| Age | Commit message (Collapse) | Author |
|---|
|
The commit 8617a5c5bc00 ("powerpc/dma: handle iommu bypass in
dma_iommu_ops") merged direct DMA ops into the IOMMU DMA ops allowing
SWIOTLB as well but only for mapping; the unmapping and bouncing parts
were left unmodified.
This adds missing direct unmapping calls to .unmap_page() and
.unmap_sg().
This adds missing sync callbacks and directs them to the direct DMA
hooks.
Fixes: 8617a5c5bc00 ("powerpc/dma: handle iommu bypass in dma_iommu_ops")
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Use the dma_get_mask() helper from dma-mapping.h instead, as they are
functionally identical.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
If you compile with KVM but without CONFIG_HAVE_HW_BREAKPOINT you fail
at linking with:
arch/powerpc/kvm/book3s_hv_rmhandlers.o:(.text+0x708): undefined reference to `dawr_force_enable'
This was caused by commit c1fe190c0672 ("powerpc: Add force enable of
DAWR on P9 option").
This moves a bunch of code around to fix this. It moves a lot of the
DAWR code in a new file and creates a new CONFIG_PPC_DAWR to enable
compiling it.
Fixes: c1fe190c0672 ("powerpc: Add force enable of DAWR on P9 option")
Signed-off-by: Michael Neuling <mikey@neuling.org>
[mpe: Minor formatting in set_dawr()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
In commit c1fe190c0672 ("powerpc: Add force enable of DAWR on P9
option") the following piece of code was added:
smp_call_function((smp_call_func_t)set_dawr, &null_brk, 0);
Since GCC 8 this triggers the following warning about incompatible
function types:
arch/powerpc/kernel/hw_breakpoint.c:408:21: error: cast between incompatible function types from 'int (*)(struct arch_hw_breakpoint *)' to 'void (*)(void *)' [-Werror=cast-function-type]
Since the warning is there for a reason, and should not be hidden behind
a cast, provide an intermediate callback function to avoid the warning.
Fixes: c1fe190c0672 ("powerpc: Add force enable of DAWR on P9 option")
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Mathieu Malaterre <malat@debian.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
ISA v3.0 radix modes provide SLBIA variants which can invalidate ERAT
for effPID!=0 or for effLPID!=0, which allows user and guest
invalidations to retain kernel/host ERAT entries.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
This makes it clear to the caller that it can only be used on POWER9
and later CPUs.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Use "ISA_3_0" rather than "ARCH_300"]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Branch to the relocated 0xc000 address early (still in real mode), to
simplify subsequent branches. Have the virt mode handler avoid just
'windup' and redo the exception from scratch, rather than branching
back to the trampoline.
Rearrange the stack setup instruction location to match the system
reset handler (e.g., right before EXCEPTION_PROLOG_COMMON).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
No code change.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Follow convention and move tramp ahead of common.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
The idle wake up code in the system reset interrupt is not very
optimal. There are two requirements: perform idle wake up quickly;
and save everything including CFAR for non-idle interrupts, with
no performance requirement.
The problem with placing the idle test in the middle of the handler
and using the normal handler code to save CFAR, is that it's quite
costly (e.g., mfcfar is serialising, speculative workarounds get
applied, SRR1 has to be reloaded, etc). It also prevents the standard
interrupt handler boilerplate being used.
This pain can be avoided by using a dedicated idle interrupt handler
at the start of the interrupt handler, which restores all registers
back to the way they were in case it was not an idle wake up. CFAR
is preserved without saving it before the non-idle case by making that
the fall-through, and idle is a taken branch.
Performance seems to be in the noise, but possibly around 0.5% faster,
the executed instructions certainly look better. The bigger benefit is
being able to drop in standard interrupt handlers after the idle code,
which helps with subsequent cleanup and consolidation.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fixup BE by using DOTSYM for idle_return_gpr_loss call]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci into arm/fixes
This set of patches fixes regressions introduced in v5.2 kernel when DA8xx
OHCI driver was converted over to use GPIO regulators.
