| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Add a section to document all the different ways in which the KVM API sucks.
I am sure there are way more, give people a place to vent so that userspace
authors are aware.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220322110712.222449-4-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add a file to document all the different ways in which the virtual CPU
emulation is imperfect. Include an example to show how to document
such errata.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Oliver Upton <oupton@google.com>
Message-Id: <20220322110712.222449-3-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
documentation
ARM already has an arm/ subdirectory, but s390 and x86 do not even though
they have a relatively large number of files specific to them. Create
new directories in Documentation/virt/kvm for these two architectures
as well.
While at it, group the API documentation and the developer documentation
in the table of contents.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220322110712.222449-2-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
kvm->mn_invalidate_lock and kvm->slots_arch_lock were not included in the
documentation, add them.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220322110720.222499-3-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Separate the various locks clearly, and include the new names of blocked_vcpu_on_cpu_lock
and blocked_vcpu_on_cpu.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220322110720.222499-2-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Clang warns:
arch/x86/kvm/cpuid.c:739:2: error: unannotated fall-through between switch labels [-Werror,-Wimplicit-fallthrough]
default:
^
arch/x86/kvm/cpuid.c:739:2: note: insert 'break;' to avoid fall-through
default:
^
break;
1 error generated.
Clang is a little more pedantic than GCC, which does not warn when
falling through to a case that is just break or return. Clang's version
is more in line with the kernel's own stance in deprecated.rst, which
states that all switch/case blocks must end in either break,
fallthrough, continue, goto, or return. Add the missing break to silence
the warning.
Fixes: f144c49e8c39 ("KVM: x86: synthesize CPUID leaf 0x80000021h if useful")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Message-Id: <20220322152906.112164-1-nathan@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This reverts commit 3d3aab1b973b01bd2a1aa46307e94a1380b1d802.
Now that the KVM module's lifetime is tied to kvm.users_count, there is
no need to also tie it's lifetime to the lifetime of the VM and vCPU
file descriptors.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220303183328.1499189-3-dmatlack@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Tie the lifetime the KVM module to the lifetime of each VM via
kvm.users_count. This way anything that grabs a reference to the VM via
kvm_get_kvm() cannot accidentally outlive the KVM module.
Prior to this commit, the lifetime of the KVM module was tied to the
lifetime of /dev/kvm file descriptors, VM file descriptors, and vCPU
file descriptors by their respective file_operations "owner" field.
This approach is insufficient because references grabbed via
kvm_get_kvm() do not prevent closing any of the aforementioned file
descriptors.
This fixes a long standing theoretical bug in KVM that at least affects
async page faults. kvm_setup_async_pf() grabs a reference via
kvm_get_kvm(), and drops it in an asynchronous work callback. Nothing
prevents the VM file descriptor from being closed and the KVM module
from being unloaded before this callback runs.
Fixes: af585b921e5d ("KVM: Halt vcpu if page it tries to access is swapped out")
Fixes: 3d3aab1b973b ("KVM: set owner of cpu and vm file operations")
Cc: stable@vger.kernel.org
Suggested-by: Ben Gardon <bgardon@google.com>
[ Based on a patch from Ben implemented for Google's kernel. ]
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220303183328.1499189-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Instead of using array_size, use a function that takes care of the
multiplication. While at it, switch to kvcalloc since this allocation
should not be very large.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
KVM_CAP_DISABLE_QUIRKS is irrevocably broken. The capability does not
advertise the set of quirks which may be disabled to userspace, so it is
impossible to predict the behavior of KVM. Worse yet,
KVM_CAP_DISABLE_QUIRKS will tolerate any value for cap->args[0], meaning
it fails to reject attempts to set invalid quirk bits.
The only valid workaround for the quirky quirks API is to add a new CAP.
Actually advertise the set of quirks that can be disabled to userspace
so it can predict KVM's behavior. Reject values for cap->args[0] that
contain invalid bits.
