The last missing piece to having vmx_l1d_flush() take interrupts after
VMEXIT into account is to set the kvm_cpu_l1tf_flush_l1d per-cpu flag on
irq entry.
Issue calls to kvm_set_cpu_l1tf_flush_l1d() from entering_irq(),
ipi_entering_ack_irq(), smp_reschedule_interrupt() and
uv_bau_message_interrupt().
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Dave Hansen reported, that it's outright dangerous to keep SMT siblings
disabled completely so they are stuck in the BIOS and wait for SIPI.
The reason is that Machine Check Exceptions are broadcasted to siblings and
the soft disabled sibling has CR4.MCE = 0. If a MCE is delivered to a
logical core with CR4.MCE = 0, it asserts IERR#, which shuts down or
reboots the machine. The MCE chapter in the SDM contains the following
blurb:
Because the logical processors within a physical package are tightly
coupled with respect to shared hardware resources, both logical
processors are notified of machine check errors that occur within a
given physical processor. If machine-check exceptions are enabled when
a fatal error is reported, all the logical processors within a physical
package are dispatched to the machine-check exception handler. If
machine-check exceptions are disabled, the logical processors enter the
shutdown state and assert the IERR# signal. When enabling machine-check
exceptions, the MCE flag in control register CR4 should be set for each
logical processor.
Reverting the commit which ignores siblings at enumeration time solves only
half of the problem. The core cpuhotplug logic needs to be adjusted as
well.
This thoughtful engineered mechanism also turns the boot process on all
Intel HT enabled systems into a MCE lottery. MCE is enabled on the boot CPU
before the secondary CPUs are brought up. Depending on the number of
physical cores the window in which this situation can happen is smaller or
larger. On a HSW-EX it's about 750ms:
MCE is enabled on the boot CPU:
[ 0.244017] mce: CPU supports 22 MCE banks
The corresponding sibling #72 boots:
[ 1.008005] .... node #0, CPUs: #72
That means if an MCE hits on physical core 0 (logical CPUs 0 and 72)
between these two points the machine is going to shutdown. At least it's a
known safe state.
It's obvious that the early boot can be hit by an MCE as well and then runs
into the same situation because MCEs are not yet enabled on the boot CPU.
But after enabling them on the boot CPU, it does not make any sense to
prevent the kernel from recovering.
Adjust the nosmt kernel parameter documentation as well.
Reverts: 2207def700 ("x86/apic: Ignore secondary threads if nosmt=force")
Reported-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Tony Luck <tony.luck@intel.com>
nosmt on the kernel command line merely prevents the onlining of the
secondary SMT siblings.
nosmt=force makes the APIC detection code ignore the secondary SMT siblings
completely, so they even do not show up as possible CPUs. That reduces the
amount of memory allocations for per cpu variables and saves other
resources from being allocated too large.
This is not fully equivalent to disabling SMT in the BIOS because the low
level SMT enabling in the BIOS can result in partitioning of resources
between the siblings, which is not undone by just ignoring them. Some CPUs
can use the full resources when their sibling is not onlined, but this is
depending on the CPU family and model and it's not well documented whether
this applies to all partitioned resources. That means depending on the
workload disabling SMT in the BIOS might result in better performance.
Linus analysis of the Intel manual:
The intel optimization manual is not very clear on what the partitioning
rules are.
I find:
"In general, the buffers for staging instructions between major pipe
stages are partitioned. These buffers include µop queues after the
execution trace cache, the queues after the register rename stage, the
reorder buffer which stages instructions for retirement, and the load
and store buffers.
In the case of load and store buffers, partitioning also provided an
easier implementation to maintain memory ordering for each logical
processor and detect memory ordering violations"
but some of that partitioning may be relaxed if the HT thread is "not
active":
"In Intel microarchitecture code name Sandy Bridge, the micro-op queue
is statically partitioned to provide 28 entries for each logical
processor, irrespective of software executing in single thread or
multiple threads. If one logical processor is not active in Intel
microarchitecture code name Ivy Bridge, then a single thread executing
on that processor core can use the 56 entries in the micro-op queue"
but I do not know what "not active" means, and how dynamic it is. Some of
that partitioning may be entirely static and depend on the early BIOS
disabling of HT, and even if we park the cores, the resources will just be
wasted.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
If the CPU is supporting SMT then the primary thread can be found by
checking the lower APIC ID bits for zero. smp_num_siblings is used to build
the mask for the APIC ID bits which need to be taken into account.
This uses the MPTABLE or ACPI/MADT supplied APIC ID, which can be different
than the initial APIC ID in CPUID. But according to AMD the lower bits have
to be consistent. Intel gave a tentative confirmation as well.
