- 04 Feb, 2021 36 commits
-
-
Like Xu authored
The current vPMU only supports Architecture Version 2. According to Intel SDM "17.4.7 Freezing LBR and Performance Counters on PMI", if IA32_DEBUGCTL.Freeze_LBR_On_PMI = 1, the LBR is frozen on the virtual PMI and the KVM would emulate to clear the LBR bit (bit 0) in IA32_DEBUGCTL. Also, guest needs to re-enable IA32_DEBUGCTL.LBR to resume recording branches. Signed-off-by:
Like Xu <like.xu@linux.intel.com> Reviewed-by:
Andi Kleen <ak@linux.intel.com> Message-Id: <20210201051039.255478-9-like.xu@linux.intel.com> Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com>
-
Like Xu authored
When the LBR records msrs has already been pass-through, there is no need to call vmx_update_intercept_for_lbr_msrs() again and again, and vice versa. Signed-off-by:
-
Like Xu authored
In addition to DEBUGCTLMSR_LBR, any KVM trap caused by LBR msrs access will result in a creation of guest LBR event per-vcpu. If the guest LBR event is scheduled on with the corresponding vcpu context, KVM will pass-through all LBR records msrs to the guest. The LBR callstack mechanism implemented in the host could help save/restore the guest LBR records during the event context switches, which reduces a lot of overhead if we save/restore tens of LBR msrs (e.g. 32 LBR records entries) in the much more frequent VMX transitions. To avoid reclaiming LBR resources from any higher priority event on host, KVM would always check the exist of guest LBR event and its state before vm-entry as late as possible. A negative result would cancel the pass-through state, and it also prevents real registers accesses and potential data leakage. If host reclaims the LBR between two checks, the interception state and LBR records can be safely preserved due to native save/restore support from guest LBR event. The KVM emits a pr_warn() when the LBR hardware is unavailable to the guest LBR event. The administer is supposed to reminder users that the guest result may be inaccurate if someone is using LBR to record hypervisor on the host side. Suggested-by:
Wei Wang <wei.w.wang@intel.com> Signed-off-by:
-
Like Xu authored
When vcpu sets DEBUGCTLMSR_LBR in the MSR_IA32_DEBUGCTLMSR, the KVM handler would create a guest LBR event which enables the callstack mode and none of hardware counter is assigned. The host perf would schedule and enable this event as usual but in an exclusive way. The guest LBR event will be released when the vPMU is reset but soon, the lazy release mechanism would be applied to this event like a vPMC. Suggested-by:
-
Like Xu authored
Usespace could set the bits [0, 5] of the IA32_PERF_CAPABILITIES MSR which tells about the record format stored in the LBR records. The LBR will be enabled on the guest if host perf supports LBR (checked via x86_perf_get_lbr()) and the vcpu model is compatible with the host one. Signed-off-by:
-
Paolo Bonzini authored
Usespace could set the bits [0, 5] of the IA32_PERF_CAPABILITIES MSR which tells about the record format stored in the LBR records. The LBR will be enabled on the guest if host perf supports LBR (checked via x86_perf_get_lbr()) and the vcpu model is compatible with the host one. Signed-off-by:
-
Paolo Bonzini authored
Once MSR_IA32_PERF_CAPABILITIES is changed via vmx_set_msr(), the value should not be changed by cpuid(). To ensure that the new value is kept, the default initialization path is moved to intel_pmu_init(). The effective value of the MSR will be 0 if PDCM is clear, however. Signed-off-by: -
Like Xu authored
To make code responsibilities clear, we may resue and invoke the vmx_set_intercept_for_msr() in other vmx-specific files (e.g. pmu_intel.c), so expose it to passthrough LBR msrs later. Signed-off-by:
-
Like Xu authored