Finally, add documentation for the new capability and describe the
existing quirks.
Signed-off-by: Oliver Upton <oupton@google.com>
Message-Id: <20220301060351.442881-5-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Non constant TSC is a nightmare on bare metal already, but with
virtualization it becomes a complete disaster because the workarounds
are horrible latency wise. That's also a preliminary for running RT in
a guest on top of a RT host.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Message-Id: <Yh5eJSG19S2sjZfy@linutronix.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Guests X86_BUG_NULL_SEG if and only if the host has them. Use the info
from static_cpu_has_bug to form the 0x80000021 CPUID leaf that was
defined for Zen3. Userspace can then set the bit even on older CPUs
that do not have the bug, such as Zen2.
Do the same for X86_FEATURE_LFENCE_RDTSC as well, since various processors
have had very different ways of detecting it and not all of them are
available to userspace.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
CPUID leaf 0x80000021 defines some features (or lack of bugs) of AMD
processors. Expose the ones that make sense via KVM_GET_SUPPORTED_CPUID.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
KVM_X86_OP_OPTIONAL_RET0 can only be used with 32-bit return values on 32-bit
systems, because unsigned long is only 32-bits wide there and 64-bit values
are returned in edx:eax.
Reported-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This reverts commit cf3e26427c08ad9015956293ab389004ac6a338e.
Multi-vCPU Hyper-V guests started crashing randomly on boot with the
latest kvm/queue and the problem can be bisected the problem to this
particular patch. Basically, I'm not able to boot e.g. 16-vCPU guest
successfully anymore. Both Intel and AMD seem to be affected. Reverting
the commit saves the day.
Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Since "KVM: x86/mmu: Zap only TDP MMU leafs in kvm_zap_gfn_range()"
is going to be reverted, it's not going to be true anymore that
the zap-page flow does not free any 'struct kvm_mmu_page'. Introduce
an early flush before tdp_mmu_zap_leafs() returns, to preserve
bisectability.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for 5.18
- Proper emulation of the OSLock feature of the debug architecture
- Scalibility improvements for the MMU lock when dirty logging is on
- New VMID allocator, which will eventually help with SVA in VMs
- Better support for PMUs in heterogenous systems
- PSCI 1.1 support, enabling support for SYSTEM_RESET2
- Implement CONFIG_DEBUG_LIST at EL2
- Make CONFIG_ARM64_ERRATUM_2077057 default y
- Reduce the overhead of VM exit when no interrupt is pending
- Remove traces of 32bit ARM host support from the documentation
- Updated vgic selftests
- Various cleanups, doc updates and spelling fixes
|
|
Various spelling mistakes in comments.
Detected with the help of Coccinelle.
Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220318103729.157574-24-Julia.Lawall@inria.fr
|
|
We currently deal with a set of booleans for VM features,
while they could be better represented as set of flags
contained in an unsigned long, similarily to what we are
doing on the CPU side.
Signed-off-by: Marc Zyngier <maz@kernel.org>
[Oliver: Flag-ify the 'ran_once' boolean]
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220311174001.605719-2-oupton@google.com
|
|
KVM/riscv changes for 5.18
- Prevent KVM_COMPAT from being selected
- Refine __kvm_riscv_switch_to() implementation
- RISC-V SBI v0.3 support
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD
KVM: s390: Fix, test and feature for 5.18 part 2
- memop selftest
- fix SCK locking
- adapter interruptions virtualization for secure guests
|
|
Test that errors occur if key protection disallows access, including
tests for storage and fetch protection override. Perform tests for both
logical vcpu and absolute vm ioctls.
Also extend the existing tests to the vm ioctl.
Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Link: https://lore.kernel.org/r/20220308125841.3271721-6-scgl@linux.ibm.com
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
|
|
Do not just test the actual copy, but also that success is indicated
when using the check only flag.
