* Logic bugs in CR0 writes and Hyper-V hypercalls
* Don't use Enlightened MSR Bitmap for L3
* Remove user-triggerable WARN
Plus a few selftest fixes and a regression test for the
user-triggerable WARN.
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmGzZuIUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroMD4Qf+Im7Q0XNRZGzK6x4Blu3ZZJSuIIkW
gEK5mDX/BWSYxoGhRN0IOkyf1Tx/A5qYwbZts87wZSvKONG2MuVzdeQ0mkDxgKc3
cYwvvIPxCKaW/dQLD2OKVlqdAv6YbeJiFURWXgszMkrcgHvw39H5Tn6ldi0B5nvg
Gvpj8LtbPDXGXab//Xrhia3+1F9TKOrcOG+obGC5G2mrGKTkG2+pi9L6LohvENhd
sOSWdpmvQTU4PeqGlhW8RCwcN+vpa+NasHT2i2tHcWZA9Lqp4P81+4ZyQLIBsRB3
psANG0c40EW+lfjFGbLL/6VR5kypxa6zy9RgX+QiRcj6C0+dJOgnwNY35A==
=cREz
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm fixes from Paolo Bonzini:
"More x86 fixes:
- Logic bugs in CR0 writes and Hyper-V hypercalls
- Don't use Enlightened MSR Bitmap for L3
- Remove user-triggerable WARN
Plus a few selftest fixes and a regression test for the
user-triggerable WARN"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
selftests: KVM: Add test to verify KVM doesn't explode on "bad" I/O
KVM: x86: Don't WARN if userspace mucks with RCX during string I/O exit
KVM: X86: Raise #GP when clearing CR0_PG in 64 bit mode
selftests: KVM: avoid failures due to reserved HyperTransport region
KVM: x86: Ignore sparse banks size for an "all CPUs", non-sparse IPI req
KVM: x86: Wait for IPIs to be delivered when handling Hyper-V TLB flush hypercall
KVM: x86: selftests: svm_int_ctl_test: fix intercept calculation
KVM: nVMX: Don't use Enlightened MSR Bitmap for L3
The function prototype of copy_fpstate_to_sigframe() is declared twice in
0ae67cc34f ("x86/fpu: Remove internal.h dependency from fpu/signal.h").
Remove one of them.
[ bp: Massage ]
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211209015550.51916-1-zhangshaokun@hisilicon.com
When building with automatic stack variable initialization, GCC 12
complains about variables defined outside of switch case statements.
Move the variable into the case that uses it, which silences the warning:
./arch/x86/include/asm/uaccess.h:317:23: warning: statement will never be executed [-Wswitch-unreachable]
317 | unsigned char x_u8__; \
| ^~~~~~
Fixes: 865c50e1d2 ("x86/uaccess: utilize CONFIG_CC_HAS_ASM_GOTO_OUTPUT")
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20211209043456.1377875-1-keescook@chromium.org
Replace a WARN with a comment to call out that userspace can modify RCX
during an exit to userspace to handle string I/O. KVM doesn't actually
support changing the rep count during an exit, i.e. the scenario can be
ignored, but the WARN needs to go as it's trivial to trigger from
userspace.
Cc: stable@vger.kernel.org
Fixes: 3b27de2718 ("KVM: x86: split the two parts of emulator_pio_in")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211025201311.1881846-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In the SDM:
If the logical processor is in 64-bit mode or if CR4.PCIDE = 1, an
attempt to clear CR0.PG causes a general-protection exception (#GP).
Software should transition to compatibility mode and clear CR4.PCIDE
before attempting to disable paging.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Message-Id: <20211207095230.53437-1-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Make arch_stack_walk() available for ARCH_STACKWALK architectures
without it being entangled in STACKTRACE.
Link: https://lore.kernel.org/lkml/20211022152104.356586621@infradead.org/
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[Mark: rebase, drop unnecessary arm change]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20211129142849.3056714-2-mark.rutland@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Do not bail early if there are no bits set in the sparse banks for a
non-sparse, a.k.a. "all CPUs", IPI request. Per the Hyper-V spec, it is
legal to have a variable length of '0', e.g. VP_SET's BankContents in
this case, if the request can be serviced without the extra info.
