| Age | Commit message (Collapse) | Author |
|---|
|
With multiple reader threads POLLing a single UFFD, the demand paging test
suffers from the thundering herd problem: performance degrades as the
number of reader threads is increased. Solve this issue [1] by switching
the the polling mechanism to EPOLL + EPOLLEXCLUSIVE.
Also, change the error-handling convention of uffd_handler_thread_fn.
Instead of just printing errors and returning early from the polling
loop, check for them via TEST_ASSERT(). "return NULL" is reserved for a
successful exit from uffd_handler_thread_fn, i.e. one triggered by a
write to the exit pipe.
Performance samples generated by the command in [2] are given below.
Num Reader Threads, Paging Rate (POLL), Paging Rate (EPOLL)
1 249k 185k
2 201k 235k
4 186k 155k
16 150k 217k
32 89k 198k
[1] Single-vCPU performance does suffer somewhat.
[2] ./demand_paging_test -u MINOR -s shmem -v 4 -o -r <num readers>
Signed-off-by: Anish Moorthy <amoorthy@google.com>
Acked-by: James Houghton <jthoughton@google.com>
Link: https://lore.kernel.org/r/20240215235405.368539-13-amoorthy@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
paging test
At the moment, demand_paging_test does not support profiling/testing
multiple vCPU threads concurrently faulting on a single uffd because
(a) "-u" (run test in userfaultfd mode) creates a uffd for each vCPU's
region, so that each uffd services a single vCPU thread.
(b) "-u -o" (userfaultfd mode + overlapped vCPU memory accesses)
simply doesn't work: the test tries to register the same memory
to multiple uffds, causing an error.
Add support for many vcpus per uffd by
(1) Keeping "-u" behavior unchanged.
(2) Making "-u -a" create a single uffd for all of guest memory.
(3) Making "-u -o" implicitly pass "-a", solving the problem in (b).
In cases (2) and (3) all vCPU threads fault on a single uffd.
With potentially multiple vCPUs per UFFD, it makes sense to allow
configuring the number of reader threads per UFFD as well: add the "-r"
flag to do so.
Signed-off-by: Anish Moorthy <amoorthy@google.com>
Acked-by: James Houghton <jthoughton@google.com>
Link: https://lore.kernel.org/r/20240215235405.368539-12-amoorthy@google.com
[sean: fix kernel style violations, use calloc() for arrays]
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Using the overall demand paging rate to measure performance can be
slightly misleading when vCPU accesses are not overlapped. Adding more
vCPUs will (usually) increase the overall demand paging rate even
if performance remains constant or even degrades on a per-vcpu basis. As
such, it makes sense to report both the total and per-vcpu paging rates.
Signed-off-by: Anish Moorthy <amoorthy@google.com>
Link: https://lore.kernel.org/r/20240215235405.368539-11-amoorthy@google.com
[sean: fix formatting]
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
commit 849c1816436f ("KVM: selftests: fix supported_flags for aarch64")
fixed the set-memory-region test for aarch64 by declaring the read-only
flag is supported. riscv also supports the read-only flag. Fix it too.
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20240403123300.63923-2-ajones@ventanamicro.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
max_guest_memory_test uses ucalls to sync with the host, but
it also resets the guest RIP back to its initial value in between
tests stages.
This makes the guest never reach the code which frees the ucall struct
and since a fixed pool of 512 ucall structs is used, the test starts
to fail when more that 256 vCPUs are used.
Fix that by replacing the manual register reset with a loop in
the guest code.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20240315143507.102629-1-mlevitsk@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add a guest assert in the PMU counters test to verify that KVM stuffs
the vCPU's post-RESET value to globally enable all general purpose
counters. Per Intel's SDM,
IA32_PERF_GLOBAL_CTRL: Sets bits n-1:0 and clears the upper bits.
and
Where "n" is the number of general-purpose counters available in
the processor.
For the edge case where there are zero GP counters, follow the spirit
of the architecture, not the SDM's literal wording, which doesn't account
for this possibility and would require the CPU to set _all_ bits in
PERF_GLOBAL_CTRL.