Add copy test with storage key checking enabled, including tests for
storage and fetch protection override.
These test cover both logical vcpu ioctls as well as absolute vm ioctls.
Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Link: https://lore.kernel.org/r/20220308125841.3271721-5-scgl@linux.ibm.com
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
|
|
The stages synchronize guest and host execution.
This helps the reader and constraits the execution of the test -- if the
observed staging differs from the expected the test fails.
Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Link: https://lore.kernel.org/r/20220308125841.3271721-4-scgl@linux.ibm.com
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
|
|
In order to achieve good test coverage we need to be able to invoke the
MEM_OP ioctl with all possible parametrizations.
However, for a given test, we want to be concise and not specify a long
list of default values for parameters not relevant for the test, so the
readers attention is not needlessly diverted.
Add a macro that enables this and convert the existing test to use it.
The macro emulates named arguments and hides some of the ioctl's
redundancy, e.g. sets the key flag if an access key is specified.
Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Link: https://lore.kernel.org/r/20220308125841.3271721-3-scgl@linux.ibm.com
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
|
|
Split success case/copy test from error test, making them independent.
This means they do not share state and are easier to understand.
Also, new test can be added in the same manner without affecting the old
ones. In order to make that simpler, introduce functionality for the
setup of commonly used variables.
Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Link: https://lore.kernel.org/r/20220308125841.3271721-2-scgl@linux.ibm.com
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
|
|
When handling the SCK instruction, the kvm lock is taken, even though
the vcpu lock is already being held. The normal locking order is kvm
lock first and then vcpu lock. This is can (and in some circumstances
does) lead to deadlocks.
The function kvm_s390_set_tod_clock is called both by the SCK handler
and by some IOCTLs to set the clock. The IOCTLs will not hold the vcpu
lock, so they can safely take the kvm lock. The SCK handler holds the
vcpu lock, but will also somehow need to acquire the kvm lock without
relinquishing the vcpu lock.
The solution is to factor out the code to set the clock, and provide
two wrappers. One is called like the original function and does the
locking, the other is called kvm_s390_try_set_tod_clock and uses
trylock to try to acquire the kvm lock. This new wrapper is then used
in the SCK handler. If locking fails, -EAGAIN is returned, which is
eventually propagated to userspace, thus also freeing the vcpu lock and
allowing for forward progress.
This is not the most efficient or elegant way to solve this issue, but
the SCK instruction is deprecated and its performance is not critical.
The goal of this patch is just to provide a simple but correct way to
fix the bug.
Fixes: 6a3f95a6b04c ("KVM: s390: Intercept SCK instruction")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Link: https://lore.kernel.org/r/20220301143340.111129-1-imbrenda@linux.ibm.com
Cc: stable@vger.kernel.org
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
|
|
The SBI v0.3 specification extends SBI HSM extension by adding SBI HSM
suspend call and related HART states. This patch extends the KVM RISC-V
HSM implementation to provide KVM guest a minimal SBI HSM suspend call
which is equivalent to a WFI instruction.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
The wait for interrupt (WFI) instruction emulation can share the VCPU
halt logic with SBI HSM suspend emulation so this patch adds a common
kvm_riscv_vcpu_wfi() function for this purpose.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
We add defines related to SBI HSM suspend call and also update HSM states
naming as-per the latest SBI specification.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
The SBI v0.3 specification defines SRST (System Reset) extension which
provides a standard poweroff and reboot interface. This patch implements
SRST extension for the KVM Guest.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
We rename kvm_sbi_system_shutdown() to kvm_riscv_vcpu_sbi_system_reset()
and move it to vcpu_sbi.c so that it can be shared by SBI v0.1 shutdown
and SBI v0.3 SRST extension.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
We upgrade SBI spec version implemented by KVM RISC-V to v0.3 so
that Guest kernel can probe and use SBI extensions added by the
SBI v0.3 specification.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Kernel uses __kvm_riscv_switch_to() and __kvm_switch_return() to switch
the context of host kernel and guest kernel. Several CSRs belonging to the
context will be read and written during the context switch. To ensure
atomic read-modify-write control of CSR and ordering of CSR accesses, some
hardware blocks flush the pipeline when writing a CSR. In this
circumstance, grouping CSR executions together as much as possible can
reduce the performance impact of the pipeline. Therefore, this commit
reorders the CSR instructions to enhance the context switch performance..