It is possible that for a given invocation of a hypercall that does
accept variable sized input headers that all the header input fits
entirely within the fixed size header. In such cases the variable sized
input header is zero-sized and the corresponding bits in the hypercall
input should be set to zero.
Bailing early results in KVM failing to send IPIs to all CPUs as expected
by the guest.
Fixes: 214ff83d44 ("KVM: x86: hyperv: implement PV IPI send hypercalls")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211207220926.718794-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Prior to commit 0baedd7927 ("KVM: x86: make Hyper-V PV TLB flush use
tlb_flush_guest()"), kvm_hv_flush_tlb() was using 'KVM_REQ_TLB_FLUSH |
KVM_REQUEST_NO_WAKEUP' when making a request to flush TLBs on other vCPUs
and KVM_REQ_TLB_FLUSH is/was defined as:
(0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
so KVM_REQUEST_WAIT was lost. Hyper-V TLFS, however, requires that
"This call guarantees that by the time control returns back to the
caller, the observable effects of all flushes on the specified virtual
processors have occurred." and without KVM_REQUEST_WAIT there's a small
chance that the vCPU making the TLB flush will resume running before
all IPIs get delivered to other vCPUs and a stale mapping can get read
there.
Fix the issue by adding KVM_REQUEST_WAIT flag to KVM_REQ_TLB_FLUSH_GUEST:
kvm_hv_flush_tlb() is the sole caller which uses it for
kvm_make_all_cpus_request()/kvm_make_vcpus_request_mask() where
KVM_REQUEST_WAIT makes a difference.
Cc: stable@kernel.org
Fixes: 0baedd7927 ("KVM: x86: make Hyper-V PV TLB flush use tlb_flush_guest()")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211209102937.584397-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If CONFIG_PARAVIRT_SPINLOCKS=y, queued_spin_unlock() is implemented
using pv_queued_spin_unlock() which is entirely inline asm based. As
such, we do not receive any KCSAN barrier instrumentation via regular
atomic operations.
Add the missing KCSAN barrier instrumentation for the
CONFIG_PARAVIRT_SPINLOCKS case.
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Prefix all barriers with __, now that asm-generic/barriers.h supports
defining the final instrumented version of these barriers. The change is
limited to barriers used by x86-64.
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This header file provides forward declartion for pgd_lock but does not
include the header defining its type. This works since the definition of
spinlock_t is usually included somehow via printk.
By trying to avoid recursive includes on PREEMPT_RT I avoided the loop
in printk and as a consequnce kernel/intel.c failed to compile due to
missing type definition.
Include the needed definition for spinlock_t.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20211102165224.wpz4zyhsvwccx5p3@linutronix.de
The variable chunks is being shifted right and re-assinged the shifted
value which is then returned. Since chunks is not being read afterwards
the assignment is redundant and the >>= operator can be replaced with a
shift >> operator instead.
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Link: https://lkml.kernel.org/r/20211207223735.35173-1-colin.i.king@gmail.com
Splitting kvm_main.c out into smaller and better-organized files is
slightly non-trivial when it involves editing a bunch of per-arch
KVM makefiles. Provide virt/kvm/Makefile.kvm for them to include.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Acked-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20211121125451.9489-3-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
I'd like to make the build include dirty_ring.c based on whether the
arch wants it or not. That's a whole lot simpler if there's a config
symbol instead of doing it implicitly on KVM_DIRTY_LOG_PAGE_OFFSET
being set to something non-zero.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211121125451.9489-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
== Problem ==
The amount of SGX memory on a system is determined by the BIOS and it
varies wildly between systems. It can be as small as dozens of MB's
and as large as many GB's on servers. Just like how applications need
to know how much regular RAM is available, enclave builders need to
know how much SGX memory an enclave can consume.
== Solution ==
Introduce a new sysfs file:
/sys/devices/system/node/nodeX/x86/sgx_total_bytes
to enumerate the amount of SGX memory available in each NUMA node.
