Make acpi_processor_idle() use the generic TLB flushing code.
This again removes RCU usage after rcu_idle_enter().
(XXX make every C3 invalidate TLBs, not just C3-BM)
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Because of system-specific EFI firmware limitations, EFI volatile
variables may not be capable of holding the required contents of
the Machine Owner Key (MOK) certificate store when the certificate
list grows above some size. Therefore, an EFI boot loader may pass
the MOK certs via a EFI configuration table created specifically for
this purpose to avoid this firmware limitation.
An EFI configuration table is a much more primitive mechanism
compared to EFI variables and is well suited for one-way passage
of static information from a pre-OS environment to the kernel.
This patch adds initial kernel support to recognize, parse,
and validate the EFI MOK configuration table, where named
entries contain the same data that would otherwise be provided
in similarly named EFI variables.
Additionally, this patch creates a sysfs binary file for each
EFI MOK configuration table entry found. These files are read-only
to root and are provided for use by user space utilities such as
mokutil.
A subsequent patch will load MOK certs into the trusted platform
key ring using this infrastructure.
Signed-off-by: Lenny Szubowicz <lszubowi@redhat.com>
Link: https://lore.kernel.org/r/20200905013107.10457-2-lszubowi@redhat.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Get rid of all the gunk and remove the 'select PCI_MSI_ARCH_FALLBACK' from
the x86 Kconfig so the weak functions in the PCI core are replaced by stubs
which emit a warning, which ensures that any fail to set the irq domain
pointer results in a warning when the device is used.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112334.086003720@linutronix.de
The arch_.*_msi_irq[s] fallbacks are compiled in whether an architecture
requires them or not. Architectures which are fully utilizing hierarchical
irq domains should never call into that code.
It's not only architectures which depend on that by implementing one or
more of the weak functions, there is also a bunch of drivers which relies
on the weak functions which invoke msi_controller::setup_irq[s] and
msi_controller::teardown_irq.
Make the architectures and drivers which rely on them select them in Kconfig
and if not selected replace them by stub functions which emit a warning and
fail the PCI/MSI interrupt allocation.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112333.992429909@linutronix.de
Now that interrupt remapping sets the irqdomain pointer when a PCI device
is added it's possible to store the default irq domain in the device struct
in pcibios_add_device().
If the bus to which a device is connected has an irq domain associated then
this domain is used otherwise the default domain (PCI/MSI native or XEN
PCI/MSI) is used. Using the bus domain ensures that special MSI bus domains
like VMD work.
This makes XEN and the non-remapped native case work solely based on the
irq domain pointer in struct device for PCI/MSI and allows to remove the
arch fallback and make most of the x86_msi ops private to XEN in the next
steps.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112333.900423047@linutronix.de
To allow utilizing the irq domain pointer in struct device it is necessary
to make XEN/MSI irq domain compatible.
While the right solution would be to truly convert XEN to irq domains, this
is an exercise which is not possible for mere mortals with limited XENology.
Provide a plain irqdomain wrapper around XEN. While this is blatant
violation of the irqdomain design, it's the only solution for a XEN igorant
person to make progress on the issue which triggered this change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20200826112333.622352798@linutronix.de
X86 cannot store the irq domain pointer in struct device without breaking
XEN because the irq domain pointer takes precedence over arch_*_msi_irqs()
fallbacks.
To achieve this XEN MSI interrupt management needs to be wrapped into an
irq domain.
Move the x86_msi ops setup into a single function to prepare for this.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20200826112333.420224092@linutronix.de
X86 cannot store the irq domain pointer in struct device without breaking
XEN because the irq domain pointer takes precedence over arch_*_msi_irqs()
fallbacks.
XENs MSI teardown relies on default_teardown_msi_irqs() which invokes
arch_teardown_msi_irq(). default_teardown_msi_irqs() is a trivial iterator
over the msi entries associated to a device.
Implement this loop in xen_teardown_msi_irqs() to prepare for removal of
the fallbacks for X86.
This is a preparatory step to wrap XEN MSI alloc/free into a irq domain
which in turn allows to store the irq domain pointer in struct device and
to use the irq domain functions directly.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20200826112333.326841410@linutronix.de
The only user is in the same file and the name is too generic because this
function is only ever used for HVM domains.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross<jgross@suse.com>
Link: https://lore.kernel.org/r/20200826112333.234097629@linutronix.de
No point in initializing the default PCI/MSI interrupt domain early and no
point to create it when XEN PV/HVM/DOM0 are active.
Move the initialization to pci_arch_init() and convert it to init ops so
that XEN can override it as XEN has it's own PCI/MSI management. The XEN
override comes in a later step.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112332.859209894@linutronix.de
Adding a function call before the first #ifdef in arch_pci_init() triggers
a 'mixed declarations and code' warning if PCI_DIRECT is enabled.
Use stub functions and move the #ifdeffery to the header file where it is
not in the way.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112332.767707340@linutronix.de
pci_msi_get_hwirq() and pci_msi_set_desc are not longer special. Enable the
generic MSI domain ops in the core and PCI MSI code unconditionally and get
rid of the x86 specific implementations in the X86 MSI code and in the
hyperv PCI driver.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112332.564274859@linutronix.de
Convert the interrupt remap drivers to retrieve the pci device from the msi
descriptor and use info::hwirq.
This is the first step to prepare x86 for using the generic MSI domain ops.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Wei Liu <wei.liu@kernel.org>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20200826112332.466405395@linutronix.de
Retrieve the PCI device from the msi descriptor instead of doing so at the
call sites.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112332.352583299@linutronix.de
Move the UV specific fields into their own struct for readability sake. Get
rid of the #ifdeffery as it does not matter at all whether the alloc info
is a couple of bytes longer or not.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112332.255792469@linutronix.de
Move the IOAPIC specific fields into their own struct and reuse the common
devid. Get rid of the #ifdeffery as it does not matter at all whether the
alloc info is a couple of bytes longer or not.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Wei Liu <wei.liu@kernel.org>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20200826112332.054367732@linutronix.de
struct irq_alloc_info is a horrible zoo of unnamed structs in a union. Many
of the struct fields can be generic and don't have to be type specific like
hpet_id, ioapic_id...
Provide a generic set of members to prepare for the consolidation. The goal
is to make irq_alloc_info have the same basic member as the generic
msi_alloc_info so generic MSI domain ops can be reused and yet more mess
can be avoided when (non-PCI) device MSI support comes along.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112331.849577844@linutronix.de
Now that the iommu implementations handle the X86_*_GET_PARENT_DOMAIN
types, consolidate the two getter functions.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20200826112331.741909337@linutronix.de
irq_remapping_ir_irq_domain() is used to retrieve the remapping parent
domain for an allocation type. irq_remapping_irq_domain() is for retrieving
the actual device domain for allocating interrupts for a device.
The two functions are similar and can be unified by using explicit modes
for parent irq domain retrieval.
Add X86_IRQ_ALLOC_TYPE_IOAPIC/HPET_GET_PARENT and use it in the iommu
implementations. Drop the parent domain retrieval for PCI_MSI/X as that is
unused.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20200826112331.436350257@linutronix.de
Setting the irq_set_vcpu_affinity() callback to
irq_chip_set_vcpu_affinity_parent() is a pointless exercise because the
function which utilizes it searchs the domain hierarchy to find a parent
domain which has such a callback.
Remove the useless indirection.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112331.250130127@linutronix.de
Composing the MSI message at the MSI chip level is wrong because the
underlying parent domain is the one which knows how the message should be
composed for the direct vector delivery or the interrupt remapping table
entry.
The interrupt remapping aware PCI/MSI chip does that already. Make the
direct delivery chip do the same and move the composition of the direct
delivery MSI message to the vector domain irq chip.
This prepares for the upcoming device MSI support to avoid having
architecture specific knowledge in the device MSI domain irq chips.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112331.157603198@linutronix.de
The documentation of irq_chip_compose_msi_msg() claims that with
hierarchical irq domains the first chip in the hierarchy which has an
irq_compose_msi_msg() callback is chosen. But the code just keeps
iterating after it finds a chip with a compose callback.
The x86 HPET MSI implementation relies on that behaviour, but that does not
make it more correct.
The message should always be composed at the domain which manages the
underlying resource (e.g. APIC or remap table) because that domain knows
about the required layout of the message.
On X86 the following hierarchies exist:
1) vector -------- PCI/MSI
2) vector -- IR -- PCI/MSI
The vector domain has a different message format than the IR (remapping)
domain. So obviously the PCI/MSI domain can't compose the message without
having knowledge about the parent domain, which is exactly the opposite of
what hierarchical domains want to achieve.
X86 actually has two different PCI/MSI chips where #1 has a compose
callback and #2 does not. #2 delegates the composition to the remap domain
where it belongs, but #1 does it at the PCI/MSI level.
For the upcoming device MSI support it's necessary to change this and just
let the first domain which can compose the message take care of it. That
way the top level chip does not have to worry about it and the device MSI
code does not need special knowledge about topologies. It just sets the
compose callback to NULL and lets the hierarchy pick the first chip which
has one.
Due to that the attempt to move the compose callback from the direct
delivery PCI/MSI domain to the vector domain made the system fail to boot
with interrupt remapping enabled because in the remapping case
irq_chip_compose_msi_msg() keeps iterating and choses the compose callback
of the vector domain which obviously creates the wrong format for the remap
table.
Break out of the loop when the first irq chip with a compose callback is
found and fixup the HPET code temporarily. That workaround will be removed
once the direct delivery compose callback is moved to the place where it
belongs in the vector domain.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Zyngier <maz@kernel.org> Link: https://lore.kernel.org/r/20200826112331.047917603@linutronix.de
The mcelog utility is not commonly used on AMD systems. Therefore,
errors logged only by the dev_mce_log() notifier will be missed. This
may occur if the EDAC modules are not loaded, in which case it's
preferable to print the error record by the default notifier.
However, the mce->kflags set by dev_mce_log() notifier makes the
default notifier skip over the errors assuming they are processed by
dev_mce_log().
Do not update kflags in the dev_mce_log() notifier on AMD systems.
Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200903234531.162484-3-Smita.KoralahalliChannabasappa@amd.com
Back in commit:
20d51a426f ("x86/mce: Reuse one of the u16 padding fields in 'struct mce'")
a field was added to "struct mce" to save the computed error severity.
Make use of this in mce_reign() to avoid re-computing the severity
for every CPU.
In the case where the machine panics, one call to mce_severity() is
still needed in order to provide the correct message giving the reason
for the panic.
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200908175519.14223-2-tony.luck@intel.com
Yunhai Zhang recently fixed a VGA software scrollback bug in commit
ebfdfeeae8 ("vgacon: Fix for missing check in scrollback handling"),
but that then made people look more closely at some of this code, and
there were more problems on the vgacon side, but also the fbcon software
scrollback.
We don't really have anybody who maintains this code - probably because
nobody actually _uses_ it any more. Sure, people still use both VGA and
the framebuffer consoles, but they are no longer the main user
interfaces to the kernel, and haven't been for decades, so these kinds
of extra features end up bitrotting and not really being used.