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Suggested-by: Hsinyi Lee <hsinyi.lee@sifive.com>
Suggested-by: Fu-Ching Yang <fu-ching.yang@sifive.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Current riscv doesn't support the 32bit KVM API. Let's make it
clear by not selecting KVM_COMPAT.
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Anup Patel <anup@brainfault.org>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
Eliminate the following coccicheck warning:
./arch/riscv/kvm/vcpu_sbi_v01.c:117:2-3: Unneeded semicolon
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
|
|
* kvm-arm64/psci-1.1:
: .
: Limited PSCI-1.1 support from Will Deacon:
:
: This small series exposes the PSCI SYSTEM_RESET2 call to guests, which
: allows the propagation of a "reset_type" and a "cookie" back to the VMM.
: Although Linux guests only ever pass 0 for the type ("SYSTEM_WARM_RESET"),
: the vendor-defined range can be used by a bootloader to provide additional
: information about the reset, such as an error code.
: .
KVM: arm64: Really propagate PSCI SYSTEM_RESET2 arguments to userspace
Signed-off-by: Marc Zyngier <maz@kernel.org>
|
|
Commit d43583b890e7 ("KVM: arm64: Expose PSCI SYSTEM_RESET2 call to the
guest") hooked up the SYSTEM_RESET2 PSCI call for guests but failed to
preserve its arguments for userspace, instead overwriting them with
zeroes via smccc_set_retval(). As Linux only passes zeroes for these
arguments, this appeared to be working for Linux guests. Oh well.
Don't call smccc_set_retval() for a SYSTEM_RESET2 heading to userspace
and instead set X0 (and only X0) explicitly to PSCI_RET_INTERNAL_FAILURE
just in case the vCPU re-enters the guest.
Fixes: d43583b890e7 ("KVM: arm64: Expose PSCI SYSTEM_RESET2 call to the guest")
Reported-by: Andrew Walbran <qwandor@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220309181308.982-1-will@kernel.org
|
|
* kvm-arm64/misc-5.18:
: .
: Misc fixes for KVM/arm64 5.18:
:
: - Drop unused kvm parameter to kvm_psci_version()
:
: - Implement CONFIG_DEBUG_LIST at EL2
:
: - Make CONFIG_ARM64_ERRATUM_2077057 default y
:
: - Only do the interrupt dance if we have exited because of an interrupt
:
: - Remove traces of 32bit ARM host support from the documentation
: .
Documentation: KVM: Update documentation to indicate KVM is arm64-only
KVM: arm64: Only open the interrupt window on exit due to an interrupt
KVM: arm64: Enable Cortex-A510 erratum 2077057 by default
Signed-off-by: Marc Zyngier <maz@kernel.org>
|
|
KVM support for 32-bit ARM hosts (KVM/arm) has been removed from the
kernel since commit 541ad0150ca4 ("arm: Remove 32bit KVM host
support"). There still exists some remnants of the old architecture in
the KVM documentation.
Remove all traces of 32-bit host support from the documentation. Note
that AArch32 guests are still supported.
Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220308172856.2997250-1-oupton@google.com
|
|
Expand KVM's mask for the AVIC host physical ID to the full 12 bits defined
by the architecture. The number of bits consumed by hardware is model
specific, e.g. early CPUs ignored bits 11:8, but there is no way for KVM
to enumerate the "true" size. So, KVM must allow using all bits, else it
risks rejecting completely legal x2APIC IDs on newer CPUs.