This serves the same function for SGX as /proc/meminfo or
/sys/devices/system/node/nodeX/meminfo does for normal RAM.
'sgx_total_bytes' is needed today to help drive the SGX selftests.
SGX-specific swap code is exercised by creating overcommitted enclaves
which are larger than the physical SGX memory on the system. They
currently use a CPUID-based approach which can diverge from the actual
amount of SGX memory available. 'sgx_total_bytes' ensures that the
selftests can work efficiently and do not attempt stupid things like
creating a 100,000 MB enclave on a system with 128 MB of SGX memory.
== Implementation Details ==
Introduce CONFIG_HAVE_ARCH_NODE_DEV_GROUP opt-in flag to expose an
arch specific attribute group, and add an attribute for the amount of
SGX memory in bytes to each NUMA node:
== ABI Design Discussion ==
As opposed to the per-node ABI, a single, global ABI was considered.
However, this would prevent enclaves from being able to size
themselves so that they fit on a single NUMA node. Essentially, a
single value would rule out NUMA optimizations for enclaves.
Create a new "x86/" directory inside each "nodeX/" sysfs directory.
'sgx_total_bytes' is expected to be the first of at least a few
sgx-specific files to be placed in the new directory. Just scanning
/proc/meminfo, these are the no-brainers that we have for RAM, but we
need for SGX:
MemTotal: xxxx kB // sgx_total_bytes (implemented here)
MemFree: yyyy kB // sgx_free_bytes
SwapTotal: zzzz kB // sgx_swapped_bytes
So, at *least* three. I think we will eventually end up needing
something more along the lines of a dozen. A new directory (as
opposed to being in the nodeX/ "root") directory avoids cluttering the
root with several "sgx_*" files.
Place the new file in a new "nodeX/x86/" directory because SGX is
highly x86-specific. It is very unlikely that any other architecture
(or even non-Intel x86 vendor) will ever implement SGX. Using "sgx/"
as opposed to "x86/" was also considered. But, there is a real chance
this can get used for other arch-specific purposes.
[ dhansen: rewrite changelog ]
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20211116162116.93081-2-jarkko@kernel.org
Move the WARN sanity checks out of the PI descriptor update loop so as
not to spam the kernel log if the condition is violated and the update
takes multiple attempts due to another writer. This also eliminates a
few extra uops from the retry path.
Technically not checking every attempt could mean KVM will now fail to
WARN in a scenario that would have failed before, but any such failure
would be inherently racy as some other agent (CPU or device) would have
to concurrent modify the PI descriptor.
Add a helper to handle the actual write and more importantly to document
why the write may need to be retried.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211208015236.1616697-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a memory barrier between writing vcpu->requests and reading
vcpu->guest_mode to ensure the read is ordered after the write when
(potentially) delivering an IRQ to L2 via nested posted interrupt. If
the request were to be completed after reading vcpu->mode, it would be
possible for the target vCPU to enter the guest without posting the
interrupt and without handling the event request.
Note, the barrier is only for documentation since atomic operations are
serializing on x86.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Fixes: 6b6977117f ("KVM: nVMX: Fix races when sending nested PI while dest enters/leaves L2")
Fixes: 705699a139 ("KVM: nVMX: Enable nested posted interrupt processing")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211208015236.1616697-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This allows to see how many interrupts were delivered via the
APICv/AVIC from the host.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211209115440.394441-3-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Make arch_restore_msi_irqs() return a boolean which indicates whether the
core code should restore the MSI message or not. Get rid of the indirection
in x86.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com> # PCI
Link: https://lore.kernel.org/r/20211206210224.485668098@linutronix.de
No point in looking up things over and over. Just look up the associated
irq data and work from there.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Link: https://lore.kernel.org/r/20211206210224.429625690@linutronix.de
The unnamed struct sucks and is in the way of further cleanups. Stick the
PCI related MSI data into a real data structure and cleanup all users.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20211206210224.374863119@linutronix.de
Currently, text_poke_bp() is very strict to only allow patching a
single instruction; however with straight-line-speculation it will be
required to patch: ret; int3, which is two instructions.
