Fix a bug in KVM_SET_CPUID{2,} where KVM looks at the wrong CPUID entries (old
vs. new) and ultimately neglects to clear PV_UNHALT from vCPUs with HLT-exiting
disabled.
KVM x86 PMU changes for 6.9:
- Fix several bugs where KVM speciously prevents the guest from utilizing
fixed counters and architectural event encodings based on whether or not
guest CPUID reports support for the _architectural_ encoding.
- Fix a variety of bugs in KVM's emulation of RDPMC, e.g. for "fast" reads,
priority of VMX interception vs #GP, PMC types in architectural PMUs, etc.
- Add a selftest to verify KVM correctly emulates RDMPC, counter availability,
and a variety of other PMC-related behaviors that depend on guest CPUID,
i.e. are difficult to validate via KVM-Unit-Tests.
- Zero out PMU metadata on AMD if the virtual PMU is disabled to avoid wasting
cycles, e.g. when checking if a PMC event needs to be synthesized when
skipping an instruction.
- Optimize triggering of emulated events, e.g. for "count instructions" events
when skipping an instruction, which yields a ~10% performance improvement in
VM-Exit microbenchmarks when a vPMU is exposed to the guest.
- Tighten the check for "PMI in guest" to reduce false positives if an NMI
arrives in the host while KVM is handling an IRQ VM-Exit.
KVM selftests changes for 6.9:
- Add macros to reduce the amount of boilerplate code needed to write "simple"
selftests, and to utilize selftest TAP infrastructure, which is especially
beneficial for KVM selftests with multiple testcases.
- Add basic smoke tests for SEV and SEV-ES, along with a pile of library
support for handling private/encrypted/protected memory.
- Fix benign bugs where tests neglect to close() guest_memfd files.
KVM_FEATURE_PV_UNHALT is expected to get cleared from KVM PV feature CPUID
data when KVM_X86_DISABLE_EXITS_HLT is enabled. Add the corresponding test
to kvm_pv_test.
Note, the newly added code doesn't actually test KVM_FEATURE_PV_UNHALT and
KVM_X86_DISABLE_EXITS_HLT features.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240228101837.93642-4-vkuznets@redhat.com
[sean: add and use vcpu_cpuid_has()]
Signed-off-by: Sean Christopherson <seanjc@google.com>
KVM's 'gtod_is_based_on_tsc()' recognizes two clocksources: 'tsc' and
'hyperv_clocksource_tsc_page' and enables kvmclock in 'masterclock'
mode when either is in use. Transform 'sys_clocksource_is_tsc()' into
'sys_clocksource_is_based_on_tsc()' to support the later. This affects
two tests: kvm_clock_test and vmx_nested_tsc_scaling_test, both seem
to work well when system clocksource is 'hyperv_clocksource_tsc_page'.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240109141121.1619463-4-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Several existing x86 selftests need to check that the underlying system
clocksource is TSC or based on TSC but every test implements its own
check. As a first step towards unification, extract check_clocksource()
from kvm_clock_test and split it into two functions: arch-neutral
'sys_get_cur_clocksource()' and x86-specific 'sys_clocksource_is_tsc()'.
Fix a couple of pre-existing issues in kvm_clock_test: memory leakage in
check_clocksource() and using TEST_ASSERT() instead of TEST_REQUIRE().
The change also makes the test fail when system clocksource can't be read
from sysfs.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240109141121.1619463-2-vkuznets@redhat.com
[sean: eliminate if-elif pattern just to set a bool true]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Add KVM_ASM_SAFE_FEP() to allow forcing emulation on an instruction that
might fault. Note, KVM skips RIP past the FEP prefix before injecting an
exception, i.e. the fixup needs to be on the instruction itself. Do not
check for FEP support, that is firmly the responsibility of whatever code
wants to use KVM_ASM_SAFE_FEP().
