- 30 Apr, 2019 8 commits
-
-
Sean Christopherson authored
Refactor kvm_x86_ops->set_hv_timer to use an explicit parameter for stating that the timer has expired. Overloading the return value is unnecessarily clever, e.g. can lead to confusion over the proper return value from start_hv_timer() when r==1. Cc: Wanpeng Li <wanpengli@tencent.com> Cc: Liran Alon <liran.alon@oracle.com> Signed-off-by:
Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com>
-
Sean Christopherson authored
Explicitly call cancel_hv_timer() instead of returning %false to coerce restart_apic_timer() into canceling it by way of start_sw_timer(). Functionally, the existing code is correct in the sense that it doesn't doing anything visibily wrong, e.g. generate spurious interrupts or miss an interrupt. But it's extremely confusing and inefficient, e.g. there are multiple extraneous calls to apic_timer_expired() that effectively get dropped due to @timer_pending being %true. Cc: Wanpeng Li <wanpengli@tencent.com> Cc: Liran Alon <liran.alon@oracle.com> Signed-off-by:
-
Sean Christopherson authored
...now that VMX's preemption timer, i.e. the hv_timer, also adjusts its programmed time based on lapic_timer_advance_ns. Without the delay, a guest can see a timer interrupt arrive before the requested time when KVM is using the hv_timer to emulate the guest's interrupt. Fixes: c5ce8235 ("KVM: VMX: Optimize tscdeadline timer latency") Cc: <stable@vger.kernel.org> Cc: Wanpeng Li <wanpengli@tencent.com> Reviewed-by:
Liran Alon <liran.alon@oracle.com> Signed-off-by:
-
Liran Alon authored
Since commits 668fffa3 ("kvm: better MWAIT emulation for guestsâ€) and 4d5422ce ("KVM: X86: Provide a capability to disable MWAIT interceptsâ€), KVM was modified to allow an admin to configure certain guests to execute MONITOR/MWAIT inside guest without being intercepted by host. This is useful in case admin wishes to allocate a dedicated logical processor for each vCPU thread. Thus, making it safe for guest to completely control the power-state of the logical processor. The ability to use this new KVM capability was introduced to QEMU by commits 6f131f13e68d ("kvm: support -overcommit cpu-pm=on|offâ€) and 2266d4431132 ("i386/cpu: make -cpu host support monitor/mwaitâ€). However, exposing MONITOR/MWAIT to a Linux guest may cause it's intel_idle kernel module to execute c1e_promotion_disable() which will attempt to RDMSR/WRMSR from/to MSR_IA32_POWER_CTL to manipulate the "C1E Enable" bit. This behaviour was introduced by commit 32e95180 ("intel_idle: export both C1 and C1Eâ€). Becuase KVM doesn't emulate this MSR, running KVM with ignore_msrs=0 will cause the above guest behaviour to raise a #GP which will cause guest to kernel panic. Therefore, add support for nop emulation of MSR_IA32_POWER_CTL to avoid #GP in guest in this scenario. Future commits can optimise emulation further by reflecting guest MSR changes to host MSR to provide guest with the ability to fine-tune the dedicated logical processor power-state. Reviewed-by:
Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by:
-
Luwei Kang authored
Let guests clear the Intel PT ToPA PMI status (bit 55 of MSR_CORE_PERF_GLOBAL_OVF_CTRL). Signed-off-by:
Luwei Kang <luwei.kang@intel.com> Signed-off-by:
-
Luwei Kang authored
Inject a PMI for KVM guest when Intel PT working in Host-Guest mode and Guest ToPA entry memory buffer was completely filled. Signed-off-by:
-
Radim Krčmář authored
This reverts commit 919f6cd8. The patch was applied twice. The first commit is eca6be56. Reported-by:
Cornelia Huck <cohuck@redhat.com> Signed-off-by:
Radim Krčmář <rkrcmar@redhat.com> Signed-off-by:
-
Paolo Bonzini authored
Merge tag 'kvm-s390-next-5.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD KVM: s390: Features and fixes for 5.2 - VSIE crypto fixes - new guest features for gen15 - disable halt polling for nested virtualization with overcommit
-
- 29 Apr, 2019 2 commits
-
-
Pierre Morel authored
Let's use the correct validity number. Fixes: 56019f9a ("KVM: s390: vsie: Allow CRYCB FORMAT-2") Signed-off-by:
Pierre Morel <pmorel@linux.ibm.com> Reviewed-by:
Christian Borntraeger <borntraeger@de.ibm.com> Message-Id: <1556269201-22918-1-git-send-email-pmorel@linux.ibm.com> Acked-by:
David Hildenbrand <david@redhat.com> Signed-off-by:
-
Pierre Morel authored
When the guest do not have AP instructions nor Key management we should return without shadowing the CRYCB. We did not check correctly in the past. Fixes: b10bd9a2 ("s390: vsie: Use effective CRYCBD.31 to check CRYCBD validity") Fixes: 6ee74098 ("KVM: s390: vsie: allow CRYCB FORMAT-0") Signed-off-by:
