d20e834e13ce349c9b901b9dd8b7013e255083e8
34080 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Konstantin Khlebnikov
|
b4fb015eef |
sched/rt: Optimize checking group RT scheduler constraints
Group RT scheduler contains protection against setting zero runtime for
cgroup with RT tasks. Right now function tg_set_rt_bandwidth() iterates
over all CPU cgroups and calls tg_has_rt_tasks() for any cgroup which
runtime is zero (not only for changed one). Default RT runtime is zero,
thus tg_has_rt_tasks() will is called for almost at CPU cgroups.
This protection already is slightly racy: runtime limit could be changed
between cpu_cgroup_can_attach() and cpu_cgroup_attach() because changing
cgroup attribute does not lock cgroup_mutex while attach does not lock
rt_constraints_mutex. Changing task scheduler class also races with
changing rt runtime: check in __sched_setscheduler() isn't protected.
Function tg_has_rt_tasks() iterates over all threads in the system.
This gives NR_CGROUPS * NR_TASKS operations under single tasklist_lock
locked for read tg_set_rt_bandwidth(). Any concurrent attempt of locking
tasklist_lock for write (for example fork) will stuck with disabled irqs.
This patch makes two optimizations:
1) Remove locking tasklist_lock and iterate only tasks in cgroup
2) Call tg_has_rt_tasks() iff rt runtime changes from non-zero to zero
All changed code is under CONFIG_RT_GROUP_SCHED.
Testcase:
# mkdir /sys/fs/cgroup/cpu/test{1..10000}
# echo 0 | tee /sys/fs/cgroup/cpu/test*/cpu.rt_runtime_us
At the same time without patch fork time will be >100ms:
# perf trace -e clone --duration 100 stress-ng --fork 1
Also remote ping will show timings >100ms caused by irq latency.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/157996383820.4651.11292439232549211693.stgit@buzz
|
||
|
Srikar Dronamraju
|
bec2860a2b |
sched/fair: Optimize select_idle_core()
Currently we loop through all threads of a core to evaluate if the core is
idle or not. This is unnecessary. If a thread of a core is not idle, skip
evaluating other threads of a core. Also while clearing the cpumask, bits
of all CPUs of a core can be cleared in one-shot.
Collecting ticks on a Power 9 SMT 8 system around select_idle_core
while running schbench shows us
(units are in ticks, hence lesser is better)
Without patch
N Min Max Median Avg Stddev
x 130 151 1083 284 322.72308 144.41494
With patch
N Min Max Median Avg Stddev Improvement
x 164 88 610 201 225.79268 106.78943 30.03%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lkml.kernel.org/r/20191206172422.6578-1-srikar@linux.vnet.ibm.com
|
||
|
Giovanni Gherdovich
|
1567c3e346 |
x86, sched: Add support for frequency invariance
Implement arch_scale_freq_capacity() for 'modern' x86. This function
is used by the scheduler to correctly account usage in the face of
DVFS.
The present patch addresses Intel processors specifically and has positive
performance and performance-per-watt implications for the schedutil cpufreq
governor, bringing it closer to, if not on-par with, the powersave governor
from the intel_pstate driver/framework.
Large performance gains are obtained when the machine is lightly loaded and
no regression are observed at saturation. The benchmarks with the largest
gains are kernel compilation, tbench (the networking version of dbench) and
shell-intensive workloads.
1. FREQUENCY INVARIANCE: MOTIVATION
* Without it, a task looks larger if the CPU runs slower
2. PECULIARITIES OF X86
* freq invariance accounting requires knowing the ratio freq_curr/freq_max
2.1 CURRENT FREQUENCY
* Use delta_APERF / delta_MPERF * freq_base (a.k.a "BusyMHz")
2.2 MAX FREQUENCY
* It varies with time (turbo). As an approximation, we set it to a
constant, i.e. 4-cores turbo frequency.
3. EFFECTS ON THE SCHEDUTIL FREQUENCY GOVERNOR
* The invariant schedutil's formula has no feedback loop and reacts faster
to utilization changes
4. KNOWN LIMITATIONS
* In some cases tasks can't reach max util despite how hard they try
5. PERFORMANCE TESTING
5.1 MACHINES
* Skylake, Broadwell, Haswell
5.2 SETUP
* baseline Linux v5.2 w/ non-invariant schedutil. Tested freq_max = 1-2-3-4-8-12
active cores turbo w/ invariant schedutil, and intel_pstate/powersave
5.3 BENCHMARK RESULTS
5.3.1 NEUTRAL BENCHMARKS
* NAS Parallel Benchmark (HPC), hackbench
5.3.2 NON-NEUTRAL BENCHMARKS
* tbench (10-30% better), kernbench (10-15% better),
shell-intensive-scripts (30-50% better)
* no regressions
5.3.3 SELECTION OF DETAILED RESULTS
5.3.4 POWER CONSUMPTION, PERFORMANCE-PER-WATT
* dbench (5% worse on one machine), kernbench (3% worse),
tbench (5-10% better), shell-intensive-scripts (10-40% better)
6. MICROARCH'ES ADDRESSED HERE
* Xeon Core before Scalable Performance processors line (Xeon Gold/Platinum
etc have different MSRs semantic for querying turbo levels)
7. REFERENCES
* MMTests performance testing framework, github.com/gormanm/mmtests
+-------------------------------------------------------------------------+
| 1. FREQUENCY INVARIANCE: MOTIVATION
+-------------------------------------------------------------------------+
For example; suppose a CPU has two frequencies: 500 and 1000 Mhz. When
running a task that would consume 1/3rd of a CPU at 1000 MHz, it would
appear to consume 2/3rd (or 66.6%) when running at 500 MHz, giving the
false impression this CPU is almost at capacity, even though it can go
faster [*]. In a nutshell, without frequency scale-invariance tasks look
larger just because the CPU is running slower.
[*] (footnote: this assumes a linear frequency/performance relation; which
everybody knows to be false, but given realities its the best approximation
we can make.)
+-------------------------------------------------------------------------+
| 2. PECULIARITIES OF X86
+-------------------------------------------------------------------------+
Accounting for frequency changes in PELT signals requires the computation of
the ratio freq_curr / freq_max. On x86 neither of those terms is readily
available.
2.1 CURRENT FREQUENCY
====================
Since modern x86 has hardware control over the actual frequency we run
at (because amongst other things, Turbo-Mode), we cannot simply use
the frequency as requested through cpufreq.
Instead we use the APERF/MPERF MSRs to compute the effective frequency
over the recent past. Also, because reading MSRs is expensive, don't
do so every time we need the value, but amortize the cost by doing it
every tick.
2.2 MAX FREQUENCY
=================
Obtaining freq_max is also non-trivial because at any time the hardware can
provide a frequency boost to a selected subset of cores if the package has
enough power to spare (eg: Turbo Boost). This means that the maximum frequency
available to a given core changes with time.
The approach taken in this change is to arbitrarily set freq_max to a constant
value at boot. The value chosen is the "4-cores (4C) turbo frequency" on most
microarchitectures, after evaluating the following candidates:
* 1-core (1C) turbo frequency (the fastest turbo state available)
* around base frequency (a.k.a. max P-state)
* something in between, such as 4C turbo
To interpret these options, consider that this is the denominator in
freq_curr/freq_max, and that ratio will be used to scale PELT signals such as
util_avg and load_avg. A large denominator will undershoot (util_avg looks a
bit smaller than it really is), viceversa with a smaller denominator PELT
signals will tend to overshoot. Given that PELT drives frequency selection
in the schedutil governor, we will have:
freq_max set to | effect on DVFS
--------------------+------------------
1C turbo | power efficiency (lower freq choices)
base freq | performance (higher util_avg, higher freq requests)
4C turbo | a bit of both
4C turbo proves to be a good compromise in a number of benchmarks (see below).
+-------------------------------------------------------------------------+
| 3. EFFECTS ON THE SCHEDUTIL FREQUENCY GOVERNOR
+-------------------------------------------------------------------------+
Once an architecture implements a frequency scale-invariant utilization (the
PELT signal util_avg), schedutil switches its frequency selection formula from
freq_next = 1.25 * freq_curr * util [non-invariant util signal]
to
freq_next = 1.25 * freq_max * util [invariant util signal]
where, in the second formula, freq_max is set to the 1C turbo frequency (max
turbo). The advantage of the second formula, whose usage we unlock with this
patch, is that freq_next doesn't depend on the current frequency in an
iterative fashion, but can jump to any frequency in a single update. This
absence of feedback in the formula makes it quicker to react to utilization
changes and more robust against pathological instabilities.
Compare it to the update formula of intel_pstate/powersave:
freq_next = 1.25 * freq_max * Busy%
where again freq_max is 1C turbo and Busy% is the percentage of time not spent
idling (calculated with delta_MPERF / delta_TSC); essentially the same as
invariant schedutil, and largely responsible for intel_pstate/powersave good
reputation. The non-invariant schedutil formula is derived from the invariant
one by approximating util_inv with util_raw * freq_curr / freq_max, but this
has limitations.
Testing shows improved performances due to better frequency selections when
the machine is lightly loaded, and essentially no change in behaviour at
saturation / overutilization.
+-------------------------------------------------------------------------+
| 4. KNOWN LIMITATIONS
+-------------------------------------------------------------------------+
It's been shown that it is possible to create pathological scenarios where a
CPU-bound task cannot reach max utilization, if the normalizing factor
freq_max is fixed to a constant value (see [Lelli-2018]).
If freq_max is set to 4C turbo as we do here, one needs to peg at least 5
cores in a package doing some busywork, and observe that none of those task
will ever reach max util (1024) because they're all running at less than the
4C turbo frequency.
While this concern still applies, we believe the performance benefit of
frequency scale-invariant PELT signals outweights the cost of this limitation.
[Lelli-2018]
https://lore.kernel.org/lkml/20180517150418.GF22493@localhost.localdomain/
+-------------------------------------------------------------------------+
| 5. PERFORMANCE TESTING
+-------------------------------------------------------------------------+
5.1 MACHINES
============
We tested the patch on three machines, with Skylake, Broadwell and Haswell
CPUs. The details are below, together with the available turbo ratios as
reported by the appropriate MSRs.
* 8x-SKYLAKE-UMA:
Single socket E3-1240 v5, Skylake 4 cores/8 threads
Max EFFiciency, BASE frequency and available turbo levels (MHz):
EFFIC 800 |********
BASE 3500 |***********************************
4C 3700 |*************************************
3C 3800 |**************************************
2C 3900 |***************************************
1C 3900 |***************************************
* 80x-BROADWELL-NUMA:
Two sockets E5-2698 v4, 2x Broadwell 20 cores/40 threads
Max EFFiciency, BASE frequency and available turbo levels (MHz):
EFFIC 1200 |************
BASE 2200 |**********************
8C 2900 |*****************************
7C 3000 |******************************
6C 3100 |*******************************
5C 3200 |********************************
4C 3300 |*********************************
3C 3400 |**********************************
2C 3600 |************************************
1C 3600 |************************************
* 48x-HASWELL-NUMA
Two sockets E5-2670 v3, 2x Haswell 12 cores/24 threads
Max EFFiciency, BASE frequency and available turbo levels (MHz):
EFFIC 1200 |************
BASE 2300 |***********************
12C 2600 |**************************
11C 2600 |**************************
10C 2600 |**************************
9C 2600 |**************************
8C 2600 |**************************
7C 2600 |**************************
6C 2600 |**************************
5C 2700 |***************************
4C 2800 |****************************
3C 2900 |*****************************
2C 3100 |*******************************
1C 3100 |*******************************
5.2 SETUP
=========
* The baseline is Linux v5.2 with schedutil (non-invariant) and the intel_pstate
driver in passive mode.