* tag 'davinci-fixes-for-v5.2-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci:
ARM: davinci: da830-evm: fix GPIO lookup for OHCI
ARM: davinci: omapl138-hawk: add missing regulator constraints for OHCI
ARM: davinci: da830-evm: add missing regulator constraints for OHCI
+ Linux 5.2-rc7
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
Kcov fails to start when compiled with kcov. Disable KCOV on
arch/uml/kernel/skas.
$ gdb -q -ex r ./vmlinux
Program received signal SIGSEGV, Segmentation fault.
check_kcov_mode (t=<>, needed_mode=<>) at kernel/kcov.c:70
70 mode = READ_ONCE(t->kcov_mode);
Signed-off-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
Remove the CONFIG_UEVENT_HELPER_PATH because:
1. It is disabled since commit 1be01d4a5714 ("driver: base: Disable
CONFIG_UEVENT_HELPER by default") as its dependency (UEVENT_HELPER) was
made default to 'n',
2. It is not recommended (help message: "This should not be used today
[...] creates a high system load") and was kept only for ancient
userland,
3. Certain userland specifically requests it to be disabled (systemd
README: "Legacy hotplug slows down the system and confuses udev").
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
Sometimes it can be useful to run with "time travel" inside the
UML instance, for example for testing. For example, some tests
for the wireless subsystem and userspace are based on hwsim, a
virtual wireless adapter. Some tests can take a long time to
run because they e.g. wait for 120 seconds to elapse for some
regulatory checks. This obviously goes faster if it need not
actually wait that long, but time inside the test environment
just "bumps up" when there's nothing to do.
Add CONFIG_UML_TIME_TRAVEL_SUPPORT to enable code to support
such modes at runtime, selected on the command line:
* just "time-travel", in which time inside the UML instance
can move faster than real time, if there's nothing to do
* "time-travel=inf-cpu" in which time also moves slower and
any CPU processing takes no time at all, which allows to
implement consistent behaviour regardless of host CPU load
(or speed) or debug overhead.
An additional "time-travel-start=<seconds>" parameter is also
supported in this case to start the wall clock at this time
(in unix epoch).
With this enabled, the test mentioned above goes from a runtime
of about 140 seconds (with startup overhead and all) to being
CPU bound and finishing in 15 seconds (on my slow laptop).
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
This makes the code clearer and lets the time travel patch have
the actual time used for these functions in just one place.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
This file just contains two unused prototypes, remove it.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
My previous commit didn't actually address the whole issue with
lockdep shutdown, I had another local modification that disabled
lockdep but that wasn't sufficient alone, so had to do the other
change.
Another issue remained though - during kfree() we acquire locks
and lockdep tries to annotate those with exactly the same issue
in the other patch - we no longer have "current".
So, just remove the garbage collection. There's no value in it
anyway since we're going to shut down anyway and marking a slab
object as free is now not very useful anymore.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
When we get into activate_mm(), lockdep complains that we're doing
something strange:
WARNING: possible circular locking dependency detected
5.1.0-10252-gb00152307319-dirty #121 Not tainted
------------------------------------------------------
inside.sh/366 is trying to acquire lock:
(____ptrval____) (&(&p->alloc_lock)->rlock){+.+.}, at: flush_old_exec+0x703/0x8d7
but task is already holding lock:
(____ptrval____) (&mm->mmap_sem){++++}, at: flush_old_exec+0x6c5/0x8d7
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&mm->mmap_sem){++++}:
[...]
__lock_acquire+0x12ab/0x139f
lock_acquire+0x155/0x18e
down_write+0x3f/0x98
flush_old_exec+0x748/0x8d7
load_elf_binary+0x2ca/0xddb
[...]
-> #0 (&(&p->alloc_lock)->rlock){+.+.}:
[...]