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20240309013641.1413400-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Initial support for RISC-V KVM ebreak test. Check the exit reason and
the PC when guest debug is enabled. Also to make sure the guest could
handle the ebreak exception without exiting to the VMM when guest debug
is not enabled.
Signed-off-by: Chao Du <duchao@eswincomputing.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20240402062628.5425-4-duchao@eswincomputing.com
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
HEAD
KVM/riscv fixes for 6.9, take #1
- Fix spelling mistake in arch_timer selftest
- Remove redundant semicolon in num_isa_ext_regs()
- Fix APLIC setipnum_le/be write emulation
- Fix APLIC in_clrip[x] read emulation
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 fixes for 6.9, part #1
- Ensure perf events programmed to count during guest execution
are actually enabled before entering the guest in the nVHE
configuration.
- Restore out-of-range handler for stage-2 translation faults.
- Several fixes to stage-2 TLB invalidations to avoid stale
translations, possibly including partial walk caches.
- Fix early handling of architectural VHE-only systems to ensure E2H is
appropriately set.
- Correct a format specifier warning in the arch_timer selftest.
- Make the KVM banner message correctly handle all of the possible
configurations.
|
|
Use %x instead of %lx when printing uint32_t variables to fix format
warnings in ARM's arch timer test.
aarch64/arch_timer.c: In function ‘guest_run_stage’:
aarch64/arch_timer.c:138:33: warning: format ‘%lx’ expects argument of type ‘long unsigned int’,
but argument 6 has type ‘uint32_t’ {aka ‘unsigned int’} [-Wformat=]
138 | "config_iter + 1 = 0x%lx, irq_iter = 0x%lx.\n"
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
......
141 | config_iter + 1, irq_iter);
| ~~~~~~~~~~~~~~~
| |
| uint32_t {aka unsigned int}
Fixes: d1dafd065a23 ("KVM: arm64: selftests: Enable tuning of error margin in arch_timer test")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20240314175116.2366301-1-seanjc@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
|
|
There are spelling mistakes in __GUEST_ASSERT messages. Fix them.
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Acked-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20240307081951.1954830-1-colin.i.king@gmail.com
|
|
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.
|
|
Pull kvm updates from Paolo Bonzini:
"S390:
- Changes to FPU handling came in via the main s390 pull request
- Only deliver to the guest the SCLP events that userspace has
requested
- More virtual vs physical address fixes (only a cleanup since
virtual and physical address spaces are currently the same)
- Fix selftests undefined behavior
x86:
- Fix a restriction that the guest can't program a PMU event whose
encoding matches an architectural event that isn't included in the
guest CPUID. The enumeration of an architectural event only says
that if a CPU supports an architectural event, then the event can
be programmed *using the architectural encoding*. The enumeration
does NOT say anything about the encoding when the CPU doesn't
report support the event *in general*. It might support it, and it
might support it using the same encoding that made it into the
architectural PMU spec
- Fix a variety of bugs in KVM's emulation of RDPMC (more details on
individual commits) and add a selftest to verify KVM correctly
emulates RDMPC, counter availability, and a variety of other
PMC-related behaviors that depend on guest CPUID and therefore are
easier to validate with selftests than with custom guests (aka
kvm-unit-tests)
- Zero out PMU state on AMD if the virtual PMU is disabled, it does
not cause any bug but it wastes time in various cases where KVM
would check if a PMC event needs to be synthesized
- Optimize triggering of emulated events, with a nice ~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
- Fix a bug where KVM would report stale/bogus exit qualification
information when exiting to userspace with an internal error exit
code
- Add a VMX flag in /proc/cpuinfo to report 5-level EPT support
- Rework TDP MMU root unload, free, and alloc to run with mmu_lock
held for read, e.g. to avoid serializing vCPUs when userspace
deletes a memslot
- Tear down TDP MMU page tables at 4KiB granularity (used to be
1GiB). KVM doesn't support yielding in the middle of processing a
zap, and 1GiB granularity resulted in multi-millisecond lags that
are quite impolite for CONFIG_PREEMPT kernels
- Allocate write-tracking metadata on-demand to avoid the memory
overhead when a kernel is built with i915 virtualization support
but the workloads use neither shadow paging nor i915 virtualization
- Explicitly initialize a variety of on-stack variables in the
