I stumbled upon an AMD box that had the BIOS using a hardware performance
counter. Instead of printing out a warning and continuing, it failed and
blocked further perf counter usage.
Looking through the history, I found this commit:
a5ebe0ba3d ("perf/x86: Check all MSRs before passing hw check")
which tweaked the rules for a Xen guest on an almost identical box and now
changed the behaviour.
Unfortunately the rules were tweaked incorrectly and will always lead to
MSR failures even though the MSRs are completely fine.
What happens now is in arch/x86/kernel/cpu/perf_event.c::check_hw_exists():
<snip>
for (i = 0; i < x86_pmu.num_counters; i++) {
reg = x86_pmu_config_addr(i);
ret = rdmsrl_safe(reg, &val);
if (ret)
goto msr_fail;
if (val & ARCH_PERFMON_EVENTSEL_ENABLE) {
bios_fail = 1;
val_fail = val;
reg_fail = reg;
}
}
<snip>
/*
* Read the current value, change it and read it back to see if it
* matches, this is needed to detect certain hardware emulators
* (qemu/kvm) that don't trap on the MSR access and always return 0s.
*/
reg = x86_pmu_event_addr(0);
^^^^
if the first perf counter is enabled, then this routine will always fail
because the counter is running. :-(
if (rdmsrl_safe(reg, &val))
goto msr_fail;
val ^= 0xffffUL;
ret = wrmsrl_safe(reg, val);
ret |= rdmsrl_safe(reg, &val_new);
if (ret || val != val_new)
goto msr_fail;
The above bios_fail used to be a 'goto' which is why it worked in the past.
Further, most vendors have migrated to using fixed counters to hide their
evilness hence this problem rarely shows up now days except on a few old boxes.
I fixed my problem and kept the spirit of the original Xen fix, by recording a
safe non-enable register to be used safely for the reading/writing check.
Because it is not enabled, this passes on bare metal boxes (like metal), but
should continue to throw an msr_fail on Xen guests because the register isn't
emulated yet.
Now I get a proper bios_fail error message and Xen should still see their
msr_fail message (untested).
Signed-off-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: george.dunlap@eu.citrix.com
Cc: konrad.wilk@oracle.com
Link: http://lkml.kernel.org/r/1431976608-56970-1-git-send-email-dzickus@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The (SNB/IVB/HSW) HT bug only affects events that can be programmed
onto GP counters, therefore we should only limit the number of GP
counters that can be used per cpu -- iow we should not constrain the
FP counters.
Furthermore, we should only enfore such a limit when there are in fact
exclusive events being scheduled on either sibling.
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
[ Fixed build fail for the !CONFIG_CPU_SUP_INTEL case. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 43b4578071 ("perf/x86: Reduce stack usage of
x86_schedule_events()") violated the rule that 'fake' scheduling; as
used for event/group validation; should not change the event state.
This went mostly un-noticed because repeated calls of
x86_pmu::get_event_constraints() would give the same result. And
x86_pmu::put_event_constraints() would mostly not do anything.
Commit e979121b1b ("perf/x86/intel: Implement cross-HT corruption
bug workaround") made the situation much worse by actually setting the
event->hw.constraint value to NULL, so when validation and actual
scheduling interact we get NULL ptr derefs.
Fix it by removing the constraint pointer from the event and move it
back to an array, this time in cpuc instead of on the stack.
validate_group()
x86_schedule_events()
event->hw.constraint = c; # store
<context switch>
perf_task_event_sched_in()
...
x86_schedule_events();
event->hw.constraint = c2; # store
...
put_event_constraints(event); # assume failure to schedule
intel_put_event_constraints()
event->hw.constraint = NULL;
<context switch end>
c = event->hw.constraint; # read -> NULL
if (!test_bit(hwc->idx, c->idxmsk)) # <- *BOOM* NULL deref
This in particular is possible when the event in question is a
cpu-wide event and group-leader, where the validate_group() tries to
add an event to the group.
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Hunter <ahh@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 43b4578071 ("perf/x86: Reduce stack usage of x86_schedule_events()")
Fixes: e979121b1b ("perf/x86/intel: Implement cross-HT corruption bug workaround")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Conflicts:
arch/x86/kernel/i387.c
This commit is conflicting:
e88221c50c ("x86/fpu: Disable XSAVES* support for now")
These functions changed a lot, move the quirk to arch/x86/kernel/fpu/init.c's
fpu__init_system_xstate_size_legacy().
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There are a number of FPU internal function prototypes and an inline function
in fpu/api.h, mostly placed so historically as the code grew over the years.