__lock_acquire+0x12ab/0x139f
lock_acquire+0x155/0x18e
_raw_spin_lock+0x30/0x83
flush_old_exec+0x703/0x8d7
load_elf_binary+0x2ca/0xddb
[...]
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&mm->mmap_sem);
lock(&(&p->alloc_lock)->rlock);
lock(&mm->mmap_sem);
lock(&(&p->alloc_lock)->rlock);
*** DEADLOCK ***
2 locks held by inside.sh/366:
#0: (____ptrval____) (&sig->cred_guard_mutex){+.+.}, at: __do_execve_file+0x12d/0x869
#1: (____ptrval____) (&mm->mmap_sem){++++}, at: flush_old_exec+0x6c5/0x8d7
stack backtrace:
CPU: 0 PID: 366 Comm: inside.sh Not tainted 5.1.0-10252-gb00152307319-dirty #121
Stack:
[...]
Call Trace:
[<600420de>] show_stack+0x13b/0x155
[<6048906b>] dump_stack+0x2a/0x2c
[<6009ae64>] print_circular_bug+0x332/0x343
[<6009c5c6>] check_prev_add+0x669/0xdad
[<600a06b4>] __lock_acquire+0x12ab/0x139f
[<6009f3d0>] lock_acquire+0x155/0x18e
[<604a07e0>] _raw_spin_lock+0x30/0x83
[<60151e6a>] flush_old_exec+0x703/0x8d7
[<601a8eb8>] load_elf_binary+0x2ca/0xddb
[...]
I think it's because in exec_mmap() we have
down_read(&old_mm->mmap_sem);
...
task_lock(tsk);
...
activate_mm(active_mm, mm);
(which does down_write(&mm->mmap_sem))
I'm not really sure why lockdep throws in the whole knowledge
about the task lock, but it seems that old_mm and mm shouldn't
ever be the same (and it doesn't deadlock) so tell lockdep that
they're different.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
Not only does the locking contradict the comment, and as
the comment says is pointless and actually harmful (all
the actual OS threads have exited already), but it also
causes crashes when lockdep is enabled, because calling
into the spinlock calls into lockdep, which then tries
to determine the current task, which no longer exists.
Remove the locking to let UML shut down cleanly in case
lockdep is enabled.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
There are some unused functions, and some others that have
unused arguments; clean up the timer code a bit.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
os_timer_one_shot() gets passed a value "unsigned long delta",
so must not have an "int ticks" as that actually ends up being
-1, and thus triggering a timer over and over again.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
The conversion of UML to use epoll based IRQ controller claimed that
clone_one_chan() can safely call um_free_irq() while starting to ignore
the delay_free_irq parameter that explicitly noted that the IRQ cannot
be freed because this is being called from chan_interrupt(). This
resulted in free_irq() getting called in interrupt context ("Trying to
free IRQ 6 from IRQ context!").
Fix this by restoring previously used delay_free_irq processing.
Fixes: ff6a17989c08 ("Epoll based IRQ controller")
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
|
|
ftrace_arch_code_modify_post_process() and ftrace_arch_code_modify_prepare()
ftrace_arch_code_modify_prepare() is acquiring text_mutex, while the
corresponding release is happening in ftrace_arch_code_modify_post_process().
This has already been documented in the code, but let's also make the fact
that this is intentional clear to the semantic analysis tools such as sparse.
Link: http://lkml.kernel.org/r/nycvar.YFH.7.76.1906292321170.27227@cbobk.fhfr.pm
Fixes: 39611265edc1a ("ftrace/x86: Add a comment to why we take text_mutex in ftrace_arch_code_modify_prepare()")
Fixes: d5b844a2cf507 ("ftrace/x86: Remove possible deadlock between register_kprobe() and ftrace_run_update_code()")
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Add a flags field to struct dev_pagemap to replace the altmap_valid
boolean to be a little more extensible. Also add a pgmap_altmap() helper
to find the optional altmap and clean up the code using the altmap using
it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Thomas reported that:
| Background:
|
| In preparation of supporting IPI shorthands I changed the CPU offline
| code to software disable the local APIC instead of just masking it.