emulator that triggered KMSAN false positives
- Fix the debugregs ABI for 32-bit KVM
- Rework the "force immediate exit" code so that vendor code
ultimately decides how and when to force the exit, which allowed
some optimization for both Intel and AMD
- Fix a long-standing bug where kvm_has_noapic_vcpu could be left
elevated if vCPU creation ultimately failed, causing extra
unnecessary work
- Cleanup the logic for checking if the currently loaded vCPU is
in-kernel
- Harden against underflowing the active mmu_notifier invalidation
count, so that "bad" invalidations (usually due to bugs elsehwere
in the kernel) are detected earlier and are less likely to hang the
kernel
x86 Xen emulation:
- Overlay pages can now be cached based on host virtual address,
instead of guest physical addresses. This removes the need to
reconfigure and invalidate the cache if the guest changes the gpa
but the underlying host virtual address remains the same
- When possible, use a single host TSC value when computing the
deadline for Xen timers in order to improve the accuracy of the
timer emulation
- Inject pending upcall events when the vCPU software-enables its
APIC to fix a bug where an upcall can be lost (and to follow Xen's
behavior)
- Fall back to the slow path instead of warning if "fast" IRQ
delivery of Xen events fails, e.g. if the guest has aliased xAPIC
IDs
RISC-V:
- Support exception and interrupt handling in selftests
- New self test for RISC-V architectural timer (Sstc extension)
- New extension support (Ztso, Zacas)
- Support userspace emulation of random number seed CSRs
ARM:
- Infrastructure for building KVM's trap configuration based on the
architectural features (or lack thereof) advertised in the VM's ID
registers
- Support for mapping vfio-pci BARs as Normal-NC (vaguely similar to
x86's WC) at stage-2, improving the performance of interacting with
assigned devices that can tolerate it
- Conversion of KVM's representation of LPIs to an xarray, utilized
to address serialization some of the serialization on the LPI
injection path
- Support for _architectural_ VHE-only systems, advertised through
the absence of FEAT_E2H0 in the CPU's ID register
- Miscellaneous cleanups, fixes, and spelling corrections to KVM and
selftests
LoongArch:
- Set reserved bits as zero in CPUCFG
- Start SW timer only when vcpu is blocking
- Do not restart SW timer when it is expired
- Remove unnecessary CSR register saving during enter guest
- Misc cleanups and fixes as usual
Generic:
- Clean up Kconfig by removing CONFIG_HAVE_KVM, which was basically
always true on all architectures except MIPS (where Kconfig
determines the available depending on CPU capabilities). It is
replaced either by an architecture-dependent symbol for MIPS, and
IS_ENABLED(CONFIG_KVM) everywhere else
- Factor common "select" statements in common code instead of
requiring each architecture to specify it
- Remove thoroughly obsolete APIs from the uapi headers
- Move architecture-dependent stuff to uapi/asm/kvm.h
- Always flush the async page fault workqueue when a work item is
being removed, especially during vCPU destruction, to ensure that
there are no workers running in KVM code when all references to
KVM-the-module are gone, i.e. to prevent a very unlikely
use-after-free if kvm.ko is unloaded
- Grab a reference to the VM's mm_struct in the async #PF worker
itself instead of gifting the worker a reference, so that there's
no need to remember to *conditionally* clean up after the worker
Selftests:
- Reduce boilerplate especially when utilize selftest TAP
infrastructure
- 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"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (246 commits)
selftests: kvm: remove meaningless assignments in Makefiles
KVM: riscv: selftests: Add Zacas extension to get-reg-list test
RISC-V: KVM: Allow Zacas extension for Guest/VM
KVM: riscv: selftests: Add Ztso extension to get-reg-list test
RISC-V: KVM: Allow Ztso extension for Guest/VM
RISC-V: KVM: Forward SEED CSR access to user space
KVM: riscv: selftests: Add sstc timer test
KVM: riscv: selftests: Change vcpu_has_ext to a common function
KVM: riscv: selftests: Add guest helper to get vcpu id
KVM: riscv: selftests: Add exception handling support
LoongArch: KVM: Remove unnecessary CSR register saving during enter guest
LoongArch: KVM: Do not restart SW timer when it is expired
LoongArch: KVM: Start SW timer only when vcpu is blocking
LoongArch: KVM: Set reserved bits as zero in CPUCFG
KVM: selftests: Explicitly close guest_memfd files in some gmem tests
KVM: x86/xen: fix recursive deadlock in timer injection
KVM: pfncache: simplify locking and make more self-contained
KVM: x86/xen: remove WARN_ON_ONCE() with false positives in evtchn delivery
KVM: x86/xen: inject vCPU upcall vector when local APIC is enabled
KVM: x86/xen: improve accuracy of Xen timers
...