This means KVM relies on hardware to not assign x2APIC IDs that exceed the
"true" width of the field, but presumably hardware is smart enough to tie
the width to the max x2APIC ID. KVM also relies on hardware to support at
least 8 bits, as the legacy xAPIC ID is writable by software. But, those
assumptions are unavoidable due to the lack of any way to enumerate the
"true" width.
Cc: stable@vger.kernel.org
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Fixes: 44a95dae1d22 ("KVM: x86: Detect and Initialize AVIC support")
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Message-Id: <20220211000851.185799-1-suravee.suthikulpanit@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add a selftest that enables populating a VM with the maximum amount of
guest memory allowed by the underlying architecture. Abuse KVM's
memslots by mapping a single host memory region into multiple memslots so
that the selftest doesn't require a system with terabytes of RAM.
Default to 512gb of guest memory, which isn't all that interesting, but
should work on all MMUs and doesn't take an exorbitant amount of memory
or time. E.g. testing with ~64tb of guest memory takes the better part
of an hour, and requires 200gb of memory for KVM's page tables when using
4kb pages.
To inflicit maximum abuse on KVM' MMU, default to 4kb pages (or whatever
the not-hugepage size is) in the backing store (memfd). Use memfd for
the host backing store to ensure that hugepages are guaranteed when
requested, and to give the user explicit control of the size of hugepage
being tested.
By default, spin up as many vCPUs as there are available to the selftest,
and distribute the work of dirtying each 4kb chunk of memory across all
vCPUs. Dirtying guest memory forces KVM to populate its page tables, and
also forces KVM to write back accessed/dirty information to struct page
when the guest memory is freed.
On x86, perform two passes with a MMU context reset between each pass to
coerce KVM into dropping all references to the MMU root, e.g. to emulate
a vCPU dropping the last reference. Perform both passes and all
rendezvous on all architectures in the hope that arm64 and s390x can gain
similar shenanigans in the future.
Measure and report the duration of each operation, which is helpful not
only to verify the test is working as intended, but also to easily
evaluate the performance differences different page sizes.
Provide command line options to limit the amount of guest memory, set the
size of each slot (i.e. of the host memory region), set the number of
vCPUs, and to enable usage of hugepages.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220226001546.360188-29-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add cpu_relax() for s390 and x86 for use in arch-agnostic tests. arm64
already defines its own version.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220226001546.360188-28-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Extract the code for allocating guest memory via memfd out of
vm_userspace_mem_region_add() and into a new helper, kvm_memfd_alloc().
A future selftest to populate a guest with the maximum amount of guest
memory will abuse KVM's memslots to alias guest memory regions to a
single memfd-backed host region, i.e. needs to back a guest with memfd
memory without a 1:1 association between a memslot and a memfd instance.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220226001546.360188-27-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Move set_memory_region_test's KVM_SET_USER_MEMORY_REGION helper to KVM's
utils so that it can be used by other tests. Provide a raw version as
well as an assert-success version to reduce the amount of boilerplate
code need for basic usage.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220226001546.360188-26-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Disallow calling tdp_mmu_set_spte_atomic() with a REMOVED "old" SPTE.
This solves a conundrum introduced by commit 3255530ab191 ("KVM: x86/mmu:
Automatically update iter->old_spte if cmpxchg fails"); if the helper
doesn't update old_spte in the REMOVED case, then theoretically the
caller could get stuck in an infinite loop as it will fail indefinitely
on the REMOVED SPTE. E.g. until recently, clear_dirty_gfn_range() didn't
check for a present SPTE and would have spun until getting rescheduled.
In practice, only the page fault path should "create" a new SPTE, all
other paths should only operate on existing, a.k.a. shadow present,
SPTEs. Now that the page fault path pre-checks for a REMOVED SPTE in all
cases, require all other paths to indirectly pre-check by verifying the
target SPTE is a shadow-present SPTE.