Preparatory patch to support disabling SMT at boot/runtime.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
apic_ack_edge() is explicitely for handling interrupt affinity cleanup when
interrupt remapping is not available or disable.
Remapped interrupts and also some of the platform specific special
interrupts, e.g. UV, invoke ack_APIC_irq() directly.
To address the issue of failing an affinity update with -EBUSY the delayed
affinity mechanism can be reused, but ack_APIC_irq() does not handle
that. Adding this to ack_APIC_irq() is not possible, because that function
is also used for exceptions and directly handled interrupts like IPIs.
Create a new function, which just contains the conditional invocation of
irq_move_irq() and the final ack_APIC_irq().
Reuse the new function in apic_ack_edge().
Preparatory change for the real fix.
Fixes: dccfe3147b ("x86/vector: Simplify vector move cleanup")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Song Liu <songliubraving@fb.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <liu.song.a23@gmail.com>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: stable@vger.kernel.org
Cc: Mike Travis <mike.travis@hpe.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Tariq Toukan <tariqt@mellanox.com>
Link: https://lkml.kernel.org/r/20180604162224.471925894@linutronix.de
The APIC ID as parsed from ACPI MADT is validity checked with the
apic->apic_id_valid() callback, which depends on the selected APIC type.
For non X2APIC types APIC IDs >= 0xFF are invalid, but values > 0x7FFFFFFF
are detected as valid. This happens because the 'apicid' argument of the
apic_id_valid() callback is type 'int'. So the resulting comparison
apicid < 0xFF
evaluates to true for all unsigned int values > 0x7FFFFFFF which are handed
to default_apic_id_valid(). As a consequence, invalid APIC IDs in !X2APIC
mode are considered valid and accounted as possible CPUs.
Change the apicid argument type of the apic_id_valid() callback to u32 so
the evaluation is unsigned and returns the correct result.
[ tglx: Massaged changelog ]
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Cc: jgross@suse.com
Cc: Dou Liyang <douly.fnst@cn.fujitsu.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/1523322966-10296-1-git-send-email-lirongqing@baidu.com
There are three places which initialize the interrupt delivery modes:
1) init_bsp_APIC() which is called early might setup the through-local-APIC
virtual wire mode on non SMP systems.
2) In an SMP-capable system, native_smp_prepare_cpus() tries to switch to
symmetric I/O model.
3) In UP system with UP_LATE_INIT=y, the local APIC and I/O APIC are set up
in smp_init().
There is no technical reason to make these initializations at random places
and run the kernel with the potentially wrong mode through the early boot
stage, but it has a problematic side effect: The late switch to symmetric
I/O mode causes dump-capture kernel to hang when the kernel command line
option 'notsc' is active.
Provide a new function to unify that three positions. Preparatory patch to
initialize an interrupt mode directly.
Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: yinghai@kernel.org
Cc: bhe@redhat.com
Link: https://lkml.kernel.org/r/1505293975-26005-3-git-send-email-douly.fnst@cn.fujitsu.com
We want to simplify <linux/sched.h>'s header dependencies, but one
roadblock to that is <asm/apic.h>'s inclusion of pm.h,
which brings in other, problematic headers.
Remove it, as it appears to be entirely spurious, apic.h does not
actually make use of any PM facilities.
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Add __rdmsr() and __wrmsr() which *only* read and write an MSR with
exception handling. Those are going to be used in early code, like the
microcode loader, which cannot stomach tracing code piggybacking on the
MSR operation.
While at it, get rid of __native_write_msr_notrace().
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170120202955.4091-3-bp@alien8.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Pull x86 idle updates from Ingo Molnar:
"There were two bigger changes in this development cycle:
- remove idle notifiers:
32 files changed, 74 insertions(+), 803 deletions(-)
These notifiers were of questionable value and the main usecase,
the i7300 driver, was essentially unmaintained and can be removed,
plus modern power management concepts don't need the callback - so
use this golden opportunity and get rid of this opaque and fragile
callback from a latency sensitive code path.
(Len Brown, Thomas Gleixner)
- improve the AMD Erratum 400 workaround that used high overhead MSR
polling in the idle loop (Borisla Petkov, Thomas Gleixner)"
* 'x86-idle-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86: Remove empty idle.h header
x86/amd: Simplify AMD E400 aware idle routine
x86/amd: Check for the C1E bug post ACPI subsystem init
x86/bugs: Separate AMD E400 erratum and C1E bug
x86/cpufeature: Provide helper to set bugs bits
x86/idle: Remove enter_idle(), exit_idle()
x86: Remove x86_test_and_clear_bit_percpu()
x86/idle: Remove is_idle flag
x86/idle: Remove idle_notifier
i7300_idle: Remove this driver
The following RCU lockdep warning led to adding irq_enter()/irq_exit() into
smp_reschedule_interrupt():
RCU used illegally from idle CPU!
rcu_scheduler_active = 1, debug_locks = 0
RCU used illegally from extended quiescent state!
no locks held by swapper/1/0.
do_trace_write_msr
native_write_msr
native_apic_msr_eoi_write
smp_reschedule_interrupt
reschedule_interrupt
As Peterz pointed out:
| So now we're making a very frequent interrupt slower because of debug
| code.
|
| The thing is, many many smp_reschedule_interrupt() invocations don't
| actually execute anything much at all and are only sent to tickle the
| return to user path (which does the actual preemption).
|
| Having to do the whole irq_enter/irq_exit dance just for this unlikely
| debug case totally blows.