So rather than try to maintain a likely unused set of code, I'll just
aggressively remove it, and see if anybody even notices. Maybe there
are people who haven't jumped on the whole GUI badnwagon yet, and think
it's just a fad. And maybe those people use the scrollback code.
If that turns out to be the case, we can resurrect this again, once
we've found the sucker^Wmaintainer for it who actually uses it.
Reported-by: NopNop Nop <nopitydays@gmail.com>
Tested-by: Willy Tarreau <w@1wt.eu>
Cc: 张云海 <zhangyunhai@nsfocus.com>
Acked-by: Andy Lutomirski <luto@amacapital.net>
Acked-by: Willy Tarreau <w@1wt.eu>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The x86-64 psABI [0] specifies special relocation types
(R_X86_64_[REX_]GOTPCRELX) for indirection through the Global Offset
Table, semantically equivalent to R_X86_64_GOTPCREL, which the linker
can take advantage of for optimization (relaxation) at link time. This
is supported by LLD and binutils versions 2.26 onwards.
The compressed kernel is position-independent code, however, when using
LLD or binutils versions before 2.27, it must be linked without the -pie
option. In this case, the linker may optimize certain instructions into
a non-position-independent form, by converting foo@GOTPCREL(%rip) to $foo.
This potential issue has been present with LLD and binutils-2.26 for a
long time, but it has never manifested itself before now:
- LLD and binutils-2.26 only relax
movq foo@GOTPCREL(%rip), %reg
to
leaq foo(%rip), %reg
which is still position-independent, rather than
mov $foo, %reg
which is permitted by the psABI when -pie is not enabled.
- GCC happens to only generate GOTPCREL relocations on mov instructions.
- CLang does generate GOTPCREL relocations on non-mov instructions, but
when building the compressed kernel, it uses its integrated assembler
(due to the redefinition of KBUILD_CFLAGS dropping -no-integrated-as),
which has so far defaulted to not generating the GOTPCRELX
relocations.
Nick Desaulniers reports [1,2]:
"A recent change [3] to a default value of configuration variable
(ENABLE_X86_RELAX_RELOCATIONS OFF -> ON) in LLVM now causes Clang's
integrated assembler to emit R_X86_64_GOTPCRELX/R_X86_64_REX_GOTPCRELX
relocations. LLD will relax instructions with these relocations based
on whether the image is being linked as position independent or not.
When not, then LLD will relax these instructions to use absolute
addressing mode (R_RELAX_GOT_PC_NOPIC). This causes kernels built with
Clang and linked with LLD to fail to boot."
Patch series [4] is a solution to allow the compressed kernel to be
linked with -pie unconditionally, but even if merged is unlikely to be
backported. As a simple solution that can be applied to stable as well,
prevent the assembler from generating the relaxed relocation types using
the -mrelax-relocations=no option. For ease of backporting, do this
unconditionally.
[0] https://gitlab.com/x86-psABIs/x86-64-ABI/-/blob/master/x86-64-ABI/linker-optimization.tex#L65
[1] https://lore.kernel.org/lkml/20200807194100.3570838-1-ndesaulniers@google.com/
[2] https://github.com/ClangBuiltLinux/linux/issues/1121
[3] https://reviews.llvm.org/rGc41a18cf61790fc898dcda1055c3efbf442c14c0
[4] https://lore.kernel.org/lkml/20200731202738.2577854-1-nivedita@alum.mit.edu/
Reported-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200812004308.1448603-1-nivedita@alum.mit.edu
- Multiple stolen time fixes, with a new capability to match x86
- Fix for hugetlbfs mappings when PUD and PMD are the same level
- Fix for hugetlbfs mappings when PTE mappings are enforced
(dirty logging, for example)
- Fix tracing output of 64bit values
x86:
- nSVM state restore fixes
- Async page fault fixes
- Lots of small fixes everywhere
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAl9dM5kUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroM+Iwf+LbISO7ccpPMK1kKtOeug/jZv+xQA
sVaBGRzYo+k2e0XtV8E8IV4N30FBtYSwXsbBKkMAoy2FpmMebgDWDQ7xspb6RJMS
/y8t1iqPwdOaLIkUkgc7UihSTlZm05Es3f3q6uZ9+oaM4Fe+V7xWzTUX4Oy89JO7
KcQsTD7pMqS4bfZGADK781ITR/WPgCi0aYx5s6dcwcZAQXhb1K1UKEjB8OGKnjUh
jliReJtxRA16rjF+S5aJ7L07Ce/ksrfwkI4NXJ4GxW+lyOfVNdSBJUBaZt1m7G2M
1We5+i5EjKCjuxmgtUUUfVdazpj1yl+gBGT7KKkLte9T9WZdXyDnixAbvg==
=OFb3
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm fixes from Paolo Bonzini:
"A bit on the bigger side, mostly due to me being on vacation, then
busy, then on parental leave, but there's nothing worrisome.
ARM:
- Multiple stolen time fixes, with a new capability to match x86
- Fix for hugetlbfs mappings when PUD and PMD are the same level
- Fix for hugetlbfs mappings when PTE mappings are enforced (dirty
logging, for example)
- Fix tracing output of 64bit values
x86:
- nSVM state restore fixes
- Async page fault fixes
- Lots of small fixes everywhere"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (25 commits)
KVM: emulator: more strict rsm checks.
KVM: nSVM: more strict SMM checks when returning to nested guest
SVM: nSVM: setup nested msr permission bitmap on nested state load
SVM: nSVM: correctly restore GIF on vmexit from nesting after migration
x86/kvm: don't forget to ACK async PF IRQ
x86/kvm: properly use DEFINE_IDTENTRY_SYSVEC() macro
KVM: VMX: Don't freeze guest when event delivery causes an APIC-access exit
KVM: SVM: avoid emulation with stale next_rip
KVM: x86: always allow writing '0' to MSR_KVM_ASYNC_PF_EN
KVM: SVM: Periodically schedule when unregistering regions on destroy
KVM: MIPS: Change the definition of kvm type
kvm x86/mmu: use KVM_REQ_MMU_SYNC to sync when needed
KVM: nVMX: Fix the update value of nested load IA32_PERF_GLOBAL_CTRL control
KVM: fix memory leak in kvm_io_bus_unregister_dev()
KVM: Check the allocation of pv cpu mask
KVM: nVMX: Update VMCS02 when L2 PAE PDPTE updates detected
KVM: arm64: Update page shift if stage 2 block mapping not supported
KVM: arm64: Fix address truncation in traces
KVM: arm64: Do not try to map PUDs when they are folded into PMD
arm64/x86: KVM: Introduce steal-time cap
...
Don't ignore return values in rsm_load_state_64/32 to avoid
loading invalid state from SMM state area if it was tampered with
by the guest.
This is primarly intended to avoid letting guest set bits in EFER
(like EFER.SVME when nesting is disabled) by manipulating SMM save area.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20200827171145.374620-8-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
* check that guest is 64 bit guest, otherwise the SVM related fields
in the smm state area are not defined
* If the SMM area indicates that SMM interrupted a running guest,
check that EFER.SVME which is also saved in this area is set, otherwise
the guest might have tampered with SMM save area, and so indicate
emulation failure which should triple fault the guest.
* Check that that guest CPUID supports SVM (due to the same issue as above)
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20200827162720.278690-4-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This code was missing and was forcing the L2 run with L1's msr
permission bitmap
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20200827162720.278690-3-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently code in svm_set_nested_state copies the current vmcb control
area to L1 control area (hsave->control), under assumption that
it mostly reflects the defaults that kvm choose, and later qemu
overrides these defaults with L2 state using standard KVM interfaces,
like KVM_SET_REGS.
However nested GIF (which is AMD specific thing) is by default is true,
and it is copied to hsave area as such.
This alone is not a big deal since on VMexit, GIF is always set to false,
regardless of what it was on VM entry. However in nested_svm_vmexit we
were first were setting GIF to false, but then we overwrite the control
fields with value from the hsave area. (including the nested GIF field
itself if GIF virtualization is enabled).
Now on normal vm entry this is not a problem, since GIF is usually false
prior to normal vm entry, and this is the value that copied to hsave,
and then restored, but this is not always the case when the nested state
is loaded as explained above.
To fix this issue, move svm_set_gif after we restore the L1 control
state in nested_svm_vmexit, so that even with wrong GIF in the
saved L1 control area, we still clear GIF as the spec says.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20200827162720.278690-2-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Merge commit 26d05b368a ("Merge branch 'kvm-async-pf-int' into HEAD")
tried to adapt the new interrupt based async PF mechanism to the newly
introduced IDTENTRY magic but unfortunately it missed the fact that
DEFINE_IDTENTRY_SYSVEC() doesn't call ack_APIC_irq() on its own and
all DEFINE_IDTENTRY_SYSVEC() users have to call it manually.
As the result all multi-CPU KVM guest hang on boot when
KVM_FEATURE_ASYNC_PF_INT is present. The breakage went unnoticed because no
KVM userspace (e.g. QEMU) currently set it (and thus async PF mechanism
is currently disabled) but we're about to change that.
Fixes: 26d05b368a ("Merge branch 'kvm-async-pf-int' into HEAD")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200908135350.355053-3-vkuznets@redhat.com>
Tested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
According to SDM 27.2.4, Event delivery causes an APIC-access VM exit.
Don't report internal error and freeze guest when event delivery causes
an APIC-access exit, it is handleable and the event will be re-injected
during the next vmentry.
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1597827327-25055-2-git-send-email-wanpengli@tencent.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
svm->next_rip is reset in svm_vcpu_run() only after calling
svm_exit_handlers_fastpath(), which will cause SVM's
skip_emulated_instruction() to write a stale RIP.
We can move svm_exit_handlers_fastpath towards the end of
svm_vcpu_run(). To align VMX with SVM, keep svm_complete_interrupts()
close as well.
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Paul K. <kronenpj@kronenpj.dyndns.org>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
[Also move vmcb_mark_all_clean before any possible write to the VMCB.
- Paolo]
Even without in-kernel LAPIC we should allow writing '0' to
MSR_KVM_ASYNC_PF_EN as we're not enabling the mechanism. In
particular, QEMU with 'kernel-irqchip=off' fails to start
a guest with
qemu-system-x86_64: error: failed to set MSR 0x4b564d02 to 0x0
Fixes: 9d3c447c72 ("KVM: X86: Fix async pf caused null-ptr-deref")
Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200911093147.484565-1-vkuznets@redhat.com>
[Actually commit the version proposed by Sean Christopherson. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
There may be many encrypted regions that need to be unregistered when a
SEV VM is destroyed. This can lead to soft lockups. For example, on a
host running 4.15:
watchdog: BUG: soft lockup - CPU#206 stuck for 11s! [t_virtual_machi:194348]
CPU: 206 PID: 194348 Comm: t_virtual_machi
RIP: 0010:free_unref_page_list+0x105/0x170
...