Move them over into fpu/internal.h where they belong. (Add sched.h include
to stackprotector.h which incorrectly relied on getting it from fpu/api.h.)
fpu/api.h is now a pure file that only contains FPU APIs intended for driver
use.
Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This unifies all the FPU related header files under a unified, hiearchical
naming scheme:
- asm/fpu/types.h: FPU related data types, needed for 'struct task_struct',
widely included in almost all kernel code, and hence kept
as small as possible.
- asm/fpu/api.h: FPU related 'public' methods exported to other subsystems.
- asm/fpu/internal.h: FPU subsystem internal methods
- asm/fpu/xsave.h: XSAVE support internal methods
(Also standardize the header guard in asm/fpu/internal.h.)
Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fix a minor header file dependency bug in asm/fpu-internal.h: it
relies on i387.h but does not include it. All users of fpu-internal.h
included it explicitly.
Also remove unnecessary includes, to reduce compilation time.
This also makes it easier to use it as a standalone header file
for FPU internals, such as an upcoming C module in arch/x86/kernel/fpu/.
Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
fpu_init() is a bit of a misnomer in that it (falsely) creates the
impression that it's related to the (old) fpu_finit() function,
which initializes FPU ctx state.
Rename it to fpu__cpu_init() to make its boot time initialization
clear, and to move it to the fpu__*() namespace.
Also fix and extend its comment block to point out that it's
called not only on the boot CPU, but on secondary CPUs as well.
Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Derek noticed that a critical MCE gets reported with the wrong
error type description:
[Hardware Error]: CPU 34: Machine Check Exception: 5 Bank 9: f200003f000100b0
[Hardware Error]: RIP !INEXACT! 10:<ffffffff812e14c1> {intel_idle+0xb1/0x170}
[Hardware Error]: TSC 49587b8e321cb
[Hardware Error]: PROCESSOR 0:306e4 TIME 1431561296 SOCKET 1 APIC 29
[Hardware Error]: Some CPUs didn't answer in synchronization
[Hardware Error]: Machine check: Invalid
^^^^^^^
The last line with 'Invalid' should have printed the high level
MCE error type description we get from mce_severity, i.e.
something like:
[Hardware Error]: Machine check: Action required: data load error in a user process
this happens due to the fact that mce_no_way_out() iterates over
all MCA banks and possibly overwrites the @msg argument which is
used in the panic printing later.
Change behavior to take the message of only and the (last)
critical MCE it detects.
Reported-by: Derek <denc716@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: <stable@vger.kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1431936437-25286-3-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull RAS updates from Borislav Petkov:
- RAS: Add support for deferred errors on AMD (Aravind Gopalakrishnan)
This is an important RAS feature which adds hardware support for
poisoned data. That means roughly that the hardware marks data which it
has detected as corrupted but wasn't able to correct, as poisoned data
and raises an APIC interrupt to signal that in the form of a deferred
error. It is the OS's responsibility then to take proper recovery action
and thus prolonge system lifetime as far as possible.
- Misc cleanups ontop. (Borislav Petkov)"
Signed-off-by: Ingo Molnar <mingo@kernel.org>
iTLB-load-misses and LLC-load-misses count incorrectly on SLM.
There is no ITLB.MISSES support on SLM. Event PAGE_WALKS.I_SIDE_WALK
should be used to count iTLB-load-misses. This event counts when an
instruction (I) page walk is completed or started. Since a page walk
implies a TLB miss, the number of TLB misses can be counted by counting
the number of pagewalks.
DMND_DATA_RD counts both demand and DCU prefetch data reads. However,
LLC-load-misses should only count demand reads. There is no way to not
include prefetches with a single counter on SLM. So the LLC-load-misses
support should be removed on SLM.
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1429608881-5055-1-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
It is useless and git history has it all detailed anyway. Update
copyright while at it.
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Deferred errors indicate error conditions that were not corrected, but
require no action from S/W (or action is optional).These errors provide
info about a latent UC MCE that can occur when a poisoned data is
consumed by the processor.
Processors that report these errors can be configured to generate APIC
interrupts to notify OS about the error.
Provide an interrupt handler in this patch so that OS can catch these
errors as and when they happen. Currently, we simply log the errors and
exit the handler as S/W action is not mandated.
Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: x86-ml <x86@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1430913538-1415-5-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Borislav Petkov <bp@suse.de>
Pull xen bug fixes from David Vrabel:
- fix blkback regression if using persistent grants
- fix various event channel related suspend/resume bugs
- fix AMD x86 regression with X86_BUG_SYSRET_SS_ATTRS
- SWIOTLB on ARM now uses frames <4 GiB (if available) so device only
capable of 32-bit DMA work.
* tag 'for-linus-4.1b-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
xen: Add __GFP_DMA flag when xen_swiotlb_init gets free pages on ARM
hypervisor/x86/xen: Unset X86_BUG_SYSRET_SS_ATTRS on Xen PV guests
xen/events: Set irq_info->evtchn before binding the channel to CPU in __startup_pirq()
xen/console: Update console event channel on resume
xen/xenbus: Update xenbus event channel on resume
xen/events: Clear cpu_evtchn_mask before resuming
xen-pciback: Add name prefix to global 'permissive' variable
xen: Suspend ticks on all CPUs during suspend
xen/grant: introduce func gnttab_unmap_refs_sync()
xen/blkback: safely unmap purge persistent grants
Deferred errors indicate error conditions that were not corrected, but
those errors have not been consumed yet. They require no action from
S/W (or action is optional). These errors provide info about a latent
uncorrectable MCE that can occur when a poisoned data is consumed by the
processor.
Newer AMD processors can generate deferred errors and can be configured
to generate APIC interrupts on such events.
SUCCOR stands for S/W UnCorrectable error COntainment and Recovery.
It indicates support for data poisoning in HW and deferred error
interrupts.
Add new bitfield to mce_vendor_flags for this. We use this to verify
presence of deferred error interrupts before we enable them in mce_amd.c
While at it, clarify comments in mce_vendor_flags to provide an
indication of usages of the bitfields.
Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: x86-ml <x86@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1430913538-1415-4-git-send-email-Aravind.Gopalakrishnan@amd.com
[ beef up commit message, do CPUID(8000_0007) only once. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
amd_decode_mce() needs value in m->addr so it can report the error
address correctly. This should be setup in __log_error() before we call
mce_log(). We do this because the error address is an important bit of
information which should be conveyed to userspace.
The correct output then reports proper address, like this:
[Hardware Error]: Corrected error, no action required.
[Hardware Error]: CPU:0 (15:60:0) MC0_STATUS [-|CE|-|-|AddrV|-|-|CECC]: 0x840041000028017b
[Hardware Error]: MC0 Error Address: 0x00001f808f0ff040
Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: x86-ml <x86@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1430913538-1415-3-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Borislav Petkov <bp@suse.de>
Pull perf fixes from Ingo Molnar:
"Mostly tooling fixes, but also an uncore PMU driver fix and an uncore
PMU driver hardware-enablement addition"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf probe: Fix segfault if passed with ''.
perf report: Fix -T/--threads option to work again
perf bench numa: Fix immediate meeting of convergence condition
perf bench numa: Fixes of --quiet argument
perf bench futex: Fix hung wakeup tasks after requeueing
perf probe: Fix bug with global variables handling
perf top: Fix a segfault when kernel map is restricted.
tools lib traceevent: Fix build failure on 32-bit arch
perf kmem: Fix compiles on RHEL6/OL6
tools lib api: Undefine _FORTIFY_SOURCE before setting it
perf kmem: Consistently use PRIu64 for printing u64 values
perf trace: Disable events and drain events when forked workload ends
perf trace: Enable events when doing system wide tracing and starting a workload
perf/x86/intel/uncore: Move PCI IDs for IMC to uncore driver
perf/x86/intel/uncore: Add support for Intel Haswell ULT (lower power Mobile Processor) IMC uncore PMUs
perf/x86/intel: Add cpu_(prepare|starting|dying) for core_pmu
Apparently, people do build microcode into the kernel image, i.e.
CONFIG_FIRMWARE_IN_KERNEL=y.
Make that work in the early loader which is where microcode should be
preferably loaded anyway.
Note that you need to specify the microcode filename with the path
relative to the toplevel firmware directory (the same like the late
loading method) in CONFIG_EXTRA_FIRMWARE=y so that early loader can
find it.
I.e., something like this (Intel variant):
CONFIG_FIRMWARE_IN_KERNEL=y
CONFIG_EXTRA_FIRMWARE="intel-ucode/06-3a-09"
CONFIG_EXTRA_FIRMWARE_DIR="/lib/firmware/"
While at it, add me to the loader copyright boilerplate.
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel J Blueman <daniel@numascale.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
It is a one-liner for checking microcode header revisions. On top of
that, it can be used wrong as it was the case in _save_mc(). Get rid of
it.
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