Note, this does not guarantee the actual SPTE isn't REMOVED, nor is that
scenario disallowed. The invariant is only that the caller mustn't
invoke tdp_mmu_set_spte_atomic() if the SPTE was REMOVED when last
observed by the caller.
Cc: David Matlack <dmatlack@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220226001546.360188-25-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Explicitly check for a REMOVED leaf SPTE prior to attempting to map
the final SPTE when handling a TDP MMU fault. Functionally, this is a
nop as tdp_mmu_set_spte_atomic() will eventually detect the frozen SPTE.
Pre-checking for a REMOVED SPTE is a minor optmization, but the real goal
is to allow tdp_mmu_set_spte_atomic() to have an invariant that the "old"
SPTE is never a REMOVED SPTE.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20220226001546.360188-24-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Zap defunct roots, a.k.a. roots that have been invalidated after their
last reference was initially dropped, asynchronously via the existing work
queue instead of forcing the work upon the unfortunate task that happened
to drop the last reference.
If a vCPU task drops the last reference, the vCPU is effectively blocked
by the host for the entire duration of the zap. If the root being zapped
happens be fully populated with 4kb leaf SPTEs, e.g. due to dirty logging
being active, the zap can take several hundred seconds. Unsurprisingly,
most guests are unhappy if a vCPU disappears for hundreds of seconds.
E.g. running a synthetic selftest that triggers a vCPU root zap with
~64tb of guest memory and 4kb SPTEs blocks the vCPU for 900+ seconds.
Offloading the zap to a worker drops the block time to <100ms.
There is an important nuance to this change. If the same work item
was queued twice before the work function has run, it would only
execute once and one reference would be leaked. Therefore, now that
queueing and flushing items is not anymore protected by kvm->slots_lock,
kvm_tdp_mmu_invalidate_all_roots() has to check root->role.invalid and
skip already invalid roots. On the other hand, kvm_mmu_zap_all_fast()
must return only after those skipped roots have been zapped as well.
These two requirements can be satisfied only if _all_ places that
change invalid to true now schedule the worker before releasing the
mmu_lock. There are just two, kvm_tdp_mmu_put_root() and
kvm_tdp_mmu_invalidate_all_roots().
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20220226001546.360188-23-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When zapping a TDP MMU root, perform the zap in two passes to avoid
zapping an entire top-level SPTE while holding RCU, which can induce RCU
stalls. In the first pass, zap SPTEs at PG_LEVEL_1G, and then
zap top-level entries in the second pass.
With 4-level paging, zapping a PGD that is fully populated with 4kb leaf
SPTEs take up to ~7 or so seconds (time varies based on kernel config,
number of (v)CPUs, etc...). With 5-level paging, that time can balloon
well into hundreds of seconds.
Before remote TLB flushes were omitted, the problem was even worse as
waiting for all active vCPUs to respond to the IPI introduced significant
overhead for VMs with large numbers of vCPUs.
By zapping 1gb SPTEs (both shadow pages and hugepages) in the first pass,
the amount of work that is done without dropping RCU protection is
strictly bounded, with the worst case latency for a single operation
being less than 100ms.
Zapping at 1gb in the first pass is not arbitrary. First and foremost,
KVM relies on being able to zap 1gb shadow pages in a single shot when
when repacing a shadow page with a hugepage. Zapping a 1gb shadow page
that is fully populated with 4kb dirty SPTEs also triggers the worst case
latency due writing back the struct page accessed/dirty bits for each 4kb
page, i.e. the two-pass approach is guaranteed to work so long as KVM can
cleany zap a 1gb shadow page.
rcu: INFO: rcu_sched self-detected stall on CPU
rcu: 52-....: (20999 ticks this GP) idle=7be/1/0x4000000000000000
softirq=15759/15759 fqs=5058
(t=21016 jiffies g=66453 q=238577)
NMI backtrace for cpu 52
Call Trace:
...