* The rationale for choosing the various freq_max values to test have been to
try all the 1-2-3-4C turbo levels (note that 1C and 2C turbo are identical
on all machines), plus one more value closer to base_freq but still in the
turbo range (8C turbo for both 80x-BROADWELL-NUMA and 48x-HASWELL-NUMA).
* In addition we've run all tests with intel_pstate/powersave for comparison.
* The filesystem is always XFS, the userspace is openSUSE Leap 15.1.
* 8x-SKYLAKE-UMA is capable of HWP (Hardware-Managed P-States), so the runs
with active intel_pstate on this machine use that.
This gives, in terms of combinations tested on each machine:
* 8x-SKYLAKE-UMA
* Baseline: Linux v5.2, non-invariant schedutil, intel_pstate passive
* intel_pstate active + powersave + HWP
* invariant schedutil, freq_max = 1C turbo
* invariant schedutil, freq_max = 3C turbo
* invariant schedutil, freq_max = 4C turbo
* both 80x-BROADWELL-NUMA and 48x-HASWELL-NUMA
* [same as 8x-SKYLAKE-UMA, but no HWP capable]
* invariant schedutil, freq_max = 8C turbo
(which on 48x-HASWELL-NUMA is the same as 12C turbo, or "all cores turbo")
5.3 BENCHMARK RESULTS
=====================
5.3.1 NEUTRAL BENCHMARKS
------------------------
Tests that didn't show any measurable difference in performance on any of the
test machines between non-invariant schedutil and our patch are:
* NAS Parallel Benchmarks (NPB) using either MPI or openMP for IPC, any
computational kernel
* flexible I/O (FIO)
* hackbench (using threads or processes, and using pipes or sockets)
5.3.2 NON-NEUTRAL BENCHMARKS
----------------------------
What follow are summary tables where each benchmark result is given a score.
* A tilde (~) means a neutral result, i.e. no difference from baseline.
* Scores are computed with the ratio result_new / result_baseline, so a tilde
means a score of 1.00.
* The results in the score ratio are the geometric means of results running
the benchmark with different parameters (eg: for kernbench: using 1, 2, 4,
... number of processes; for pgbench: varying the number of clients, and so
on).
* The first three tables show higher-is-better kind of tests (i.e. measured in
operations/second), the subsequent three show lower-is-better kind of tests
(i.e. the workload is fixed and we measure elapsed time, think kernbench).
* "gitsource" is a name we made up for the test consisting in running the
entire unit tests suite of the Git SCM and measuring how long it takes. We
take it as a typical example of shell-intensive serialized workload.
* In the "I_PSTATE" column we have the results for intel_pstate/powersave. Other
columns show invariant schedutil for different values of freq_max. 4C turbo
is circled as it's the value we've chosen for the final implementation.
80x-BROADWELL-NUMA (comparison ratio; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
pgbench-ro 1.14 ~ ~ | 1.11 | 1.14
pgbench-rw ~ ~ ~ | ~ | ~
netperf-udp 1.06 ~ 1.06 | 1.05 | 1.07
netperf-tcp ~ 1.03 ~ | 1.01 | 1.02
tbench4 1.57 1.18 1.22 | 1.30 | 1.56
+------+
8x-SKYLAKE-UMA (comparison ratio; higher is better)
+------+
I_PSTATE/HWP 1C 3C | 4C |
pgbench-ro ~ ~ ~ | ~ |
pgbench-rw ~ ~ ~ | ~ |
netperf-udp ~ ~ ~ | ~ |
netperf-tcp ~ ~ ~ | ~ |
tbench4 1.30 1.14 1.14 | 1.16 |
+------+
48x-HASWELL-NUMA (comparison ratio; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 12C
pgbench-ro 1.15 ~ ~ | 1.06 | 1.16
pgbench-rw ~ ~ ~ | ~ | ~
netperf-udp 1.05 0.97 1.04 | 1.04 | 1.02
netperf-tcp 0.96 1.01 1.01 | 1.01 | 1.01
tbench4 1.50 1.05 1.13 | 1.13 | 1.25
+------+
In the table above we see that active intel_pstate is slightly better than our
4C-turbo patch (both in reference to the baseline non-invariant schedutil) on
read-only pgbench and much better on tbench. Both cases are notable in which
it shows that lowering our freq_max (to 8C-turbo and 12C-turbo on
80x-BROADWELL-NUMA and 48x-HASWELL-NUMA respectively) helps invariant
schedutil to get closer.
If we ignore active intel_pstate and focus on the comparison with baseline
alone, there are several instances of double-digit performance improvement.
80x-BROADWELL-NUMA (comparison ratio; lower is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
dbench4 1.23 0.95 0.95 | 0.95 | 0.95
kernbench 0.93 0.83 0.83 | 0.83 | 0.82
gitsource 0.98 0.49 0.49 | 0.49 | 0.48
+------+
8x-SKYLAKE-UMA (comparison ratio; lower is better)
+------+
I_PSTATE/HWP 1C 3C | 4C |
dbench4 ~ ~ ~ | ~ |
kernbench ~ ~ ~ | ~ |
gitsource 0.92 0.55 0.55 | 0.55 |
+------+
48x-HASWELL-NUMA (comparison ratio; lower is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
dbench4 ~ ~ ~ | ~ | ~
kernbench 0.94 0.90 0.89 | 0.90 | 0.90
gitsource 0.97 0.69 0.69 | 0.69 | 0.69
+------+
dbench is not very remarkable here, unless we notice how poorly active
intel_pstate is performing on 80x-BROADWELL-NUMA: 23% regression versus
non-invariant schedutil. We repeated that run getting consistent results. Out
of scope for the patch at hand, but deserving future investigation. Other than
that, we previously ran this campaign with Linux v5.0 and saw the patch doing
better on dbench a the time. We haven't checked closely and can only speculate
at this point.
On the NUMA boxes kernbench gets 10-15% improvements on average; we'll see in
the detailed tables that the gains concentrate on low process counts (lightly
loaded machines).
The test we call "gitsource" (running the git unit test suite, a long-running
single-threaded shell script) appears rather spectacular in this table (gains
of 30-50% depending on the machine). It is to be noted, however, that
gitsource has no adjustable parameters (such as the number of jobs in
kernbench, which we average over in order to get a single-number summary
score) and is exactly the kind of low-parallelism workload that benefits the
most from this patch. When looking at the detailed tables of kernbench or
tbench4, at low process or client counts one can see similar numbers.
5.3.3 SELECTION OF DETAILED RESULTS
-----------------------------------
Machine : 48x-HASWELL-NUMA
Benchmark : tbench4 (i.e. dbench4 over the network, actually loopback)
Varying parameter : number of clients
Unit : MB/sec (higher is better)
5.2.0 vanilla (BASELINE) 5.2.0 intel_pstate 5.2.0 1C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Hmean 1 126.73 +- 0.31% ( ) 315.91 +- 0.66% ( 149.28%) 125.03 +- 0.76% ( -1.34%)
Hmean 2 258.04 +- 0.62% ( ) 614.16 +- 0.51% ( 138.01%) 269.58 +- 1.45% ( 4.47%)
Hmean 4 514.30 +- 0.67% ( ) 1146.58 +- 0.54% ( 122.94%) 533.84 +- 1.99% ( 3.80%)
Hmean 8 1111.38 +- 2.52% ( ) 2159.78 +- 0.38% ( 94.33%) 1359.92 +- 1.56% ( 22.36%)
Hmean 16 2286.47 +- 1.36% ( ) 3338.29 +- 0.21% ( 46.00%) 2720.20 +- 0.52% ( 18.97%)
Hmean 32 4704.84 +- 0.35% ( ) 4759.03 +- 0.43% ( 1.15%) 4774.48 +- 0.30% ( 1.48%)
Hmean 64 7578.04 +- 0.27% ( ) 7533.70 +- 0.43% ( -0.59%) 7462.17 +- 0.65% ( -1.53%)
Hmean 128 6998.52 +- 0.16% ( ) 6987.59 +- 0.12% ( -0.16%) 6909.17 +- 0.14% ( -1.28%)
Hmean 192 6901.35 +- 0.25% ( ) 6913.16 +- 0.10% ( 0.17%) 6855.47 +- 0.21% ( -0.66%)
5.2.0 3C-turbo 5.2.0 4C-turbo 5.2.0 12C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Hmean 1 128.43 +- 0.28% ( 1.34%) 130.64 +- 3.81% ( 3.09%) 153.71 +- 5.89% ( 21.30%)
Hmean 2 311.70 +- 6.15% ( 20.79%) 281.66 +- 3.40% ( 9.15%) 305.08 +- 5.70% ( 18.23%)
Hmean 4 641.98 +- 2.32% ( 24.83%) 623.88 +- 5.28% ( 21.31%) 906.84 +- 4.65% ( 76.32%)
Hmean 8 1633.31 +- 1.56% ( 46.96%) 1714.16 +- 0.93% ( 54.24%) 2095.74 +- 0.47% ( 88.57%)
Hmean 16 3047.24 +- 0.42% ( 33.27%) 3155.02 +- 0.30% ( 37.99%) 3634.58 +- 0.15% ( 58.96%)
Hmean 32 4734.31 +- 0.60% ( 0.63%) 4804.38 +- 0.23% ( 2.12%) 4674.62 +- 0.27% ( -0.64%)
Hmean 64 7699.74 +- 0.35% ( 1.61%) 7499.72 +- 0.34% ( -1.03%) 7659.03 +- 0.25% ( 1.07%)
Hmean 128 6935.18 +- 0.15% ( -0.91%) 6942.54 +- 0.10% ( -0.80%) 7004.85 +- 0.12% ( 0.09%)
Hmean 192 6901.62 +- 0.12% ( 0.00%) 6856.93 +- 0.10% ( -0.64%) 6978.74 +- 0.10% ( 1.12%)
This is one of the cases where the patch still can't surpass active
intel_pstate, not even when freq_max is as low as 12C-turbo. Otherwise, gains are
visible up to 16 clients and the saturated scenario is the same as baseline.
The scores in the summary table from the previous sections are ratios of
geometric means of the results over different clients, as seen in this table.
