect on the
CPU when the VM-exit is completed. No more NMIs will be recognized until
the execution of an "iret".
Prior to this change the NMI handler was dispatched via a software interrupt
with interrupts enabled. This meant that an interrupt could be recognized
by the processor before the NMI handler completed its execution. The "iret"
issued by the interrupt handler would then cause the "blocking by NMI" to
be cleared prematurely.
This is now fixed by handling the NMI with interrupts disabled in addition
to "blocking by NMI" already established by the VM-exit.
- Similar to the hack for bootinfo32.c in userboot, define
_MACHINE_ELF_WANT_32BIT in the load_elf32 file handlers in userboot.
This allows userboot to load 32-bit kernels and modules.
- Copy the SMAP generation code out of bootinfo64.c and into its own
file so it can be shared with bootinfo32.c to pass an SMAP to the i386
kernel.
- Use uint32_t instead of u_long when aligning module metadata in
bootinfo32.c in userboot, as otherwise the metadata used 64-bit
alignment which corrupted the layout.
- Populate the basemem and extmem members of the bootinfo struct passed
to 32-bit kernels.
- Fix the 32-bit stack in userboot to start at the top of the stack
instead of the bottom so that there is room to grow before the
kernel switches to its own stack.
- Push a fake return address onto the 32-bit stack in addition to the
arguments normally passed to exec() in the loader. This return
address is needed to convince recover_bootinfo() in the 32-bit
locore code that it is being invoked from a "new" boot block.
- Add a routine to libvmmapi to setup a 32-bit flat mode register state
including a GDT and TSS that is able to start the i386 kernel and
update bhyveload to use it when booting an i386 kernel.
- Use the guest register state to determine the CPU's current instruction
mode (32-bit vs 64-bit) and paging mode (flat, 32-bit, PAE, or long
mode) in the instruction emulation code. Update the gla2gpa() routine
used when fetching instructions to handle flat mode, 32-bit paging, and
PAE paging in addition to long mode paging. Don't look for a REX
prefix when the CPU is in 32-bit mode, and use the detected mode to
enable the existing 32-bit mode code when decoding the mod r/m byte.
Reviewed by: grehan, neel
MFC after: 1 month
- Convert VMM_CTR to VCPU_CTR KTR macros
- Special handling of halt, save rflags for VMM layer to emulate
halt for vcpu(sleep to be awakened by interrupt or stop it)
- Cleanup of RVI exit handling code
Submitted by: Anish Gupta (akgupt3@gmail.com)
Reviewed by: grehan
Prior to this change the cached value of 'pm_eptgen' was tracked per-vcpu
and per-hostcpu. In the degenerate case where 'N' vcpus were sharing
a single hostcpu this could result in 'N - 1' unnecessary TLB invalidations.
Since an 'invept' invalidates mappings for all VPIDs the first 'invept'
is sufficient.
Fix this by moving the 'eptgen[MAXCPU]' array from 'vmxctx' to 'struct vmx'.
If it is known that an 'invept' is going to be done before entering the
guest then it is safe to skip the 'invvpid'. The stat VPU_INVVPID_SAVED
counts the number of 'invvpid' invalidations that were avoided because
they were subsumed by an 'invept'.
Discussed with: grehan
the virtio backends.
- Add a new ioctl to export the count of pins on the I/O APIC from vmm
to the hypervisor.
- Use pins on the I/O APIC >= 16 for PCI interrupts leaving 0-15 for
ISA interrupts.
- Populate the MP Table with I/O interrupt entries for any PCI INTx
interrupts.
- Create a _PRT table under the PCI root bridge in ACPI to route any
PCI INTx interrupts appropriately.
- Track which INTx interrupts are in use per-slot so that functions
that share a slot attempt to distribute their INTx interrupts across
the four available pins.
- Implicitly mask INTx interrupts if either MSI or MSI-X is enabled
and when the INTx DIS bit is set in a function's PCI command register.
Either assert or deassert the associated I/O APIC pin when the
state of one of those conditions changes.
- Add INTx support to the virtio backends.
- Always advertise the MSI capability in the virtio backends.
Submitted by: neel (7)
Reviewed by: neel
MFC after: 2 weeks
The VMCS field EOI_bitmap[] is an array of 256 bits - one for each vector.
If a bit is set to '1' in the EOI_bitmap[] then the processor will trigger
an EOI-induced VM-exit when it is doing EOI virtualization.
The EOI-induced VM-exit results in the EOI being forwarded to the vioapic
so that level triggered interrupts can be properly handled.
Tested by: Anish Gupta (akgupt3@gmail.com)
injected into the vcpu but the VM-entry interruption information field
already has the valid bit set.
Pointed out by: David Reed (david.reed@tidalscale.com)
via a software interrupt.
This is safe to do because the logical processor is already cognizant of the
NMI and further NMIs are blocked until the host's NMI handler executes "iret".