Sadly, chaining variadic arguments that contain commas doesn't work, thus
the unfortunate amount of copy+paste.
Tested-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20240109230250.424295-28-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Extend the kvm_x86_pmu_feature framework to allow querying for fixed
counters via {kvm,this}_pmu_has(). Like architectural events, checking
for a fixed counter annoyingly requires checking multiple CPUID fields, as
a fixed counter exists if:
FxCtr[i]_is_supported := ECX[i] || (EDX[4:0] > i);
Note, KVM currently doesn't actually support exposing fixed counters via
the bitmask, but that will hopefully change sooner than later, and Intel's
SDM explicitly "recommends" checking both the number of counters and the
mask.
Rename the intermedate "anti_feature" field to simply 'f' since the fixed
counter bitmask (thankfully) doesn't have reversed polarity like the
architectural events bitmask.
Note, ideally the helpers would use BUILD_BUG_ON() to assert on the
incoming register, but the expected usage in PMU tests can't guarantee the
inputs are compile-time constants.
Opportunistically define macros for all of the known architectural events
and fixed counters.
Tested-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20240109230250.424295-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Add helpers for x86 guests to invoke the KVM_HC_MAP_GPA_RANGE hypercall,
which KVM will forward to userspace and thus can be used by tests to
coordinate private<=>shared conversions between host userspace code and
guest code.
Signed-off-by: Vishal Annapurve <vannapurve@google.com>
[sean: drop shared/private helpers (let tests specify flags)]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-29-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Extend x86's state to forcefully load *all* host-supported xfeatures by
modifying xstate_bv in the saved state. Stuffing xstate_bv ensures that
the selftest is verifying KVM's full ABI regardless of whether or not the
guest code is successful in getting various xfeatures out of their INIT
state, e.g. see the disaster that is/was MPX.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20230928001956.924301-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Modify support XSAVE state in the "state test's" guest code so that saving
and loading state via KVM_{G,S}ET_XSAVE actually does something useful,
i.e. so that xstate_bv in XSAVE state isn't empty.
Punt on BNDCSR for now, it's easier to just stuff that xfeature from the
host side.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20230928001956.924301-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM selftests, and an AMX/XCR0 bugfix, for 6.4:
- Don't advertise XTILE_CFG in KVM_GET_SUPPORTED_CPUID if XTILE_DATA is
not being reported due to userspace not opting in via prctl()
- Overhaul the AMX selftests to improve coverage and cleanup the test
- Misc cleanups
Check both architectural rules and KVM's ABI for KVM_GET_SUPPORTED_CPUID
to ensure the supported xfeatures[1] don't violate any of them.
The architectural rules[2] and KVM's contract with userspace ensure for a
given feature, e.g. sse, avx, amx, etc... their associated xfeatures are
either all sets or none of them are set, and any dependencies are enabled
if needed.
[1] EDX:EAX of CPUID.(EAX=0DH,ECX=0)
[2] SDM vol 1, 13.3 ENABLING THE XSAVE FEATURE SET AND XSAVE-ENABLED
FEATURES
Cc: Mingwei Zhang <mizhang@google.com>
Signed-off-by: Aaron Lewis <aaronlewis@google.com>
[sean: expand comments, use a fancy X86_PROPERTY]
Reviewed-by: Aaron Lewis <aaronlewis@google.com>
Tested-by: Aaron Lewis <aaronlewis@google.com>
Link: https://lore.kernel.org/r/20230405004520.421768-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Take the XFeature mask in __vm_xsave_require_permission() instead of the
bit so that there's no need to define macros for both the bit and the
mask. Asserting that only a single bit is set and retrieving said bit
is easy enough via log2 helpers.
Opportunistically clean up the error message for the
ARCH_REQ_XCOMP_GUEST_PERM sanity check.