| That's done by clearing the APIC_SPIV_APIC_ENABLED bit in the APIC_SPIV
| register.
|
| Failure:
|
| When the CPU comes back online the startup code triggers occasionally
| the warning in apic_pending_intr_clear(). That complains that the IRRs
| are not empty.
|
| The offending vector is the local APIC timer vector who's IRR bit is set
| and stays set.
|
| It took me quite some time to reproduce the issue locally, but now I can
| see what happens.
|
| It requires apicv_enabled=0, i.e. full apic emulation. With apicv_enabled=1
| (and hardware support) it behaves correctly.
|
| Here is the series of events:
|
| Guest CPU
|
| goes down
|
| native_cpu_disable()
|
| apic_soft_disable();
|
| play_dead()
|
| ....
|
| startup()
|
| if (apic_enabled())
| apic_pending_intr_clear() <- Not taken
|
| enable APIC
|
| apic_pending_intr_clear() <- Triggers warning because IRR is stale
|
| When this happens then the deadline timer or the regular APIC timer -
| happens with both, has fired shortly before the APIC is disabled, but the
| interrupt was not serviced because the guest CPU was in an interrupt
| disabled region at that point.
|
| The state of the timer vector ISR/IRR bits:
|
| ISR IRR
| before apic_soft_disable() 0 1
| after apic_soft_disable() 0 1
|
| On startup 0 1
|
| Now one would assume that the IRR is cleared after the INIT reset, but this
| happens only on CPU0.
|
| Why?
|
| Because our CPU0 hotplug is just for testing to make sure nothing breaks
| and goes through an NMI wakeup vehicle because INIT would send it through
| the boots-trap code which is not really working if that CPU was not
| physically unplugged.
|
| Now looking at a real world APIC the situation in that case is:
|
| ISR IRR
| before apic_soft_disable() 0 1
| after apic_soft_disable() 0 1
|
| On startup 0 0
|
| Why?
|
| Once the dying CPU reenables interrupts the pending interrupt gets
| delivered as a spurious interupt and then the state is clear.
|
| While that CPU0 hotplug test case is surely an esoteric issue, the APIC
| emulation is still wrong, Even if the play_dead() code would not enable
| interrupts then the pending IRR bit would turn into an ISR .. interrupt
| when the APIC is reenabled on startup.
From SDM 10.4.7.2 Local APIC State After It Has Been Software Disabled
* Pending interrupts in the IRR and ISR registers are held and require
masking or handling by the CPU.
In Thomas's testing, hardware cpu will not respect soft disable LAPIC
when IRR has already been set or APICv posted-interrupt is in flight,
so we can skip soft disable APIC checking when clearing IRR and set ISR,
continue to respect soft disable APIC when attempting to set IRR.
Reported-by: Rong Chen <rong.a.chen@intel.com>
Reported-by: Feng Tang <feng.tang@intel.com>
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rong Chen <rong.a.chen@intel.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Currently KVM_STATE_NESTED_EVMCS is used to signal that eVMCS
capability is enabled on vCPU.
As indicated by vmx->nested.enlightened_vmcs_enabled.
This is quite bizarre as userspace VMM should make sure to expose
same vCPU with same CPUID values in both source and destination.
In case vCPU is exposed with eVMCS support on CPUID, it is also
expected to enable KVM_CAP_HYPERV_ENLIGHTENED_VMCS capability.
Therefore, KVM_STATE_NESTED_EVMCS is redundant.
KVM_STATE_NESTED_EVMCS is currently used on restore path
(vmx_set_nested_state()) only to enable eVMCS capability in KVM
and to signal need_vmcs12_sync such that on next VMEntry to guest
nested_sync_from_vmcs12() will be called to sync vmcs12 content
into eVMCS in guest memory.
However, because restore nested-state is rare enough, we could
have just modified vmx_set_nested_state() to always signal
need_vmcs12_sync.