-
- 26 Apr, 2019 2 commits
-
-
Christian Borntraeger authored
We do track the current steal time of the host CPUs. Let us use this value to disable halt polling if the steal time goes beyond a configured value. Signed-off-by:
-
Christian Borntraeger authored
There are cases where halt polling is unwanted. For example when running KVM on an over committed LPAR we rather want to give back the CPU to neighbour LPARs instead of polling. Let us provide a callback that allows architectures to disable polling. Signed-off-by:
-
- 25 Apr, 2019 2 commits
-
-
Christian Borntraeger authored
Instead of adding a new machine option to disable/enable the keywrapping options of pckmo (like for AES and DEA) we can now use the CPU model to decide. As ECC is also wrapped with the AES key we need that to be enabled. Signed-off-by:
-
Christian Borntraeger authored
This enables stfle.151 and adds the subfunctions for DFLTCC. Bit 151 is added to the list of facilities that will be enabled when there is no cpu model involved as DFLTCC requires no additional handling from userspace, e.g. for migration. Please note that a cpu model enabled user space can and will have the final decision on the facility bits for a guests. Signed-off-by:
Collin Walling <walling@linux.ibm.com> Reviewed-by:
-
- 18 Apr, 2019 6 commits
-
-
Christian Borntraeger authored
This enables stfle.150 and adds the subfunctions for SORTL. Bit 150 is added to the list of facilities that will be enabled when there is no cpu model involved as sortl requires no additional handling from userspace, e.g. for migration. Please note that a cpu model enabled user space can and will have the final decision on the facility bits for a guests. Signed-off-by:
-
Christian Borntraeger authored
Some of the new features have a 32byte response for the query function. Provide a new wrapper similar to __cpacf_query. We might want to factor this out if other users come up, as of today there is none. So let us keep the function within KVM. Signed-off-by:
-
Christian Borntraeger authored
This enables stfle.155 and adds the subfunctions for KDSA. Bit 155 is added to the list of facilities that will be enabled when there is no cpu model involved as MSA9 requires no additional handling from userspace, e.g. for migration. Please note that a cpu model enabled user space can and will have the final decision on the facility bits for a guests. Signed-off-by:
Janosch Frank <frankja@linux.ibm.com> Reviewed-by:
-
Christian Borntraeger authored
If vector support is enabled, the vector BCD enhancements facility might also be enabled. We can directly forward this facility to the guest if available and VX is requested by user space. Please note that user space can and will have the final decision on the facility bits for a guests. Signed-off-by:
-
Christian Borntraeger authored
If vector support is enabled, the vector enhancements facility 2 might also be enabled. We can directly forward this facility to the guest if available and VX is requested by user space. Please note that user space can and will have the final decision on the facility bits for a guests. Signed-off-by:
-
Eric Farman authored
Fix some warnings from smatch: arch/s390/kvm/interrupt.c:2310 get_io_adapter() warn: potential spectre issue 'kvm->arch.adapters' [r] (local cap) arch/s390/kvm/interrupt.c:2341 register_io_adapter() warn: potential spectre issue 'dev->kvm->arch.adapters' [w] Signed-off-by:
Eric Farman <farman@linux.ibm.com> Message-Id: <20190417005414.47801-1-farman@linux.ibm.com> Reviewed-by:
-
- 16 Apr, 2019 20 commits
-
-
Paolo Bonzini authored
All architectures except MIPS were defining it in the same way, and memory slots are handled entirely by common code so there is no point in keeping the definition per-architecture. Signed-off-by: -
Sean Christopherson authored
EFER.LME and EFER.NX are considered reserved if their respective feature bits are not advertised to the guest. Signed-off-by:
-
Sean Christopherson authored
KVM allows userspace to violate consistency checks related to the guest's CPUID model to some degree. Generally speaking, userspace has carte blanche when it comes to guest state so long as jamming invalid state won't negatively affect the host. Currently this is seems to be a non-issue as most of the interesting EFER checks are missing, e.g. NX and LME, but those will be added shortly. Proactively exempt userspace from the CPUID checks so as not to break userspace. Note, the efer_reserved_bits check still applies to userspace writes as that mask reflects the host's capabilities, e.g. KVM shouldn't allow a guest to run with NX=1 if it has been disabled in the host. Fixes: d8017474 ("KVM: SVM: Only allow setting of EFER_SVME when CPUID SVM is set") Cc: stable@vger.kernel.org Signed-off-by:
-
Sean Christopherson authored
Most, but not all, helpers that are related to emulating consistency checks for nested VM-Entry return -EINVAL when a check fails. Convert the holdouts to have consistency throughout and to make it clear that the functions are signaling pass/fail as opposed to "resume guest" vs. "exit to userspace". Opportunistically fix bad indentation in nested_vmx_check_guest_state(). Signed-off-by:
-
Paolo Bonzini authored
Convert all top-level nested VM-Enter consistency check functions to return 0/-EINVAL instead of failure codes, since now they can only ever return one failure code. This also does not give the false impression that failure information is always consumed and/or relevant, e.g. vmx_set_nested_state() only cares whether or not the checks were successful. nested_check_host_control_regs() can also now be inlined into its caller, nested_vmx_check_host_state, since the two have effectively become the same function. Based on a patch by Sean Christopherson. Signed-off-by: -
Sean Christopherson authored
Rename the top-level consistency check functions to (loosely) align with the SDM. Historically, KVM has used the terms "prereq" and "postreq" to differentiate between consistency checks that lead to VM-Fail and those that lead to VM-Exit. The terms are vague and potentially misleading, e.g. "postreq" might be interpreted as occurring after VM-Entry. Note, while the SDM lumps controls and host state into a single section, "Checks on VMX Controls and Host-State Area", split them into separate top-level functions as the two categories of checks result in different VM instruction errors. This split will allow for additional cleanup. Note #2, "vmentry" is intentionally dropped from the new function names to avoid confusion with nested_check_vm_entry_controls(), and to keep the length of the functions names somewhat manageable. Suggested-by:
Krish Sadhukhan <krish.sadhukhan@oracle.com> Signed-off-by:
-
Sean Christopherson authored
Per Intel's SDM, volume 3, section Checking and Loading Guest State: Because the checking and the loading occur concurrently, a failure may be discovered only after some state has been loaded. For this reason, the logical processor responds to such failures by loading state from the host-state area, as it would for a VM exit. In other words, a failed non-register state consistency check results in a VM-Exit, not VM-Fail. Moving the non-reg state checks also paves the way for renaming nested_vmx_check_vmentry_postreqs() to align with the SDM, i.e. nested_vmx_check_vmentry_guest_state(). Fixes: 26539bd0 ("KVM: nVMX: check vmcs12 for valid activity state") Signed-off-by:
-
Krish Sadhukhan authored
According to section "Checking and Loading Guest State" in Intel SDM vol 3C, the following check is performed on vmentry: If the "load IA32_PAT" VM-entry control is 1, the value of the field for the IA32_PAT MSR must be one that could be written by WRMSR without fault at CPL 0. Specifically, each of the 8 bytes in the field must have one of the values 0 (UC), 1 (WC), 4 (WT), 5 (WP), 6 (WB), or 7 (UC-). Signed-off-by:Karl Heubaum <karl.heubaum@oracle.com> Suggested-by:
Jim Mattson <jmattson@google.com> Signed-off-by:
-
Krish Sadhukhan authored
According to section "Checks on Host Control Registers and MSRs" in Intel SDM vol 3C, the following check is performed on vmentry: If the "load IA32_PAT" VM-exit control is 1, the value of the field for the IA32_PAT MSR must be one that could be written by WRMSR without fault at CPL 0. Specifically, each of the 8 bytes in the field must have one of the values 0 (UC), 1 (WC), 4 (WT), 5 (WP), 6 (WB), or 7 (UC-). Signed-off-by: -
Paolo Bonzini authored
This check will soon be done on every nested vmentry and vmexit, "parallelize" it using bitwise operations. Reviewed-by:
-
Paolo Bonzini authored
This is not needed, PAT writes always take an MSR vmexit. Reviewed-by:
-
Paolo Bonzini authored
The SVI, RVI, virtual-APIC page address and APIC-access page address fields were left out of dump_vmcs. Add them. KERN_CONT technically isn't SMP safe, but it's okay to use it here since the whole of dump_vmcs() is a single huge multi-line piece of output that isn't SMP-safe. Signed-off-by: -
Vitaly Kuznetsov authored
