These checks were inconsistently applied across the various hwpmc
classes. The condition is already checked by the generic code in
hwpmc_mod.c, so remove them.
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D31388
It is always a good idea. In one case, attempting to allocate N+1 PMCs
from a class with N hardware counters would incorrectly attempt to
allocate from the next class in the list. Without this validation, this
can lead to all kinds of strange behaviour.
Since powerpc_allocate_pmc() is used by both the mpc7xxx and ppc970
classes, add a new global to track which is active (it will never be
both).
Reviewed by: luporl, ray
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D31387
Use the KPI to tweak MSRs in mitigation code.
Reviewed by: markj, scottl
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D22431
The forthcoming microcode update will fix a TSX bug by clobbering PMC3
when TSX instructions are executed (even speculatively). There is an
alternate mode where CPU executes all TSX instructions by aborting
them, in which case PMC3 is still available to OS. Any code that
correctly uses TSX must be ready to handle abort anyway.
Since it is believed that FreeBSD population of hwpmc(4) users is
significantly larger than the population of TSX users, switch the
microcode into TSX abort mode whenever a pmc is allocated, and back to
bug avoidance mode when the last pmc is deallocated.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
pmc_process_interrupt takes 5 arguments when only 3 are needed.
cpu is always available in curcpu and inuserspace can always be
derived from the passed trapframe.
While facially a reasonable cleanup this change was motivated
by the need to workaround a compiler bug.
core2_intr(cpu, tf) ->
pmc_process_interrupt(cpu, ring, pmc, tf, inuserspace) ->
pmc_add_sample(cpu, ring, pm, tf, inuserspace)
In the process of optimizing the tail call the tf pointer was getting
clobbered:
(kgdb) up
at /storage/mmacy/devel/freebsd/sys/dev/hwpmc/hwpmc_mod.c:4709
4709 pmc_save_kernel_callchain(ps->ps_pc,
(kgdb) up
1205 error = pmc_process_interrupt(cpu, PMC_HR, pm, tf,
resulting in a crash in pmc_save_kernel_callchain.
- increase pmc cpuid field from 8 to 12 bits
- add cpuid version string to initialize entry in the log
so that filter can identify which counter index an
event name maps to
- GC unused config flags
- make fixed counter assignment more robust as well as the
changes needed to be properly identified for filter
Intel now provides comprehensive tables for all performance counters
and the various valid configuration permutations as text .json files.
Libpmc has been converted to use these and hwpmc_core has been greatly
simplified by moving to passthrough of the table values.
The one gotcha is that said tables don't support pentium pro and and pentium
IV. There's very few users of hwpmc on _amd64_ kernels on new hardware. It is
unlikely that anyone is doing low level optimization on 15 year old Intel
hardware. Nonetheless, if someone feels strongly enough to populate the
corresponding tables for p4 and ppro I will reinstate the files in to the
build.
Code for the K8 counters and !x86 architectures remains unchanged.
vendor provided pmu-events tables and sundry cleanups.
The vendor pmu-events tables provide counter descriptions, default
sample rates, event, umask, and flag values for all the counter
configuration permutations. Using this gives us:
- much simpler kernel code for the MD component
- helpful long and short event descriptions
- simpler user code
- sample rates that won't overload the system
Update man page with newer sample types and remove unused sample type.
vendor provided pmu-events tables and sundry cleanups.
The vendor pmu-events tables provide counter descriptions, default
sample rates, event, umask, and flag values for all the counter
configuration permutations. Using this gives us:
- much simpler kernel code for the MD component
- helpful long and short event descriptions
- simpler user code
- sample rates that won't overload the system
Update man page with newer sample types and remove unused sample type.