Call Trace:
[<0>] release_pages+0x159/0x3d0
[<0>] sev_unpin_memory+0x2c/0x50 [kvm_amd]
[<0>] __unregister_enc_region_locked+0x2f/0x70 [kvm_amd]
[<0>] svm_vm_destroy+0xa9/0x200 [kvm_amd]
[<0>] kvm_arch_destroy_vm+0x47/0x200
[<0>] kvm_put_kvm+0x1a8/0x2f0
[<0>] kvm_vm_release+0x25/0x30
[<0>] do_exit+0x335/0xc10
[<0>] do_group_exit+0x3f/0xa0
[<0>] get_signal+0x1bc/0x670
[<0>] do_signal+0x31/0x130
Although the CLFLUSH is no longer issued on every encrypted region to be
unregistered, there are no other changes that can prevent soft lockups for
very large SEV VMs in the latest kernel.
Periodically schedule if necessary. This still holds kvm->lock across the
resched, but since this only happens when the VM is destroyed this is
assumed to be acceptable.
Signed-off-by: David Rientjes <rientjes@google.com>
Message-Id: <alpine.DEB.2.23.453.2008251255240.2987727@chino.kir.corp.google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When kvm_mmu_get_page() gets a page with unsynced children, the spt
pagetable is unsynchronized with the guest pagetable. But the
guest might not issue a "flush" operation on it when the pagetable
entry is changed from zero or other cases. The hypervisor has the
responsibility to synchronize the pagetables.
KVM behaved as above for many years, But commit 8c8560b833
("KVM: x86/mmu: Use KVM_REQ_TLB_FLUSH_CURRENT for MMU specific flushes")
inadvertently included a line of code to change it without giving any
reason in the changelog. It is clear that the commit's intention was to
change KVM_REQ_TLB_FLUSH -> KVM_REQ_TLB_FLUSH_CURRENT, so we don't
needlessly flush other contexts; however, one of the hunks changed
a nearby KVM_REQ_MMU_SYNC instead. This patch changes it back.
Link: https://lore.kernel.org/lkml/20200320212833.3507-26-sean.j.christopherson@intel.com/
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Message-Id: <20200902135421.31158-1-jiangshanlai@gmail.com>
fixes: 8c8560b833 ("KVM: x86/mmu: Use KVM_REQ_TLB_FLUSH_CURRENT for MMU specific flushes")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
A minor fix for the update of VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL field
in exit_ctls_high.
Fixes: 03a8871add ("KVM: nVMX: Expose load IA32_PERF_GLOBAL_CTRL
VM-{Entry,Exit} control")
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Message-Id: <20200828085622.8365-5-chenyi.qiang@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
check the allocation of per-cpu __pv_cpu_mask. Initialize ops only when
successful.
Signed-off-by: Haiwei Li <lihaiwei@tencent.com>
Message-Id: <d59f05df-e6d3-3d31-a036-cc25a2b2f33f@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When L2 uses PAE, L0 intercepts of L2 writes to CR0/CR3/CR4 call
load_pdptrs to read the possibly updated PDPTEs from the guest
physical address referenced by CR3. It loads them into
vcpu->arch.walk_mmu->pdptrs and sets VCPU_EXREG_PDPTR in
vcpu->arch.regs_dirty.
At the subsequent assumed reentry into L2, the mmu will call
vmx_load_mmu_pgd which calls ept_load_pdptrs. ept_load_pdptrs sees
VCPU_EXREG_PDPTR set in vcpu->arch.regs_dirty and loads
VMCS02.GUEST_PDPTRn from vcpu->arch.walk_mmu->pdptrs[]. This all works
if the L2 CRn write intercept always resumes L2.
The resume path calls vmx_check_nested_events which checks for
exceptions, MTF, and expired VMX preemption timers. If
vmx_check_nested_events finds any of these conditions pending it will
reflect the corresponding exit into L1. Live migration at this point
would also cause a missed immediate reentry into L2.
After L1 exits, vmx_vcpu_run calls vmx_register_cache_reset which
clears VCPU_EXREG_PDPTR in vcpu->arch.regs_dirty. When L2 next
resumes, ept_load_pdptrs finds VCPU_EXREG_PDPTR clear in
vcpu->arch.regs_dirty and does not load VMCS02.GUEST_PDPTRn from
vcpu->arch.walk_mmu->pdptrs[]. prepare_vmcs02 will then load
VMCS02.GUEST_PDPTRn from vmcs12->pdptr0/1/2/3 which contain the stale
values stored at last L2 exit. A repro of this bug showed L2 entering
triple fault immediately due to the bad VMCS02.GUEST_PDPTRn values.
When L2 is in PAE paging mode add a call to ept_load_pdptrs before
leaving L2. This will update VMCS02.GUEST_PDPTRn if they are dirty in
vcpu->arch.walk_mmu->pdptrs[].
Tested:
kvm-unit-tests with new directed test: vmx_mtf_pdpte_test.
Verified that test fails without the fix.
Also ran Google internal VMM with an Ubuntu 16.04 4.4.0-83 guest running a
custom hypervisor with a 32-bit Windows XP L2 guest using PAE. Prior to fix
would repro readily. Ran 14 simultaneous L2s for 140 iterations with no
failures.
Signed-off-by: Peter Shier <pshier@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20200820230545.2411347-1-pshier@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
- Multiple stolen time fixes, with a new capability to match x86
- Fix for hugetlbfs mappings when PUD and PMD are the same level
- Fix for hugetlbfs mappings when PTE mappings are enforced
(dirty logging, for example)
- Fix tracing output of 64bit values
-----BEGIN PGP SIGNATURE-----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=VBrL
-----END PGP SIGNATURE-----
Merge tag 'kvmarm-fixes-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 fixes for Linux 5.9, take #1
- Multiple stolen time fixes, with a new capability to match x86
- Fix for hugetlbfs mappings when PUD and PMD are the same level
- Fix for hugetlbfs mappings when PTE mappings are enforced
(dirty logging, for example)
- Fix tracing output of 64bit values
If an exception needs to be handled while reading an MSR - which is in
most of the cases caused by a #GP on a non-existent MSR - then this
is most likely the incarnation of a BIOS or a hardware bug. Such bug
violates the architectural guarantee that MCA banks are present with all
MSRs belonging to them.
The proper fix belongs in the hardware/firmware - not in the kernel.
Handling an #MC exception which is raised while an NMI is being handled
would cause the nasty NMI nesting issue because of the shortcoming of
IRET of reenabling NMIs when executed. And the machine is in an #MC
context already so <Deity> be at its side.
Tracing MSR accesses while in #MC is another no-no due to tracing being
inherently a bad idea in atomic context:
vmlinux.o: warning: objtool: do_machine_check()+0x4a: call to mce_rdmsrl() leaves .noinstr.text section
so remove all that "additional" functionality from mce_rdmsrl() and
provide it with a special exception handler which panics the machine
when that MSR is not accessible.
The exception handler prints a human-readable message explaining what
the panic reason is but, what is more, it panics while in the #GP
handler and latter won't have executed an IRET, thus opening the NMI
nesting issue in the case when the #MC has happened while handling
an NMI. (#MC itself won't be reenabled until MCG_STATUS hasn't been
cleared).
Suggested-by: Andy Lutomirski <luto@kernel.org>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
[ Add missing prototypes for ex_handler_* ]
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200906212130.GA28456@zn.tnic
x86_64 zero extends 32bit operations, so for 64bit operands,
XORL r32,r32 is functionally equal to XORQ r64,r64, but avoids
a REX prefix byte when legacy registers are used.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
x86_64 zero extends 32bit operations, so for 64bit operands,
XORL r32,r32 is functionally equal to XORL r64,r64, but avoids
a REX prefix byte when legacy registers are used.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Make sure the machine supports RDRAND, otherwise there is no trusted
source of randomness in the system.
To also check this in the pre-decompression stage, make has_cpuflag()
not depend on CONFIG_RANDOMIZE_BASE anymore.
Signed-off-by: Martin Radev <martin.b.radev@gmail.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-73-joro@8bytes.org
Calling down to EFI runtime services can result in the firmware
performing VMGEXIT calls. The firmware is likely to use the GHCB of the
OS (e.g., for setting EFI variables), so each GHCB in the system needs
to be identity-mapped in the EFI page tables, as unencrypted, to avoid
page faults.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: Moved GHCB mapping loop to sev-es.c ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-72-joro@8bytes.org
Commit
0c2a3913d6 ("x86/fpu: Parse clearcpuid= as early XSAVE argument")
changed clearcpuid parsing from __setup() to cmdline_find_option().
While the __setup() function would have been called for each clearcpuid=
parameter on the command line, cmdline_find_option() will only return
the last one, so the change effectively made it impossible to disable
more than one bit.
Allow a comma-separated list of bit numbers as the argument for
clearcpuid to allow multiple bits to be disabled again. Log the bits
being disabled for informational purposes.
Also fix the check on the return value of cmdline_find_option(). It
returns -1 when the option is not found, so testing as a boolean is
incorrect.
Fixes: 0c2a3913d6 ("x86/fpu: Parse clearcpuid= as early XSAVE argument")
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907213919.2423441-1-nivedita@alum.mit.edu
Unwind hints are useful to provide objtool with information about stack
states in non-standard functions/code.
While the type of information being provided might be very arch
specific, the mechanism to provide the information can be useful for
other architectures.
Move the relevant unwint hint definitions for all architectures to
see.
[ jpoimboe: REGS_IRET -> REGS_PARTIAL ]
Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Header frame.h is getting more code annotations to help objtool analyze
object files.
Rename the file to objtool.h.
[ jpoimboe: add objtool.h to MAINTAINERS ]
Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Compiler is not happy about one function prototype:
CC kernel/dma/swiotlb.o
kernel/dma/swiotlb.c:275:1: warning: no previous prototype for ‘swiotlb_late_init_with_default_size’ [-Wmissing-prototypes]
275 | swiotlb_late_init_with_default_size(size_t default_size)
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Since it's used outside of the module, move its declaration to the header
from the user.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Stephane Eranian found a bug in that IBS' current Fetch counter was not
being reset when the driver would write the new value to clear it along
with the enable bit set, and found that adding an MSR write that would
first disable IBS Fetch would make IBS Fetch reset its current count.
Indeed, the PPR for AMD Family 17h Model 31h B0 55803 Rev 0.54 - Sep 12,
2019 states "The periodic fetch counter is set to IbsFetchCnt [...] when
IbsFetchEn is changed from 0 to 1."
Explicitly set IbsFetchEn to 0 and then to 1 when re-enabling IBS Fetch,
so the driver properly resets the internal counter to 0 and IBS
Fetch starts counting again.
A family 15h machine tested does not have this problem, and the extra
wrmsr is also not needed on Family 19h, so only do the extra wrmsr on
families 16h through 18h.
Reported-by: Stephane Eranian <stephane.eranian@google.com>
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
[peterz: optimized]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537
Family 19h RAPL support did not change from Family 17h; extend
the existing Fam17h support to work on Family 19h too.
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200908214740.18097-8-kim.phillips@amd.com
IBS hardware with the OpCntExt feature gets a 7-bit wider internal
counter. Both the maximum and current count bitfields in the
IBS_OP_CTL register are extended to support reading and writing it.
No changes are necessary to the driver for handling the extra
contiguous current count bits (IbsOpCurCnt), as the driver already
passes through 32 bits of that field. However, the driver has to do
some extra bit manipulation when converting from a period to the
non-contiguous (although conveniently aligned) extra bits in the
IbsOpMaxCnt bitfield.