From all the above, it seems that we could have just removed
the usage of KVM_STATE_NESTED_EVMCS. However, in order to preserve
backwards migration compatibility, we cannot do that.
(vmx_get_nested_state() needs to signal flag when migrating from
new kernel to old kernel).
Returning KVM_STATE_NESTED_EVMCS when just vCPU have eVMCS enabled
have a bad side-effect of userspace VMM having to send nested-state
from source to destination as part of migration stream. Even if
guest have never used eVMCS as it doesn't even run a nested
hypervisor workload. This requires destination userspace VMM and
KVM to support setting nested-state. Which make it more difficult
to migrate from new host to older host.
To avoid this, change KVM_STATE_NESTED_EVMCS to signal eVMCS is
not only enabled but also active. i.e. Guest have made some
eVMCS active via an enlightened VMEntry. i.e. vmcs12 is copied
from eVMCS and therefore should be restored into eVMCS resident
in memory (by copy_vmcs12_to_enlightened()).
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maran Wilson <maran.wilson@oracle.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
As comment in code specifies, SMM temporarily disables VMX so we cannot
be in guest mode, nor can VMLAUNCH/VMRESUME be pending.
However, code currently assumes that these are the only flags that can be
set on kvm_state->flags. This is not true as KVM_STATE_NESTED_EVMCS
can also be set on this field to signal that eVMCS should be enabled.
Therefore, fix code to check for guest-mode and pending VMLAUNCH/VMRESUME
explicitly.
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This warning can be triggered easily by userspace, so it should certainly not
cause a panic if panic_on_warn is set.
Reported-by: syzbot+c03f30b4f4c46bdf8575@syzkaller.appspotmail.com
Suggested-by: Alexander Potapenko <glider@google.com>
Acked-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This bit is purely advisory. Passing it through to the guest indicates
that the virtual processor, like the physical processor, prefers that
STIBP is only set once during boot and not changed.
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When L0 is executing handle_invept(), the TDP MMU is active. Emulating
an L1 INVEPT does require synchronizing the appropriate shadow EPT
root(s), but a call to kvm_mmu_sync_roots in this context won't do
that. Similarly, the hardware TLB and paging-structure-cache entries
associated with the appropriate shadow EPT root(s) must be flushed,
but requesting a TLB_FLUSH from this context won't do that either.
How did this ever work? KVM always does a sync_roots and TLB flush (in
the correct context) when transitioning from L1 to L2. That isn't the
best choice for nested VM performance, but it effectively papers over
the mistakes here.
Remove the unnecessary operations and leave a comment to try to do
better in the future.
Reported-by: Junaid Shahid <junaids@google.com>
Fixes: bfd0a56b90005f ("nEPT: Nested INVEPT")
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Nadav Har'El <nyh@il.ibm.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>
Cc: Xinhao Xu <xinhao.xu@intel.com>
Cc: Yang Zhang <yang.z.zhang@Intel.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by Peter Shier <pshier@google.com>
Reviewed-by: Junaid Shahid <junaids@google.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Expose PV_SCHED_YIELD feature bit to guest, the guest can check this
feature bit before using paravirtualized sched yield.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The target vCPUs are in runnable state after vcpu_kick and suitable
as a yield target. This patch implements the sched yield hypercall.
17% performance increasement of ebizzy benchmark can be observed in an
over-subscribe environment. (w/ kvm-pv-tlb disabled, testing TLB flush
call-function IPI-many since call-function is not easy to be trigged
by userspace workload).
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When sending a call-function IPI-many to vCPUs, yield if any of
the IPI target vCPUs was preempted, we just select the first
preempted target vCPU which we found since the state of target
vCPUs can change underneath and to avoid race conditions.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When Enlightened VMCS is in use, it is valid to do VMCLEAR and,
according to TLFS, this should "transition an enlightened VMCS from the
active to the non-active state". It is, however, wrong to assume that
it is only valid to do VMCLEAR for the eVMCS which is currently active
on the vCPU performing VMCLEAR.