Squashed commit of the following:
commit 4459d43eff815bec08ccc5533dbe5de846f03128
Author: Matt Macy <mmacy@mattmacy.io>
Date: Sat May 26 00:06:31 2018 -0700
libpmc: fix pmu function signatures for non amd64
commit a2cb8bbc586c65d41f9b291430a2261ec67b59fe
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 22:38:11 2018 -0700
pmcstat: fix indentation of usage
commit f686954b15ff56a833ac80404898977cb80a265b
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 22:19:49 2018 -0700
pmclog(3): add callchain and pmcallocatedyn, remove pcsample
commit 73e13a0d2e9498c81c150d14d022050cee7511bb
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 22:19:00 2018 -0700
pmclog.h: GC pcsample field
commit 3e93ffd65da641fa657539dad3c48e281f8b5798
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 22:05:57 2018 -0700
hwpmc: make Intel core CPUs use external event tables
commit 634f5fae1e1644ac324003136c66cd9c619d1c93
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 22:00:06 2018 -0700
pmclog: update log record types, bump PMC_MAJOR
- explicitly make log record types a multiple of 8 bytes
- hook in pmu event types for pmc_allocate records
- remove references to no longer PCSAMPLE record
commit 83d84fcd2d65bdf6ddcb2e155a22f0cfa2a9c225
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 21:52:10 2018 -0700
libpmc: add support for having vendor table driven pmc_allocate
commit 9e6ad63c40c2fce8404847ace5078ca6cb33a736
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 19:11:33 2018 -0700
hwpmc_core: add accessors for EVSEL & UMASK, make IAP_UMASK useful to user
commit 859dceb93daa6419a48c794db99b6758e5b041c9
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 19:09:45 2018 -0700
pmcstat: update usage and man page as well as make -L consistent with pmccontrol
commit 79c7d8597e28c2eb13f5f9113e65ec2792ca57b1
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 18:07:03 2018 -0700
pmu_util: add support for all current intel event keywords
commit d8089c7f6a6c8527f38324252b1ffb47004694c6
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 17:45:00 2018 -0700
add description for new arguments
commit 058336740bab53c62ec88a3a026ea848cf3878c6
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 17:38:15 2018 -0700
libpmc: move pmu_events table and pmu_utils out of libpmcstat so that they can be used by pmc_allocate
commit 049b66b382e2f833c3f47bc8df9e750cb265709f
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 16:12:41 2018 -0700
pmcstat: hook pmu_events counter description utility routines in
commit f5e01e7b37a691dc045e1aa16b3ebdd162515de8
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 16:11:59 2018 -0700
pmu_events: add utility routines for listing counters and their descriptions
commit cba4d4f8907f772279f86f18f915e0d74d33ac56
Author: Matt Macy <mmacy@mattmacy.io>
Date: Fri May 25 16:09:50 2018 -0700
pmu-events: expand out skylake regex to simplify string matches
On non-trivial SMP systems the contention on the pmc_owner mutex leads
to a substantial number of samples captured being from the pmc process
itself. This change a) makes buffers larger to avoid contention on the
global list b) makes the working sample buffer per cpu.
Run pmcstat in the background (default event rate of 64k):
pmcstat -S UNHALTED_CORE_CYCLES -O /dev/null sleep 600 &
Before:
make -j96 buildkernel -s >&/dev/null 3336.68s user 24684.10s system 7442% cpu 6:16.50 total
After:
make -j96 buildkernel -s >&/dev/null 2697.82s user 1347.35s system 6058% cpu 1:06.77 total
For more realistic overhead measurement set the sample rate for ~2khz
on a 2.1Ghz processor:
pmcstat -n 1050000 -S UNHALTED_CORE_CYCLES -O /dev/null sleep 6000 &
Collecting 10 samples of `make -j96 buildkernel` from each:
x before
+ after
real time:
N Min Max Median Avg Stddev
x 10 76.4 127.62 84.845 88.577 15.100031
+ 10 59.71 60.79 60.135 60.179 0.29957192
Difference at 95.0% confidence
-28.398 +/- 10.0344
-32.0602% +/- 7.69825%
(Student's t, pooled s = 10.6794)
system time:
N Min Max Median Avg Stddev
x 10 2277.96 6948.53 2949.47 3341.492 1385.2677
+ 10 1038.7 1081.06 1070.555 1064.017 15.85404