This decreases IBS Op interrupt overhead when the period is over
1,048,560 (0xffff0), which would previously activate the driver's
software counter. That threshold is now 134,217,712 (0x7fffff0).
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200908214740.18097-7-kim.phillips@amd.com
Neither IbsBrTarget nor OPDATA4 are populated in IBS Fetch mode.
Don't accumulate them into raw sample user data in that case.
Also, in Fetch mode, add saving the IBS Fetch Control Extended MSR.
Technically, there is an ABI change here with respect to the IBS raw
sample data format, but I don't see any perf driver version information
being included in perf.data file headers, but, existing users can detect
whether the size of the sample record has reduced by 8 bytes to
determine whether the IBS driver has this fix.
Fixes: 904cb3677f ("perf/x86/amd/ibs: Update IBS MSRs and feature definitions")
Reported-by: Stephane Eranian <stephane.eranian@google.com>
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20200908214740.18097-6-kim.phillips@amd.com
get_ibs_op_count() adds hardware's current count (IbsOpCurCnt) bits
to its count regardless of hardware's valid status.
According to the PPR for AMD Family 17h Model 31h B0 55803 Rev 0.54,
if the counter rolls over, valid status is set, and the lower 7 bits
of IbsOpCurCnt are randomized by hardware.
Don't include those bits in the driver's event count.
Fixes: 8b1e13638d ("perf/x86-ibs: Fix usage of IBS op current count")
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537
Commit 5738891229 ("perf/x86/amd: Add support for Large Increment
per Cycle Events") mistakenly zeroes the upper 16 bits of the count
in set_period(). That's fine for counting with perf stat, but not
sampling with perf record when only Large Increment events are being
sampled. To enable sampling, we sign extend the upper 16 bits of the
merged counter pair as described in the Family 17h PPRs:
"Software wanting to preload a value to a merged counter pair writes the
high-order 16-bit value to the low-order 16 bits of the odd counter and
then writes the low-order 48-bit value to the even counter. Reading the
even counter of the merged counter pair returns the full 64-bit value."
Fixes: 5738891229 ("perf/x86/amd: Add support for Large Increment per Cycle Events")
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537
Commit 2f217d58a8 ("perf/x86/amd/uncore: Set the thread mask for
F17h L3 PMCs") inadvertently changed the uncore driver's behaviour
wrt perf tool invocations with or without a CPU list, specified with
-C / --cpu=.
Change the behaviour of the driver to assume the former all-cpu (-a)
case, which is the more commonly desired default. This fixes
'-a -A' invocations without explicit cpu lists (-C) to not count
L3 events only on behalf of the first thread of the first core
in the L3 domain.
BEFORE:
Activity performed by the first thread of the last core (CPU#43) in
CPU#40's L3 domain is not reported by CPU#40:
sudo perf stat -a -A -e l3_request_g1.caching_l3_cache_accesses taskset -c 43 perf bench mem memcpy -s 32mb -l 100 -f default
...
CPU36 21,835 l3_request_g1.caching_l3_cache_accesses
CPU40 87,066 l3_request_g1.caching_l3_cache_accesses
CPU44 17,360 l3_request_g1.caching_l3_cache_accesses
...
AFTER:
The L3 domain activity is now reported by CPU#40:
sudo perf stat -a -A -e l3_request_g1.caching_l3_cache_accesses taskset -c 43 perf bench mem memcpy -s 32mb -l 100 -f default
...
CPU36 354,891 l3_request_g1.caching_l3_cache_accesses
CPU40 1,780,870 l3_request_g1.caching_l3_cache_accesses
CPU44 315,062 l3_request_g1.caching_l3_cache_accesses
...
Fixes: 2f217d58a8 ("perf/x86/amd/uncore: Set the thread mask for F17h L3 PMCs")
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20200908214740.18097-2-kim.phillips@amd.com
A warning as below may be triggered when sampling with large PEBS.
[ 410.411250] perf: interrupt took too long (72145 > 71975), lowering
kernel.perf_event_max_sample_rate to 2000
[ 410.724923] ------------[ cut here ]------------
[ 410.729822] WARNING: CPU: 0 PID: 16397 at arch/x86/events/core.c:1422
x86_pmu_stop+0x95/0xa0
[ 410.933811] x86_pmu_del+0x50/0x150
[ 410.937304] event_sched_out.isra.0+0xbc/0x210
[ 410.941751] group_sched_out.part.0+0x53/0xd0
[ 410.946111] ctx_sched_out+0x193/0x270
[ 410.949862] __perf_event_task_sched_out+0x32c/0x890
[ 410.954827] ? set_next_entity+0x98/0x2d0
[ 410.958841] __schedule+0x592/0x9c0
[ 410.962332] schedule+0x5f/0xd0
[ 410.965477] exit_to_usermode_loop+0x73/0x120
[ 410.969837] prepare_exit_to_usermode+0xcd/0xf0
[ 410.974369] ret_from_intr+0x2a/0x3a
[ 410.977946] RIP: 0033:0x40123c
[ 411.079661] ---[ end trace bc83adaea7bb664a ]---
In the non-overflow context, e.g., context switch, with large PEBS, perf
may stop an event twice. An example is below.
//max_samples_per_tick is adjusted to 2
//NMI is triggered
intel_pmu_handle_irq()
handle_pmi_common()
drain_pebs()
__intel_pmu_pebs_event()
perf_event_overflow()
__perf_event_account_interrupt()
hwc->interrupts = 1
return 0
//A context switch happens right after the NMI.
//In the same tick, the perf_throttled_seq is not changed.
perf_event_task_sched_out()
perf_pmu_sched_task()
intel_pmu_drain_pebs_buffer()
__intel_pmu_pebs_event()
perf_event_overflow()
__perf_event_account_interrupt()
++hwc->interrupts >= max_samples_per_tick
return 1
x86_pmu_stop(); # First stop
perf_event_context_sched_out()
task_ctx_sched_out()
ctx_sched_out()
event_sched_out()
x86_pmu_del()
x86_pmu_stop(); # Second stop and trigger the warning
Perf should only invoke the perf_event_overflow() in the overflow
context.
Current drain_pebs() is called from:
- handle_pmi_common() -- overflow context
- intel_pmu_pebs_sched_task() -- non-overflow context
- intel_pmu_pebs_disable() -- non-overflow context
- intel_pmu_auto_reload_read() -- possible overflow context
With PERF_SAMPLE_READ + PERF_FORMAT_GROUP, the function may be
invoked in the NMI handler. But, before calling the function, the
PEBS buffer has already been drained. The __intel_pmu_pebs_event()
will not be called in the possible overflow context.
To fix the issue, an indicator is required to distinguish between the
overflow context aka handle_pmi_common() and other cases.
The dummy regs pointer can be used as the indicator.
In the non-overflow context, perf should treat the last record the same
as other PEBS records, and doesn't invoke the generic overflow handler.
Fixes: 21509084f9 ("perf/x86/intel: Handle multiple records in the PEBS buffer")
Reported-by: Like Xu <like.xu@linux.intel.com>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Like Xu <like.xu@linux.intel.com>
Link: https://lkml.kernel.org/r/20200902210649.2743-1-kan.liang@linux.intel.com
Latch sequence counters have unique read and write APIs, and thus
seqcount_latch_t was recently introduced at seqlock.h.
Use that new data type instead of plain seqcount_t. This adds the
necessary type-safety and ensures that only latching-safe seqcount APIs
are to be used.
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
[peterz: unwreck cyc2ns_read_begin()]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200827114044.11173-7-a.darwish@linutronix.de
When running under SEV-ES, the kernel has to tell the hypervisor when to
open the NMI window again after an NMI was injected. This is done with
an NMI-complete message to the hypervisor.
Add code to the kernel's NMI handler to send this message right at the
beginning of do_nmi(). This always allows nesting NMIs.
[ bp: Mark __sev_es_nmi_complete() noinstr:
vmlinux.o: warning: objtool: exc_nmi()+0x17: call to __sev_es_nmi_complete()
leaves .noinstr.text section
While at it, use __pa_nodebug() for the same reason due to
CONFIG_DEBUG_VIRTUAL=y:
vmlinux.o: warning: objtool: __sev_es_nmi_complete()+0xd9: call to __phys_addr()
leaves .noinstr.text section ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-71-joro@8bytes.org
Add a play_dead handler when running under SEV-ES. This is needed
because the hypervisor can't deliver an SIPI request to restart the AP.
Instead, the kernel has to issue a VMGEXIT to halt the VCPU until the
hypervisor wakes it up again.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-70-joro@8bytes.org
The APs are not ready to handle exceptions when verify_cpu() is called
in secondary_startup_64().
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-69-joro@8bytes.org
The IDT on 64-bit contains vectors which use paranoid_entry() and/or IST
stacks. To make these vectors work, the TSS and the getcpu GDT entry need
to be set up before the IDT is loaded.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-68-joro@8bytes.org
As part of the GHCB specification, the booting of APs under SEV-ES
requires an AP jump table when transitioning from one layer of code to
another (e.g. when going from UEFI to the OS). As a result, each layer
that parks an AP must provide the physical address of an AP jump table
to the next layer via the hypervisor.
Upon booting of the kernel, read the AP jump table address from the
hypervisor. Under SEV-ES, APs are started using the INIT-SIPI-SIPI
sequence. Before issuing the first SIPI request for an AP, the start
CS and IP is programmed into the AP jump table. Upon issuing the SIPI
request, the AP will awaken and jump to that start CS:IP address.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: - Adapted to different code base
- Moved AP table setup from SIPI sending path to
real-mode setup code
- Fix sparse warnings ]
Co-developed-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-67-joro@8bytes.org
The code at the trampoline entry point is executed in real-mode. In
real-mode, #VC exceptions can't be handled so anything that might cause
such an exception must be avoided.
In the standard trampoline entry code this is the WBINVD instruction and
the call to verify_cpu(), which are both not needed anyway when running
as an SEV-ES guest.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-66-joro@8bytes.org
Implement the callbacks to copy the processor state required by KVM to
the GHCB.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: - Split out of a larger patch
- Adapt to different callback functions ]
Co-developed-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-64-joro@8bytes.org
Add two new paravirt callbacks to provide hypervisor-specific processor
state in the GHCB and to copy state from the hypervisor back to the
processor.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-63-joro@8bytes.org
Handle #VC exceptions caused by #DB exceptions in the guest. Those
must be handled outside of instrumentation_begin()/end() so that the
handler will not be raised recursively.
Handle them by calling the kernel's debug exception handler.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-62-joro@8bytes.org
Implement a handler for #VC exceptions caused by #AC exceptions. The
#AC exception is just forwarded to do_alignment_check() and not pushed
down to the hypervisor, as requested by the SEV-ES GHCB Standardization
Specification.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-61-joro@8bytes.org
Implement a handler for #VC exceptions caused by VMMCALL instructions.
This is only a starting point, VMMCALL emulation under SEV-ES needs
further hypervisor-specific changes to provide additional state.
[ bp: Drop "this patch". ]
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: Adapt to #VC handling infrastructure ]
Co-developed-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-60-joro@8bytes.org
Implement a handler for #VC exceptions caused by INVD instructions.