Use the wrmsr_notrace() variant in native_apic_msr_write_eoi, annotate the
kvm variant with notrace and add a native_apic_eoi callback to the apic
structure so KVM guests are covered as well.
This allows to revert the irq_enter/irq_exit dance in
smp_reschedule_interrupt().
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org
Cc: Mike Galbraith <efault@gmx.de>
Cc: Borislav Petkov <bp@alien8.de>
Link: http://lkml.kernel.org/r/1478488420-5982-3-git-send-email-wanpeng.li@hotmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
===============================
[ INFO: suspicious RCU usage. ]
4.8.0-rc6+ #5 Not tainted
-------------------------------
./arch/x86/include/asm/msr-trace.h:47 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
RCU used illegally from idle CPU!
rcu_scheduler_active = 1, debug_locks = 0
RCU used illegally from extended quiescent state!
no locks held by swapper/2/0.
stack backtrace:
CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.8.0-rc6+ #5
Hardware name: Dell Inc. OptiPlex 7020/0F5C5X, BIOS A03 01/08/2015
0000000000000000 ffff8d1bd6003f10 ffffffff94446949 ffff8d1bd4a68000
0000000000000001 ffff8d1bd6003f40 ffffffff940e9247 ffff8d1bbdfcf3d0
000000000000080b 0000000000000000 0000000000000000 ffff8d1bd6003f70
Call Trace:
<IRQ> [<ffffffff94446949>] dump_stack+0x99/0xd0
[<ffffffff940e9247>] lockdep_rcu_suspicious+0xe7/0x120
[<ffffffff9448e0d5>] do_trace_write_msr+0x135/0x140
[<ffffffff9406e750>] native_write_msr+0x20/0x30
[<ffffffff9406503d>] native_apic_msr_eoi_write+0x1d/0x30
[<ffffffff9405b17e>] smp_trace_call_function_interrupt+0x1e/0x270
[<ffffffff948cb1d6>] trace_call_function_interrupt+0x96/0xa0
<EOI> [<ffffffff947200f4>] ? cpuidle_enter_state+0xe4/0x360
[<ffffffff947200df>] ? cpuidle_enter_state+0xcf/0x360
[<ffffffff947203a7>] cpuidle_enter+0x17/0x20
[<ffffffff940df008>] cpu_startup_entry+0x338/0x4d0
[<ffffffff9405bfc4>] start_secondary+0x154/0x180
This can be reproduced readily by running ftrace test case of kselftest.
Move the irq_enter() call before ack_APIC_irq(), because irq_enter() tells
the RCU susbstems to end the extended quiescent state, so that the
following trace call in ack_APIC_irq() works correctly. The same applies to
exiting_ack_irq() which calls ack_APIC_irq() after irq_exit().
[ tglx: Massaged changelog ]
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1474198491-3738-1-git-send-email-wanpeng.li@hotmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This patch eliminates a source of imprecise APIC timer interrupts,
which imprecision may result in double interrupts or even late
interrupts.
The TSC deadline clockevent devices' configuration and registration
happens before the TSC frequency calibration is refined in
tsc_refine_calibration_work().
This results in the TSC clocksource and the TSC deadline clockevent
devices being configured with slightly different frequencies: the former
gets the refined one and the latter are configured with the inaccurate
frequency detected earlier by means of the "Fast TSC calibration using PIT".
Within the APIC code, introduce the notifier function
lapic_update_tsc_freq() which reconfigures all per-CPU TSC deadline
clockevent devices with the current tsc_khz.
Call it from the TSC code after TSC calibration refinement has happened.