Machine : 80x-BROADWELL-NUMA
Benchmark : kernbench (kernel compilation)
Varying parameter : number of jobs
Unit : seconds (lower is better)
5.2.0 vanilla (BASELINE) 5.2.0 intel_pstate 5.2.0 1C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 2 379.68 +- 0.06% ( ) 330.20 +- 0.43% ( 13.03%) 285.93 +- 0.07% ( 24.69%)
Amean 4 200.15 +- 0.24% ( ) 175.89 +- 0.22% ( 12.12%) 153.78 +- 0.25% ( 23.17%)
Amean 8 106.20 +- 0.31% ( ) 95.54 +- 0.23% ( 10.03%) 86.74 +- 0.10% ( 18.32%)
Amean 16 56.96 +- 1.31% ( ) 53.25 +- 1.22% ( 6.50%) 48.34 +- 1.73% ( 15.13%)
Amean 32 34.80 +- 2.46% ( ) 33.81 +- 0.77% ( 2.83%) 30.28 +- 1.59% ( 12.99%)
Amean 64 26.11 +- 1.63% ( ) 25.04 +- 1.07% ( 4.10%) 22.41 +- 2.37% ( 14.16%)
Amean 128 24.80 +- 1.36% ( ) 23.57 +- 1.23% ( 4.93%) 21.44 +- 1.37% ( 13.55%)
Amean 160 24.85 +- 0.56% ( ) 23.85 +- 1.17% ( 4.06%) 21.25 +- 1.12% ( 14.49%)
5.2.0 3C-turbo 5.2.0 4C-turbo 5.2.0 8C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 2 284.08 +- 0.13% ( 25.18%) 283.96 +- 0.51% ( 25.21%) 285.05 +- 0.21% ( 24.92%)
Amean 4 153.18 +- 0.22% ( 23.47%) 154.70 +- 1.64% ( 22.71%) 153.64 +- 0.30% ( 23.24%)
Amean 8 87.06 +- 0.28% ( 18.02%) 86.77 +- 0.46% ( 18.29%) 86.78 +- 0.22% ( 18.28%)
Amean 16 48.03 +- 0.93% ( 15.68%) 47.75 +- 1.99% ( 16.17%) 47.52 +- 1.61% ( 16.57%)
Amean 32 30.23 +- 1.20% ( 13.14%) 30.08 +- 1.67% ( 13.57%) 30.07 +- 1.67% ( 13.60%)
Amean 64 22.59 +- 2.02% ( 13.50%) 22.63 +- 0.81% ( 13.32%) 22.42 +- 0.76% ( 14.12%)
Amean 128 21.37 +- 0.67% ( 13.82%) 21.31 +- 1.15% ( 14.07%) 21.17 +- 1.93% ( 14.63%)
Amean 160 21.68 +- 0.57% ( 12.76%) 21.18 +- 1.74% ( 14.77%) 21.22 +- 1.00% ( 14.61%)
The patch outperform active intel_pstate (and baseline) by a considerable
margin; the summary table from the previous section says 4C turbo and active
intel_pstate are 0.83 and 0.93 against baseline respectively, so 4C turbo is
0.83/0.93=0.89 against intel_pstate (~10% better on average). There is no
noticeable difference with regard to the value of freq_max.
Machine : 8x-SKYLAKE-UMA
Benchmark : gitsource (time to run the git unit test suite)
Varying parameter : none
Unit : seconds (lower is better)
5.2.0 vanilla 5.2.0 intel_pstate/hwp 5.2.0 1C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 858.85 +- 1.16% ( ) 791.94 +- 0.21% ( 7.79%) 474.95 ( 44.70%)
5.2.0 3C-turbo 5.2.0 4C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 475.26 +- 0.20% ( 44.66%) 474.34 +- 0.13% ( 44.77%)
In this test, which is of interest as representing shell-intensive
(i.e. fork-intensive) serialized workloads, invariant schedutil outperforms
intel_pstate/powersave by a whopping 40% margin.
5.3.4 POWER CONSUMPTION, PERFORMANCE-PER-WATT
---------------------------------------------
The following table shows average power consumption in watt for each
benchmark. Data comes from turbostat (package average), which in turn is read
from the RAPL interface on CPUs. We know the patch affects CPU frequencies so
it's reasonable to ignore other power consumers (such as memory or I/O). Also,
we don't have a power meter available in the lab so RAPL is the best we have.
turbostat sampled average power every 10 seconds for the entire duration of
each benchmark. We took all those values and averaged them (i.e. with don't
have detail on a per-parameter granularity, only on whole benchmarks).
80x-BROADWELL-NUMA (power consumption, watts)
+--------+
BASELINE I_PSTATE 1C 3C | 4C | 8C
pgbench-ro 130.01 142.77 131.11 132.45 | 134.65 | 136.84
pgbench-rw 68.30 60.83 71.45 71.70 | 71.65 | 72.54
dbench4 90.25 59.06 101.43 99.89 | 101.10 | 102.94
netperf-udp 65.70 69.81 66.02 68.03 | 68.27 | 68.95
netperf-tcp 88.08 87.96 88.97 88.89 | 88.85 | 88.20
tbench4 142.32 176.73 153.02 163.91 | 165.58 | 176.07
kernbench 92.94 101.95 114.91 115.47 | 115.52 | 115.10
gitsource 40.92 41.87 75.14 75.20 | 75.40 | 75.70
+--------+
8x-SKYLAKE-UMA (power consumption, watts)
+--------+
BASELINE I_PSTATE/HWP 1C 3C | 4C |
pgbench-ro 46.49 46.68 46.56 46.59 | 46.52 |
pgbench-rw 29.34 31.38 30.98 31.00 | 31.00 |
dbench4 27.28 27.37 27.49 27.41 | 27.38 |
netperf-udp 22.33 22.41 22.36 22.35 | 22.36 |
netperf-tcp 27.29 27.29 27.30 27.31 | 27.33 |
tbench4 41.13 45.61 43.10 43.33 | 43.56 |
kernbench 42.56 42.63 43.01 43.01 | 43.01 |
gitsource 13.32 13.69 17.33 17.30 | 17.35 |
+--------+
48x-HASWELL-NUMA (power consumption, watts)
+--------+
BASELINE I_PSTATE 1C 3C | 4C | 12C
pgbench-ro 128.84 136.04 129.87 132.43 | 132.30 | 134.86
pgbench-rw 37.68 37.92 37.17 37.74 | 37.73 | 37.31
dbench4 28.56 28.73 28.60 28.73 | 28.70 | 28.79
netperf-udp 56.70 60.44 56.79 57.42 | 57.54 | 57.52
netperf-tcp 75.49 75.27 75.87 76.02 | 76.01 | 75.95
tbench4 115.44 139.51 119.53 123.07 | 123.97 | 130.22
kernbench 83.23 91.55 95.58 95.69 | 95.72 | 96.04
gitsource 36.79 36.99 39.99 40.34 | 40.35 | 40.23
+--------+
A lower power consumption isn't necessarily better, it depends on what is done
with that energy. Here are tables with the ratio of performance-per-watt on
each machine and benchmark. Higher is always better; a tilde (~) means a
neutral ratio (i.e. 1.00).
80x-BROADWELL-NUMA (performance-per-watt ratios; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
pgbench-ro 1.04 1.06 0.94 | 1.07 | 1.08
pgbench-rw 1.10 0.97 0.96 | 0.96 | 0.97
dbench4 1.24 0.94 0.95 | 0.94 | 0.92
netperf-udp ~ 1.02 1.02 | ~ | 1.02
netperf-tcp ~ 1.02 ~ | ~ | 1.02
tbench4 1.26 1.10 1.06 | 1.12 | 1.26
kernbench 0.98 0.97 0.97 | 0.97 | 0.98
gitsource ~ 1.11 1.11 | 1.11 | 1.13
+------+
8x-SKYLAKE-UMA (performance-per-watt ratios; higher is better)
+------+
I_PSTATE/HWP 1C 3C | 4C |
pgbench-ro ~ ~ ~ | ~ |
pgbench-rw 0.95 0.97 0.96 | 0.96 |
dbench4 ~ ~ ~ | ~ |
netperf-udp ~ ~ ~ | ~ |
netperf-tcp ~ ~ ~ | ~ |
tbench4 1.17 1.09 1.08 | 1.10 |
kernbench ~ ~ ~ | ~ |
gitsource 1.06 1.40 1.40 | 1.40 |
+------+
48x-HASWELL-NUMA (performance-per-watt ratios; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 12C
pgbench-ro 1.09 ~ 1.09 | 1.03 | 1.11
pgbench-rw ~ 0.86 ~ | ~ | 0.86
dbench4 ~ 1.02 1.02 | 1.02 | ~
netperf-udp ~ 0.97 1.03 | 1.02 | ~
netperf-tcp 0.96 ~ ~ | ~ | ~
tbench4 1.24 ~ 1.06 | 1.05 | 1.11
kernbench 0.97 0.97 0.98 | 0.97 | 0.96
gitsource 1.03 1.33 1.32 | 1.32 | 1.33
+------+
These results are overall pleasing: in plenty of cases we observe
performance-per-watt improvements. The few regressions (read/write pgbench and
dbench on the Broadwell machine) are of small magnitude. kernbench loses a few
percentage points (it has a 10-15% performance improvement, but apparently the
increase in power consumption is larger than that). tbench4 and gitsource, which
benefit the most from the patch, keep a positive score in this table which is
a welcome surprise; that suggests that in those particular workloads the
non-invariant schedutil (and active intel_pstate, too) makes some rather
suboptimal frequency selections.
+-------------------------------------------------------------------------+
| 6. MICROARCH'ES ADDRESSED HERE
+-------------------------------------------------------------------------+
The patch addresses Xeon Core processors that use MSR_PLATFORM_INFO and
MSR_TURBO_RATIO_LIMIT to advertise their base frequency and turbo frequencies
respectively. This excludes the recent Xeon Scalable Performance processors
line (Xeon Gold, Platinum etc) whose MSRs have to be parsed differently.
Subsequent patches will address:
* Xeon Scalable Performance processors and Atom Goldmont/Goldmont Plus
* Xeon Phi (Knights Landing, Knights Mill)
* Atom Silvermont
+-------------------------------------------------------------------------+
| 7. REFERENCES
+-------------------------------------------------------------------------+
Tests have been run with the help of the MMTests performance testing
framework, see github.com/gormanm/mmtests. The configuration file names for
the benchmark used are:
db-pgbench-timed-ro-small-xfs
db-pgbench-timed-rw-small-xfs
io-dbench4-async-xfs
network-netperf-unbound
network-tbench
scheduler-unbound
workload-kerndevel-xfs
workload-shellscripts-xfs
hpc-nas-c-class-mpi-full-xfs
hpc-nas-c-class-omp-full
All those benchmarks are generally available on the web:
pgbench: https://www.postgresql.org/docs/10/pgbench.html
netperf: https://hewlettpackard.github.io/netperf/
dbench/tbench: https://dbench.samba.org/
gitsource: git unit test suite, github.com/git/git
NAS Parallel Benchmarks: https://www.nas.nasa.gov/publications/npb.html
hackbench: https://people.redhat.com/mingo/cfs-scheduler/tools/hackbench.c
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Giovanni Gherdovich <ggherdovich@suse.cz>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Doug Smythies <dsmythies@telus.net>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lkml.kernel.org/r/20200122151617.531-2-ggherdovich@suse.cz
|
||
|
Vincent Guittot
|
2a4b03ffc6 |
sched/fair: Prevent unlimited runtime on throttled group
When a running task is moved on a throttled task group and there is no
other task enqueued on the CPU, the task can keep running using 100% CPU
whatever the allocated bandwidth for the group and although its cfs rq is
throttled. Furthermore, the group entity of the cfs_rq and its parents are
not enqueued but only set as curr on their respective cfs_rqs.