SVM already has specific handlers of MSR_IA32_DEBUGCTLMSR in the svm_get/set_msr, so the x86 common part can be safely moved to VMX. This allows KVM to store the bits it supports in GUEST_IA32_DEBUGCTL. Add vmx_supported_debugctl() to refactor the throwing logic of #GP. Signed-off-by:
-
Sean Christopherson authored
Use x2apic_mode instead of x2apic_enabled() when adjusting the destination ID during Posted Interrupt updates. This avoids the costly RDMSR that is hidden behind x2apic_enabled(). Reported-by:
luferry <luferry@163.com> Signed-off-by:
Sean Christopherson <seanjc@google.com> Message-Id: <20210115220354.434807-3-seanjc@google.com> Signed-off-by:
-
Sean Christopherson authored
Export x2apic_mode so that KVM can query whether x2APIC is active without having to incur the RDMSR in x2apic_enabled(). When Posted Interrupts are in use for a guest with an assigned device, KVM ends up checking for x2APIC at least once every time a vCPU halts. KVM could obviously snapshot x2apic_enabled() to avoid the RDMSR, but that's rather silly given that x2apic_mode holds the exact info needed by KVM. Signed-off-by:
-
Chenyi Qiang authored
Introduce a new capability named KVM_CAP_X86_BUS_LOCK_EXIT, which is used to handle bus locks detected in guest. It allows the userspace to do custom throttling policies to mitigate the 'noisy neighbour' problem. Signed-off-by:
Chenyi Qiang <chenyi.qiang@intel.com> Message-Id: <20201106090315.18606-5-chenyi.qiang@intel.com> Signed-off-by:
-
Chenyi Qiang authored
Virtual Machine can exploit bus locks to degrade the performance of system. Bus lock can be caused by split locked access to writeback(WB) memory or by using locks on uncacheable(UC) memory. The bus lock is typically >1000 cycles slower than an atomic operation within a cache line. It also disrupts performance on other cores (which must wait for the bus lock to be released before their memory operations can complete). To address the threat, bus lock VM exit is introduced to notify the VMM when a bus lock was acquired, allowing it to enforce throttling or other policy based mitigations. A VMM can enable VM exit due to bus locks by setting a new "Bus Lock Detection" VM-execution control(bit 30 of Secondary Processor-based VM execution controls). If delivery of this VM exit was preempted by a higher priority VM exit (e.g. EPT misconfiguration, EPT violation, APIC access VM exit, APIC write VM exit, exception bitmap exiting), bit 26 of exit reason in vmcs field is set to 1. In current implementation, the KVM exposes this capability through KVM_CAP_X86_BUS_LOCK_EXIT. The user can get the supported mode bitmap (i.e. off and exit) and enable it explicitly (disabled by default). If bus locks in guest are detected by KVM, exit to user space even when current exit reason is handled by KVM internally. Set a new field KVM_RUN_BUS_LOCK in vcpu->run->flags to inform the user space that there is a bus lock detected in guest. Document for Bus Lock VM exit is now available at the latest "Intel Architecture Instruction Set Extensions Programming Reference". Document Link: https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.htmlCo-developed-by:
Xiaoyao Li <xiaoyao.li@intel.com> Signed-off-by:
-
Chenyi Qiang authored
Reset the vcpu->run->flags at the beginning of kvm_arch_vcpu_ioctl_run. It can avoid every thunk of code that needs to set the flag clear it, which increases the odds of missing a case and ending up with a flag in an undefined state. Signed-off-by:
-
Sean Christopherson authored