Since Linux should never use INVD, just mark it as unsupported.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: Adapt to #VC handling infrastructure ]
Co-developed-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-57-joro@8bytes.org
Implement a handler for #VC exceptions caused by RDTSC and RDTSCP
instructions. Also make it available in the pre-decompression stage
because the KASLR code uses RDTSC/RDTSCP to gather entropy and some
hypervisors intercept these instructions.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: - Adapt to #VC handling infrastructure
- Make it available early ]
Co-developed-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-55-joro@8bytes.org
Add code to handle #VC exceptions on DR7 register reads and writes.
This is needed early because show_regs() reads DR7 to print it out.
Under SEV-ES, there is currently no support for saving/restoring the
DRx registers but software expects to be able to write to the DR7
register. For now, cache the value written to DR7 and return it on
read attempts, but do not touch the real hardware DR7.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: - Adapt to #VC handling framework
- Support early usage ]
Co-developed-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-53-joro@8bytes.org
Add handling for emulation of the MOVS instruction on MMIO regions, as
done by the memcpy_toio() and memcpy_fromio() functions.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-51-joro@8bytes.org
Add a handler for #VC exceptions caused by MMIO intercepts. These
intercepts come along as nested page faults on pages with reserved
bits set.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
[ jroedel@suse.de: Adapt to VC handling framework ]
Co-developed-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-50-joro@8bytes.org
When a #VC exception is triggered by user-space, the instruction decoder
needs to read the instruction bytes from user addresses. Enhance
vc_decode_insn() to safely fetch kernel and user instructions.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-49-joro@8bytes.org
The #VC handler needs special entry code because:
1. It runs on an IST stack
2. It needs to be able to handle nested #VC exceptions
To make this work, the entry code is implemented to pretend it doesn't
use an IST stack. When entered from user-mode or early SYSCALL entry
path it switches to the task stack. If entered from kernel-mode it tries
to switch back to the previous stack in the IRET frame.
The stack found in the IRET frame is validated first, and if it is not
safe to use it for the #VC handler, the code will switch to a
fall-back stack (the #VC2 IST stack). From there, it can cause nested
exceptions again.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-46-joro@8bytes.org
The get_stack_info() functionality is needed in the entry code for the
#VC exception handler. Provide a version of it in the .text.noinstr
section which can be called safely from there.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-45-joro@8bytes.org
When an NMI hits in the #VC handler entry code before it has switched to
another stack, any subsequent #VC exception in the NMI code-path will
overwrite the interrupted #VC handler's stack.
Make sure this doesn't happen by explicitly adjusting the #VC IST entry
in the NMI handler for the time it can cause #VC exceptions.
[ bp: Touchups, spelling fixes. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-44-joro@8bytes.org
Allocate and map an IST stack and an additional fall-back stack for
the #VC handler. The memory for the stacks is allocated only when
SEV-ES is active.
The #VC handler needs to use an IST stack because a #VC exception can be
raised from kernel space with unsafe stack, e.g. in the SYSCALL entry
path.
Since the #VC exception can be nested, the #VC handler switches back to
the interrupted stack when entered from kernel space. If switching back
is not possible, the fall-back stack is used.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-43-joro@8bytes.org
The runtime handler needs one GHCB per-CPU. Set them up and map them
unencrypted.
[ bp: Touchups and simplification. ]
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-42-joro@8bytes.org
Add the infrastructure to handle #VC exceptions when the kernel runs on
virtual addresses and has mapped a GHCB. This handler will be used until
the runtime #VC handler takes over.
Since the handler runs very early, disable instrumentation for sev-es.c.
[ bp: Make vc_ghcb_invalidate() __always_inline so that it can be
inlined in noinstr functions like __sev_es_nmi_complete(). ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200908123816.GB3764@8bytes.org
Setup an early handler for #VC exceptions. There is no GHCB mapped
yet, so just re-use the vc_no_ghcb_handler(). It can only handle
CPUID exit-codes, but that should be enough to get the kernel through
verify_cpu() and __startup_64() until it runs on virtual addresses.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
[ boot failure Error: kernel_ident_mapping_init() failed. ]
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lkml.kernel.org/r/20200908123517.GA3764@8bytes.org
Setup sev-es.c and include the code from the pre-decompression stage
to also build it into the image of the running kernel. Temporarily add
__maybe_unused annotations to avoid build warnings until the functions
get used.
[ bp: Use the non-tracing rd/wrmsr variants because:
vmlinux.o: warning: objtool: __sev_es_nmi_complete()+0x11f: \
call to do_trace_write_msr() leaves .noinstr.text section
as __sev_es_nmi_complete() is noinstr due to being called from the
NMI handler exc_nmi(). ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-39-joro@8bytes.org
A recent refresh of the defconfigs got rid of the following
(unset) config:
# CONFIG_64BIT is not set
Innocuous as it seems, when the config file is saved again the
behavior is changed so that CONFIG_64BIT=y.
Currently,
$ make i386_defconfig
$ grep CONFIG_64BIT .config
CONFIG_64BIT=y
whereas previously (and with this patch):
$ make i386_defconfig
$ grep CONFIG_64BIT .config
# CONFIG_64BIT is not set
( This was found with weird compiler errors on OpenEmbedded
builds, as the compiler was unable to cope with 64-bits data
types. )
Fixes: 1d0e12fd3a ("x86/defconfigs: Refresh defconfig files")
Reported-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Daniel Díaz <daniel.diaz@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Refactor the message printed to the kernel log which indicates whether
SEV or SME, etc is active. This will scale better in the future when
more memory encryption features might be added. Also add SEV-ES to the
list of features.
[ bp: Massage. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-38-joro@8bytes.org
Add a sev_es_active() function for checking whether SEV-ES is enabled.
Also cache the value of MSR_AMD64_SEV at boot to speed up the feature
checking in the running code.
[ bp: Remove "!!" in sev_active() too. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-37-joro@8bytes.org
Move the assembly coded dispatch between page-faults and all other
exceptions to C code to make it easier to maintain and extend.
Also change the return-type of early_make_pgtable() to bool and make it
static.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-36-joro@8bytes.org
Move these two functions from kernel/idt.c to include/asm/desc.h:
* init_idt_data()
* idt_init_desc()
These functions are needed to setup IDT entries very early and need to
be called from head64.c. To be usable this early, these functions need
to be compiled without instrumentation and the stack-protector feature.
These features need to be kept enabled for kernel/idt.c, so head64.c
must use its own versions.
[ bp: Take Kees' suggested patch title and add his Rev-by. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-35-joro@8bytes.org
Add a separate bringup IDT for the CPU bringup code that will be used
until the kernel switches to the idt_table. There are two reasons for a
separate IDT:
1) When the idt_table is set up and the secondary CPUs are
booted, it contains entries (e.g. IST entries) which
require certain CPU state to be set up. This includes a
working TSS (for IST), MSR_GS_BASE (for stack protector) or
CR4.FSGSBASE (for paranoid_entry) path. By using a
dedicated IDT for early boot this state need not to be set
up early.
2) The idt_table is static to idt.c, so any function
using/modifying must be in idt.c too. That means that all
compiler driven instrumentation like tracing or KASAN is
also active in this code. But during early CPU bringup the
environment is not set up for this instrumentation to work
correctly.
To avoid all of these hassles and make early exception handling robust,
use a dedicated bringup IDT.
The IDT is loaded two times, first on the boot CPU while the kernel is
still running on direct mapped addresses, and again later after the
switch to kernel addresses has happened. The second IDT load happens on
the boot and secondary CPUs.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-34-joro@8bytes.org
Make sure there is a stack once the kernel runs from virtual addresses.
At this stage any secondary CPU which boots will have lost its stack
because the kernel switched to a new page-table which does not map the
real-mode stack anymore.
This is needed for handling early #VC exceptions caused by instructions
like CPUID.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-33-joro@8bytes.org
Make sure segments are properly set up before setting up an IDT and
doing anything that might cause a #VC exception. This is later needed
for early exception handling.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-32-joro@8bytes.org
Load the GDT right after switching to virtual addresses to make sure
there is a defined GDT for exception handling.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-31-joro@8bytes.org
Handling exceptions during boot requires a working GDT. The kernel GDT
can't be used on the direct mapping, so load a startup GDT and setup
segments.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-30-joro@8bytes.org
The code to setup idt_data is needed for early exception handling, but
set_intr_gate() can't be used that early because it has pv-ops in its
code path which don't work that early.
Split out the idt_data initialization part from set_intr_gate() so
that it can be used separately.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-29-joro@8bytes.org
The xgetbv() function is needed in the pre-decompression boot code,
but asm/fpu/internal.h can't be included there directly. Doing so
opens the door to include-hell due to various include-magic in
boot/compressed/misc.h.
Avoid that by moving xgetbv()/xsetbv() to a separate header file and
include it instead.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-27-joro@8bytes.org
Force a page-fault on any further accesses to the GHCB page when they
shouldn't happen anymore. This will catch any bugs where a #VC exception
is raised even though none is expected anymore.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-25-joro@8bytes.org
Install an exception handler for #VC exception that uses a GHCB. Also
add the infrastructure for handling different exit-codes by decoding
the instruction that caused the exception and error handling.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-24-joro@8bytes.org
The functions are needed to map the GHCB for SEV-ES guests. The GHCB
is used for communication with the hypervisor, so its content must not
be encrypted. After the GHCB is not needed anymore it must be mapped
encrypted again so that the running kernel image can safely re-use the
memory.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-23-joro@8bytes.org
Call set_sev_encryption_mask() while still on the stage 1 #VC-handler
because the stage 2 handler needs the kernel's own page tables to be
set up, to which calling set_sev_encryption_mask() is a prerequisite.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-21-joro@8bytes.org
Add the first handler for #VC exceptions. At stage 1 there is no GHCB
yet because the kernel might still be running on the EFI page table.
The stage 1 handler is limited to the MSR-based protocol to talk to the
hypervisor and can only support CPUID exit-codes, but that is enough to
get to stage 2.
[ bp: Zap superfluous newlines after rd/wrmsr instruction mnemonics. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-20-joro@8bytes.org
Changing the function to take start and end as parameters instead of
start and size simplifies the callers which don't need to calculate the
size if they already have start and end.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-19-joro@8bytes.org
With the page-fault handler in place, he identity mapping can be built
on-demand. So remove the code which manually creates the mappings and
unexport/remove the functions used for it.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-18-joro@8bytes.org
When booted through startup_64(), the kernel keeps running on the EFI
page table until the KASLR code sets up its own page table. Without
KASLR, the pre-decompression boot code never switches off the EFI page
table. Change that by unconditionally switching to a kernel-controlled
page table after relocation.
This makes sure the kernel can make changes to the mapping when
necessary, for example map pages unencrypted in SEV and SEV-ES guests.
Also, remove the debug_putstr() calls in initialize_identity_maps()
because the function now runs before console_init() is called.
[ bp: Massage commit message. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-17-joro@8bytes.org
Install a page-fault handler to add an identity mapping to addresses
not yet mapped. Also do some checking whether the error code is sane.
This makes non SEV-ES machines use the exception handling
infrastructure in the pre-decompressions boot code too, making it less
likely to break in the future.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-16-joro@8bytes.org
The file contains only code related to identity-mapped page tables.