Currently, the logic in handle_vmclear() is broken: in case, there is no
active eVMCS on the vCPU doing VMCLEAR we treat the argument as a 'normal'
VMCS and kvm_vcpu_write_guest() to the 'launch_state' field irreversibly
corrupts the memory area.
So, in case the VMCLEAR argument is not the current active eVMCS on the
vCPU, how can we know if the area it is pointing to is a normal or an
enlightened VMCS?
Thanks to the bug in Hyper-V (see commit 72aeb60c52bf7 ("KVM: nVMX: Verify
eVMCS revision id match supported eVMCS version on eVMCS VMPTRLD")) we can
not, the revision can't be used to distinguish between them. So let's
assume it is always enlightened in case enlightened vmentry is enabled in
the assist page. Also, check if vmx->nested.enlightened_vmcs_enabled to
minimize the impact for 'unenlightened' workloads.
Fixes: b8bbab928fb1 ("KVM: nVMX: implement enlightened VMPTRLD and VMCLEAR")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Apparently, Windows doesn't maintain clean fields data after it does
VMCLEAR for an enlightened VMCS so we can only use it on VMRESUME.
The issue went unnoticed because currently we do nested_release_evmcs()
in handle_vmclear() and the consecutive enlightened VMPTRLD invalidates
clean fields when a new eVMCS is mapped but we're going to change the
logic.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This allows userspace to know which MSRs are supported by the hypervisor.
Unfortunately userspace must resort to tricks for everything except
MSR_IA32_VMX_VMFUNC (which was just added in the previous patch).
One possibility is to use the feature control MSR, which is tied to nested
VMX as well and is present on all KVM versions that support feature MSRs.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Allow userspace to set a custom value for the VMFUNC controls MSR, as long
as the capabilities it advertises do not exceed those of the host.
Fixes: 27c42a1bb ("KVM: nVMX: Enable VMFUNC for the L1 hypervisor", 2017-08-03)
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Some secondary controls are automatically enabled/disabled based on the CPUID
values that are set for the guest. However, they are still available at a
global level and therefore should be present when KVM_GET_MSRS is sent to
/dev/kvm.
Fixes: 1389309c811 ("KVM: nVMX: expose VMX capabilities for nested hypervisors to userspace", 2018-02-26)
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The fixed regulator driver doesn't specify any con_id for gpio lookup
so it must be NULL in the table entry.
Fixes: 274e4c336192 ("ARM: davinci: da830-evm: add a fixed regulator for ohci-da8xx")
Cc: stable@vger.kernel.org
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
|
|
We need to enable status changes for the fixed power supply for the USB
controller.
Fixes: 1d272894ec4f ("ARM: davinci: omapl138-hawk: add a fixed regulator for ohci-da8xx")
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
|
|
We need to enable status changes for the fixed power supply for the USB
controller.
Fixes: 274e4c336192 ("ARM: davinci: da830-evm: add a fixed regulator for ohci-da8xx")
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
|
|
AP Queue Interruption Control (AQIC) facility gives
the guest the possibility to control interruption for
the Cryptographic Adjunct Processor queues.
Signed-off-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Harald Freudenberger <freude@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
[ Modified while picking: we may not expose STFLE facility 65
unconditionally because AIV is a pre-requirement.]
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
|
|
We prepare the interception of the PQAP/AQIC instruction for
the case the AQIC facility is enabled in the guest.
First of all we do not want to change existing behavior when
intercepting AP instructions without the SIE allowing the guest
to use AP instructions.
In this patch we only handle the AQIC interception allowed by
facility 65 which will be enabled when the complete interception
infrastructure will be present.
We add a callback inside the KVM arch structure for s390 for
a VFIO driver to handle a specific response to the PQAP
instruction with the AQIC command and only this command.
But we want to be able to return a correct answer to the guest
even there is no VFIO AP driver in the kernel.
Therefor, we inject the correct exceptions from inside KVM for the
case the callback is not initialized, which happens when the vfio_ap
driver is not loaded.