As such, relax the constraints a little to allow int3 padding for all
instructions that do not imply the execution of the next instruction,
ie: RET, JMP.d8 and JMP.d32.
While there, rename the text_poke_loc::rel32 field to ::disp.
Note: this fills up the text_poke_loc structure which is now a round
16 bytes big.
[ bp: Put comments ontop instead of on the side. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211204134908.082342723@infradead.org
For x86 hybrid CPUs like Alder Lake, the order of CPU selection should
be based strictly on CPU priority. Don't include cluster topology for
hybrid CPUs to avoid interference with such CPU selection order.
On Alder Lake, the Atom CPU cluster has more capacity (4 Atom CPUs) vs
Big core cluster (2 hyperthread CPUs). This could potentially bias CPU
selection towards Atom over Big Core, when Big core CPU has higher
priority.
Fixes: 66558b730f ("sched: Add cluster scheduler level for x86")
Suggested-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Tested-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Link: https://lkml.kernel.org/r/20211204091402.GM16608@worktop.programming.kicks-ass.net
Raptor Lake S(RPL-S) is a version 12
Display, Media and Render. For all i915
purposes it is the same as Alder Lake S (ADL-S).
Introduce RPL-S as a subplatform
of ADL-S. This patch adds PCI ids for RPL-S.
BSpec: 53655
Cc: x86@kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com> # arch/x86
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211203063545.2254380-2-anusha.srivatsa@intel.com
Replace all ret/retq instructions with ASM_RET in preparation of
making it more than a single instruction.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211204134907.964635458@infradead.org
SEV and TDX both protect guest memory from host accesses. They both use
guest physical address bits to communicate to the hardware which pages
receive protection or not. SEV and TDX both assume that all I/O (real
devices and virtio) must be performed to pages *without* protection.
To add this support, AMD SEV code forces force_dma_unencrypted() to
decrypt DMA pages when DMA pages were allocated for I/O. It also uses
swiotlb_update_mem_attributes() to update decryption bits in SWIOTLB DMA
buffers.
Since TDX also uses a similar memory sharing design, all the above
mentioned changes can be reused. So move force_dma_unencrypted(),
SWIOTLB update code and virtio changes out of mem_encrypt_amd.c to
mem_encrypt.c.
Introduce a new config option X86_MEM_ENCRYPT that can be selected by
platforms which use x86 memory encryption features (needed in both AMD
SEV and Intel TDX guest platforms).
Since the code is moved from mem_encrypt_amd.c, inherit the same make
flags.
This is preparation for enabling TDX memory encryption support and it
has no functional changes.
Co-developed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20211206135505.75045-4-kirill.shutemov@linux.intel.com
Both Intel TDX and AMD SEV implement memory encryption features. But the
bulk of the code in mem_encrypt.c is AMD-specific. Rename the file to
mem_encrypt_amd.c. A subsequent patch will extract the parts that can be
shared by both TDX and AMD SEV/SME into a generic file.
No functional changes.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20211206135505.75045-3-kirill.shutemov@linux.intel.com
INS/OUTS are not supported in TDX guests and cause #UD. Kernel has to
avoid them when running in TDX guest. To support existing usage, string
I/O operations are unrolled using IN/OUT instructions.
AMD SEV platform implements this support by adding unroll
logic in ins#bwl()/outs#bwl() macros with SEV-specific checks.
Since TDX VM guests will also need similar support, use
CC_ATTR_GUEST_UNROLL_STRING_IO and generic cc_platform_has() API to
implement it.
String I/O helpers were the last users of sev_key_active() interface and
sev_enable_key static key. Remove them.
[ bp: Move comment too and do not delete it. ]
Suggested-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lkml.kernel.org/r/20211206135505.75045-2-kirill.shutemov@linux.intel.com
Theoretically, when the hardware signature in FACS changes, the OS
is supposed to gracefully decline to attempt to resume from S4:
"If the signature has changed, OSPM will not restore the system
context and can boot from scratch"
In practice, Windows doesn't do this and many laptop vendors do allow
the signature to change especially when docking/undocking, so it would
be a bad idea to simply comply with the specification by default in the
general case.