Difference at 95.0% confidence
-2277.47 +/- 920.425
-68.1574% +/- 8.77623%
(Student's t, pooled s = 979.596)
x no pmc
+ pmc running
real time:
HEAD:
N Min Max Median Avg Stddev
x 10 58.38 59.15 58.86 58.847 0.22504567
+ 10 76.4 127.62 84.845 88.577 15.100031
Difference at 95.0% confidence
29.73 +/- 10.0335
50.5208% +/- 17.0525%
(Student's t, pooled s = 10.6785)
patched:
N Min Max Median Avg Stddev
x 10 58.38 59.15 58.86 58.847 0.22504567
+ 10 59.71 60.79 60.135 60.179 0.29957192
Difference at 95.0% confidence
1.332 +/- 0.248939
2.2635% +/- 0.426506%
(Student's t, pooled s = 0.264942)
system time:
HEAD:
N Min Max Median Avg Stddev
x 10 1010.15 1073.31 1025.465 1031.524 18.135705
+ 10 2277.96 6948.53 2949.47 3341.492 1385.2677
Difference at 95.0% confidence
2309.97 +/- 920.443
223.937% +/- 89.3039%
(Student's t, pooled s = 979.616)
patched:
N Min Max Median Avg Stddev
x 10 1010.15 1073.31 1025.465 1031.524 18.135705
+ 10 1038.7 1081.06 1070.555 1064.017 15.85404
Difference at 95.0% confidence
32.493 +/- 16.0042
3.15% +/- 1.5794%
(Student's t, pooled s = 17.0331)
Reviewed by: jeff@
Approved by: sbruno@
Differential Revision: https://reviews.freebsd.org/D15155
Mainly focus on files that use BSD 2-Clause license, however the tool I
was using misidentified many licenses so this was mostly a manual - error
prone - task.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
supported, use full-width aliases MSRs for writes. This fixes the
"[pmc,X] negative increment" assertion on the context switch when
clipped counter value is sign-extended.
Add definitions for the MSR IA32_PERF_CAPABILITIES needed to detect
the feature.
PR: 207068
Submitted by: joss.upton@yahoo.com
MFC after: 2 weeks
IAP_F_FM's as well as incorrect umask specifications for
some of the new Broadwell/Skylake PMC's. Also silvermont
had a *lot* of missing IAP_F_FM.
Sponsored by: Netflix Inc.
tested on the Broadwell-Xeon with a hacked up version of pmcstudy -T. I still need
to circle back and add in to pmcstudy all the new tests from the Broadwell Vtune
guide (for the hacked up version I just made it so I could run the -T option). The
Skylake CPU is not yet available (even though Intel is advertising it .. imagine that).
The Skylake PMC's will need to be tested once we can get a sample skylake CPU :-)
Sponsored by: Netflix Inc.
In both cases, the the effect of the bug was that a very small positive
number was written to the counter. This means that a large number of
events needed to occur before the next sampling interrupt would trigger.
Even with very frequently occurring events like clock cycles wrapping all
the way around could take a long time. Both bugs occurred when updating
the saved reload count for an outgoing thread on a context switch.
First, the counter-independent code compares the current reload count
against the count set when the thread switched in and generates a delta
to apply to the saved count. If this delta causes the reload counter
to go negative, it would add a full reload interval to wrap it around to
a positive value. The fix is to add the full reload interval if the
resulting counter is zero.
Second, occasionally the raw counter value read during a context switch
has actually wrapped, but an interrupt has not yet triggered. In this
case the existing logic would return a very large reload count (e.g.
2^48 - 2 if the counter had overflowed by a count of 2). This was seen
both for fixed-function and programmable counters on an E5-2643.
Workaround this case by returning a reload count of zero.
PR: 198149
Differential Revision: https://reviews.freebsd.org/D2557
Reviewed by: emaste
MFC after: 1 week
Sponsored by: Norse Corp, Inc.
The MEM_UOPS_RETIRED actually work the same way as the Sandy
Bridge counters, but the counters were documented in a different
way and that seemed to cause the Ivy Bridge counters to be
implemented incorrectly. Use the same counter definitions as
Sandy Bridge. While I'm here, rename the counters to match
what's documented in the datasheet.
Differential Revision: https://reviews.freebsd.org/D1590
MFC after: 1 month
Sponsored by: Sandvine Inc.