Signed-off-by: Nicolai Stange <nicstange@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Christopher S. Hall <christopher.s.hall@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Link: http://lkml.kernel.org/r/20160714152255.18295-3-nicstange@gmail.com
[ Pushed #ifdef CONFIG_X86_LOCAL_APIC into header, improved changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since 4.4, I've been able to trigger this occasionally:
===============================
[ INFO: suspicious RCU usage. ]
4.5.0-rc7-think+ #3 Not tainted
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/20160315012054.GA17765@codemonkey.org.uk
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
-------------------------------
./arch/x86/include/asm/msr-trace.h:47 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
RCU used illegally from idle CPU!
rcu_scheduler_active = 1, debug_locks = 1
RCU used illegally from extended quiescent state!
no locks held by swapper/3/0.
stack backtrace:
CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.5.0-rc7-think+ #3
ffffffff92f821e0 1f3e5c340597d7fc ffff880468e07f10 ffffffff92560c2a
ffff880462145280 0000000000000001 ffff880468e07f40 ffffffff921376a6
ffffffff93665ea0 0000cc7c876d28da 0000000000000005 ffffffff9383dd60
Call Trace:
<IRQ> [<ffffffff92560c2a>] dump_stack+0x67/0x9d
[<ffffffff921376a6>] lockdep_rcu_suspicious+0xe6/0x100
[<ffffffff925ae7a7>] do_trace_write_msr+0x127/0x1a0
[<ffffffff92061c83>] native_apic_msr_eoi_write+0x23/0x30
[<ffffffff92054408>] smp_trace_call_function_interrupt+0x38/0x360
[<ffffffff92d1ca60>] trace_call_function_interrupt+0x90/0xa0
<EOI> [<ffffffff92ac5124>] ? cpuidle_enter_state+0x1b4/0x520
Move the entering_irq() call before ack_APIC_irq(), because entering_irq()
tells the RCU susbstems to end the extended quiescent state, so that the
following trace call in ack_APIC_irq() works correctly.
Suggested-by: Andi Kleen <ak@linux.intel.com>
Fixes: 4787c368a9 "x86/tracing: Add irq_enter/exit() in smp_trace_reschedule_interrupt()"
Signed-off-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Some CONFIG_X86_X2APIC functions, especially x2apic_enabled(), are not
declared if !CONFIG_X86_LOCAL_APIC. However, the same stubs that work
for !CONFIG_X86_X2APIC are okay even if there is no local APIC support
at all.
Avoid the introduction of #ifdefs by moving the x2apic declarations
completely outside the CONFIG_X86_LOCAL_APIC block. (Unfortunately,
diff generation messes up the actual change that this patch makes).
There is no semantic change because CONFIG_X86_X2APIC depends on
CONFIG_X86_LOCAL_APIC.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Feng Wu <feng.wu@intel.com>
Link: http://lkml.kernel.org/r/1443435991-35750-1-git-send-email-pbonzini@redhat.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
smp.c and irq_work.c implement the same inline helper. Move it to
apic.h and use it everywhere.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Pull x86 asm changes from Ingo Molnar:
"There were lots of changes in this development cycle:
- over 100 separate cleanups, restructuring changes, speedups and
fixes in the x86 system call, irq, trap and other entry code, part
of a heroic effort to deobfuscate a decade old spaghetti asm code
and its C code dependencies (Denys Vlasenko, Andy Lutomirski)
- alternatives code fixes and enhancements (Borislav Petkov)
- simplifications and cleanups to the compat code (Brian Gerst)
- signal handling fixes and new x86 testcases (Andy Lutomirski)
- various other fixes and cleanups
By their nature many of these changes are risky - we tried to test
them well on many different x86 systems (there are no known
regressions), and they are split up finely to help bisection - but
there's still a fair bit of residual risk left so caveat emptor"
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (148 commits)
perf/x86/64: Report regs_user->ax too in get_regs_user()
perf/x86/64: Simplify regs_user->abi setting code in get_regs_user()
perf/x86/64: Do report user_regs->cx while we are in syscall, in get_regs_user()
perf/x86/64: Do not guess user_regs->cs, ss, sp in get_regs_user()
x86/asm/entry/32: Tidy up JNZ instructions after TESTs
x86/asm/entry/64: Reduce padding in execve stubs
x86/asm/entry/64: Remove GET_THREAD_INFO() in ret_from_fork
x86/asm/entry/64: Simplify jumps in ret_from_fork
x86/asm/entry/64: Remove a redundant jump
x86/asm/entry/64: Optimize [v]fork/clone stubs
x86/asm/entry: Zero EXTRA_REGS for stub32_execve() too
x86/asm/entry/64: Move stub_x32_execvecloser() to stub_execveat()
x86/asm/entry/64: Use common code for rt_sigreturn() epilogue
x86/asm/entry/64: Add forgotten CFI annotation
x86/asm/entry/irq: Simplify interrupt dispatch table (IDT) layout
x86/asm/entry/64: Move opportunistic sysret code to syscall code path
x86, selftests: Add sigreturn selftest
x86/alternatives: Guard NOPs optimization
x86/asm/entry: Clear EXTRA_REGS for all executable formats
x86/signal: Remove pax argument from restore_sigcontext
...
