Pull perf updates from Ingo Molnar:
"The main kernel side changes in this cycle were:
- Various Intel-PT updates and optimizations (Alexander Shishkin)
- Prohibit kprobes on Xen/KVM emulate prefixes (Masami Hiramatsu)
- Add support for LSM and SELinux checks to control access to the
perf syscall (Joel Fernandes)
- Misc other changes, optimizations, fixes and cleanups - see the
shortlog for details.
There were numerous tooling changes as well - 254 non-merge commits.
Here are the main changes - too many to list in detail:
- Enhancements to core tooling infrastructure, perf.data, libperf,
libtraceevent, event parsing, vendor events, Intel PT, callchains,
BPF support and instruction decoding.
- There were updates to the following tools:
perf annotate
perf diff
perf inject
perf kvm
perf list
perf maps
perf parse
perf probe
perf record
perf report
perf script
perf stat
perf test
perf trace
- And a lot of other changes: please see the shortlog and Git log for
more details"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (279 commits)
perf parse: Fix potential memory leak when handling tracepoint errors
perf probe: Fix spelling mistake "addrees" -> "address"
libtraceevent: Fix memory leakage in copy_filter_type
libtraceevent: Fix header installation
perf intel-bts: Does not support AUX area sampling
perf intel-pt: Add support for decoding AUX area samples
perf intel-pt: Add support for recording AUX area samples
perf pmu: When using default config, record which bits of config were changed by the user
perf auxtrace: Add support for queuing AUX area samples
perf session: Add facility to peek at all events
perf auxtrace: Add support for dumping AUX area samples
perf inject: Cut AUX area samples
perf record: Add aux-sample-size config term
perf record: Add support for AUX area sampling
perf auxtrace: Add support for AUX area sample recording
perf auxtrace: Move perf_evsel__find_pmu()
perf record: Add a function to test for kernel support for AUX area sampling
perf tools: Add kernel AUX area sampling definitions
perf/core: Make the mlock accounting simple again
perf report: Jump to symbol source view from total cycles view
...
It's enough to check the value and issue the direct call.
After this commit is applied, here the most common retpolines executed
under a high resolution timer workload in the guest on a VMX host:
[..]
@[
trace_retpoline+1
__trace_retpoline+30
__x86_indirect_thunk_rax+33
do_syscall_64+89
entry_SYSCALL_64_after_hwframe+68
]: 267
@[]: 2256
@[
trace_retpoline+1
__trace_retpoline+30
__x86_indirect_thunk_rax+33
__kvm_wait_lapic_expire+284
vmx_vcpu_run.part.97+1091
vcpu_enter_guest+377
kvm_arch_vcpu_ioctl_run+261
kvm_vcpu_ioctl+559
do_vfs_ioctl+164
ksys_ioctl+96
__x64_sys_ioctl+22
do_syscall_64+89
entry_SYSCALL_64_after_hwframe+68
]: 2390
@[]: 33410
@total: 315707
Note the highest hit above is __delay so probably not worth optimizing
even if it would be more frequent than 2k hits per sec.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The events in the same group don't start or stop simultaneously.
Here is the ftrace when enabling event group for uncore_iio_0:
# perf stat -e "{uncore_iio_0/event=0x1/,uncore_iio_0/event=0xe/}"
<idle>-0 [000] d.h. 8959.064832: read_msr: a41, value
b2b0b030 //Read counter reg of IIO unit0 counter0
<idle>-0 [000] d.h. 8959.064835: write_msr: a48, value
400001 //Write Ctrl reg of IIO unit0 counter0 to enable
counter0. <------ Although counter0 is enabled, Unit Ctrl is still
freezed. Nothing will count. We are still good here.
<idle>-0 [000] d.h. 8959.064836: read_msr: a40, value
30100 //Read Unit Ctrl reg of IIO unit0
<idle>-0 [000] d.h. 8959.064838: write_msr: a40, value
30000 //Write Unit Ctrl reg of IIO unit0 to enable all
counters in the unit by clear Freeze bit <------Unit0 is un-freezed.
Counter0 has been enabled. Now it starts counting. But counter1 has not
been enabled yet. The issue starts here.