Reviewed-by: Aaron Lewis <aaronlewis@google.com>
Tested-by: Aaron Lewis <aaronlewis@google.com>
Link: https://lore.kernel.org/r/20230405004520.421768-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Assert that KVM provides "read what you wrote" semantics for all "durable"
MSRs (for lack of a better name). The extra coverage is cheap from a
runtime performance perspective, and verifying the behavior in the common
helper avoids gratuitous copy+paste in individual tests.
Note, this affects all tests that set MSRs from userspace!
Link: https://lore.kernel.org/r/20230311004618.920745-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reimplement vcpu_set_msr() as a macro and pretty print the failing MSR
(when possible) and the value if KVM_SET_MSRS fails instead of using the
using the standard KVM_IOCTL_ERROR(). KVM_SET_MSRS is somewhat odd in
that it returns the index of the last successful write, i.e. will be
'0' on failure barring an entirely different KVM bug. And for writing
MSRs, the MSR being written and the value being written are almost always
relevant to the failure, i.e. just saying "failed!" doesn't help debug.
Place the string goo in a separate macro in anticipation of using it to
further expand MSR testing.
Link: https://lore.kernel.org/r/20230311004618.920745-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Add a working xstate data structure for the usage of AMX and potential
future usage on other xstate components. AMX selftest requires checking
both the xstate_bv and xcomp_bv. Existing code relies on pointer
arithmetics to fetch xstate_bv and does not support xcomp_bv.
So, add a working xstate data structure into processor.h for x86.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Mingwei Zhang <mizhang@google.com>
Link: https://lore.kernel.org/r/20230221163655.920289-3-mizhang@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Add wrappers to do hypercalls using VMCALL/VMMCALL and Xen's register ABI
(as opposed to full Xen-style hypercalls through a hypervisor provided
page). Using the common helpers dedups a pile of code, and uses the
native hypercall instruction when running on AMD.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20230204024151.1373296-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a test for the newly introduced Hyper-V invariant TSC control feature:
- HV_X64_MSR_TSC_INVARIANT_CONTROL is not available without
HV_ACCESS_TSC_INVARIANT CPUID bit set and available with it.
- BIT(0) of HV_X64_MSR_TSC_INVARIANT_CONTROL controls the filtering of
architectural invariant TSC (CPUID.80000007H:EDX[8]) bit.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20221013095849.705943-8-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Misc KVM x86 fixes and cleanups for 6.2:
- One-off fixes for various emulation flows (SGX, VMXON, NRIPS=0).
- Reinstate IBPB on emulated VM-Exit that was incorrectly dropped a few
years back when eliminating unnecessary barriers when switching between
vmcs01 and vmcs02.
- Clean up the MSR filter docs.
- Clean up vmread_error_trampoline() to make it more obvious that params
must be passed on the stack, even for x86-64.
- Let userspace set all supported bits in MSR_IA32_FEAT_CTL irrespective
of the current guest CPUID.
- Fudge around a race with TSC refinement that results in KVM incorrectly
thinking a guest needs TSC scaling when running on a CPU with a
constant TSC, but no hardware-enumerated TSC frequency.
Define and use kvm_static_assert() in the common KVM selftests headers to
provide deterministic behavior, and to allow creating static asserts
without dummy messages.
The kernel's static_assert() makes the message param optional, and on the
surface, tools/include/linux/build_bug.h appears to follow suit. However,
glibc may override static_assert() and redefine it as a direct alias of
_Static_assert(), which makes the message parameter mandatory. This leads
to non-deterministic behavior as KVM selftests code that utilizes
static_assert() without a custom message may or not compile depending on
the order of includes. E.g. recently added asserts in
x86_64/processor.h fail on some systems with errors like
In file included from lib/memstress.c:11:0:
include/x86_64/processor.h: In function ‘this_cpu_has_p’:
include/x86_64/processor.h:193:34: error: expected ‘,’ before ‘)’ token
static_assert(low_bit < high_bit); \
^
due to _Static_assert() expecting a comma before a message. The "message
optional" version of static_assert() uses macro magic to strip away the
comma when presented with empty an __VA_ARGS__
#ifndef static_assert
#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
#endif // static_assert
and effectively generates "_Static_assert(expr, #expr)".