|
|
$(shell ...) expands to the output of the command. It expands to the
empty string when the command does not print anything to stdout.
Hence, $(shell mkdir ...) is sufficient and does not need any
variable assignment in front of it.
Commit c2bd08ba20a5 ("treewide: remove meaningless assignments in
Makefiles", 2024-02-23) did this to all of tools/ but ignored in-flight
changes to tools/testing/selftests/kvm/Makefile, so reapply the change.
Cc: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools
Pull perf tools updates from Namhyung Kim:
"perf stat:
- Support new 'cluster' aggregation mode for shared resources
depending on the hardware configuration:
$ sudo perf stat -a --per-cluster -e cycles,instructions sleep 1
Performance counter stats for 'system wide':
S0-D0-CLS0 2 85,051,822 cycles
S0-D0-CLS0 2 73,909,908 instructions # 0.87 insn per cycle
S0-D0-CLS2 2 93,365,918 cycles
S0-D0-CLS2 2 83,006,158 instructions # 0.89 insn per cycle
S0-D0-CLS4 2 104,157,523 cycles
S0-D0-CLS4 2 53,234,396 instructions # 0.51 insn per cycle
S0-D0-CLS6 2 65,891,079 cycles
S0-D0-CLS6 2 41,478,273 instructions # 0.63 insn per cycle
1.002407989 seconds time elapsed
- Various fixes and cleanups for event metrics including NaN handling
perf script:
- Use libcapstone if available to disassemble the instructions. This
enables 'perf script -F disasm' and 'perf script --insn-trace=disasm'
(for Intel-PT):
$ perf script -F event,ip,disasm
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffa9839d25 movq %rax, %r14
cycles:P: ffffffffa9cdcaf0 endbr64
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffaa401f86 iretq
cycles:P: ffffffffa99c4de5 movq 0x30(%rcx), %r8
cycles:P: ffffffffa988d428 wrmsr
cycles:P: ffffffffaa401f86 iretq
cycles:P: ffffffffa9907983 movl 0x68(%rbx), %eax
cycles:P: ffffffffa988d428 wrmsr
- Expose sample ID / stream ID to python scripts
perf test:
- Add more perf test cases from Redhat internal test suites. This
time it adds the base infra and a few perf probe tests. More to
come. :)
- Add 'perf test -p' for parallel execution and fix some issues found
by the parallel test
- Support symbol test to print symbols in given (active) module:
$ perf test -F -v Symbols --dso /lib/modules/$(uname -r)/kernel/fs/ext4/ext4.ko
--- start ---
Testing /lib/modules/6.5.13-1rodete2-amd64/kernel/fs/ext4/ext4.ko
Overlapping symbols:
7a990-7a9a0 l __pfx_ext4_exit_fs
7a990-7a9a0 g __pfx_cleanup_module
Overlapping symbols:
7a9a0-7aa1c l ext4_exit_fs
7a9a0-7aa1c g cleanup_module
...
JSON metric updates:
- A new round of Intel metric updates
- Support Power11 PVR (compatible to Power10)
- Fix cache latency events on Zen 4 to set SliceId properly
Internal:
- Fix reference counting for 'map' data structure, tireless work from
Ian!
- More memory optimization for struct thread and annotate histogram.
Now, 'perf report' (TUI) and 'perf annotate' should be much
lighter-weight in terms of memory footprint
- Support cross-arch perf register access. Clean up the build
configuration so that it can detect arch-register support at
runtime. This can allow to parse register data in sample which was
recorded in a different arch
Others:
- Sync task state in 'perf sched' to kernel using trace event fields.