<idle>-0 [000] d.h. 8959.064846: read_msr: a42, value 0
//Read counter reg of IIO unit0 counter1
<idle>-0 [000] d.h. 8959.064847: write_msr: a49, value
40000e //Write Ctrl reg of IIO unit0 counter1 to enable
counter1. <------ Now, counter1 just starts to count. Counter0 has
been running for a while.
Current code un-freezes the Unit Ctrl right after the first counter is
enabled. The subsequent group events always loses some counter values.
Implement pmu_enable and pmu_disable support for uncore, which can help
to batch hardware accesses.
No one uses uncore_enable_box and uncore_disable_box. Remove them.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: linux-drivers-review@eclists.intel.com
Cc: linux-perf@eclists.intel.com
Fixes: 087bfbb032 ("perf/x86: Add generic Intel uncore PMU support")
Link: https://lkml.kernel.org/r/1572014593-31591-1-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In current mainline, the degree of access to perf_event_open(2) system
call depends on the perf_event_paranoid sysctl. This has a number of
limitations:
1. The sysctl is only a single value. Many types of accesses are controlled
based on the single value thus making the control very limited and
coarse grained.
2. The sysctl is global, so if the sysctl is changed, then that means
all processes get access to perf_event_open(2) opening the door to
security issues.
This patch adds LSM and SELinux access checking which will be used in
Android to access perf_event_open(2) for the purposes of attaching BPF
programs to tracepoints, perf profiling and other operations from
userspace. These operations are intended for production systems.
5 new LSM hooks are added:
1. perf_event_open: This controls access during the perf_event_open(2)
syscall itself. The hook is called from all the places that the
perf_event_paranoid sysctl is checked to keep it consistent with the
systctl. The hook gets passed a 'type' argument which controls CPU,
kernel and tracepoint accesses (in this context, CPU, kernel and
tracepoint have the same semantics as the perf_event_paranoid sysctl).
Additionally, I added an 'open' type which is similar to
perf_event_paranoid sysctl == 3 patch carried in Android and several other
distros but was rejected in mainline [1] in 2016.
2. perf_event_alloc: This allocates a new security object for the event
which stores the current SID within the event. It will be useful when
the perf event's FD is passed through IPC to another process which may
try to read the FD. Appropriate security checks will limit access.
3. perf_event_free: Called when the event is closed.
4. perf_event_read: Called from the read(2) and mmap(2) syscalls for the event.
5. perf_event_write: Called from the ioctl(2) syscalls for the event.
[1] https://lwn.net/Articles/696240/
Since Peter had suggest LSM hooks in 2016 [1], I am adding his
Suggested-by tag below.
To use this patch, we set the perf_event_paranoid sysctl to -1 and then
apply selinux checking as appropriate (default deny everything, and then
add policy rules to give access to domains that need it). In the future
we can remove the perf_event_paranoid sysctl altogether.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Co-developed-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: James Morris <jmorris@namei.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: rostedt@goodmis.org
Cc: Yonghong Song <yhs@fb.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: jeffv@google.com
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: primiano@google.com
Cc: Song Liu <songliubraving@fb.com>
Cc: rsavitski@google.com
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Matthew Garrett <matthewgarrett@google.com>
Link: https://lkml.kernel.org/r/20191014170308.70668-1-joel@joelfernandes.org
Comet Lake is the new 10th Gen Intel processor. From the perspective of
Intel cstate residency counters, there is nothing changed compared with
Kaby Lake.
Share hswult_cstates with Kaby Lake.
Update the comments for Comet Lake.
Kaby Lake is missed in the comments for some Residency Counters. Update
the comments for Kaby Lake as well.
The External Design Specification (EDS) is not published yet. It comes
from an authoritative internal source.
The patch has been tested on real hardware.
Signed-off-by: Kan Liang <kan.liang@linux.intel.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>
Link: https://lkml.kernel.org/r/1570549810-25049-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
It turns out that the NMI latency workaround from commit:
6d3edaae16 ("x86/perf/amd: Resolve NMI latency issues for active PMCs")
ends up being too conservative and results in the perf NMI handler claiming
NMIs too easily on AMD hardware when the NMI watchdog is active.