Rename the file and compile it always in.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-15-joro@8bytes.org
Add code needed to setup an IDT in the early pre-decompression
boot-code. The IDT is loaded first in startup_64, which is after
EfiExitBootServices() has been called, and later reloaded when the
kernel image has been relocated to the end of the decompression area.
This allows to setup different IDT handlers before and after the
relocation.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-14-joro@8bytes.org
The x86-64 ABI defines a red-zone on the stack:
The 128-byte area beyond the location pointed to by %rsp is considered
to be reserved and shall not be modified by signal or interrupt
handlers. Therefore, functions may use this area for temporary data
that is not needed across function calls. In particular, leaf
functions may use this area for their entire stack frame, rather than
adjusting the stack pointer in the prologue and epilogue. This area is
known as the red zone.
This is not compatible with exception handling, because the IRET frame
written by the hardware at the stack pointer and the functions to handle
the exception will overwrite the temporary variables of the interrupted
function, causing undefined behavior. So disable red-zones for the
pre-decompression boot code.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-13-joro@8bytes.org
Add a function to check whether an instruction has a REP prefix.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-12-joro@8bytes.org
Add a function to the instruction decoder which returns the pt_regs
offset of the register specified in the reg field of the modrm byte.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-11-joro@8bytes.org
Factor out the code used to decode an instruction with the correct
address and operand sizes to a helper function.
No functional changes.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-10-joro@8bytes.org
Factor out the code to fetch the instruction from user-space to a helper
function.
No functional changes.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-9-joro@8bytes.org
The inat-tables.c file has some arrays in it that contain pointers to
other arrays. These pointers need to be relocated when the kernel
image is moved to a different location.
The pre-decompression boot-code has no support for applying ELF
relocations, so initialize these arrays at runtime in the
pre-decompression code to make sure all pointers are correctly
initialized.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-8-joro@8bytes.org
Move the definition of the x86 page-fault error code bits to a new
header file asm/trap_pf.h. This makes it easier to include them into
pre-decompression boot code. No functional changes.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-7-joro@8bytes.org
Add CPU feature detection for Secure Encrypted Virtualization with
Encrypted State. This feature enhances SEV by also encrypting the
guest register state, making it in-accessible to the hypervisor.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-6-joro@8bytes.org
Use the shorthand to make it more readable.
No functional changes.
Signed-off-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-5-joro@8bytes.org
Building a correct GHCB for the hypervisor requires setting valid bits
in the GHCB. Simplify that process by providing accessor functions to
set values and to update the valid bitmap and to check the valid bitmap
in KVM.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-4-joro@8bytes.org
Extend the vmcb_safe_area with SEV-ES fields and add a new
'struct ghcb' which will be used for guest-hypervisor communication.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-3-joro@8bytes.org
Do not allocate a vmcb_control_area and a vmcb_save_area on the stack,
as these structures will become larger with future extenstions of
SVM and thus the svm_set_nested_state() function will become a too large
stack frame.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-2-joro@8bytes.org
...because future AMD systems will support up to 64 MCA banks per CPU.
MAX_NR_BANKS is used to allocate a number of data structures, and it is
used as a ceiling for values read from MCG_CAP[Count]. Therefore, this
change will have no functional effect on existing systems with 32 or
fewer MCA banks per CPU.
However, this will increase the size of the following structures:
Global bitmaps:
- core.c / mce_banks_ce_disabled
- core.c / all_banks
- core.c / valid_banks
- core.c / toclear
- Total: 32 new bits * 4 bitmaps = 16 new bytes
Per-CPU bitmaps:
- core.c / mce_poll_banks
- intel.c / mce_banks_owned
- Total: 32 new bits * 2 bitmaps = 8 new bytes
The bitmaps are arrays of longs. So this change will only affect 32-bit
execution, since there will be one additional long used. There will be
no additional memory use on 64-bit execution, because the size of long
is 64 bits.
Global structs:
- amd.c / struct smca_bank smca_banks[]: 16 bytes per bank
- core.c / struct mce_bank_dev mce_bank_devs[]: 56 bytes per bank
- Total: 32 new banks * (16 + 56) bytes = 2304 new bytes
Per-CPU structs:
- core.c / struct mce_bank mce_banks_array[]: 16 bytes per bank
- Total: 32 new banks * 16 bytes = 512 new bytes
32-bit
Total global size increase: 2320 bytes
Total per-CPU size increase: 520 bytes
64-bit
Total global size increase: 2304 bytes
Total per-CPU size increase: 512 bytes
This additional memory should still fit within the existing .data
section of the kernel binary. However, in the case where it doesn't
fit, an additional page (4kB) of memory will be added to the binary to
accommodate the extra data which will be the maximum size increase of
vmlinux.
Signed-off-by: Akshay Gupta <Akshay.Gupta@amd.com>
[ Adjust commit message and code comment. ]
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200828192412.320052-1-Yazen.Ghannam@amd.com
Andy reported that the syscall treacing for 32bit fast syscall fails:
# ./tools/testing/selftests/x86/ptrace_syscall_32
...
[RUN] SYSEMU
[FAIL] Initial args are wrong (nr=224, args=10 11 12 13 14 4289172732)
...
[RUN] SYSCALL
[FAIL] Initial args are wrong (nr=29, args=0 0 0 0 0 4289172732)
The eason is that the conversion to generic entry code moved the retrieval
of the sixth argument (EBP) after the point where the syscall entry work
runs, i.e. ptrace, seccomp, audit...
Unbreak it by providing a split up version of syscall_enter_from_user_mode().
- syscall_enter_from_user_mode_prepare() establishes state and enables
interrupts
- syscall_enter_from_user_mode_work() runs the entry work
Replace the call to syscall_enter_from_user_mode() in the 32bit fast
syscall C-entry with the split functions and stick the EBP retrieval
between them.
Fixes: 27d6b4d14f ("x86/entry: Use generic syscall entry function")
Reported-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/87k0xdjbtt.fsf@nanos.tec.linutronix.de
Current usage of thread.debugreg6 is convoluted at best. It starts life as
a copy of the hardware DR6 value, but then various bits are cleared and
set.
Replace this with a new variable thread.virtual_dr6 that is initialized to
0 when DR6 is read and only gains bits, at the same time the actual (on
stack) dr6 value which is read from the hardware only gets bits cleared.
Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.415372940@infradead.org
DR6 has a whole bunch of bits that have negative polarity; they were
architecturally reserved and defined to be 1 and are now getting used.
Since they're 1 by default, 0 becomes the signal value.
Handle this by xor'ing the read DR6 value by the reserved mask, this
will flip them around such that 1 is the signal value (positive
polarity).
Current Linux doesn't yet support any of these bits, but there's two
defined:
- DR6[11] Bus Lock Debug Exception (ISEr39)
- DR6[16] Restricted Transactional Memory (SDM)
Update ptrace_{set,get}_debugreg() to provide/consume the value in
architectural polarity. Although afaict ptrace_set_debugreg(6) is
pointless, the value is not consumed anywhere.
Change hw_breakpoint_restore() to alway write the DR6_RESERVED value
to DR6, again, no consumer for that write.
Suggested-by: Andrew Cooper <Andrew.Cooper3@citrix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.354220797@infradead.org
This is called with interrupts disabled, there's no point in using
get_cpu() and per_cpu().
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.292906672@infradead.org
Unused remnants for the bit-bucket.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.233022474@infradead.org
Remove the historical junk and replace it with a WARN and a comment.
The problem is that even though the kernel only uses TF single-step in
kprobes and KGDB, both of which consume the event before this, QEMU/KVM has
bugs in this area that can trigger this state so it has to be dealt with.
Suggested-by: Brian Gerst <brgerst@gmail.com>
Suggested-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.170216274@infradead.org
The cond_local_irq_enable() block, dealing with vm86 and sending
signals is only relevant for #DB-from-user, move it there.
This then reduces handle_debug() to only the notifier call, so rename
it to notify_debug().
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.094265982@infradead.org
The historical SYSENTER junk is explicitly for from-kernel, so move it
to the #DB-from-kernel handler.
It is ordered after the notifier, which is important for KGDB which uses TF
single-step and needs to consume the event before that point.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.031099736@infradead.org
There's no point in calculating si_code if it's not going to be used.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133200.967434217@infradead.org
The handle_debug(.user) argument is used to terminate the #DB handler early
for the INT1-from-kernel case, since the kernel doesn't use INT1.
Remove the argument and handle this explicitly in #DB-from-kernel.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20200902133200.907020598@infradead.org
Kprobes are on kernel text, and thus only matter for #DB-from-kernel.
Kprobes are ordered before the generic notifier, preserve that order.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20200902133200.847465360@infradead.org
Move the BTF sync near the DR6 load, as this will be the only common
code guaranteed to run on every #DB.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20200902133200.786888252@infradead.org
Trying to clear DR7 around a #DB from usermode malfunctions if the tasks
schedules when delivering SIGTRAP.
Rather than trying to define a special no-recursion region, just allow a
single level of recursion. The same mechanism is used for NMI, and it
hasn't caused any problems yet.
Fixes: 9f58fdde95 ("x86/db: Split out dr6/7 handling")
Reported-by: Kyle Huey <me@kylehuey.com>
Debugged-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/8b9bd05f187231df008d48cf818a6a311cbd5c98.1597882384.git.luto@kernel.org
Link: https://lore.kernel.org/r/20200902133200.726584153@infradead.org
The WARN added in commit 3c73b81a91 ("x86/entry, selftests: Further
improve user entry sanity checks") unconditionally triggers on a IVB
machine because it does not support SMAP.
For !SMAP hardware the CLAC/STAC instructions are patched out and thus if
userspace sets AC, it is still have set after entry.
Fixes: 3c73b81a91 ("x86/entry, selftests: Further improve user entry sanity checks")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200902133200.666781610@infradead.org
On i386, the order of parameters passed on regs is eax,edx,and ecx
(as per regparm(3) calling conventions).
Change the mapping in regs_get_kernel_argument(), so that arg1=ax
arg2=dx, and arg3=cx.
Running the selftests testcase kprobes_args_use.tc shows the result
as passed.
Fixes: 3c88ee194c ("x86: ptrace: Add function argument access API")
Signed-off-by: Vamshi K Sthambamkadi <vamshi.k.sthambamkadi@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20200828113242.GA1424@cosmos
inst.h was included in calling.h solely to instantiate the RDPID macro.
The usage of RDPID was removed in
6a3ea3e68b ("x86/entry/64: Do not use RDPID in paranoid entry to accomodate KVM")
so remove the include.
Fixes: 6a3ea3e68b ("x86/entry/64: Do not use RDPID in paranoid entry to accomodate KVM")
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200827171735.93825-1-ubizjak@gmail.com
XORL %0,%0 is equivalent to XORQ %0,%0 as both will zero the entire
register. Use XORL %0,%0 for all operand sizes to avoid REX prefix byte
when legacy registers are used and to avoid size prefix byte when 16bit
registers are used.
Zeroing the full register is OK in this use case.
As a result, the size of the .fixup section decreases by 20 bytes.