The task states have been changed so tools cannot assume a fixed
encoding
- Clean up 'perf mem' to generalize the arch-specific events
- Add support for local and global variables to data type profiling.
This would increase the success rate of type resolution with DWARF
- Add short option -H for --hierarchy in 'perf report' and 'perf top'"
* tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (154 commits)
perf annotate: Add comments in the data structures
perf annotate: Remove sym_hist.addr[] array
perf annotate: Calculate instruction overhead using hashmap
perf annotate: Add a hashmap for symbol histogram
perf threads: Reduce table size from 256 to 8
perf threads: Switch from rbtree to hashmap
perf threads: Move threads to its own files
perf machine: Move machine's threads into its own abstraction
perf machine: Move fprintf to for_each loop and a callback
perf trace: Ignore thread hashing in summary
perf report: Sort child tasks by tid
perf vendor events amd: Fix Zen 4 cache latency events
perf version: Display availability of OpenCSD support
perf vendor events intel: Add umasks/occ_sel to PCU events.
perf map: Fix map reference count issues
libperf evlist: Avoid out-of-bounds access
perf lock contention: Account contending locks too
perf metrics: Fix segv for metrics with no events
perf metrics: Fix metric matching
perf pmu: Fix a potential memory leak in perf_pmu__lookup()
...
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD
- Memop selftest rotate fix
- SCLP event bits over indication fix
- Missing virt_to_phys for the CRYCB fix
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux
Pull s390 updates from Heiko Carstens:
- Various virtual vs physical address usage fixes
- Fix error handling in Processor Activity Instrumentation device
driver, and export number of counters with a sysfs file
- Allow for multiple events when Processor Activity Instrumentation
counters are monitored in system wide sampling
- Change multiplier and shift values of the Time-of-Day clock source to
improve steering precision
- Remove a couple of unneeded GFP_DMA flags from allocations
- Disable mmap alignment if randomize_va_space is also disabled, to
avoid a too small heap
- Various changes to allow s390 to be compiled with LLVM=1, since
ld.lld and llvm-objcopy will have proper s390 support witch clang 19
- Add __uninitialized macro to Compiler Attributes. This is helpful
with s390's FPU code where some users have up to 520 byte stack
frames. Clearing such stack frames (if INIT_STACK_ALL_PATTERN or
INIT_STACK_ALL_ZERO is enabled) before they are used contradicts the
intention (performance improvement) of such code sections.
- Convert switch_to() to an out-of-line function, and use the generic
switch_to header file
- Replace the usage of s390's debug feature with pr_debug() calls
within the zcrypt device driver
- Improve hotplug support of the Adjunct Processor device driver
- Improve retry handling in the zcrypt device driver
- Various changes to the in-kernel FPU code:
- Make in-kernel FPU sections preemptible
- Convert various larger inline assemblies and assembler files to
C, mainly by using singe instruction inline assemblies. This
increases readability, but also allows makes it easier to add
proper instrumentation hooks
- Cleanup of the header files
- Provide fast variants of csum_partial() and
csum_partial_copy_nocheck() based on vector instructions
- Introduce and use a lock to synchronize accesses to zpci device data
structures to avoid inconsistent states caused by concurrent accesses
- Compile the kernel without -fPIE. This addresses the following
problems if the kernel is compiled with -fPIE:
- It uses dynamic symbols (.dynsym), for which the linker refuses
to allow more than 64k sections. This can break features which
use '-ffunction-sections' and '-fdata-sections', including
kpatch-build and function granular KASLR
- It unnecessarily uses GOT relocations, adding an extra layer of
indirection for many memory accesses
- Fix shared_cpu_list for CPU private L2 caches, which incorrectly were
reported as globally shared
* tag 's390-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (117 commits)
s390/tools: handle rela R_390_GOTPCDBL/R_390_GOTOFF64
s390/cache: prevent rebuild of shared_cpu_list
s390/crypto: remove retry loop with sleep from PAES pkey invocation
s390/pkey: improve pkey retry behavior
s390/zcrypt: improve zcrypt retry behavior
s390/zcrypt: introduce retries on in-kernel send CPRB functions
s390/ap: introduce mutex to lock the AP bus scan
s390/ap: rework ap_scan_bus() to return true on config change
s390/ap: clarify AP scan bus related functions and variables
s390/ap: rearm APQNs bindings complete completion
s390/configs: increase number of LOCKDEP_BITS
s390/vfio-ap: handle hardware checkstop state on queue reset operation
s390/pai: change sampling event assignment for PMU device driver
s390/boot: fix minor comment style damages
s390/boot: do not check for zero-termination relocation entry
s390/boot: make type of __vmlinux_relocs_64_start|end consistent
s390/boot: sanitize kaslr_adjust_relocs() function prototype
s390/boot: simplify GOT handling
s390: vmlinux.lds.S: fix .got.plt assertion
s390/boot: workaround current 'llvm-objdump -t -j ...' behavior
...