We do consider the responsibility of the driver to always initialize
the PQAP callback if it defines queues by initializing the CRYCB for
a guest.
If the callback has been setup we call it.
If not we setup an answer considering that no queue is available
for the guest when no callback has been setup.
Signed-off-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Harald Freudenberger <freude@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
|
|
Kasan instrumentation of backchain unwinder stack reads is disabled
completely and simply uses READ_ONCE_NOCHECK now.
READ_ONCE_TASK_STACK macro is unused and could be removed.
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
|
|
Avoid kasan false positive when current task is interrupted in-between
stack frame allocation and backchain write instructions leaving new stack
frame backchain invalid. In particular if backchain is 0 the unwinder
tries to read pt_regs from the stack and might hit kasan poisoned bytes,
leading to kasan "stack-out-of-bounds" report.
Disable kasan instrumentation of unwinder stack reads, since this
limitation couldn't be handled otherwise with current backchain unwinder
implementation.
Fixes: 78c98f907413 ("s390/unwind: introduce stack unwind API")
Reported-by: Julian Wiedmann <jwi@linux.ibm.com>
Tested-by: Benjamin Block <bblock@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
|
|
The bad stack test in interrupt handlers has a few problems. For
performance it is taken in the common case, which is a fetch bubble
and a waste of i-cache.
For code development and maintainence, it requires yet another stack
frame setup routine, and that constrains all exception handlers to
follow the same register save pattern which inhibits future
optimisation.
Remove the test/branch and replace it with a trap. Teach the program
check handler to use the emergency stack for this case.
This does not result in quite so nice a message, however the SRR0 and
SRR1 of the crashed interrupt can be seen in r11 and r12, as is the
original r1 (adjusted by INT_FRAME_SIZE). These are the most important
parts to debugging the issue.
The original r9-12 and cr0 is lost, which is the main downside.
kernel BUG at linux/arch/powerpc/kernel/exceptions-64s.S:847!
Oops: Exception in kernel mode, sig: 5 [#1]
BE SMP NR_CPUS=2048 NUMA PowerNV
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted
NIP: c000000000009108 LR: c000000000cadbcc CTR: c0000000000090f0
REGS: c0000000fffcbd70 TRAP: 0700 Not tainted
MSR: 9000000000021032 <SF,HV,ME,IR,DR,RI> CR: 28222448 XER: 20040000
CFAR: c000000000009100 IRQMASK: 0
GPR00: 000000000000003d fffffffffffffd00 c0000000018cfb00 c0000000f02b3166
GPR04: fffffffffffffffd 0000000000000007 fffffffffffffffb 0000000000000030
GPR08: 0000000000000037 0000000028222448 0000000000000000 c000000000ca8de0
GPR12: 9000000002009032 c000000001ae0000 c000000000010a00 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
GPR20: c0000000f00322c0 c000000000f85200 0000000000000004 ffffffffffffffff
GPR24: fffffffffffffffe 0000000000000000 0000000000000000 000000000000000a
GPR28: 0000000000000000 0000000000000000 c0000000f02b391c c0000000f02b3167
NIP [c000000000009108] decrementer_common+0x18/0x160
LR [c000000000cadbcc] .vsnprintf+0x3ec/0x4f0
Call Trace:
Instruction dump:
996d098a 994d098b 38610070 480246ed 48005518 60000000 38200000 718a4000
7c2a0b78 3821fd00 41c20008 e82d0970 <0981fd00> f92101a0 f9610170 f9810178
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Since the system reset interrupt began to use its own stack, and
machine check interrupts have done so for some time, r1 can be
changed without clearing MSR[RI], provided no other interrupts
(including SLB misses) are taken.
MSR[RI] does have to be cleared when using SCRATCH0, however.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
No generated code change.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Although the 0x1500 interrupt only applies to bare metal, it is better
to just use the standard macro for scratch save.
Runtime code path remains unchanged (due to instruction patching).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