[ bp: Massage commit message. ]
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Link: https://lkml.kernel.org/r/20200827180904.96399-1-ubizjak@gmail.com
One can not simply remove vmalloc faulting on x86-32. Upstream
commit: 7f0a002b5a ("x86/mm: remove vmalloc faulting")
removed it on x86 alltogether because previously the
arch_sync_kernel_mappings() interface was introduced. This interface
added synchronization of vmalloc/ioremap page-table updates to all
page-tables in the system at creation time and was thought to make
vmalloc faulting obsolete.
But that assumption was incredibly naive.
It turned out that there is a race window between the time the vmalloc
or ioremap code establishes a mapping and the time it synchronizes
this change to other page-tables in the system.
During this race window another CPU or thread can establish a vmalloc
mapping which uses the same intermediate page-table entries (e.g. PMD
or PUD) and does no synchronization in the end, because it found all
necessary mappings already present in the kernel reference page-table.
But when these intermediate page-table entries are not yet
synchronized, the other CPU or thread will continue with a vmalloc
address that is not yet mapped in the page-table it currently uses,
causing an unhandled page fault and oops like below:
BUG: unable to handle page fault for address: fe80c000
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
*pde = 33183067 *pte = a8648163
Oops: 0002 [#1] SMP
CPU: 1 PID: 13514 Comm: cve-2017-17053 Tainted: G
...
Call Trace:
ldt_dup_context+0x66/0x80
dup_mm+0x2b3/0x480
copy_process+0x133b/0x15c0
_do_fork+0x94/0x3e0
__ia32_sys_clone+0x67/0x80
__do_fast_syscall_32+0x3f/0x70
do_fast_syscall_32+0x29/0x60
do_SYSENTER_32+0x15/0x20
entry_SYSENTER_32+0x9f/0xf2
EIP: 0xb7eef549
So the arch_sync_kernel_mappings() interface is racy, but removing it
would mean to re-introduce the vmalloc_sync_all() interface, which is
even more awful. Keep arch_sync_kernel_mappings() in place and catch
the race condition in the page-fault handler instead.
Do a partial revert of above commit to get vmalloc faulting on x86-32
back in place.
Fixes: 7f0a002b5a ("x86/mm: remove vmalloc faulting")
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200902155904.17544-1-joro@8bytes.org
When CONFIG_RETPOLINE is disabled, Clang uses a jump table for the
switch statement in cmdline_find_option (jump tables are disabled when
CONFIG_RETPOLINE is enabled). This function is called very early in boot
from sme_enable() if CONFIG_AMD_MEM_ENCRYPT is enabled. At this time,
the kernel is still executing out of the identity mapping, but the jump
table will contain virtual addresses.
Fix this by disabling jump tables for cmdline.c when AMD_MEM_ENCRYPT is
enabled.
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200903023056.3914690-1-nivedita@alum.mit.edu
We don't want to depend on the linker's orphan section placement
heuristics as these can vary between linkers, and may change between
versions. All sections need to be explicitly handled in the linker
script.
Now that all sections are explicitly handled, enable orphan section
warnings.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20200902025347.2504702-6-keescook@chromium.org
We don't want to depend on the linker's orphan section placement
heuristics as these can vary between linkers, and may change between
versions. All sections need to be explicitly handled in the linker script.
Now that all sections are explicitly handled, enable orphan section
warnings.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20200902025347.2504702-5-keescook@chromium.org
In preparation for warning on orphan sections, stop the linker from
generating the .eh_frame* sections, discard unwanted non-zero-sized
generated sections, and enforce other expected-to-be-zero-sized sections
(since discarding them might hide problems with them suddenly gaining
unexpected entries).
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200821194310.3089815-28-keescook@chromium.org
In preparation for warning on orphan sections, enforce other
expected-to-be-zero-sized sections (since discarding them might hide
problems with them suddenly gaining unexpected entries).
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200821194310.3089815-25-keescook@chromium.org
The .got.plt section should always be zero (or filled only with the
linker-generated lazy dispatch entry). Enforce this with an assert and
mark the section as INFO. This is more sensitive than just blindly
discarding the section.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200821194310.3089815-24-keescook@chromium.org
When !CONFIG_KPROBES, do not generate kprobe sections. This makes
sure there are no unexpected sections encountered by the linker scripts.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200821194310.3089815-23-keescook@chromium.org
Replace many of the indirect calls with static_call().
The average PMI time, as measured by perf_sample_event_took()*:
PRE: 3283.03 [ns]
POST: 3145.12 [ns]
Which is a ~138 [ns] win per PMI, or a ~4.2% decrease.
[*] on an IVB-EP, using: 'perf record -a -e cycles -- make O=defconfig-build/ -j80'
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.338001015@infradead.org
In order to use static_call() to wire up x86_pmu, we need to
initialize earlier, specifically before memory allocation works; copy
some of the tricks from jump_label to enable this.
Primarily we overload key->next to store a sites pointer when there
are no modules, this avoids having to use kmalloc() to initialize the
sites and allows us to run much earlier.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20200818135805.220737930@infradead.org
Verify the text we're about to change is as we expect it to be.
Requested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200818135805.161974981@infradead.org
GCC can turn our static_call(name)(args...) into a tail call, in which
case we get a JMP.d32 into the trampoline (which then does a further
tail-call).
Teach objtool to recognise and mark these in .static_call_sites and
adjust the code patching to deal with this.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.101186767@infradead.org
Extend the static_call infrastructure to optimize the following common
pattern:
if (func_ptr)
func_ptr(args...)
For the trampoline (which is in effect a tail-call), we patch the
JMP.d32 into a RET, which then directly consumes the trampoline call.
For the in-line sites we replace the CALL with a NOP5.
NOTE: this is 'obviously' limited to functions with a 'void' return type.
NOTE: DEFINE_STATIC_COND_CALL() only requires a typename, as opposed
to a full function.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.042977182@infradead.org
Future patches will need to poke a RET instruction, provide the
infrastructure required for this.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20200818135804.982214828@infradead.org
Add the inline static call implementation for x86-64. The generated code
is identical to the out-of-line case, except we move the trampoline into
it's own section.
Objtool uses the trampoline naming convention to detect all the call
sites. It then annotates those call sites in the .static_call_sites
section.
During boot (and module init), the call sites are patched to call
directly into the destination function. The temporary trampoline is
then no longer used.
[peterz: merged trampolines, put trampoline in section]
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.864271425@infradead.org
Add the x86 out-of-line static call implementation. For each key, a
permanent trampoline is created which is the destination for all static
calls for the given key. The trampoline has a direct jump which gets
patched by static_call_update() when the destination function changes.
[peterz: fixed trampoline, rewrote patching code]
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.804315175@infradead.org
Similar to how we disallow kprobes on any other dynamic text
(ftrace/jump_label) also disallow kprobes on inline static_call()s.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200818135804.744920586@infradead.org
The .comment section doesn't belong in STABS_DEBUG. Split it out into a
new macro named ELF_DETAILS. This will gain other non-debug sections
that need to be accounted for when linking with --orphan-handling=warn.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/r/20200821194310.3089815-5-keescook@chromium.org
TSX suspend load tracking instruction is supported by the Intel uarch
Sapphire Rapids. It aims to give a way to choose which memory accesses
do not need to be tracked in the TSX read set. It's availability is
indicated as CPUID.(EAX=7,ECX=0):EDX[bit 16].
Expose TSX Suspend Load Address Tracking feature in KVM CPUID, so KVM
could pass this information to guests and they can make use of this
feature accordingly.
Signed-off-by: Cathy Zhang <cathy.zhang@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/1598316478-23337-3-git-send-email-cathy.zhang@intel.com
- Move disabling of the local APIC after invoking fixup_irqs() to ensure
that interrupts which are incoming are noted in the IRR and not ignored.
- Unbreak affinity setting. The rework of the entry code reused the
regular exception entry code for device interrupts. The vector number is
pushed into the errorcode slot on the stack which is then lifted into an
argument and set to -1 because that's regs->orig_ax which is used in
quite some places to check whether the entry came from a syscall. But it
was overlooked that orig_ax is used in the affinity cleanup code to
validate whether the interrupt has arrived on the new target. It turned
out that this vector check is pointless because interrupts are never
moved from one vector to another on the same CPU. That check is a
historical leftover from the time where x86 supported multi-CPU
affinities, but not longer needed with the now strict single CPU
affinity. Famous last words ...
- Add a missing check for an empty cpumask into the matrix allocator. The
affinity change added a warning to catch the case where an interrupt is
moved on the same CPU to a different vector. This triggers because a
condition with an empty cpumask returns an assignment from the allocator
as the allocator uses for_each_cpu() without checking the cpumask for
being empty. The historical inconsistent for_each_cpu() behaviour of
ignoring the cpumask and unconditionally claiming that CPU0 is in the
mask striked again. Sigh.
-----BEGIN PGP SIGNATURE-----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=zIi4
-----END PGP SIGNATURE-----
Merge tag 'x86-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Thomas Gleixner:
"Three interrupt related fixes for X86:
- Move disabling of the local APIC after invoking fixup_irqs() to
ensure that interrupts which are incoming are noted in the IRR and
not ignored.
- Unbreak affinity setting.
The rework of the entry code reused the regular exception entry
code for device interrupts. The vector number is pushed into the
errorcode slot on the stack which is then lifted into an argument
and set to -1 because that's regs->orig_ax which is used in quite
some places to check whether the entry came from a syscall.
But it was overlooked that orig_ax is used in the affinity cleanup
code to validate whether the interrupt has arrived on the new
target. It turned out that this vector check is pointless because
interrupts are never moved from one vector to another on the same
CPU. That check is a historical leftover from the time where x86
supported multi-CPU affinities, but not longer needed with the now
strict single CPU affinity. Famous last words ...
- Add a missing check for an empty cpumask into the matrix allocator.
The affinity change added a warning to catch the case where an
interrupt is moved on the same CPU to a different vector. This
triggers because a condition with an empty cpumask returns an
assignment from the allocator as the allocator uses for_each_cpu()
without checking the cpumask for being empty. The historical
inconsistent for_each_cpu() behaviour of ignoring the cpumask and
unconditionally claiming that CPU0 is in the mask struck again.
Sigh.
plus a new entry into the MAINTAINER file for the HPE/UV platform"
* tag 'x86-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq/matrix: Deal with the sillyness of for_each_cpu() on UP
x86/irq: Unbreak interrupt affinity setting
x86/hotplug: Silence APIC only after all interrupts are migrated
MAINTAINERS: Add entry for HPE Superdome Flex (UV) maintainers
- Prevent recursion by using raw_cpu_* operations
- Fixup the interrupt state in the cpu idle code to be consistent
- Push rcu_idle_enter/exit() invocations deeper into the idle path so
that the lock operations are inside the RCU watching sections
- Move trace_cpu_idle() into generic code so it's called before RCU goes
idle.
- Handle raw_local_irq* vs. local_irq* operations correctly
- Move the tracepoints out from under the lockdep recursion handling
which turned out to be fragile and inconsistent.
-----BEGIN PGP SIGNATURE-----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=Hgt6
-----END PGP SIGNATURE-----
Merge tag 'locking-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking fixes from Thomas Gleixner:
"A set of fixes for lockdep, tracing and RCU:
- Prevent recursion by using raw_cpu_* operations
- Fixup the interrupt state in the cpu idle code to be consistent
- Push rcu_idle_enter/exit() invocations deeper into the idle path so
that the lock operations are inside the RCU watching sections
- Move trace_cpu_idle() into generic code so it's called before RCU
goes idle.