|
|
KVM Xen and pfncache changes for 6.9:
- Rip out the half-baked support for using gfn_to_pfn caches to manage pages
that are "mapped" into guests via physical addresses.
- Add support for using gfn_to_pfn caches with only a host virtual address,
i.e. to bypass the "gfn" stage of the cache. The primary use case is
overlay pages, where the guest may change the gfn used to reference the
overlay page, but the backing hva+pfn remains the same.
- Add an ioctl() to allow mapping Xen's shared_info page using an hva instead
of a gpa, so that userspace doesn't need to reconfigure and invalidate the
cache/mapping if the guest changes the gpa (but userspace keeps the resolved
hva the same).
- When possible, use a single host TSC value when computing the deadline for
Xen timers in order to improve the accuracy of the timer emulation.
- Inject pending upcall events when the vCPU software-enables its APIC to fix
a bug where an upcall can be lost (and to follow Xen's behavior).
- Fall back to the slow path instead of warning if "fast" IRQ delivery of Xen
events fails, e.g. if the guest has aliased xAPIC IDs.
- Extend gfn_to_pfn_cache's mutex to cover (de)activation (in addition to
refresh), and drop a now-redundant acquisition of xen_lock (that was
protecting the shared_info cache) to fix a deadlock due to recursively
acquiring xen_lock.
|
|
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/riscv changes for 6.9
- Exception and interrupt handling for selftests
- Sstc (aka arch_timer) selftest
- Forward seed CSR access to KVM userspace
- Ztso extension support for Guest/VM
- Zacas extension support for Guest/VM
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for 6.9
- Infrastructure for building KVM's trap configuration based on the
architectural features (or lack thereof) advertised in the VM's ID
registers
- Support for mapping vfio-pci BARs as Normal-NC (vaguely similar to
x86's WC) at stage-2, improving the performance of interacting with
assigned devices that can tolerate it
- Conversion of KVM's representation of LPIs to an xarray, utilized to
address serialization some of the serialization on the LPI injection
path
- Support for _architectural_ VHE-only systems, advertised through the
absence of FEAT_E2H0 in the CPU's ID register
- Miscellaneous cleanups, fixes, and spelling corrections to KVM and
selftests
|
|
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>
|
|
The KVM RISC-V allows Zacas extension for Guest/VM so add this
extension to get-reg-list test.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
The KVM RISC-V allows Ztso extension for Guest/VM so add this
extension to get-reg-list test.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Add a KVM selftests to validate the Sstc timer functionality.
The test was ported from arm64 arch timer test.
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Move vcpu_has_ext to the processor.c and rename it to __vcpu_has_ext
so that other test cases can use it for vCPU extension check.
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Add guest_get_vcpuid() helper to simplify accessing to per-cpu
private data. The sscratch CSR was used to store the vcpu id.
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Add the infrastructure for guest exception handling in riscv selftests.
Customized handlers can be enabled by vm_install_exception_handler(vector)
or vm_install_interrupt_handler().
The code is inspired from that of x86/arm64.
Signed-off-by: Haibo Xu <haibo1.xu@intel.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Explicitly close() guest_memfd files in various guest_memfd and
private_mem_conversions tests, there's no reason to keep the files open
until the test exits.
Fixes: 8a89efd43423 ("KVM: selftests: Add basic selftest for guest_memfd()")
Fixes: 43f623f350ce ("KVM: selftests: Add x86-only selftest for private memory conversions")
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Link: https://lore.kernel.org/r/20240227015716.27284-1-dongli.zhang@oracle.com
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
vpmu_counter_access's disable_counter() carries a bug that disables
all the counters that are enabled, instead of just the requested one.