However, there are use cases where we do want the compliant behaviour
and we know it's safe. Specifically, when resuming virtual machines where
we know the hypervisor has changed sufficiently that resume will fail.
We really want to be able to *tell* the guest kernel not to try, so it
boots cleanly and doesn't just crash. This patch provides a way to opt
in to the spec-compliant behaviour on the command line.
A follow-up patch may do this automatically for certain "known good"
machines based on a DMI match, or perhaps just for all hypervisor
guests since there's no good reason a hypervisor would change the
hardware_signature that it exposes to guests *unless* it wants them
to obey the ACPI specification.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Updating MSR bitmap for L2 is not cheap and rearly needed. TLFS for Hyper-V
offers 'Enlightened MSR Bitmap' feature which allows L1 hypervisor to
inform L0 when it changes MSR bitmap, this eliminates the need to examine
L1's MSR bitmap for L2 every time when 'real' MSR bitmap for L2 gets
constructed.
Use 'vmx->nested.msr_bitmap_changed' flag to implement the feature.
Note, KVM already uses 'Enlightened MSR bitmap' feature when it runs as a
nested hypervisor on top of Hyper-V. The newly introduced feature is going
to be used by Hyper-V guests on KVM.
When the feature is enabled for Win10+WSL2, it shaves off around 700 CPU
cycles from a nested vmexit cost (tight cpuid loop test).
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211129094704.326635-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Introduce a flag to keep track of whether MSR bitmap for L2 needs to be
rebuilt due to changes in MSR bitmap for L1 or switching to a different
L2. This information will be used for Enlightened MSR Bitmap feature for
Hyper-V guests.
Note, setting msr_bitmap_changed to 'true' from set_current_vmptr() is
not really needed for Enlightened MSR Bitmap as the feature can only
be used in conjunction with Enlightened VMCS but let's keep tracking
information complete, it's cheap and in the future similar PV feature can
easily be implemented for KVM on KVM too.
No functional change intended.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211129094704.326635-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In preparation to enabling 'Enlightened MSR Bitmap' feature for Hyper-V
guests move MSR bitmap update tracking to a dedicated helper.
Note: vmx_msr_bitmap_l01_changed() is called when MSR bitmap might be
updated. KVM doesn't check if the bit we're trying to set is already set
(or the bit it's trying to clear is already cleared). Such situations
should not be common and a few false positives should not be a problem.
No functional change intended.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211129094704.326635-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Replace all ret/retq instructions with RET in preparation of making
RET a macro. Since AS is case insensitive it's a big no-op without
RET defined.
find arch/x86/ -name \*.S | while read file
do
sed -i 's/\<ret[q]*\>/RET/' $file
done
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211204134907.905503893@infradead.org
MCA handlers check the valid bit in each status register
(MCA_STATUS[Val]) and continue processing the error only if the valid
bit is set.
Set the valid bit unconditionally in the corresponding MCA_STATUS
register and correct any Val=0 injections made by the user as such
errors will get ignored and such injections will be largely pointless.
Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211104215846.254012-3-Smita.KoralahalliChannabasappa@amd.com
The MCA_IPID register uniquely identifies a bank's type on Scalable MCA
(SMCA) systems. When an MCA bank is not populated, the MCA_IPID register
will read as zero and writes to it will be ignored.
On a hw-type error injection (injection which writes the actual MCA
registers in an attempt to cause a real MCE) check the value of this
register before trying to inject the error.
Do not impose any limitations on a sw injection and allow the user to
test out all the decoding paths without relying on the available hardware,
as its purpose is to just test the code.
[ bp: Heavily massage. ]
Link: https://lkml.kernel.org/r/20211019233641.140275-2-Smita.KoralahalliChannabasappa@amd.com
Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211104215846.254012-2-Smita.KoralahalliChannabasappa@amd.com
Principally, in order to get rid of #define RET in this code to make
place for a new RET, but also to clarify the code, rename a bunch of
things:
s/UNLOCK/IRQ_RESTORE/
s/LOCK/IRQ_SAVE/
s/BEGIN/BEGIN_IRQ_SAVE/
s/\<RET\>/RET_IRQ_RESTORE/
s/RET_ENDP/\tRET_IRQ_RESTORE\rENDP/
which then leaves RET unused so it can be removed.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211204134907.841623970@infradead.org
Currently, RETPOLINE*_CFLAGS are defined in the top-level Makefile
but only x86 makes use of them. Move them there. If ever another
architecture finds the need, it can be reconsidered.