- Handle raw_local_irq* vs. local_irq* operations correctly
- Move the tracepoints out from under the lockdep recursion handling
which turned out to be fragile and inconsistent"
* tag 'locking-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
lockdep,trace: Expose tracepoints
lockdep: Only trace IRQ edges
mips: Implement arch_irqs_disabled()
arm64: Implement arch_irqs_disabled()
nds32: Implement arch_irqs_disabled()
locking/lockdep: Cleanup
x86/entry: Remove unused THUNKs
cpuidle: Move trace_cpu_idle() into generic code
cpuidle: Make CPUIDLE_FLAG_TLB_FLUSHED generic
sched,idle,rcu: Push rcu_idle deeper into the idle path
cpuidle: Fixup IRQ state
lockdep: Use raw_cpu_*() for per-cpu variables
Intel TSX suspend load tracking instructions aim to give a way to choose
which memory accesses do not need to be tracked in the TSX read set. Add
TSX suspend load tracking CPUID feature flag TSXLDTRK for enumeration.
A processor supports Intel TSX suspend load address tracking if
CPUID.0x07.0x0:EDX[16] is present. Two instructions XSUSLDTRK, XRESLDTRK
are available when this feature is present.
The CPU feature flag is shown as "tsxldtrk" in /proc/cpuinfo.
Signed-off-by: Kyung Min Park <kyung.min.park@intel.com>
Signed-off-by: Cathy Zhang <cathy.zhang@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/1598316478-23337-2-git-send-email-cathy.zhang@intel.com
Remove asm/io_apic.h which is included more than once.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Link: https://lkml.kernel.org/r/20200819112910.7629-1-wanghai38@huawei.com
Several people reported that 5.8 broke the interrupt affinity setting
mechanism.
The consolidation of the entry code reused the regular exception entry code
for device interrupts and changed the way how the vector number is conveyed
from ptregs->orig_ax to a function argument.
The low level entry uses the hardware error code slot to push the vector
number onto the stack which is retrieved from there into a function
argument and the slot on stack is set to -1.
The reason for setting it to -1 is that the error code slot is at the
position where pt_regs::orig_ax is. A positive value in pt_regs::orig_ax
indicates that the entry came via a syscall. If it's not set to a negative
value then a signal delivery on return to userspace would try to restart a
syscall. But there are other places which rely on pt_regs::orig_ax being a
valid indicator for syscall entry.
But setting pt_regs::orig_ax to -1 has a nasty side effect vs. the
interrupt affinity setting mechanism, which was overlooked when this change
was made.
Moving interrupts on x86 happens in several steps. A new vector on a
different CPU is allocated and the relevant interrupt source is
reprogrammed to that. But that's racy and there might be an interrupt
already in flight to the old vector. So the old vector is preserved until
the first interrupt arrives on the new vector and the new target CPU. Once
that happens the old vector is cleaned up, but this cleanup still depends
on the vector number being stored in pt_regs::orig_ax, which is now -1.
That -1 makes the check for cleanup: pt_regs::orig_ax == new_vector
always false. As a consequence the interrupt is moved once, but then it
cannot be moved anymore because the cleanup of the old vector never
happens.
There would be several ways to convey the vector information to that place
in the guts of the interrupt handling, but on deeper inspection it turned
out that this check is pointless and a leftover from the old affinity model
of X86 which supported multi-CPU affinities. Under this model it was
possible that an interrupt had an old and a new vector on the same CPU, so
the vector match was required.
Under the new model the effective affinity of an interrupt is always a
single CPU from the requested affinity mask. If the affinity mask changes
then either the interrupt stays on the CPU and on the same vector when that
CPU is still in the new affinity mask or it is moved to a different CPU, but
it is never moved to a different vector on the same CPU.
Ergo the cleanup check for the matching vector number is not required and
can be removed which makes the dependency on pt_regs:orig_ax go away.
The remaining check for new_cpu == smp_processsor_id() is completely
sufficient. If it matches then the interrupt was successfully migrated and
the cleanup can proceed.
For paranoia sake add a warning into the vector assignment code to
validate that the assumption of never moving to a different vector on
the same CPU holds.
Fixes: 633260fa14 ("x86/irq: Convey vector as argument and not in ptregs")
Reported-by: Alex bykov <alex.bykov@scylladb.com>
Reported-by: Avi Kivity <avi@scylladb.com>
Reported-by: Alexander Graf <graf@amazon.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Alexander Graf <graf@amazon.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/87wo1ltaxz.fsf@nanos.tec.linutronix.de
There is a race when taking a CPU offline. Current code looks like this:
native_cpu_disable()
{
...
apic_soft_disable();
/*
* Any existing set bits for pending interrupt to
* this CPU are preserved and will be sent via IPI
* to another CPU by fixup_irqs().
*/
cpu_disable_common();
{
....
/*
* Race window happens here. Once local APIC has been
* disabled any new interrupts from the device to
* the old CPU are lost
*/
fixup_irqs(); // Too late to capture anything in IRR.
...
}
}
The fix is to disable the APIC *after* cpu_disable_common().
Testing was done with a USB NIC that provided a source of frequent
interrupts. A script migrated interrupts to a specific CPU and
then took that CPU offline.
Fixes: 60dcaad573 ("x86/hotplug: Silence APIC and NMI when CPU is dead")
Reported-by: Evan Green <evgreen@chromium.org>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Tested-by: Evan Green <evgreen@chromium.org>
Reviewed-by: Evan Green <evgreen@chromium.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/lkml/875zdarr4h.fsf@nanos.tec.linutronix.de/
Link: https://lore.kernel.org/r/1598501530-45821-1-git-send-email-ashok.raj@intel.com
A long time ago, Linux cleared IA32_MCG_STATUS at the very end of machine
check processing.
Then, some fancy recovery and IST manipulation was added in:
d4812e169d ("x86, mce: Get rid of TIF_MCE_NOTIFY and associated mce tricks")
and clearing IA32_MCG_STATUS was pulled earlier in the function.
Next change moved the actual recovery out of do_machine_check() and
just used task_work_add() to schedule it later (before returning to the
user):
5567d11c21 ("x86/mce: Send #MC singal from task work")
Most recently the fancy IST footwork was removed as no longer needed:
b052df3da8 ("x86/entry: Get rid of ist_begin/end_non_atomic()")
At this point there is no reason remaining to clear IA32_MCG_STATUS early.
It can move back to the very end of the function.
Also move sync_core(). The comments for this function say that it should
only be called when instructions have been changed/re-mapped. Recovery
for an instruction fetch may change the physical address. But that
doesn't happen until the scheduled work runs (which could be on another
CPU).
[ bp: Massage commit message. ]
Reported-by: Gabriele Paoloni <gabriele.paoloni@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200824221237.5397-1-tony.luck@intel.com
Early Intel hardware implementations of Memory Bandwidth Allocation (MBA)
could only control bandwidth at the processor core level. This meant that
when two processes with different bandwidth allocations ran simultaneously
on the same core the hardware had to resolve this difference. It did so by
applying the higher throttling value (lower bandwidth) to both processes.
Newer implementations can apply different throttling values to each
thread on a core.
Introduce a new resctrl file, "thread_throttle_mode", on Intel systems
that shows to the user how throttling values are allocated, per-core or
per-thread.
On systems that support per-core throttling, the file will display "max".
On newer systems that support per-thread throttling, the file will display
"per-thread".
AMD confirmed in [1] that AMD bandwidth allocation is already at thread
level but that the AMD implementation does not use a memory delay
throttle mode. So to avoid confusion the thread throttling mode would be
UNDEFINED on AMD systems and the "thread_throttle_mode" file will not be
visible.
Originally-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/1598296281-127595-3-git-send-email-fenghua.yu@intel.com
Link: [1] https://lore.kernel.org/lkml/18d277fd-6523-319c-d560-66b63ff606b8@amd.com
Some systems support per-thread Memory Bandwidth Allocation (MBA) which
applies a throttling delay value to each hardware thread instead of to
a core. Per-thread MBA is enumerated by CPUID.
No feature flag is shown in /proc/cpuinfo. User applications need to
check a resctrl throttling mode info file to know if the feature is
supported.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/1598296281-127595-2-git-send-email-fenghua.yu@intel.com
Unused remnants
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Marco Elver <elver@google.com>
Link: https://lkml.kernel.org/r/20200821085348.487040689@infradead.org
Remove trace_cpu_idle() from the arch_cpu_idle() implementations and
put it in the generic code, right before disabling RCU. Gets rid of
more trace_*_rcuidle() users.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Marco Elver <elver@google.com>
Link: https://lkml.kernel.org/r/20200821085348.428433395@infradead.org
This allows moving the leave_mm() call into generic code before
rcu_idle_enter(). Gets rid of more trace_*_rcuidle() users.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Marco Elver <elver@google.com>
Link: https://lkml.kernel.org/r/20200821085348.369441600@infradead.org
ptrace and prctl() are not really fast paths to warrant the use of
static_cpu_has() and cause alternatives patching for no good reason.
Replace with boot_cpu_has() which is simple and fast enough.
No functional changes.
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200818103715.32736-1-bp@alien8.de
path and unconditionally uses LSL to retrieve the CPU number. RDPID depends
on MSR_TSX_AUX. KVM has an optmization to avoid expensive MRS read/writes
on VMENTER/EXIT. It caches the MSR values and restores them either when
leaving the run loop, on preemption or when going out to user
space. MSR_TSX_AUX is part of that lazy MSR set, so after writing the guest
value and before the lazy restore any exception using the paranoid entry
will read the guest value and use it as CPU number to retrieve the GSBASE
value for the current CPU when FSGSBASE is enabled. As RDPID is only used
in that particular entry path, there is no reason to burden VMENTER/EXIT
with two extra MSR writes. Remove the RDPID optimization, which is not even
backed by numbers from the paranoid entry path instead.
-----BEGIN PGP SIGNATURE-----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=AEel
-----END PGP SIGNATURE-----
Merge tag 'x86-urgent-2020-08-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fix from Thomas Gleixner:
"A single fix for x86 which removes the RDPID usage from the paranoid
entry path and unconditionally uses LSL to retrieve the CPU number.
RDPID depends on MSR_TSX_AUX. KVM has an optmization to avoid
expensive MRS read/writes on VMENTER/EXIT. It caches the MSR values
and restores them either when leaving the run loop, on preemption or
when going out to user space. MSR_TSX_AUX is part of that lazy MSR
set, so after writing the guest value and before the lazy restore any
exception using the paranoid entry will read the guest value and use
it as CPU number to retrieve the GSBASE value for the current CPU when
FSGSBASE is enabled. As RDPID is only used in that particular entry
path, there is no reason to burden VMENTER/EXIT with two extra MSR
writes. Remove the RDPID optimization, which is not even backed by
numbers from the paranoid entry path instead"
* tag 'x86-urgent-2020-08-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/entry/64: Do not use RDPID in paranoid entry to accomodate KVM