Fortunately, it's not an issue as there are no callers of it. Hence,
instead of fixing it, remove the definition entirely.
Remove enable_counter() as it's unused as well.
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20231122221526.2750966-1-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
|
|
Extend sev_smoke_test to also run a minimal SEV-ES smoke test so that it's
possible to test KVM's unique VMRUN=>#VMEXIT path for SEV-ES guests
without needing a full blown SEV-ES capable VM, which requires a rather
absurd amount of properly configured collateral.
Punt on proper GHCB and ucall support, and instead use the GHCB MSR
protocol to signal test completion. The most important thing at this
point is to have _any_ kind of testing of KVM's __svm_sev_es_vcpu_run().
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Cc: Peter Gonda <pgonda@google.com>
Cc: Carlos Bilbao <carlos.bilbao@amd.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Link: https://lore.kernel.org/r/20240223004258.3104051-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add a basic smoke test for SEV guests to verify that KVM can launch an
SEV guest and run a few instructions without exploding. To verify that
SEV is indeed enabled, assert that SEV is reported as enabled in
MSR_AMD64_SEV, a.k.a. SEV_STATUS, which cannot be intercepted by KVM
(architecturally enforced).
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerly Tng <ackerleytng@google.com>
cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Suggested-by: Michael Roth <michael.roth@amd.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Signed-off-by: Peter Gonda <pgonda@google.com>
[sean: rename to "sev_smoke_test"]
Link: https://lore.kernel.org/r/20240223004258.3104051-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Port the existing intra-host SEV(-ES) migration test to the recently added
SEV library, which handles much of the boilerplate needed to create and
configure SEV guests.
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Link: https://lore.kernel.org/r/20240223004258.3104051-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add a library/APIs for creating and interfacing with SEV guests, all of
which need some amount of common functionality, e.g. an open file handle
for the SEV driver (/dev/sev), ioctl() wrappers to pass said file handle
to KVM, tracking of the C-bit, etc.
Add an x86-specific hook to initialize address properties, a.k.a. the
location of the C-bit. An arch specific hook is rather gross, but x86
already has a dedicated #ifdef-protected kvm_get_cpu_address_width() hook,
i.e. the ugliest code already exists.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerly Tng <ackerleytng@google.com>
cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Originally-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Peter Gonda <pgonda@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20240223004258.3104051-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add support for tagging and untagging guest physical address, e.g. to
allow x86's SEV and TDX guests to embed shared vs. private information in
the GPA. SEV (encryption, a.k.a. C-bit) and TDX (shared, a.k.a. S-bit)
steal bits from the guest's physical address space that is consumed by the
CPU metadata, i.e. effectively aliases the "real" GPA.
Implement generic "tagging" so that the shared vs. private metadata can be
managed by x86 without bleeding too many details into common code.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerly Tng <ackerleytng@google.com>
cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Originally-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Peter Gonda <pgonda@google.com>
Link: https://lore.kernel.org/r/20240223004258.3104051-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Allocate the common ucall pool using vm_vaddr_alloc_shared() so that the
ucall structures will be placed in shared (unencrypted) memory for VMs
with support for protected (encrypted) memory, e.g. x86's SEV.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerly Tng <ackerleytng@google.com>
cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Signed-off-by: Peter Gonda <pgonda@google.com>
[sean: massage changelog]
Link: https://lore.kernel.org/r/20240223004258.3104051-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Test programs may wish to allocate shared vaddrs for things like
sharing memory with the guest. Since protected vms will have their
memory encrypted by default an interface is needed to explicitly
request shared pages.
Implement this by splitting the common code out from vm_vaddr_alloc()
and introducing a new vm_vaddr_alloc_shared().