[ bp: Massage a bit. ]
Suggested-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lkml.kernel.org/r/20211119165630.219152765@infradead.org
With more NICs supporting CHECKSUM_COMPLETE, and IPv6 being widely
used csum_partial() is heavily used with small amount of bytes, and is
consuming many cycles.
IPv6 header size, for instance, is 40 bytes.
Another thing to consider is that NET_IP_ALIGN is 0 on x86, meaning
that network headers are not word-aligned, unless the driver forces
this.
This means that csum_partial() fetches one u16 to 'align the buffer',
then performs three u64 additions with carry in a loop, then a
remaining u32, then a remaining u16.
With this new version, it performs a loop only for the 64 bytes blocks,
then the remaining is bisected.
Testing on various CPUs, all of them show a big reduction in
csum_partial() cost (by 50 to 80 %)
Before:
4.16% [kernel] [k] csum_partial
After:
0.83% [kernel] [k] csum_partial
If run in a loop 1,000,000 times:
Before:
26,922,913 cycles # 3846130.429 GHz
80,302,961 instructions # 2.98 insn per cycle
21,059,816 branches # 3008545142.857 M/sec
2,896 branch-misses # 0.01% of all branches
After:
17,960,709 cycles # 3592141.800 GHz
41,292,805 instructions # 2.30 insn per cycle
11,058,119 branches # 2211623800.000 M/sec
2,997 branch-misses # 0.03% of all branches
[ bp: Massage, merge in subsequent fixes into a single patch:
- um compilation error due to missing load_unaligned_zeropad():
- Reported-by: kernel test robot <lkp@intel.com>
- Link: https://lkml.kernel.org/r/20211118175239.1525650-1-eric.dumazet@gmail.com
- Fix initial seed for odd buffers
- Reported-by: Noah Goldstein <goldstein.w.n@gmail.com>
- Link: https://lkml.kernel.org/r/20211125141817.3541501-1-eric.dumazet@gmail.com
]
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20211112161950.528886-1-eric.dumazet@gmail.com
em_rdmsr() and em_wrmsr() return X86EMUL_IO_NEEDED if MSR accesses
required an exit to userspace. However, x86_emulate_insn() doesn't return
X86EMUL_*, so x86_emulate_instruction() doesn't directly act on
X86EMUL_IO_NEEDED; instead, it looks for other signals to differentiate
between PIO, MMIO, etc. causing RDMSR/WRMSR emulation not to
exit to userspace now.
Nevertheless, if the userspace_msr_exit_test testcase in selftests
is changed to test RDMSR/WRMSR with a forced emulation prefix,
the test passes. What happens is that first userspace exit
information is filled but the userspace exit does not happen.
Because x86_emulate_instruction() returns 1, the guest retries
the instruction---but this time RIP has already been adjusted
past the forced emulation prefix, so the guest executes RDMSR/WRMSR
and the userspace exit finally happens.
Since the X86EMUL_IO_NEEDED path has provided a complete_userspace_io
callback, x86_emulate_instruction() can just return 0 if the
callback is not NULL. Then RDMSR/WRMSR instruction emulation will
exit to userspace directly, without the RDMSR/WRMSR vmexit.
Fixes: 1ae099540e ("KVM: x86: Allow deflecting unknown MSR accesses to user space")
Signed-off-by: Hou Wenlong <houwenlong93@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <56f9df2ee5c05a81155e2be366c9dc1f7adc8817.1635842679.git.houwenlong93@linux.alibaba.com>
When KVM runs as a nested hypervisor on top of Hyper-V it uses Enlightened
VMCS and enables Enlightened MSR Bitmap feature for its L1s and L2s (which
are actually L2s and L3s from Hyper-V's perspective). When MSR bitmap is
updated, KVM has to reset HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP from
clean fields to make Hyper-V aware of the change. For KVM's L1s, this is
done in vmx_disable_intercept_for_msr()/vmx_enable_intercept_for_msr().