Convert vcpu_vmx.exit_reason from a u32 to a union (of size u32). The full VM_EXIT_REASON field is comprised of a 16-bit basic exit reason in bits 15:0, and single-bit modifiers in bits 31:16. Historically, KVM has only had to worry about handling the "failed VM-Entry" modifier, which could only be set in very specific flows and required dedicated handling. I.e. manually stripping the FAILED_VMENTRY bit was a somewhat viable approach. But even with only a single bit to worry about, KVM has had several bugs related to comparing a basic exit reason against the full exit reason store in vcpu_vmx. Upcoming Intel features, e.g. SGX, will add new modifier bits that can be set on more or less any VM-Exit, as opposed to the significantly more restricted FAILED_VMENTRY, i.e. correctly handling everything in one-off flows isn't scalable. Tracking exit reason in a union forces code to explicitly choose between consuming the full exit reason and the basic exit, and is a convenient way to document and access the modifiers. No functional change intended. Cc: Xiaoyao Li <xiaoyao.li@intel.com> Signed-off-by:
Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by:
-
Brijesh Singh authored
The SEV FW version >= 0.23 added a new command that can be used to query the attestation report containing the SHA-256 digest of the guest memory encrypted through the KVM_SEV_LAUNCH_UPDATE_{DATA, VMSA} commands and sign the report with the Platform Endorsement Key (PEK). See the SEV FW API spec section 6.8 for more details. Note there already exist a command (KVM_SEV_LAUNCH_MEASURE) that can be used to get the SHA-256 digest. The main difference between the KVM_SEV_LAUNCH_MEASURE and KVM_SEV_ATTESTATION_REPORT is that the latter can be called while the guest is running and the measurement value is signed with PEK. Cc: James Bottomley <jejb@linux.ibm.com> Cc: Tom Lendacky <Thomas.Lendacky@amd.com> Cc: David Rientjes <rientjes@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Borislav Petkov <bp@alien8.de> Cc: John Allen <john.allen@amd.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: linux-crypto@vger.kernel.org Reviewed-by:Tom Lendacky <thomas.lendacky@amd.com> Acked-by:
David Rientjes <rientjes@google.com> Tested-by:
James Bottomley <jejb@linux.ibm.com> Signed-off-by:
Brijesh Singh <brijesh.singh@amd.com> Message-Id: <20210104151749.30248-1-brijesh.singh@amd.com> Signed-off-by:
-
Ben Gardon authored
Disabling dirty logging is much more intestesting from a testing perspective if the vCPUs are still running. This also excercises the code-path in which collapsible SPTEs must be faulted back in at a higher level after disabling dirty logging. To: linux-kselftest@vger.kernel.org CC: Peter Xu <peterx@redhat.com> CC: Andrew Jones <drjones@redhat.com> CC: Thomas Huth <thuth@redhat.com> Signed-off-by:
Ben Gardon <bgardon@google.com> Message-Id: <20210202185734.1680553-29-bgardon@google.com> Signed-off-by:
-
Ben Gardon authored
Add a parameter to control the backing memory type for dirty_log_perf_test so that the test can be run with hugepages. To: linux-kselftest@vger.kernel.org CC: Peter Xu <peterx@redhat.com> CC: Andrew Jones <drjones@redhat.com> CC: Thomas Huth <thuth@redhat.com> Signed-off-by:
-
Ben Gardon authored
Add a memslot modification stress test in which a memslot is repeatedly created and removed while vCPUs access memory in another memslot. Most userspaces do not create or remove memslots on running VMs which makes it hard to test races in adding and removing memslots without a dedicated test. Adding and removing a memslot also has the effect of tearing down the entire paging structure, which leads to more page faults and pressure on the page fault handling path than a one-and-done memory population test. Reviewed-by:
Jacob Xu <jacobhxu@google.com> Signed-off-by:
-
Ben Gardon authored
Add an option to overlap the ranges of memory each vCPU accesses instead of partitioning them. This option will increase the probability of multiple vCPUs faulting on the same page at the same time, and causing interesting races, if there are bugs in the page fault handler or elsewhere in the kernel. Reviewed-by:
Makarand Sonare <makarandsonare@google.com> Signed-off-by:
-