The incompatible version of static_assert() gets defined by this snippet
in /usr/include/assert.h:
#if defined __USE_ISOC11 && !defined __cplusplus
# undef static_assert
# define static_assert _Static_assert
#endif
which yields "_Static_assert(expr)" and thus fails as above.
KVM selftests don't actually care about using C11, but __USE_ISOC11 gets
defined because of _GNU_SOURCE, which many tests do #define. _GNU_SOURCE
triggers a massive pile of defines in /usr/include/features.h, including
_ISOC11_SOURCE:
/* If _GNU_SOURCE was defined by the user, turn on all the other features. */
#ifdef _GNU_SOURCE
# undef _ISOC95_SOURCE
# define _ISOC95_SOURCE 1
# undef _ISOC99_SOURCE
# define _ISOC99_SOURCE 1
# undef _ISOC11_SOURCE
# define _ISOC11_SOURCE 1
# undef _POSIX_SOURCE
# define _POSIX_SOURCE 1
# undef _POSIX_C_SOURCE
# define _POSIX_C_SOURCE 200809L
# undef _XOPEN_SOURCE
# define _XOPEN_SOURCE 700
# undef _XOPEN_SOURCE_EXTENDED
# define _XOPEN_SOURCE_EXTENDED 1
# undef _LARGEFILE64_SOURCE
# define _LARGEFILE64_SOURCE 1
# undef _DEFAULT_SOURCE
# define _DEFAULT_SOURCE 1
# undef _ATFILE_SOURCE
# define _ATFILE_SOURCE 1
#endif
which further down in /usr/include/features.h leads to:
/* This is to enable the ISO C11 extension. */
#if (defined _ISOC11_SOURCE \
|| (defined __STDC_VERSION__ && __STDC_VERSION__ >= 201112L))
# define __USE_ISOC11 1
#endif
To make matters worse, /usr/include/assert.h doesn't guard against
multiple inclusion by turning itself into a nop, but instead #undefs a
few macros and continues on. As a result, it's all but impossible to
ensure the "message optional" version of static_assert() will actually be
used, e.g. explicitly including assert.h and #undef'ing static_assert()
doesn't work as a later inclusion of assert.h will again redefine its
version.
#ifdef _ASSERT_H
# undef _ASSERT_H
# undef assert
# undef __ASSERT_VOID_CAST
# ifdef __USE_GNU
# undef assert_perror
# endif
#endif /* assert.h */
#define _ASSERT_H 1
#include <features.h>
Fixes: fcba483e82 ("KVM: selftests: Sanity check input to ioctls() at build time")
Fixes: ee37955366 ("KVM: selftests: Refactor X86_FEATURE_* framework to prep for X86_PROPERTY_*")
Fixes: 53a7dc0f21 ("KVM: selftests: Add X86_PROPERTY_* framework to retrieve CPUID values")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221122013309.1872347-1-seanjc@google.com
Restore the assert (on x86-64) that <10% of pages are still idle when NOT
running as a nested VM in the access tracking test. The original assert
was converted to a "warning" to avoid false failures when running the
test in a VM, but the non-nested case does not suffer from the same
"infinite TLB size" issue.
Using the HYPERVISOR flag isn't infallible as VMMs aren't strictly
required to enumerate the "feature" in CPUID, but practically speaking
anyone that is running KVM selftests in VMs is going to be using a VMM
and hypervisor that sets the HYPERVISOR flag.
Cc: David Matlack <dmatlack@google.com>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221129175300.4052283-3-seanjc@google.com
Verify the KVM allows userspace to set all supported bits in the
IA32_FEATURE_CONTROL MSR irrespective of the current guest CPUID, and
that all unsupported bits are rejected.