We have the following sequence:
sched_move_task
-dequeue_task: dequeue task and group_entities.
-put_prev_task: put task and group entities.
-sched_change_group: move task to new group.
-enqueue_task: enqueue only task but not group entities because cfs_rq is
throttled.
-set_next_task : set task and group_entities as current sched_entity of
their cfs_rq.
Another impact is that the root cfs_rq runnable_load_avg at root rq stays
null because the group_entities are not enqueued. This situation will stay
the same until an "external" event triggers a reschedule. Let trigger it
immediately instead.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Ben Segall <bsegall@google.com>
Link: https://lkml.kernel.org/r/1579011236-31256-1-git-send-email-vincent.guittot@linaro.org
|
||
|
Wanpeng Li
|
e938b9c941 |
sched/nohz: Optimize get_nohz_timer_target()
On a machine, CPU 0 is used for housekeeping, the other 39 CPUs in the
same socket are in nohz_full mode. We can observe huge time burn in the
loop for seaching nearest busy housekeeper cpu by ftrace.
2) | get_nohz_timer_target() {
2) 0.240 us | housekeeping_test_cpu();
2) 0.458 us | housekeeping_test_cpu();
...
2) 0.292 us | housekeeping_test_cpu();
2) 0.240 us | housekeeping_test_cpu();
2) 0.227 us | housekeeping_any_cpu();
2) + 43.460 us | }
This patch optimizes the searching logic by finding a nearest housekeeper
CPU in the housekeeping cpumask, it can minimize the worst searching time
from ~44us to < 10us in my testing. In addition, the last iterated busy
housekeeper can become a random candidate while current CPU is a better
fallback if it is a housekeeper.
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/1578876627-11938-1-git-send-email-wanpengli@tencent.com
|
||
|
Qais Yousef
|
b562d14064 |
sched/uclamp: Reject negative values in cpu_uclamp_write()
The check to ensure that the new written value into cpu.uclamp.{min,max}
is within range, [0:100], wasn't working because of the signed
comparison
7301 if (req.percent > UCLAMP_PERCENT_SCALE) {
7302 req.ret = -ERANGE;
7303 return req;
7304 }
# echo -1 > cpu.uclamp.min
# cat cpu.uclamp.min
42949671.96
Cast req.percent into u64 to force the comparison to be unsigned and
work as intended in capacity_from_percent().
# echo -1 > cpu.uclamp.min
sh: write error: Numerical result out of range
Fixes:
|
||
|
Mel Gorman
|
b396f52326 |
sched/fair: Allow a small load imbalance between low utilisation SD_NUMA domains
The CPU load balancer balances between different domains to spread load and strives to have equal balance everywhere. Communicating tasks can migrate so they are topologically close to each other but these decisions are independent. On a lightly loaded NUMA machine, two communicating tasks pulled together at wakeup time can be pushed apart by the load balancer. In isolation, the load balancer decision is fine but it ignores the tasks data locality and the wakeup/LB paths continually conflict. NUMA balancing is also a factor but it also simply conflicts with the load balancer. This patch allows a fixed degree of imbalance of two tasks to exist between NUMA domains regardless of utilisation levels. In many cases, this prevents communicating tasks being pulled apart. It was evaluated whether the imbalance should be scaled to the domain size. However, no additional benefit was measured across a range of workloads and machines and scaling adds the risk that lower domains have to be rebalanced. While this could change again in the future, such a change should specify the use case and benefit. The most obvious impact is on netperf TCP_STREAM -- two simple communicating tasks with some softirq offload depending on the transmission rate. 2-socket Haswell machine 48 core, HT enabled netperf-tcp -- mmtests config config-network-netperf-unbound baseline lbnuma-v3 Hmean 64 568.73 ( 0.00%) 577.56 * 1.55%* Hmean 128 1089.98 ( 0.00%) 1128.06 * 3.49%* Hmean 256 2061.72 ( 0.00%) 2104.39 * 2.07%* Hmean 1024 7254.27 ( 0.00%) 7557.52 * 4.18%* Hmean 2048 11729.20 ( 0.00%) 13350.67 * 13.82%* Hmean 3312 15309.08 ( 0.00%) 18058.95 * 17.96%* Hmean 4096 17338.75 ( 0.00%) 20483.66 * 18.14%* Hmean 8192 25047.12 ( 0.00%) 27806.84 * 11.02%* Hmean 16384 27359.55 ( 0.00%) 33071.88 * 20.88%* Stddev 64 2.16 ( 0.00%) 2.02 ( 6.53%) Stddev 128 2.31 ( 0.00%) 2.19 ( 5.05%) Stddev 256 11.88 ( 0.00%) 3.22 ( 72.88%) Stddev 1024 23.68 ( 0.00%) 7.24 ( 69.43%) Stddev 2048 79.46 ( 0.00%) 71.49 ( 10.03%) Stddev 3312 26.71 ( 0.00%) 57.80 (-116.41%) Stddev 4096 185.57 ( 0.00%) 96.15 ( 48.19%) Stddev 8192 245.80 ( 0.00%) 100.73 ( 59.02%) Stddev 16384 207.31 ( 0.00%) 141.65 ( 31.67%) In this case, there was a sizable improvement to performance and a general reduction in variance. However, this is not univeral. For most machines, the impact was roughly a 3% performance gain. Ops NUMA base-page range updates 19796.00 292.00 Ops NUMA PTE updates 19796.00 292.00 Ops NUMA PMD updates 0.00 0.00 Ops NUMA hint faults 16113.00 143.00 Ops NUMA hint local faults % 8407.00 142.00 Ops NUMA hint local percent 52.18 99.30 Ops NUMA pages migrated 4244.00 1.00 Without the patch, only 52.18% of sampled accesses are local. In an earlier changelog, 100% of sampled accesses are local and indeed on most machines, this was still the case. In this specific case, the local sampled rates was 99.3% but note the "base-page range updates" and "PTE updates". The activity with the patch is negligible as were the number of faults. The small number of pages migrated were related to shared libraries. A 2-socket Broadwell showed better results on average but are not presented for brevity as the performance was similar except it showed 100% of the sampled NUMA hints were local. The patch holds up for a 4-socket Haswell, an AMD EPYC and AMD Epyc 2 machine. For dbench, the impact depends on the filesystem used and the number of clients. On XFS, there is little difference as the clients typically communicate with workqueues which have a separate class of scheduler problem at the moment. For ext4, performance is generally better, particularly for small numbers of clients as NUMA balancing activity is negligible with the patch applied. A more interesting example is the Facebook schbench which uses a number of messaging threads to communicate with worker threads. In this configuration, one messaging thread is used per NUMA node and the number of worker threads is varied. The 50, 75, 90, 95, 99, 99.5 and 99.9 percentiles for response latency is then reported. Lat 50.00th-qrtle-1 44.00 ( 0.00%) 37.00 ( 15.91%) Lat 75.00th-qrtle-1 53.00 ( 0.00%) 41.00 ( 22.64%) Lat 90.00th-qrtle-1 57.00 ( 0.00%) 42.00 ( 26.32%) Lat 95.00th-qrtle-1 63.00 ( 0.00%) 43.00 ( 31.75%) Lat 99.00th-qrtle-1 76.00 ( 0.00%) 51.00 ( 32.89%) Lat 99.50th-qrtle-1 89.00 ( 0.00%) 52.00 ( 41.57%) Lat 99.90th-qrtle-1 98.00 ( 0.00%) 55.00 ( 43.88%) Lat 50.00th-qrtle-2 42.00 ( 0.00%) 42.00 ( 0.00%) Lat 75.00th-qrtle-2 48.00 ( 0.00%) 47.00 ( 2.08%) Lat 90.00th-qrtle-2 53.00 ( 0.00%) 52.00 ( 1.89%) Lat 95.00th-qrtle-2 55.00 ( 0.00%) 53.00 ( 3.64%) Lat 99.00th-qrtle-2 62.00 ( 0.00%) 60.00 ( 3.23%) Lat 99.50th-qrtle-2 63.00 ( 0.00%) 63.00 ( 0.00%) Lat 99.90th-qrtle-2 68.00 ( 0.00%) 66.00 ( 2.94% For higher worker threads, the differences become negligible but it's interesting to note the difference in wakeup latency at low utilisation and mpstat confirms that activity was almost all on one node until the number of worker threads increase. Hackbench generally showed neutral results across a range of machines. This is different to earlier versions of the patch which allowed imbalances for higher degrees of utilisation. perf bench pipe showed negligible differences in overall performance as the differences are very close to the noise. An earlier prototype of the patch showed major regressions for NAS C-class when running with only half of the available CPUs -- 20-30% performance hits were measured at the time. With this version of the patch, the impact is negligible with small gains/losses within the noise measured. This is because the number of threads far exceeds the small imbalance the aptch cares about. Similarly, there were report of regressions for the autonuma benchmark against earlier versions but again, normal load balancing now applies for that workload. In general, the patch simply seeks to avoid unnecessary cross-node migrations in the basic case where imbalances are very small. For low utilisation communicating workloads, this patch generally behaves better with less NUMA balancing activity. For high utilisation, there is no change in behaviour. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Valentin Schneider <valentin.schneider@arm.com> Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Phil Auld <pauld@redhat.com> Tested-by: Phil Auld <pauld@redhat.com> Link: https://lkml.kernel.org/r/20200114101319.GO3466@techsingularity.net |
||
|
Peter Zijlstra (Intel)
|
ebc0f83c78 |
timers/nohz: Update NOHZ load in remote tick
The way loadavg is tracked during nohz only pays attention to the load upon entering nohz. This can be particularly noticeable if full nohz is entered while non-idle, and then the cpu goes idle and stays that way for a long time. Use the remote tick to ensure that full nohz cpus report their deltas within a reasonable time. [ swood: Added changelog and removed recheck of stopped tick. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Scott Wood <swood@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lkml.kernel.org/r/1578736419-14628-3-git-send-email-swood@redhat.com |
||
|
Scott Wood
|
488603b815 |
sched/core: Don't skip remote tick for idle CPUs
This will be used in the next patch to get a loadavg update from nohz cpus. The delta check is skipped because idle_sched_class doesn't update se.exec_start. Signed-off-by: Scott Wood <swood@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lkml.kernel.org/r/1578736419-14628-2-git-send-email-swood@redhat.com |
||
|
Song Liu
|
07c5972951 |
perf/cgroups: Install cgroup events to correct cpuctx
cgroup events are always installed in the cpuctx. However, when it is not
installed via IPI, list_update_cgroup_event() adds it to cpuctx of current
CPU, which triggers list corruption:
[] list_add double add: new=ffff888ff7cf0db0, prev=ffff888ff7ce82f0, next=ffff888ff7cf0db0.