Ben Gardon authored
Currently the population stage in the dirty_log_perf_test does nothing as the per-vCPU iteration counters are not initialized and the loop does not wait for each vCPU. Remedy those errors. Reviewed-by:
-
Ben Gardon authored
In order to add an iteration -1 to indicate that the memory population phase has not yet completed, convert the interations counters to ints. No functional change intended. Reviewed-by:
-
Ben Gardon authored
Peter Xu pointed out that a log message printed while waiting for the memory population phase of the dirty_log_perf_test will flood the debug logs as there is no delay after printing the message. Since the message does not provide much value anyway, remove it. Reviewed-by:
-
Ben Gardon authored
In response to some earlier comments from Peter Xu, rename timespec_diff_now to the much more sensible timespec_elapsed. No functional change intended. Reviewed-by:
-
Sean Christopherson authored
Remove the update_pte() shadow paging logic, which was obsoleted by commit 4731d4c7 ("KVM: MMU: out of sync shadow core"), but never removed. As pointed out by Yu, KVM never write protects leaf page tables for the purposes of shadow paging, and instead marks their associated shadow page as unsync so that the guest can write PTEs at will. The update_pte() path, which predates the unsync logic, optimizes COW scenarios by refreshing leaf SPTEs when they are written, as opposed to zapping the SPTE, restarting the guest, and installing the new SPTE on the subsequent fault. Since KVM no longer write-protects leaf page tables, update_pte() is unreachable and can be dropped. Reported-by:
Yu Zhang <yu.c.zhang@intel.com> Signed-off-by:
-
Peter Shier authored
When a guest is using xAPIC KVM allocates a backing page for the required EPT entry for the APIC access address set in the VMCS. If mm decides to move that page the KVM mmu notifier will update the VMCS with the new HPA. This test induces a page move to test that APIC access continues to work correctly. It is a directed test for commit e649b3f0 "KVM: x86: Fix APIC page invalidation race". Tested: ran for 1 hour on a skylake, migrating backing page every 1ms Depends on patch "selftests: kvm: Add exception handling to selftests" from aaronlewis@google.com that has not yet been queued. Signed-off-by:
Peter Shier <pshier@google.com> Reviewed-by:
Jim Mattson <jmattson@google.com> Reviewed-by:
Ricardo Koller <ricarkol@google.com> Message-Id: <20201105223823.850068-1-pshier@google.com> Signed-off-by:
-
Yang Zhong authored
Expose AVX (VEX-encoded) versions of the Vector Neural Network Instructions to guest. The bit definition: CPUID.(EAX=7,ECX=1):EAX[bit 4] AVX_VNNI The following instructions are available when this feature is present in the guest. 1. VPDPBUS: Multiply and Add Unsigned and Signed Bytes 2. VPDPBUSDS: Multiply and Add Unsigned and Signed Bytes with Saturation 3. VPDPWSSD: Multiply and Add Signed Word Integers 4. VPDPWSSDS: Multiply and Add Signed Integers with Saturation This instruction is currently documented in the latest "extensions" manual (ISE). It will appear in the "main" manual (SDM) in the future. Signed-off-by:
Yang Zhong <yang.zhong@intel.com> Reviewed-by:
Tony Luck <tony.luck@intel.com> Message-Id: <20210105004909.42000-3-yang.zhong@intel.com> Signed-off-by:
-
Kyung Min Park authored
Add AVX version of the Vector Neural Network (VNNI) Instructions. A processor supports AVX VNNI instructions if CPUID.0x07.0x1:EAX[4] is present. The following instructions are available when this feature is present. 1. VPDPBUS: Multiply and Add Unsigned and Signed Bytes 2. VPDPBUSDS: Multiply and Add Unsigned and Signed Bytes with Saturation 3. VPDPWSSD: Multiply and Add Signed Word Integers 4. VPDPWSSDS: Multiply and Add Signed Integers with Saturation The only in-kernel usage of this is kvm passthrough. The CPU feature flag is shown as "avx_vnni" in /proc/cpuinfo. This instruction is currently documented in the latest "extensions" manual (ISE). It will appear in the "main" manual (SDM) in the future. Signed-off-by:
Kyung Min Park <kyung.min.park@intel.com> Signed-off-by:
Borislav Petkov <bp@suse.de> Signed-off-by:
-
YANG LI authored
Fix the following coccicheck warning: ./arch/x86/kvm/x86.c:8012:5-48: WARNING: Comparison to bool Signed-off-by:
YANG LI <abaci-bugfix@linux.alibaba.com> Reported-by:
Abaci Robot <abaci@linux.alibaba.com> Message-Id: <1610357578-66081-1-git-send-email-abaci-bugfix@linux.alibaba.com> Reviewed-by:
Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by:
-
Sean Christopherson authored
Walk the list of MMU pages in reverse in kvm_mmu_zap_oldest_mmu_pages(). The list is FIFO, meaning new pages are inserted at the head and thus the oldest pages are at the tail. Using a "forward" iterator causes KVM to zap MMU pages that were just added, which obliterates guest performance once the max number of shadow MMU pages is reached. Fixes: 6b82ef2c ("KVM: x86/mmu: Batch zap MMU pages when recycling oldest pages") Reported-by:
Zdenek Kaspar <zkaspar82@gmail.com> Cc: stable@vger.kernel.org Signed-off-by:
-
Sean Christopherson authored
Return a 'bool' instead of an 'int' for various PTE accessors that are boolean in nature, e.g. is_shadow_present_pte(). Returning an int is goofy and potentially dangerous, e.g. if a flag being checked is moved into the upper 32 bits of a SPTE, then the compiler may silently squash the entire check since casting to an int is guaranteed to yield a return value of '0'. Opportunistically refactor is_last_spte() so that it naturally returns a bool value instead of letting it implicitly cast 0/1 to false/true. No functional change intended. Signed-off-by:
-
Tian Tao authored
fixed the following warning： /virt/kvm/dirty_ring.c:70:20-27: WARNING: vzalloc should be used for ring -> dirty_gfns, instead of vmalloc/memset. Signed-off-by:
Tian Tao <tiantao6@hisilicon.com> Message-Id: <1611547045-13669-1-git-send-email-tiantao6@hisilicon.com> Signed-off-by:
-
Sean Christopherson authored
Enter a SRCU critical section for a memslots lookup during steal time update if and only if a steal time update is actually needed. Taking the lock can be avoided if steal time is disabled by the guest, or if KVM knows it has already flagged the vCPU as being preempted. Reword the comment to be more precise as to exactly why memslots will be queried. Signed-off-by:
-
Sean Christopherson authored
Remove the disabling of page faults across kvm_steal_time_set_preempted() as KVM now accesses the steal time struct (shared with the guest) via a cached mapping (see commit b0431382, "x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed".) The cache lookup is flagged as atomic, thus it would be a bug if KVM tried to resolve a new pfn, i.e. we want the splat that would be reached via might_fault(). Signed-off-by:
-
Paolo Bonzini authored
In order to convert an HVA to a PFN, KVM usually tries to use the get_user_pages family of functinso. This however is not possible for VM_IO vmas; in that case, KVM instead uses follow_pfn. In doing this however KVM loses the information on whether the PFN is writable. That is usually not a problem because the main use of VM_IO vmas with KVM is for BARs in PCI device assignment, however it is a bug. To fix it, use follow_pte and check pte_write while under the protection of the PTE lock. The information can be used to fail hva_to_pfn_remapped or passed back to the caller via *writable. Usage of follow_pfn was introduced in commit add6a0cd ("KVM: MMU: try to fix up page faults before giving up", 2016-07-05); however, even older version have the same issue, all the way back to commit 2e2e3738 ("KVM: Handle vma regions with no backing page", 2008-07-20), as they also did not check whether the PFN was writable. Fixes: 2e2e3738 ("KVM: Handle vma regions with no backing page") Reported-by:
David Stevens <stevensd@google.com> Cc: 3pvd@google.com Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: stable@vger.kernel.org Signed-off-by:
-
Ben Gardon authored
There is a bug in the TDP MMU function to zap SPTEs which could be replaced with a larger mapping which prevents the function from doing anything. Fix this by correctly zapping the last level SPTEs. Cc: stable@vger.kernel.org Fixes: 14881998 ("kvm: x86/mmu: Support disabling dirty logging for the tdp MMU") Signed-off-by:
-
- 03 Feb, 2021 2 commits
-
-
Paolo Bonzini authored
If not in long mode, the low bits of CR3 are reserved but not enforced to be zero, so remove those checks. If in long mode, however, the MBZ bits extend down to the highest physical address bit of the guest, excluding the encryption bit. Make the checks consistent with the above, and match them between nested_vmcb_checks and KVM_SET_SREGS. Cc: stable@vger.kernel.org Fixes: 761e4169 ("KVM: nSVM: Check that MBZ bits in CR3 and CR4 are not set on vmrun of nested guests") Fixes: a780a3ea ("KVM: X86: Fix reserved bits check for MOV to CR3") Reviewed-by:
-
Sean Christopherson authored
Don't let KVM load when running as an SEV guest, regardless of what CPUID says. Memory is encrypted with a key that is not accessible to the host (L0), thus it's impossible for L0 to emulate SVM, e.g. it'll see garbage when reading the VMCB. Technically, KVM could decrypt all memory that needs to be accessible to the L0 and use shadow paging so that L0 does not need to shadow NPT, but exposing such information to L0 largely defeats the purpose of running as an SEV guest. This can always be revisited if someone comes up with a use case for running VMs inside SEV guests. Note, VMLOAD, VMRUN, etc... will also #GP on GPAs with C-bit set, i.e. KVM is doomed even if the SEV guest is debuggable and the hypervisor is willing to decrypt the VMCB. This may or may not be fixed on CPUs that have the SVME_ADDR_CHK fix. Cc: stable@vger.kernel.org Signed-off-by:
-
- 02 Feb, 2021 1 commit
-
-
Sean Christopherson authored
Set the emulator context to PROT64 if SYSENTER transitions from 32-bit userspace (compat mode) to a 64-bit kernel, otherwise the RIP update at the end of x86_emulate_insn() will incorrectly truncate the new RIP. Note, this bug is mostly limited to running an Intel virtual CPU model on an AMD physical CPU, as other combinations of virtual and physical CPUs do not trigger full emulation. On Intel CPUs, SYSENTER in compatibility mode is legal, and unconditionally transitions to 64-bit mode. On AMD CPUs, SYSENTER is illegal in compatibility mode and #UDs. If the vCPU is AMD, KVM injects a #UD on SYSENTER in compat mode. If the pCPU is Intel, SYSENTER will execute natively and not trigger #UD->VM-Exit (ignoring guest TLB shenanigans). Fixes: fede8076 ("KVM: x86: handle wrap around 32-bit address space") Cc: stable@vger.kernel.org Signed-off-by:
Jonny Barker <jonny@jonnybarker.com> [sean: wrote changelog] Signed-off-by:
-
- 01 Feb, 2021 1 commit
-
-
Vitaly Kuznetsov authored
Commit 7a873e45 ("KVM: selftests: Verify supported CR4 bits can be set before KVM_SET_CPUID2") reveals that KVM allows to set X86_CR4_PCIDE even when PCID support is missing: ==== Test Assertion Failure ==== x86_64/set_sregs_test.c:41: rc pid=6956 tid=6956 - Invalid argument 1 0x000000000040177d: test_cr4_feature_bit at set_sregs_test.c:41 2 0x00000000004014fc: main at set_sregs_test.c:119 3 0x00007f2d9346d041: ?? ??:0 4 0x000000000040164d: _start at ??:? KVM allowed unsupported CR4 bit (0x20000) Add X86_FEATURE_PCID feature check to __cr4_reserved_bits() to make kvm_is_valid_cr4() fail. Signed-off-by:
-