This has an impact, for example, on the hpwdt (HPE watchdog timer) module.
This module can produce an NMI that is used to reset the system. It
registers an NMI handler for the NMI_UNKNOWN type and relies on the fact
that nothing has claimed an NMI so that its handler will be invoked when
the watchdog device produces an NMI. After the referenced commit, the
hpwdt module is unable to process its generated NMI if the NMI watchdog is
active, because the current NMI latency mitigation results in the NMI
being claimed by the perf NMI handler.
Update the AMD perf NMI latency mitigation workaround to, instead, use a
window of time. Whenever a PMC is handled in the perf NMI handler, set a
timestamp which will act as a perf NMI window. Any NMIs arriving within
that window will be claimed by perf. Anything outside that window will
not be claimed by perf. The value for the NMI window is set to 100 msecs.
This is a conservative value that easily covers any NMI latency in the
hardware. While this still results in a window in which the hpwdt module
will not receive its NMI, the window is now much, much smaller.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jerry Hoemann <jerry.hoemann@hpe.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 6d3edaae16 ("x86/perf/amd: Resolve NMI latency issues for active PMCs")
Link: https://lkml.kernel.org/r/Message-ID:
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull x86 mm updates from Ingo Molnar:
- Make cpumask_of_node() more robust against invalid node IDs
- Simplify and speed up load_mm_cr4()
- Unexport and remove various unused set_memory_*() APIs
- Misc cleanups
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm: Fix cpumask_of_node() error condition
x86/mm: Remove the unused set_memory_wt() function
x86/mm: Remove set_pages_x() and set_pages_nx()
x86/mm: Remove the unused set_memory_array_*() functions
x86/mm: Unexport set_memory_x() and set_memory_nx()
x86/fixmap: Cleanup outdated comments
x86/kconfig: Remove X86_DIRECT_GBPAGES dependency on !DEBUG_PAGEALLOC
x86/mm: Avoid redundant interrupt disable in load_mm_cr4()
Pull x86 cpu-feature updates from Ingo Molnar:
- Rework the Intel model names symbols/macros, which were decades of
ad-hoc extensions and added random noise. It's now a coherent, easy
to follow nomenclature.
- Add new Intel CPU model IDs:
- "Tiger Lake" desktop and mobile models
- "Elkhart Lake" model ID
- and the "Lightning Mountain" variant of Airmont, plus support code
- Add the new AVX512_VP2INTERSECT instruction to cpufeatures
- Remove Intel MPX user-visible APIs and the self-tests, because the
toolchain (gcc) is not supporting it going forward. This is the
first, lowest-risk phase of MPX removal.
- Remove X86_FEATURE_MFENCE_RDTSC
- Various smaller cleanups and fixes
* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
x86/cpu: Update init data for new Airmont CPU model
x86/cpu: Add new Airmont variant to Intel family
x86/cpu: Add Elkhart Lake to Intel family
x86/cpu: Add Tiger Lake to Intel family
x86: Correct misc typos
x86/intel: Add common OPTDIFFs
x86/intel: Aggregate microserver naming
x86/intel: Aggregate big core graphics naming
x86/intel: Aggregate big core mobile naming
x86/intel: Aggregate big core client naming
x86/cpufeature: Explain the macro duplication
x86/ftrace: Remove mcount() declaration
x86/PCI: Remove superfluous returns from void functions
x86/msr-index: Move AMD MSRs where they belong
x86/cpu: Use constant definitions for CPU models
lib: Remove redundant ftrace flag removal
x86/crash: Remove unnecessary comparison
x86/bitops: Use __builtin_constant_p() directly instead of IS_IMMEDIATE()
x86: Remove X86_FEATURE_MFENCE_RDTSC
x86/mpx: Remove MPX APIs
...
When building with C=2, sparse makes note of a number of things:
arch/x86/events/intel/rapl.c:637:30: warning: symbol 'rapl_attr_update' was not declared. Should it be static?
arch/x86/events/intel/cstate.c:449:30: warning: symbol 'core_attr_update' was not declared. Should it be static?
arch/x86/events/intel/cstate.c:457:30: warning: symbol 'pkg_attr_update' was not declared. Should it be static?
arch/x86/events/msr.c:170:30: warning: symbol 'attr_update' was not declared. Should it be static?
arch/x86/events/intel/lbr.c:276:1: warning: symbol 'lbr_from_quirk_key' was not declared. Should it be static?