To reproduce this, we can simply run:
# perf stat -e cs -a &
# perf stat -e cs -G anycgroup
Fix this by installing it to cpuctx that contains event->ctx, and the
proper cgrp_cpuctx_list.
Fixes:
|
||
|
Song Liu
|
003461559e |
perf/core: Fix mlock accounting in perf_mmap()
Decreasing sysctl_perf_event_mlock between two consecutive perf_mmap()s of
a perf ring buffer may lead to an integer underflow in locked memory
accounting. This may lead to the undesired behaviors, such as failures in
BPF map creation.
Address this by adjusting the accounting logic to take into account the
possibility that the amount of already locked memory may exceed the
current limit.
Fixes:
|
||
|
Linus Torvalds
|
c677124e63 |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
"These were the main changes in this cycle:
- More -rt motivated separation of CONFIG_PREEMPT and
CONFIG_PREEMPTION.
- Add more low level scheduling topology sanity checks and warnings
to filter out nonsensical topologies that break scheduling.
- Extend uclamp constraints to influence wakeup CPU placement
- Make the RT scheduler more aware of asymmetric topologies and CPU
capacities, via uclamp metrics, if CONFIG_UCLAMP_TASK=y
- Make idle CPU selection more consistent
- Various fixes, smaller cleanups, updates and enhancements - please
see the git log for details"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (58 commits)
sched/fair: Define sched_idle_cpu() only for SMP configurations
sched/topology: Assert non-NUMA topology masks don't (partially) overlap
idle: fix spelling mistake "iterrupts" -> "interrupts"
sched/fair: Remove redundant call to cpufreq_update_util()
sched/psi: create /proc/pressure and /proc/pressure/{io|memory|cpu} only when psi enabled
sched/fair: Fix sgc->{min,max}_capacity calculation for SD_OVERLAP
sched/fair: calculate delta runnable load only when it's needed
sched/cputime: move rq parameter in irqtime_account_process_tick
stop_machine: Make stop_cpus() static
sched/debug: Reset watchdog on all CPUs while processing sysrq-t
sched/core: Fix size of rq::uclamp initialization
sched/uclamp: Fix a bug in propagating uclamp value in new cgroups
sched/fair: Load balance aggressively for SCHED_IDLE CPUs
sched/fair : Improve update_sd_pick_busiest for spare capacity case
watchdog: Remove soft_lockup_hrtimer_cnt and related code
sched/rt: Make RT capacity-aware
sched/fair: Make EAS wakeup placement consider uclamp restrictions
sched/fair: Make task_fits_capacity() consider uclamp restrictions
sched/uclamp: Rename uclamp_util_with() into uclamp_rq_util_with()
sched/uclamp: Make uclamp util helpers use and return UL values
...
|
||
|
Linus Torvalds
|
c0e809e244 |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"Kernel side changes:
- Ftrace is one of the last W^X violators (after this only KLP is
left). These patches move it over to the generic text_poke()
interface and thereby get rid of this oddity. This requires a
surprising amount of surgery, by Peter Zijlstra.
- x86/AMD PMUs: add support for 'Large Increment per Cycle Events' to
count certain types of events that have a special, quirky hw ABI
(by Kim Phillips)
- kprobes fixes by Masami Hiramatsu
Lots of tooling updates as well, the following subcommands were
updated: annotate/report/top, c2c, clang, record, report/top TUI,
sched timehist, tests; plus updates were done to the gtk ui, libperf,
headers and the parser"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
perf/x86/amd: Add support for Large Increment per Cycle Events
perf/x86/amd: Constrain Large Increment per Cycle events
perf/x86/intel/rapl: Add Comet Lake support
tracing: Initialize ret in syscall_enter_define_fields()
perf header: Use last modification time for timestamp
perf c2c: Fix return type for histogram sorting comparision functions
perf beauty sockaddr: Fix augmented syscall format warning
perf/ui/gtk: Fix gtk2 build
perf ui gtk: Add missing zalloc object
perf tools: Use %define api.pure full instead of %pure-parser
libperf: Setup initial evlist::all_cpus value
perf report: Fix no libunwind compiled warning break s390 issue
perf tools: Support --prefix/--prefix-strip
perf report: Clarify in help that --children is default
tools build: Fix test-clang.cpp with Clang 8+
perf clang: Fix build with Clang 9
kprobes: Fix optimize_kprobe()/unoptimize_kprobe() cancellation logic
tools lib: Fix builds when glibc contains strlcpy()
perf report/top: Make 'e' visible in the help and make it toggle showing callchains
perf report/top: Do not offer annotation for symbols without samples
...
|
||
|
Linus Torvalds
|
2180f214f4 |
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar: "Just a handful of changes in this cycle: an ARM64 performance optimization, a comment fix and a debug output fix" * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: locking/osq: Use optimized spinning loop for arm64 locking/qspinlock: Fix inaccessible URL of MCS lock paper locking/lockdep: Fix lockdep_stats indentation problem |
||
|
Linus Torvalds
|
d99391ec2b |
Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RCU updates from Ingo Molnar: "The RCU changes in this cycle were: - Expedited grace-period updates - kfree_rcu() updates - RCU list updates - Preemptible RCU updates - Torture-test updates - Miscellaneous fixes - Documentation updates" * 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits) rcu: Remove unused stop-machine #include powerpc: Remove comment about read_barrier_depends() .mailmap: Add entries for old paulmck@kernel.org addresses srcu: Apply *_ONCE() to ->srcu_last_gp_end rcu: Switch force_qs_rnp() to for_each_leaf_node_cpu_mask() rcu: Move rcu_{expedited,normal} definitions into rcupdate.h rcu: Move gp_state_names[] and gp_state_getname() to tree_stall.h rcu: Remove the declaration of call_rcu() in tree.h rcu: Fix tracepoint tracking RCU CPU kthread utilization rcu: Fix harmless omission of "CONFIG_" from #if condition rcu: Avoid tick_dep_set_cpu() misordering rcu: Provide wrappers for uses of ->rcu_read_lock_nesting rcu: Use READ_ONCE() for ->expmask in rcu_read_unlock_special() rcu: Clear ->rcu_read_unlock_special only once rcu: Clear .exp_hint only when deferred quiescent state has been reported rcu: Rename some instance of CONFIG_PREEMPTION to CONFIG_PREEMPT_RCU rcu: Remove kfree_call_rcu_nobatch() rcu: Remove kfree_rcu() special casing and lazy-callback handling rcu: Add support for debug_objects debugging for kfree_rcu() rcu: Add multiple in-flight batches of kfree_rcu() work ... |
||
|
Sebastian Andrzej Siewior
|
25a3a15417 |
smp: Remove superfluous cond_func check in smp_call_function_many_cond()
It was requested to remove the cond_func check but the follow up patch was
overlooked. Remove it now.
Fixes:
|
||
|
Mike Christie
|
8d19f1c8e1 |
prctl: PR_{G,S}ET_IO_FLUSHER to support controlling memory reclaim
There are several storage drivers like dm-multipath, iscsi, tcmu-runner, amd nbd that have userspace components that can run in the IO path. For example, iscsi and nbd's userspace deamons may need to recreate a socket and/or send IO on it, and dm-multipath's daemon multipathd may need to send SG IO or read/write IO to figure out the state of paths and re-set them up. In the kernel these drivers have access to GFP_NOIO/GFP_NOFS and the memalloc_*_save/restore functions to control the allocation behavior, but for userspace we would end up hitting an allocation that ended up writing data back to the same device we are trying to allocate for. The device is then in a state of deadlock, because to execute IO the device needs to allocate memory, but to allocate memory the memory layers want execute IO to the device. Here is an example with nbd using a local userspace daemon that performs network IO to a remote server. We are using XFS on top of the nbd device, but it can happen with any FS or other modules layered on top of the nbd device that can write out data to free memory. Here a nbd daemon helper thread, msgr-worker-1, is performing a write/sendmsg on a socket to execute a request. This kicks off a reclaim operation which results in a WRITE to the nbd device and the nbd thread calling back into the mm layer. [ 1626.609191] msgr-worker-1 D 0 1026 1 0x00004000 [ 1626.609193] Call Trace: [ 1626.609195] ? __schedule+0x29b/0x630 [ 1626.609197] ? wait_for_completion+0xe0/0x170 [ 1626.609198] schedule+0x30/0xb0 [ 1626.609200] schedule_timeout+0x1f6/0x2f0 [ 1626.609202] ? blk_finish_plug+0x21/0x2e [ 1626.609204] ? _xfs_buf_ioapply+0x2e6/0x410 [ 1626.609206] ? wait_for_completion+0xe0/0x170 [ 1626.609208] wait_for_completion+0x108/0x170 [ 1626.609210] ? wake_up_q+0x70/0x70 [ 1626.609212] ? __xfs_buf_submit+0x12e/0x250 [ 1626.609214] ? xfs_bwrite+0x25/0x60 [ 1626.609215] xfs_buf_iowait+0x22/0xf0 [ 1626.609218] __xfs_buf_submit+0x12e/0x250 [ 1626.609220] xfs_bwrite+0x25/0x60 [ 1626.609222] xfs_reclaim_inode+0x2e8/0x310 [ 1626.609224] xfs_reclaim_inodes_ag+0x1b6/0x300 [ 1626.609227] xfs_reclaim_inodes_nr+0x31/0x40 [ 1626.609228] super_cache_scan+0x152/0x1a0 [ 1626.609231] do_shrink_slab+0x12c/0x2d0 [ 1626.609233] shrink_slab+0x9c/0x2a0 [ 1626.609235] shrink_node+0xd7/0x470 [ 1626.609237] do_try_to_free_pages+0xbf/0x380 [ 1626.609240] try_to_free_pages+0xd9/0x1f0 [ 1626.609245] __alloc_pages_slowpath+0x3a4/0xd30 [ 1626.609251] ? ___slab_alloc+0x238/0x560 [ 1626.609254] __alloc_pages_nodemask+0x30c/0x350 [ 1626.609259] skb_page_frag_refill+0x97/0xd0 [ 1626.609274] sk_page_frag_refill+0x1d/0x80 [ 1626.609279] tcp_sendmsg_locked+0x2bb/0xdd0 [ 1626.609304] tcp_sendmsg+0x27/0x40 [ 1626.609307] sock_sendmsg+0x54/0x60 [ 1626.609308] ___sys_sendmsg+0x29f/0x320 [ 1626.609313] ? sock_poll+0x66/0xb0 [ 1626.609318] ? ep_item_poll.isra.15+0x40/0xc0 [ 1626.609320] ? ep_send_events_proc+0xe6/0x230 [ 1626.609322] ? hrtimer_try_to_cancel+0x54/0xf0 [ 1626.609324] ? ep_read_events_proc+0xc0/0xc0 [ 1626.609326] ? _raw_write_unlock_irq+0xa/0x20 [ 1626.609327] ? ep_scan_ready_list.constprop.19+0x218/0x230 [ 1626.609329] ? __hrtimer_init+0xb0/0xb0 [ 1626.609331] ? _raw_spin_unlock_irq+0xa/0x20 [ 1626.609334] ? ep_poll+0x26c/0x4a0 [ 1626.609337] ? tcp_tsq_write.part.54+0xa0/0xa0 [ 1626.609339] ? release_sock+0x43/0x90 [ 1626.609341] ? _raw_spin_unlock_bh+0xa/0x20 [ 1626.609342] __sys_sendmsg+0x47/0x80 [ 1626.609347] do_syscall_64+0x5f/0x1c0 [ 1626.609349] ? prepare_exit_to_usermode+0x75/0xa0 [ 1626.609351] entry_SYSCALL_64_after_hwframe+0x44/0xa9 This patch adds a new prctl command that daemons can use after they have done their initial setup, and before they start to do allocations that are in the IO path. It sets the PF_MEMALLOC_NOIO and PF_LESS_THROTTLE flags so both userspace block and FS threads can use it to avoid the allocation recursion and try to prevent from being throttled while writing out data to free up memory. Signed-off-by: Mike Christie <mchristi@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Tested-by: Masato Suzuki <masato.suzuki@wdc.com> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Link: https://lore.kernel.org/r/20191112001900.9206-1-mchristi@redhat.com Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> |
||
|
Ingo Molnar
|
0cc4bd8f70 |
Merge branch 'core/kprobes' into perf/core, to pick up fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org> |
||
|
Linus Torvalds
|
3d3b44a61a |
Merge tag 'irq-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq updates from Thomas Gleixner:
"The interrupt departement provides:
- A mechanism to shield isolated tasks from managed interrupts:
The affinity of managed interrupts is completely controlled by the
kernel and user space has no influence on them. The reason is that
the automatically assigned affinity correlates to the multi-queue
CPU handling of block devices.