Throw the testcase into vmx_msrs_test even though it's not technically a
VMX MSR; it's close enough, and the most frequently feature controlled by
the MSR is VMX.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20220607232353.3375324-4-seanjc@google.com
vmmcall()/vmcall() are used to exit from L2 to L1 and no concrete hypercall
ABI is currenty followed. With the introduction of Hyper-V L2 TLB flush
it becomes (theoretically) possible that L0 will take responsibility for
handling the call and no L1 exit will happen. Prevent this by stuffing RAX
(KVM ABI) and RCX (Hyper-V ABI) with 'safe' values.
While on it, convert vmmcall() to 'static inline', make it setup stack
frame and move to include/x86_64/svm_util.h.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20221101145426.251680-45-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This fixes three issues in nested SVM:
1) in the shutdown_interception() vmexit handler we call kvm_vcpu_reset().
However, if running nested and L1 doesn't intercept shutdown, the function
resets vcpu->arch.hflags without properly leaving the nested state.
This leaves the vCPU in inconsistent state and later triggers a kernel
panic in SVM code. The same bug can likely be triggered by sending INIT
via local apic to a vCPU which runs a nested guest.
On VMX we are lucky that the issue can't happen because VMX always
intercepts triple faults, thus triple fault in L2 will always be
redirected to L1. Plus, handle_triple_fault() doesn't reset the vCPU.
INIT IPI can't happen on VMX either because INIT events are masked while
in VMX mode.
Secondarily, KVM doesn't honour SHUTDOWN intercept bit of L1 on SVM.
A normal hypervisor should always intercept SHUTDOWN, a unit test on
the other hand might want to not do so.
Finally, the guest can trigger a kernel non rate limited printk on SVM
from the guest, which is fixed as well.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop kvm_get_supported_cpuid_entry() and its inner helper now that all
known usage can use X86_FEATURE_*, X86_PROPERTY_*, X86_PMU_FEATURE_*, or
the dedicated Family/Model helpers. Providing "raw" access to CPUID
leafs is undesirable as it encourages open coding CPUID checks, which is
often error prone and not self-documenting.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221006005125.680782-13-seanjc@google.com
Add KVM variants of the x86 Family and Model helpers, and use them in the
PMU event filter test. Open code the retrieval of KVM's supported CPUID
entry 0x1.0 in anticipation of dropping kvm_get_supported_cpuid_entry().
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221006005125.680782-12-seanjc@google.com
Add dedicated helpers for getting x86's Family and Model, which are the
last holdouts that "need" raw access to CPUID information. FMS info is
a mess and requires not only splicing together multiple values, but
requires doing so conditional in the Family case.
Provide wrappers to reduce the odds of copy+paste errors, but mostly to
allow for the eventual removal of kvm_get_supported_cpuid_entry().
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221006005125.680782-11-seanjc@google.com
Add an X86_PMU_FEATURE_* framework to simplify probing architectural
events on Intel PMUs, which require checking the length of a bit vector
and the _absence_ of a "feature" bit. Add helpers for both KVM and
"this CPU", and use the newfangled magic (along with X86_PROPERTY_*)
to clean up pmu_event_filter_test.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221006005125.680782-10-seanjc@google.com
Introduce X86_PROPERTY_* to allow retrieving values/properties from CPUID
leafs, e.g. MAXPHYADDR from CPUID.0x80000008. Use the same core code as
X86_FEATURE_*, the primary difference is that properties are multi-bit
values, whereas features enumerate a single bit.
Add this_cpu_has_p() to allow querying whether or not a property exists
based on the maximum leaf associated with the property, e.g. MAXPHYADDR
doesn't exist if the max leaf for 0x8000_xxxx is less than 0x8000_0008.
Use the new property infrastructure in vm_compute_max_gfn() to prove
that the code works as intended. Future patches will convert additional
selftests code.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221006005125.680782-4-seanjc@google.com