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerly Tng <ackerleytng@google.com>
cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Reviewed-by: Itaru Kitayama <itaru.kitayama@fujitsu.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Peter Gonda <pgonda@google.com>
Link: https://lore.kernel.org/r/20240223004258.3104051-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add support for differentiating between protected (a.k.a. private, a.k.a.
encrypted) memory and normal (a.k.a. shared) memory for VMs that support
protected guest memory, e.g. x86's SEV. Provide and manage a common
bitmap for tracking whether a given physical page resides in protected
memory, as support for protected memory isn't x86 specific, i.e. adding a
arch hook would be a net negative now, and in the future.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerley Tng <ackerleytng@google.com>
cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Reviewed-by: Itaru Kitayama <itaru.kitayama@fujitsu.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Originally-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Peter Gonda <pgonda@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20240223004258.3104051-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Add sparsebit_for_each_set_range() to allow iterator over a range of set
bits in a range. This will be used by x86 SEV guests to process protected
physical pages (each such page needs to be encrypted _after_ being "added"
to the VM).
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
[sean: split to separate patch]
Link: https://lore.kernel.org/r/20240223004258.3104051-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Make all sparsebit struct pointers "const" where appropriate. This will
allow adding a bitmap to track protected/encrypted physical memory that
tests can access in a read-only fashion.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerley Tng <ackerleytng@google.com>
Cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Peter Gonda <pgonda@google.com>
[sean: massage changelog]
Link: https://lore.kernel.org/r/20240223004258.3104051-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Carve out space in the @shape passed to the various VM creation helpers to
allow using the shape to control the subtype of VM, e.g. to identify x86's
SEV VMs (which are "regular" VMs as far as KVM is concerned).
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerley Tng <ackerleytng@google.com>
Cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Michael Roth <michael.roth@amd.com>
Tested-by: Carlos Bilbao <carlos.bilbao@amd.com>
Link: https://lore.kernel.org/r/20240223004258.3104051-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Use the kselftest_harness.h interface in this test to get TAP
output, so that it is easier for the user to see what the test
is doing.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-9-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Use the kvm_test_harness.h interface in this test to get TAP
output, so that it is easier for the user to see what the test
is doing.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-8-thuth@redhat.com
[sean: make host_cap static]
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Use the kvm_test_harness.h interface in this test to get TAP
output, so that it is easier for the user to see what the test
is doing.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-7-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
The sync_regs test currently does not have any output (unless one
of the TEST_ASSERT statement fails), so it's hard to say for a user
whether a certain new sub-test has been included in the binary or
not. Let's make this a little bit more user-friendly and include
some TAP output via the kselftest_harness.h / kvm_test_harness.h
interface.
To be able to use the interface, we have to break up the huge main()
function here in more fine grained parts - then we can use the new
KVM_ONE_VCPU_TEST() macro to define the individual tests. Since these
are run with a separate VM now, we have also to make sure to create
the expected state at the beginning of each test, so some parts grow
a little bit - which should be OK considering that the individual
tests are more self-contained now.
Suggested-by: David Matlack <dmatlack@google.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-6-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Most tests are currently not giving any proper output for the user
to see how much sub-tests have already been run, or whether new
sub-tests are part of a binary or not. So it would be good to
support TAP output in the KVM selftests. There is already a nice
framework for this in the kselftest_harness.h header which we can
use. But since we also need a vcpu in most KVM selftests, it also
makes sense to introduce our own wrapper around this which takes
care of creating a VM with one vcpu, so we don't have to repeat
this boilerplate in each and every test. Thus let's introduce
a KVM_ONE_VCPU_TEST() macro here which takes care of this.
Suggested-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/all/Y2v+B3xxYKJSM%2FfH@google.com/
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-5-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
Extract the code to set a vCPU's entry point out of vm_arch_vcpu_add() and
into a new API, vcpu_arch_set_entry_point(). Providing a separate API
will allow creating a KVM selftests hardness that can handle tests that
use different entry points for sub-tests, whereas *requiring* the entry
point to be specified at vCPU creation makes it difficult to create a
generic harness, e.g. the boilerplate setup/teardown can't easily create
and destroy the VM and vCPUs.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-4-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
The regs structure just accidentally contains the right values
from the previous test in the spot where we want to change rbx.
It's cleaner if we properly initialize the structure here before
using it.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-3-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
|
In the spots where we are expecting a successful run, we should
use vcpu_run() instead of _vcpu_run() to make sure that the run
did not fail.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Link: https://lore.kernel.org/r/20240208204844.119326-2-thuth@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