If the generated affinity mask spaws both housekeeping and isolated
CPUs the interrupt could be routed to an isolated CPU which would
then be disturbed by I/O submitted by a housekeeping CPU.
The new mechamism ensures that as long as one housekeeping CPU is
online in the assigned affinity mask the interrupt is routed to a
housekeeping CPU.
If there is no online housekeeping CPU in the affinity mask, then
the interrupt is routed to an isolated CPU to keep the device queue
intact, but unless the isolated CPU submits I/O by itself these
interrupts are not raised.
- A small addon to the device tree irqdomain core code to avoid
duplication in irq chip drivers
- Conversion of the SiFive PLIC to hierarchical domains
- The usual pile of new irq chip drivers: SiFive GPIO, Aspeed SCI,
NXP INTMUX, Meson A1 GPIO
- The first cut of support for the new ARM GICv4.1
- The usual pile of fixes and improvements in core and driver code"
* tag 'irq-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
genirq, sched/isolation: Isolate from handling managed interrupts
irqchip/gic-v4.1: Allow direct invalidation of VLPIs
irqchip/gic-v4.1: Suppress per-VLPI doorbell
irqchip/gic-v4.1: Add VPE INVALL callback
irqchip/gic-v4.1: Add VPE eviction callback
irqchip/gic-v4.1: Add VPE residency callback
irqchip/gic-v4.1: Add mask/unmask doorbell callbacks
irqchip/gic-v4.1: Plumb skeletal VPE irqchip
irqchip/gic-v4.1: Implement the v4.1 flavour of VMOVP
irqchip/gic-v4.1: Don't use the VPE proxy if RVPEID is set
irqchip/gic-v4.1: Implement the v4.1 flavour of VMAPP
irqchip/gic-v4.1: VPE table (aka GICR_VPROPBASER) allocation
irqchip/gic-v3: Add GICv4.1 VPEID size discovery
irqchip/gic-v3: Detect GICv4.1 supporting RVPEID
irqchip/gic-v3-its: Fix get_vlpi_map() breakage with doorbells
irqdomain: Fix a memory leak in irq_domain_push_irq()
irqchip: Add NXP INTMUX interrupt multiplexer support
dt-bindings: interrupt-controller: Add binding for NXP INTMUX interrupt multiplexer
irqchip: Define EXYNOS_IRQ_COMBINER
irqchip/meson-gpio: Add support for meson a1 SoCs
...
|
||
|
Linus Torvalds
|
ab67f60025 |
Merge tag 'smp-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core SMP updates from Thomas Gleixner:
"A small set of SMP core code changes:
- Rework the smp function call core code to avoid the allocation of
an additional cpumask
- Remove the not longer required GFP argument from on_each_cpu_cond()
and on_each_cpu_cond_mask() and fixup the callers"
* tag 'smp-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
smp: Remove allocation mask from on_each_cpu_cond.*()
smp: Add a smp_cond_func_t argument to smp_call_function_many()
smp: Use smp_cond_func_t as type for the conditional function
|
||
|
Linus Torvalds
|
e279160f49 |
Merge tag 'timers-core-2020-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer updates from Thomas Gleixner:
"The timekeeping and timers departement provides:
- Time namespace support:
If a container migrates from one host to another then it expects
that clocks based on MONOTONIC and BOOTTIME are not subject to
disruption. Due to different boot time and non-suspended runtime
these clocks can differ significantly on two hosts, in the worst
case time goes backwards which is a violation of the POSIX
requirements.
The time namespace addresses this problem. It allows to set offsets
for clock MONOTONIC and BOOTTIME once after creation and before
tasks are associated with the namespace. These offsets are taken
into account by timers and timekeeping including the VDSO.
Offsets for wall clock based clocks (REALTIME/TAI) are not provided
by this mechanism. While in theory possible, the overhead and code
complexity would be immense and not justified by the esoteric
potential use cases which were discussed at Plumbers '18.
The overhead for tasks in the root namespace (ie where host time
offsets = 0) is in the noise and great effort was made to ensure
that especially in the VDSO. If time namespace is disabled in the
kernel configuration the code is compiled out.
Kudos to Andrei Vagin and Dmitry Sofanov who implemented this
feature and kept on for more than a year addressing review
comments, finding better solutions. A pleasant experience.
- Overhaul of the alarmtimer device dependency handling to ensure
that the init/suspend/resume ordering is correct.
- A new clocksource/event driver for Microchip PIT64
- Suspend/resume support for the Hyper-V clocksource
- The usual pile of fixes, updates and improvements mostly in the
driver code"
* tag 'timers-core-2020-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (71 commits)
alarmtimer: Make alarmtimer_get_rtcdev() a stub when CONFIG_RTC_CLASS=n
alarmtimer: Use wakeup source from alarmtimer platform device
alarmtimer: Make alarmtimer platform device child of RTC device
alarmtimer: Update alarmtimer_get_rtcdev() docs to reflect reality
hrtimer: Add missing sparse annotation for __run_timer()
lib/vdso: Only read hrtimer_res when needed in __cvdso_clock_getres()
MIPS: vdso: Define BUILD_VDSO32 when building a 32bit kernel
clocksource/drivers/hyper-v: Set TSC clocksource as default w/ InvariantTSC
clocksource/drivers/hyper-v: Untangle stimers and timesync from clocksources
clocksource/drivers/timer-microchip-pit64b: Fix sparse warning
clocksource/drivers/exynos_mct: Rename Exynos to lowercase
clocksource/drivers/timer-ti-dm: Fix uninitialized pointer access
clocksource/drivers/timer-ti-dm: Switch to platform_get_irq
clocksource/drivers/timer-ti-dm: Convert to devm_platform_ioremap_resource
clocksource/drivers/em_sti: Fix variable declaration in em_sti_probe
clocksource/drivers/em_sti: Convert to devm_platform_ioremap_resource
clocksource/drivers/bcm2835_timer: Fix memory leak of timer
clocksource/drivers/cadence-ttc: Use ttc driver as platform driver
clocksource/drivers/timer-microchip-pit64b: Add Microchip PIT64B support
clocksource/drivers/hyper-v: Reserve PAGE_SIZE space for tsc page
...
|
||
|
Linus Torvalds
|
b11c89a158 |
Merge tag 'core-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull watchdog updates from Thomas Gleixner:
"A set of watchdog/softlockup related improvements:
- Enforce that the watchdog timestamp is always valid on boot. The
original implementation caused a watchdog disabled gap of one
second in the boot process due to truncation of the underlying
sched clock.
The sched clock is divided by 1e9 to convert nanoseconds to
seconds. So for the first second of the boot process the result is
0 which is at the same time the indicator to disable the watchdog.
The trivial fix is to change the disabled indicator to ULONG_MAX.
- Two cleanup patches removing unused and redundant code which got
forgotten to be cleaned up in previous changes"
* tag 'core-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
watchdog/softlockup: Enforce that timestamp is valid on boot
watchdog/softlockup: Remove obsolete check of last reported task
watchdog: Remove soft_lockup_hrtimer_cnt and related code
|
||
|
Linus Torvalds
|
a56c41e5d7 |
Merge tag 'timers-urgent-2020-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer fixes from Thomas Gleixner:
"Two fixes for the generic VDSO code which missed 5.5:
- Make the update to the coarse timekeeper unconditional.
This is required because the coarse timekeeper interfaces in the
VDSO do not depend on a VDSO capable clocksource. If the system
does not have a VDSO capable clocksource and the update is
depending on the VDSO capable clocksource, the coarse VDSO
interfaces would operate on stale data forever.
- Invert the logic of __arch_update_vdso_data() to avoid further head
scratching.
Tripped over this several times while analyzing the update problem
above"
* tag 'timers-urgent-2020-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
lib/vdso: Update coarse timekeeper unconditionally
lib/vdso: Make __arch_update_vdso_data() logic understandable
|
||
|
Linus Torvalds
|
07e309a972 |
Merge tag 'audit-pr-20200127' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit
Pull audit update from Paul Moore: "One small audit patch for the Linux v5.6 merge window, and unsurprisingly it passes our test suite with flying colors" * tag 'audit-pr-20200127' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit: audit: Add __rcu annotation to RCU pointer |
||
|
Linus Torvalds
|
03aa8c8cfa |
Merge branch 'for-5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup updates from Tejun Heo: - cgroup2 interface for hugetlb controller. I think this was the last remaining bit which was missing from cgroup2 - fixes for race and a spurious warning in threaded cgroup handling - other minor changes * 'for-5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: iocost: Fix iocost_monitor.py due to helper type mismatch cgroup: Prevent double killing of css when enabling threaded cgroup cgroup: fix function name in comment mm: hugetlb controller for cgroups v2 |
||
|
Linus Torvalds
|
16d06120d7 |
Merge branch 'for-5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq
Pull workqueue updates from Tejun Heo: "Just a couple tracepoint patches" * 'for-5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: workqueue: remove workqueue_work event class workqueue: add worker function to workqueue_execute_end tracepoint |
||
|
Linus Torvalds
|
6d277aca48 |
Merge tag 'pm-5.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management updates from Rafael Wysocki:
"These add ACPI support to the intel_idle driver along with an admin
guide document for it, add support for CPR (Core Power Reduction) to
the AVS (Adaptive Voltage Scaling) subsystem, add new hardware support
in a few places, add some new sysfs attributes, debugfs files and
tracepoints, fix bugs and clean up a bunch of things all over.