mark_page_accessed+0x266/0x2f0
kvm_set_pfn_accessed+0x31/0x40
handle_removed_tdp_mmu_page+0x259/0x2e0
__handle_changed_spte+0x223/0x2c0
handle_removed_tdp_mmu_page+0x1c1/0x2e0
__handle_changed_spte+0x223/0x2c0
handle_removed_tdp_mmu_page+0x1c1/0x2e0
__handle_changed_spte+0x223/0x2c0
zap_gfn_range+0x141/0x3b0
kvm_tdp_mmu_zap_invalidated_roots+0xc8/0x130
kvm_mmu_zap_all_fast+0x121/0x190
kvm_mmu_invalidate_zap_pages_in_memslot+0xe/0x10
kvm_page_track_flush_slot+0x5c/0x80
kvm_arch_flush_shadow_memslot+0xe/0x10
kvm_set_memslot+0x172/0x4e0
__kvm_set_memory_region+0x337/0x590
kvm_vm_ioctl+0x49c/0xf80
Reported-by: David Matlack <dmatlack@google.com>
Cc: Ben Gardon <bgardon@google.com>
Cc: Mingwei Zhang <mizhang@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20220226001546.360188-22-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Allow yielding when zapping SPTEs after the last reference to a valid
root is put. Because KVM must drop all SPTEs in response to relevant
mmu_notifier events, mark defunct roots invalid and reset their refcount
prior to zapping the root. Keeping the refcount elevated while the zap
is in-progress ensures the root is reachable via mmu_notifier until the
zap completes and the last reference to the invalid, defunct root is put.
Allowing kvm_tdp_mmu_put_root() to yield fixes soft lockup issues if the
root in being put has a massive paging structure, e.g. zapping a root
that is backed entirely by 4kb pages for a guest with 32tb of memory can
take hundreds of seconds to complete.
watchdog: BUG: soft lockup - CPU#49 stuck for 485s! [max_guest_memor:52368]
RIP: 0010:kvm_set_pfn_dirty+0x30/0x50 [kvm]
__handle_changed_spte+0x1b2/0x2f0 [kvm]
handle_removed_tdp_mmu_page+0x1a7/0x2b8 [kvm]
__handle_changed_spte+0x1f4/0x2f0 [kvm]
handle_removed_tdp_mmu_page+0x1a7/0x2b8 [kvm]
__handle_changed_spte+0x1f4/0x2f0 [kvm]
tdp_mmu_zap_root+0x307/0x4d0 [kvm]
kvm_tdp_mmu_put_root+0x7c/0xc0 [kvm]
kvm_mmu_free_roots+0x22d/0x350 [kvm]
kvm_mmu_reset_context+0x20/0x60 [kvm]
kvm_arch_vcpu_ioctl_set_sregs+0x5a/0xc0 [kvm]
kvm_vcpu_ioctl+0x5bd/0x710 [kvm]
__se_sys_ioctl+0x77/0xc0
__x64_sys_ioctl+0x1d/0x20
do_syscall_64+0x44/0xa0
entry_SYSCALL_64_after_hwframe+0x44/0xae
KVM currently doesn't put a root from a non-preemptible context, so other
than the mmu_notifier wrinkle, yielding when putting a root is safe.
Yield-unfriendly iteration uses for_each_tdp_mmu_root(), which doesn't
take a reference to each root (it requires mmu_lock be held for the
entire duration of the walk).
tdp_mmu_next_root() is used only by the yield-friendly iterator.
tdp_mmu_zap_root_work() is explicitly yield friendly.
kvm_mmu_free_roots() => mmu_free_root_page() is a much bigger fan-out,
but is still yield-friendly in all call sites, as all callers can be
traced back to some combination of vcpu_run(), kvm_destroy_vm(), and/or
kvm_create_vm().
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220226001546.360188-21-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