And they can all indeed be static.
Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/128059.1565286242@turing-police
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Conflicts:
tools/power/x86/turbostat/turbostat.c
Recent turbostat changes conflicted with a pending rename of x86 model names in tip:x86/cpu,
sort it out.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When counting dispatched micro-ops with cnt_ctl=1, in order to prevent
sample bias, IBS hardware preloads the least significant 7 bits of
current count (IbsOpCurCnt) with random values, such that, after the
interrupt is handled and counting resumes, the next sample taken
will be slightly perturbed.
The current count bitfield is in the IBS execution control h/w register,
alongside the maximum count field.
Currently, the IBS driver writes that register with the maximum count,
leaving zeroes to fill the current count field, thereby overwriting
the random bits the hardware preloaded for itself.
Fix the driver to actually retain and carry those random bits from the
read of the IBS control register, through to its write, instead of
overwriting the lower current count bits with zeroes.
Tested with:
perf record -c 100001 -e ibs_op/cnt_ctl=1/pp -a -C 0 taskset -c 0 <workload>
'perf annotate' output before:
15.70 65: addsd %xmm0,%xmm1
17.30 add $0x1,%rax
15.88 cmp %rdx,%rax
je 82
17.32 72: test $0x1,%al
jne 7c
7.52 movapd %xmm1,%xmm0
5.90 jmp 65
8.23 7c: sqrtsd %xmm1,%xmm0
12.15 jmp 65
'perf annotate' output after:
16.63 65: addsd %xmm0,%xmm1
16.82 add $0x1,%rax
16.81 cmp %rdx,%rax
je 82
16.69 72: test $0x1,%al
jne 7c
8.30 movapd %xmm1,%xmm0
8.13 jmp 65
8.24 7c: sqrtsd %xmm1,%xmm0
8.39 jmp 65
Tested on Family 15h and 17h machines.
Machines prior to family 10h Rev. C don't have the RDWROPCNT capability,
and have the IbsOpCurCnt bitfield reserved, so this patch shouldn't
affect their operation.
It is unknown why commit db98c5faf8 ("perf/x86: Implement 64-bit
counter support for IBS") ignored the lower 4 bits of the IbsOpCurCnt
field; the number of preloaded random bits has always been 7, AFAICT.
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "Arnaldo Carvalho de Melo" <acme@kernel.org>
Cc: <x86@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "Borislav Petkov" <bp@alien8.de>
Cc: Stephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: "Namhyung Kim" <namhyung@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lkml.kernel.org/r/20190826195730.30614-1-kim.phillips@amd.com
If PEBS declares ability to output its data to Intel PT stream, use the
aux_output attribute bit to enable PEBS data output to PT. This requires
a PT event to be present and scheduled in the same context. Unlike the
DS area, the kernel does not extract PEBS records from the PT stream to
generate corresponding records in the perf stream, because that would
require real time in-kernel PT decoding, which is not feasible. The PMI,
however, can still be used.
The output setting is per-CPU, so all PEBS events must be either writing
to PT or to the DS area, therefore, in case of conflict, the conflicting
event will fail to schedule, allowing the rotation logic to alternate
between the PEBS->PT and PEBS->DS events.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: kan.liang@linux.intel.com
Link: https://lkml.kernel.org/r/20190806084606.4021-3-alexander.shishkin@linux.intel.com
In order to quickly find a ToPA entry by its page offset in the buffer,
we're using a reverse lookup table. The problem with it is that it's a
large array of mostly similar pointers, especially so now that we're
using high order allocations from the page allocator. Because its size
is limited to whatever is the maximum for kmalloc(), it places a limit
on the number of ToPA entries per buffer, and therefore, on the total
buffer size, which otherwise doesn't have to be there.
Replace the reverse lookup table with a simple runtime lookup. With the
high order AUX allocations in place, the runtime penalty of such a lookup
is much smaller and in cases where all entries in a ToPA table are of
the same size, the complexity is O(1).
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/20190821124727.73310-7-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