Specifics:
- Update the ACPI processor driver in order to export
acpi_processor_evaluate_cst() to the code outside of it, add ACPI
support to the intel_idle driver based on that and clean up that
driver somewhat (Rafael Wysocki).
- Add an admin guide document for the intel_idle driver (Rafael
Wysocki).
- Clean up cpuidle core and drivers, enable compilation testing for
some of them (Benjamin Gaignard, Krzysztof Kozlowski, Rafael
Wysocki, Yangtao Li).
- Fix reference counting of OPP (operating performance points) table
structures (Viresh Kumar).
- Add support for CPR (Core Power Reduction) to the AVS (Adaptive
Voltage Scaling) subsystem (Niklas Cassel, Colin Ian King,
YueHaibing).
- Add support for TigerLake Mobile and JasperLake to the Intel RAPL
power capping driver (Zhang Rui).
- Update cpufreq drivers:
- Add i.MX8MP support to imx-cpufreq-dt (Anson Huang).
- Fix usage of a macro in loongson2_cpufreq (Alexandre Oliva).
- Fix cpufreq policy reference counting issues in s3c and
brcmstb-avs (chenqiwu).
- Fix ACPI table reference counting issue and HiSilicon quirk
handling in the CPPC driver (Hanjun Guo).
- Clean up spelling mistake in intel_pstate (Harry Pan).
- Convert the kirkwood and tegra186 drivers to using
devm_platform_ioremap_resource() (Yangtao Li).
- Update devfreq core:
- Add 'name' sysfs attribute for devfreq devices (Chanwoo Choi).
- Clean up the handing of transition statistics and allow them to
be reset by writing 0 to the 'trans_stat' devfreq device
attribute in sysfs (Kamil Konieczny).
- Add 'devfreq_summary' to debugfs (Chanwoo Choi).
- Clean up kerneldoc comments and Kconfig indentation (Krzysztof
Kozlowski, Randy Dunlap).
- Update devfreq drivers:
- Add dynamic scaling for the imx8m DDR controller and clean up
imx8m-ddrc (Leonard Crestez, YueHaibing).
- Fix DT node reference counting and nitialization error code path
in rk3399_dmc and add COMPILE_TEST and HAVE_ARM_SMCCC dependency
for it (Chanwoo Choi, Yangtao Li).
- Fix DT node reference counting in rockchip-dfi and make it use
devm_platform_ioremap_resource() (Yangtao Li).
- Fix excessive stack usage in exynos-ppmu (Arnd Bergmann).
- Fix initialization error code paths in exynos-bus (Yangtao Li).
- Clean up exynos-bus and exynos somewhat (Artur Świgoń, Krzysztof
Kozlowski).
- Add tracepoints for tracking usage_count updates unrelated to
status changes in PM-runtime (Michał Mirosław).
- Add sysfs attribute to control the "sync on suspend" behavior
during system-wide suspend (Jonas Meurer).
- Switch system-wide suspend tests over to 64-bit time (Alexandre
Belloni).
- Make wakeup sources statistics in debugfs cover deleted ones which
used to be the case some time ago (zhuguangqing).
- Clean up computations carried out during hibernation, update
messages related to hibernation and fix a spelling mistake in one
of them (Wen Yang, Luigi Semenzato, Colin Ian King).
- Add mailmap entry for maintainer e-mail address that has not been
functional for several years (Rafael Wysocki)"
* tag 'pm-5.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (83 commits)
cpufreq: loongson2_cpufreq: adjust cpufreq uses of LOONGSON_CHIPCFG
intel_idle: Clean up irtl_2_usec()
intel_idle: Move 3 functions closer to their callers
intel_idle: Annotate initialization code and data structures
intel_idle: Move and clean up intel_idle_cpuidle_devices_uninit()
intel_idle: Rearrange intel_idle_cpuidle_driver_init()
intel_idle: Clean up NULL pointer check in intel_idle_init()
intel_idle: Fold intel_idle_probe() into intel_idle_init()
intel_idle: Eliminate __setup_broadcast_timer()
cpuidle: fix cpuidle_find_deepest_state() kerneldoc warnings
cpuidle: sysfs: fix warnings when compiling with W=1
cpuidle: coupled: fix warnings when compiling with W=1
cpufreq: brcmstb-avs: fix imbalance of cpufreq policy refcount
PM: suspend: Add sysfs attribute to control the "sync on suspend" behavior
PM / devfreq: Add debugfs support with devfreq_summary file
Documentation: admin-guide: PM: Add intel_idle document
cpuidle: arm: Enable compile testing for some of drivers
PM-runtime: add tracepoints for usage_count changes
cpufreq: intel_pstate: fix spelling mistake: "Whethet" -> "Whether"
PM: hibernate: fix spelling mistake "shapshot" -> "snapshot"
...
|
||
|
Linus Torvalds
|
0238d3c753 |
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Will Deacon:
"The changes are a real mixed bag this time around.
The only scary looking one from the diffstat is the uapi change to
asm-generic/mman-common.h, but this has been acked by Arnd and is
actually just adding a pair of comments in an attempt to prevent
allocation of some PROT values which tend to get used for
arch-specific purposes. We'll be using them for Branch Target
Identification (a CFI-like hardening feature), which is currently
under review on the mailing list.
New architecture features:
- Support for Armv8.5 E0PD, which benefits KASLR in the same way as
KPTI but without the overhead. This allows KPTI to be disabled on
CPUs that are not affected by Meltdown, even is KASLR is enabled.
- Initial support for the Armv8.5 RNG instructions, which claim to
provide access to a high bandwidth, cryptographically secure
hardware random number generator. As well as exposing these to
userspace, we also use them as part of the KASLR seed and to seed
the crng once all CPUs have come online.
- Advertise a bunch of new instructions to userspace, including
support for Data Gathering Hint, Matrix Multiply and 16-bit
floating point.
Kexec:
- Cleanups in preparation for relocating with the MMU enabled
- Support for loading crash dump kernels with kexec_file_load()
Perf and PMU drivers:
- Cleanups and non-critical fixes for a couple of system PMU drivers
FPU-less (aka broken) CPU support:
- Considerable fixes to support CPUs without the FP/SIMD extensions,
including their presence in heterogeneous systems. Good luck
finding a 64-bit userspace that handles this.
Modern assembly function annotations:
- Start migrating our use of ENTRY() and ENDPROC() over to the
new-fangled SYM_{CODE,FUNC}_{START,END} macros, which are intended
to aid debuggers
Kbuild:
- Cleanup detection of LSE support in the assembler by introducing
'as-instr'
- Remove compressed Image files when building clean targets
IP checksumming:
- Implement optimised IPv4 checksumming routine when hardware offload
is not in use. An IPv6 version is in the works, pending testing.
Hardware errata:
- Work around Cortex-A55 erratum #1530923
Shadow call stack:
- Work around some issues with Clang's integrated assembler not
liking our perfectly reasonable assembly code
- Avoid allocating the X18 register, so that it can be used to hold
the shadow call stack pointer in future
ACPI:
- Fix ID count checking in IORT code. This may regress broken
firmware that happened to work with the old implementation, in
which case we'll have to revert it and try something else
- Fix DAIF corruption on return from GHES handler with pseudo-NMIs
Miscellaneous:
- Whitelist some CPUs that are unaffected by Spectre-v2
- Reduce frequency of ASID rollover when KPTI is compiled in but
inactive
- Reserve a couple of arch-specific PROT flags that are already used
by Sparc and PowerPC and are planned for later use with BTI on
arm64
- Preparatory cleanup of our entry assembly code in preparation for
moving more of it into C later on
- Refactoring and cleanup"
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (73 commits)
arm64: acpi: fix DAIF manipulation with pNMI
arm64: kconfig: Fix alignment of E0PD help text
arm64: Use v8.5-RNG entropy for KASLR seed
arm64: Implement archrandom.h for ARMv8.5-RNG
arm64: kbuild: remove compressed images on 'make ARCH=arm64 (dist)clean'
arm64: entry: Avoid empty alternatives entries
arm64: Kconfig: select HAVE_FUTEX_CMPXCHG
arm64: csum: Fix pathological zero-length calls
arm64: entry: cleanup sp_el0 manipulation
arm64: entry: cleanup el0 svc handler naming
arm64: entry: mark all entry code as notrace
arm64: assembler: remove smp_dmb macro
arm64: assembler: remove inherit_daif macro
ACPI/IORT: Fix 'Number of IDs' handling in iort_id_map()
mm: Reserve asm-generic prot flags 0x10 and 0x20 for arch use
arm64: Use macros instead of hard-coded constants for MAIR_EL1
arm64: Add KRYO{3,4}XX CPU cores to spectre-v2 safe list
arm64: kernel: avoid x18 in __cpu_soft_restart
arm64: kvm: stop treating register x18 as caller save
arm64/lib: copy_page: avoid x18 register in assembler code
...
|
||
|
Steven Rostedt (VMware)
|
20279420ae |
tracing/kprobes: Have uname use __get_str() in print_fmt
Thomas Richter reported:
> Test case 66 'Use vfs_getname probe to get syscall args filenames'
> is broken on s390, but works on x86. The test case fails with:
>
> [root@m35lp76 perf]# perf test -F 66
> 66: Use vfs_getname probe to get syscall args filenames
> :Recording open file:
> [ perf record: Woken up 1 times to write data ]
> [ perf record: Captured and wrote 0.004 MB /tmp/__perf_test.perf.data.TCdYj\
> (20 samples) ]
> Looking at perf.data file for vfs_getname records for the file we touched:
> FAILED!
> [root@m35lp76 perf]#
The root cause was the print_fmt of the kprobe event that referenced the
"ustring"
> Setting up the kprobe event using perf command:
>
> # ./perf probe "vfs_getname=getname_flags:72 pathname=filename:ustring"
>
> generates this format file:
> [root@m35lp76 perf]# cat /sys/kernel/debug/tracing/events/probe/\
> vfs_getname/format
> name: vfs_getname
> ID: 1172
> format:
> field:unsigned short common_type; offset:0; size:2; signed:0;
> field:unsigned char common_flags; offset:2; size:1; signed:0;
> field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
> field:int common_pid; offset:4; size:4; signed:1;
>
> field:unsigned long __probe_ip; offset:8; size:8; signed:0;
> field:__data_loc char[] pathname; offset:16; size:4; signed:1;
>
> print fmt: "(%lx) pathname=\"%s\"", REC->__probe_ip, REC->pathname
Instead of using "__get_str(pathname)" it referenced it directly.