On Sandy Bridge and later, to count branch-related events you
have to or together a mask indicating the type of branch
instruction to count (e.g. direct jump, branch, etc) and a bits
indicating whether to count taken and not-taken branches. The
current counter definitions where defining this bits individually,
so the counters never worked and always just counted 0.
Fix the counter definitions to instead contain the proper
combination of masks. Also update the man pages to reflect the
new counters.
Differential Revision: https://reviews.freebsd.org/D1587
MFC after: 1 month
Sponsored by: Sandvine Inc.
A couple of pmc counters did not work because there were being
restricted to the wrong PMC unit. I've verified that these
counters now work and match the documented restrictions.
Differential Revision: https://reviews.freebsd.org/D1586
MFC after: 1 month
Sponsored by: Sandvine Inc
go back through HASWELL, IVY_BRIDGE, IVY_BRIDGE_XEON and SANDY_BRIDGE
to straighten out all the missing PMCs. We also add a new pmc tool
pmcstudy, this allows one to run the various formulas from
the documents "Using Intel Vtune Amplifier XE on XXX Generation platforms" for
IB/SB and Haswell. The tool also allows one to postulate your own
formulas with any of the various PMC's. At some point I will enahance
this to work with Brendan Gregg's flame-graphs so we can flamegraph
various PMC interactions. Note the manual page also needs some
work (lots of work) but gnn has committed to help me with that ;-)
Reviewed by: gnn
MFC after:1 month
Sponsored by: Netflix Inc.
events we have actually counted 'Branch Instruction Retired' when people
asked for 'Unhalted core cycles' using the 'unhalted-core-cycles' event mask
mnemonic.
Reviewed by: jimharris
Discussed with: gnn, rwatson
MFC after: 3 days
Sponsored by: DARPA/AFRL
Core i7 and Westmere processors, the uncore PMC subsystem is
completely different from the uncore PMC on smaller versions of CPUs.
Disable existing uncore hwpmc code for EX, otherwise non-existing MSRs
are accessed.
The cores PMCs seems to be identical for non-EX and EX, according to
the SDM.
Reviewed by: davide, fabient
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
using cpuid can be quirky (this is the case of VMWare without the
vPMC support) but fail to probe hwpmc.
o Apply the fix for XEON family of processors as established by
315338-020 document (bug AJ85).
Sponsored by: EMC / Isilon storage division
Reviewed by: fabient
bridge Xeon.
Summary: These are PEBS events but they're also available as normal
counter/sample events. The source table (Table 19-2) lists the
base versions (LOAD, STLB_MISS, SPLIT, ALL) but it says they must
be qualified with other values. This particular commit fleshes
out those umask values.
Source:
* Linux; SDM June 2013, Volume 3B, Table 19-2 and 18-21.
Tested:
* Sandy Bridge (non-Xeon)
* Add in MEM_LOAD_UOPS_LLC_HIT_RETIRED for both sandy bridge and sandy
bridge Xeon. Right now it only is enabled for Sandy Bridge.
* D2/0F is actually a combination rather than a separate counter, so
just flip that on for the CPU types that support it.
There's an errata for using this on SB Xeon hardware - I've documented
it in kern/181346.
Tested:
* Sandy Bridge
* Sandy Bridge Xeon
Sponsored by: Netflix, Inc.
versions than the one in base (dim@ mentioned he tried on 4.7.3 and 4.8.1)
do not whine about it, so, at some point this workaround will be reverted.
Reported by: ache
Discussed with: dim
those of some non-architectural core events. This is not a problem in the
general case as long as there's an 1:1 mapping between the two, but there
are few exceptions. For example, 3CH_01H on Nehalem/Westmere represents
both unhalted-reference-cycles and CPU_CLK_UNHALTED.REF_P.
CPU_CLK_UNHALTED.REF_P on the aforementioned architectures does not measure
reference (i.e. bus) but TSC, so there's the need to disambiguate.
In order to avoid the namespace collision rename all the architectural
events in a way they cannot be ambigous and refactor the architectural
events handling function to reflect this change.
While here, per Jim Harris request, rename
iap_architectural_event_is_unsupported() to iap_event_is_architectural().
Discussed with: jimharris
Reviewed by: jimharris, gnn