MSR bitmap for L2 is build in nested_vmx_prepare_msr_bitmap() by blending
MSR bitmap for L1 and L1's idea of MSR bitmap for L2. KVM, however, doesn't
check if the resulting bitmap is different and never cleans
HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP in eVMCS02. This is incorrect and
may result in Hyper-V missing the update.
The issue could've been solved by calling evmcs_touch_msr_bitmap() for
eVMCS02 from nested_vmx_prepare_msr_bitmap() unconditionally but doing so
would not give any performance benefits (compared to not using Enlightened
MSR Bitmap at all). 3-level nesting is also not a very common setup
nowadays.
Don't enable 'Enlightened MSR Bitmap' feature for KVM's L2s (real L3s) for
now.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211129094704.326635-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If msr access triggers an exit to userspace, the
complete_userspace_io callback would skip instruction by vendor
callback for kvm_skip_emulated_instruction(). However, when msr
access comes from the emulator, e.g. if kvm.force_emulation_prefix
is enabled and the guest uses rdmsr/wrmsr with kvm prefix,
VM_EXIT_INSTRUCTION_LEN in vmcs is invalid and
kvm_emulate_instruction() should be used to skip instruction
instead.
As Sean noted, unlike the previous case, there's no #UD if
unrestricted guest is disabled and the guest accesses an MSR in
Big RM. So the correct way to fix this is to attach a different
callback when the msr access comes from the emulator.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Hou Wenlong <houwenlong93@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <34208da8f51580a06e45afefac95afea0e3f96e3.1635842679.git.houwenlong93@linux.alibaba.com>
The next patch would use kvm_emulate_instruction() with
EMULTYPE_SKIP in complete_userspace_io callback to fix a
problem in msr access emulation. However, EMULTYPE_SKIP
only updates RIP, more things like updating interruptibility
state and injecting single-step #DBs would be done in the
callback. Since the emulator also does those things after
x86_emulate_insn(), add a new emulation type to pair with
EMULTYPE_SKIP to do those things for completion of user exits
within the emulator.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Hou Wenlong <houwenlong93@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <8f8c8e268b65f31d55c2881a4b30670946ecfa0d.1635842679.git.houwenlong93@linux.alibaba.com>
Truncate the new EIP to a 32-bit value when handling EMULTYPE_SKIP as the
decode phase does not truncate _eip. Wrapping the 32-bit boundary is
legal if and only if CS is a flat code segment, but that check is
implicitly handled in the form of limit checks in the decode phase.
Opportunstically prepare for a future fix by storing the result of any
truncation in "eip" instead of "_eip".
Fixes: 1957aa63be ("KVM: VMX: Handle single-step #DB for EMULTYPE_SKIP on EPT misconfig")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <093eabb1eab2965201c9b018373baf26ff256d85.1635842679.git.houwenlong93@linux.alibaba.com>
merge pv_eoi_get_pending and pv_eoi_clr_pending into a single
function pv_eoi_test_and_clear_pending, which returns and clear
the value of the pending bit.
This makes it possible to clear the pending bit only if the guest
had set it, and otherwise skip the call to pv_eoi_put_user().
This can save up to 300 nsec on AMD EPYC processors.
Suggested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Message-Id: <1636026974-50555-2-git-send-email-lirongqing@baidu.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If guest gives MSR_KVM_PV_EOI_EN a wrong value, this printk() will
be trigged, and kernel log is spammed with the useless message
Fixes: 0d88800d54 ("kvm: x86: ioapic and apic debug macros cleanup")
Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Cc: stable@kernel.org
Message-Id: <1636026974-50555-1-git-send-email-lirongqing@baidu.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
It uses vcpu->arch.walk_mmu always; nested EPT does not have PDPTRs,
and nested NPT treats them like all other non-leaf page table levels
instead of caching them.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Message-Id: <20211124122055.64424-11-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