In __apic_accept_irq() interface trig_mode is int and actually on some code paths it is set above u8: kvm_apic_set_irq() extracts it from 'struct kvm_lapic_irq' where trig_mode is u16. This is done on purpose as e.g. kvm_set_msi_irq() sets it to (1 << 15) & e->msi.data kvm_apic_local_deliver sets it to reg & (1 << 15). Fix the immediate issue by making 'tm' into u16. We may also want to adjust __apic_accept_irq() interface and use proper sizes for vector, level, trig_mode but this is not urgent. Signed-off-by:
Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by:
-
Paolo Bonzini authored
These were found with smatch, and then generalized when applicable. Signed-off-by: -
Hariprasad Kelam authored
Changed passing argument as "0 to NULL" which resolves below sparse warning arch/x86/kvm/x86.c:3096:61: warning: Using plain integer as NULL pointer Signed-off-by:
Hariprasad Kelam <hariprasad.kelam@gmail.com> Signed-off-by:
-
Vitaly Kuznetsov authored
Add a simple test for SMM, based on VMX. The test implements its own sync between the guest and the host as using our ucall library seems to be too cumbersome: SMI handler is happening in real-address mode. This patch also fixes KVM_SET_NESTED_STATE to happen after KVM_SET_VCPU_EVENTS, in fact it places it last. This is because KVM needs to know whether the processor is in SMM or not. Signed-off-by:
-
Paolo Bonzini authored
-no-pie was added to GCC at the same time as their configuration option --enable-default-pie. Compilers that were built before do not have -no-pie, but they also do not need it. Detect the option at build time. Signed-off-by: -
Paolo Bonzini authored
Starting state migration after an IO exit without first completing IO may result in test failures. We already have two tests that need this (this patch in fact fixes evmcs_test, similar to what was fixed for state_test in commit 0f73bbc8, "KVM: selftests: complete IO before migrating guest state", 2019-03-13) and a third is coming. So, move the code to vcpu_save_state, and while at it do not access register state until after I/O is complete. Signed-off-by:
-
Sean Christopherson authored
Invoking the 64-bit variation on a 32-bit kenrel will crash the guest, trigger a WARN, and/or lead to a buffer overrun in the host, e.g. rsm_load_state_64() writes r8-r15 unconditionally, but enum kvm_reg and thus x86_emulate_ctxt._regs only define r8-r15 for CONFIG_X86_64. KVM allows userspace to report long mode support via CPUID, even though the guest is all but guaranteed to crash if it actually tries to enable long mode. But, a pure 32-bit guest that is ignorant of long mode will happily plod along. SMM complicates things as 64-bit CPUs use a different SMRAM save state area. KVM handles this correctly for 64-bit kernels, e.g. uses the legacy save state map if userspace has hid long mode from the guest, but doesn't fare well when userspace reports long mode support on a 32-bit host kernel (32-bit KVM doesn't support 64-bit guests). Since the alternative is to crash the guest, e.g. by not loading state or explicitly requesting shutdown, unconditionally use the legacy SMRAM save state map for 32-bit KVM. If a guest has managed to get far enough to handle SMIs when running under a weird/buggy userspace hypervisor, then don't deliberately crash the guest since there are no downsides (from KVM's perspective) to allow it to continue running. Fixes: 660a5d51 ("KVM: x86: save/load state on SMM switch") Cc: stable@vger.kernel.org Signed-off-by:
-
Sean Christopherson authored
Neither AMD nor Intel CPUs have an EFER field in the legacy SMRAM save state area, i.e. don't save/restore EFER across SMM transitions. KVM somewhat models this, e.g. doesn't clear EFER on entry to SMM if the guest doesn't support long mode. But during RSM, KVM unconditionally clears EFER so that it can get back to pure 32-bit mode in order to start loading CRs with their actual non-SMM values. Clear EFER only when it will be written when loading the non-SMM state so as to preserve bits that can theoretically be set on 32-bit vCPUs, e.g. KVM always emulates EFER_SCE. And because CR4.PAE is cleared only to play nice with EFER, wrap that code in the long mode check as well. Note, this may result in a compiler warning about cr4 being consumed uninitialized. Re-read CR4 even though it's technically unnecessary, as doing so allows for more readable code and RSM emulation is not a performance critical path. Fixes: 660a5d51 ("KVM: x86: save/load state on SMM switch") Cc: stable@vger.kernel.org Signed-off-by:
-