Link: http://lkml.kernel.org/r/20200124100742.4050c15e@gandalf.local.home
Cc: stable@vger.kernel.org
Fixes:
|
||
|
David S. Miller
|
9e0703a265 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2020-01-27 The following pull-request contains BPF updates for your *net-next* tree. We've added 20 non-merge commits during the last 5 day(s) which contain a total of 24 files changed, 433 insertions(+), 104 deletions(-). The main changes are: 1) Make BPF trampolines and dispatcher aware for the stack unwinder, from Jiri Olsa. 2) Improve handling of failed CO-RE relocations in libbpf, from Andrii Nakryiko. 3) Several fixes to BPF sockmap and reuseport selftests, from Lorenz Bauer. 4) Various cleanups in BPF devmap's XDP flush code, from John Fastabend. 5) Fix BPF flow dissector when used with port ranges, from Yoshiki Komachi. 6) Fix bpffs' map_seq_next callback to always inc position index, from Vasily Averin. 7) Allow overriding LLVM tooling for runqslower utility, from Andrey Ignatov. 8) Silence false-positive lockdep splats in devmap hash lookup, from Amol Grover. 9) Fix fentry/fexit selftests to initialize a variable before use, from John Sperbeck. ==================== Signed-off-by: David S. Miller <davem@davemloft.net> |
||
|
Rafael J. Wysocki
|
245224d1cb |
Merge branches 'pm-cpufreq' and 'pm-sleep'
* pm-cpufreq: cpufreq: loongson2_cpufreq: adjust cpufreq uses of LOONGSON_CHIPCFG cpufreq: brcmstb-avs: fix imbalance of cpufreq policy refcount cpufreq: intel_pstate: fix spelling mistake: "Whethet" -> "Whether" cpufreq: s3c: fix unbalances of cpufreq policy refcount cpufreq: imx-cpufreq-dt: Add i.MX8MP support cpufreq: Use imx-cpufreq-dt for i.MX8MP's speed grading cpufreq: tegra186: convert to devm_platform_ioremap_resource cpufreq: kirkwood: convert to devm_platform_ioremap_resource cpufreq: CPPC: put ACPI table after using it cpufreq : CPPC: Break out if HiSilicon CPPC workaround is matched * pm-sleep: PM: suspend: Add sysfs attribute to control the "sync on suspend" behavior PM: hibernate: fix spelling mistake "shapshot" -> "snapshot" PM: hibernate: Add more logging on hibernation failure PM: hibernate: improve arithmetic division in preallocate_highmem_fraction() PM: wakeup: Show statistics for deleted wakeup sources again PM: sleep: Switch to rtc_time64_to_tm()/rtc_tm_to_time64() |
||
|
John Fastabend
|
b23bfa5633 |
bpf, xdp: Remove no longer required rcu_read_{un}lock()
Now that we depend on rcu_call() and synchronize_rcu() to also wait for preempt_disabled region to complete the rcu read critical section in __dev_map_flush() is no longer required. Except in a few special cases in drivers that need it for other reasons. These originally ensured the map reference was safe while a map was also being free'd. And additionally that bpf program updates via ndo_bpf did not happen while flush updates were in flight. But flush by new rules can only be called from preempt-disabled NAPI context. The synchronize_rcu from the map free path and the rcu_call from the delete path will ensure the reference there is safe. So lets remove the rcu_read_lock and rcu_read_unlock pair to avoid any confusion around how this is being protected. If the rcu_read_lock was required it would mean errors in the above logic and the original patch would also be wrong. Now that we have done above we put the rcu_read_lock in the driver code where it is needed in a driver dependent way. I think this helps readability of the code so we know where and why we are taking read locks. Most drivers will not need rcu_read_locks here and further XDP drivers already have rcu_read_locks in their code paths for reading xdp programs on RX side so this makes it symmetric where we don't have half of rcu critical sections define in driver and the other half in devmap. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/1580084042-11598-4-git-send-email-john.fastabend@gmail.com |
||
|
John Fastabend
|
42a84a8cd0 |
bpf, xdp: Update devmap comments to reflect napi/rcu usage
Now that we rely on synchronize_rcu and call_rcu waiting to
exit perempt-disable regions (NAPI) lets update the comments
to reflect this.
Fixes:
|
||
|
Vasily Averin
|
90435a7891 |
bpf: map_seq_next should always increase position index
If seq_file .next fuction does not change position index, read after some lseek can generate an unexpected output. See also: https://bugzilla.kernel.org/show_bug.cgi?id=206283 v1 -> v2: removed missed increment in end of function Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/eca84fdd-c374-a154-d874-6c7b55fc3bc4@virtuozzo.com |
||
|
Madhuparna Bhowmik
|
913292c97d |
sched.h: Annotate sighand_struct with __rcu
This patch fixes the following sparse errors by annotating the sighand_struct with __rcu kernel/fork.c:1511:9: error: incompatible types in comparison expression kernel/exit.c💯19: error: incompatible types in comparison expression kernel/signal.c:1370:27: error: incompatible types in comparison expression This fix introduces the following sparse error in signal.c due to checking the sighand pointer without rcu primitives: kernel/signal.c:1386:21: error: incompatible types in comparison expression This new sparse error is also fixed in this patch. Signed-off-by: Madhuparna Bhowmik <madhuparnabhowmik10@gmail.com> Acked-by: Paul E. McKenney <paulmck@kernel.org> Link: https://lore.kernel.org/r/20200124045908.26389-1-madhuparnabhowmik10@gmail.com Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> |
||
|
David S. Miller
|
4d8773b68e |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Minor conflict in mlx5 because changes happened to code that has moved meanwhile. Signed-off-by: David S. Miller <davem@davemloft.net> |
||
|
Paul E. McKenney
|
59d8cc6b2e |
rcu: Forgive slow expedited grace periods at boot time
Boot-time processing often loops in the kernel longer than one might prefer, which can prevent expedited grace periods from completing in a timely manner. This in turn triggers a splat In nohz_full CPUs One could argue that long-looping code should be fixed, but on the other hand, boot time is a bit special. This commit therefore removes the splat. Later commits will add the splat back in, but in a way that removes false positives. Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Paul E. McKenney <paulmck@kernel.org> |
||
|
Steven Rostedt (VMware)
|
24589e3a20 |
tracing: Use pr_err() instead of WARN() for memory failures
As warnings can trigger panics, especially when "panic_on_warn" is set, memory failure warnings can cause panics and fail fuzz testers that are stressing memory. Create a MEM_FAIL() macro to use instead of WARN() in the tracing code (perhaps this should be a kernel wide macro?), and use that for memory failure issues. This should stop failing fuzz tests due to warnings. Link: https://lore.kernel.org/r/CACT4Y+ZP-7np20GVRu3p+eZys9GPtbu+JpfV+HtsufAzvTgJrg@mail.gmail.com Suggested-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> |
||
|
Jiri Olsa
|
e9b4e606c2 |
bpf: Allow to resolve bpf trampoline and dispatcher in unwind
When unwinding the stack we need to identify each address to successfully continue. Adding latch tree to keep trampolines for quick lookup during the unwind. The patch uses first 48 bytes for latch tree node, leaving 4048 bytes from the rest of the page for trampoline or dispatcher generated code. It's still enough not to affect trampoline and dispatcher progs maximum counts. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200123161508.915203-3-jolsa@kernel.org |
||
|
Jiri Olsa
|
84ad7a7ab6 |
bpf: Allow BTF ctx access for string pointers
When accessing the context we allow access to arguments with scalar type and pointer to struct. But we deny access for pointer to scalar type, which is the case for many functions. Alexei suggested to take conservative approach and allow currently only string pointer access, which is the case for most functions now: Adding check if the pointer is to string type and allow access to it. Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200123161508.915203-2-jolsa@kernel.org |
||
|
Ingo Molnar
|
f8a4bb6bfa |
Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu
Pull RCU updates from Paul E. McKenney: - Expedited grace-period updates - kfree_rcu() updates - RCU list updates - Preemptible RCU updates - Torture-test updates - Miscellaneous fixes - Documentation updates Signed-off-by: Ingo Molnar <mingo@kernel.org> |
||
|
Steven Rostedt (VMware)
|
28394da258 |
tracing: Decrement trace_array when bootconfig creates an instance
The trace_array_get_by_name() creates a ftrace instance and
trace_array_put() is used to remove the reference. Even though the
trace_array_get_by_name() creates the instance, it also adds a reference
count to it, that prevents user space from removing it.
As the bootconfig just creates the instance on boot up, it should still be
used where it can be deleted by user space after boot. A trace_array_put()
is required to let that happen.
Also, change the documentation on trace_array_get_by_name() to make this not
be so confusing.
Link: https://lore.kernel.org/r/20200124205927.76128804@rorschach.local.home
Fixes:
|
||
|
Dan Carpenter
|
b3f7a6cd49 |
tracing: Remove unneeded NULL check
We checked "iter->trace" earlier so there is no need to check here. Link: http://lkml.kernel.org/r/20141122183012.GB6994@mwanda Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> [ Pulled from the archeological digging of my INBOX ] Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> |
||
|
Josef Bacik
|
cbc3b92ce0 |
tracing: Set kernel_stack's caller size properly
I noticed when trying to use the trace-cmd python interface that reading the raw buffer wasn't working for kernel_stack events. This is because it uses a stubbed version of __dynamic_array that doesn't do the __data_loc trick and encode the length of the array into the field. Instead it just shows up as a size of 0. So change this to __array and set the len to FTRACE_STACK_ENTRIES since this is what we actually do in practice and matches how user_stack_trace works. Link: http://lkml.kernel.org/r/1411589652-1318-1-git-send-email-jbacik@fb.com Signed-off-by: Josef Bacik <jbacik@fb.com> [ Pulled from the archeological digging of my INBOX ] Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> |
||
|
Luis Henriques
|
afccc00f75 |
tracing: Fix tracing_stat return values in error handling paths
tracing_stat_init() was always returning '0', even on the error paths. It
now returns -ENODEV if tracing_init_dentry() fails or -ENOMEM if it fails
to created the 'trace_stat' debugfs directory.
Link: http://lkml.kernel.org/r/1410299381-20108-1-git-send-email-luis.henriques@canonical.com
Fixes:
|
||
|
Steven Rostedt (VMware)
|
dfb6cd1e65 |
tracing: Fix very unlikely race of registering two stat tracers
Looking through old emails in my INBOX, I came across a patch from Luis
Henriques that attempted to fix a race of two stat tracers registering the
same stat trace (extremely unlikely, as this is done in the kernel, and
probably doesn't even exist). The submitted patch wasn't quite right as it
needed to deal with clean up a bit better (if two stat tracers were the
same, it would have the same files).
But to make the code cleaner, all we needed to do is to keep the
all_stat_sessions_mutex held for most of the registering function.
Link: http://lkml.kernel.org/r/1410299375-20068-1-git-send-email-luis.henriques@canonical.com
Fixes:
|
||
|
Stephen Boyd
|
fd928f3e32 |
alarmtimer: Make alarmtimer_get_rtcdev() a stub when CONFIG_RTC_CLASS=n
The stubbed version of alarmtimer_get_rtcdev() is not exported. so this won't work if this function is used in a module when CONFIG_RTC_CLASS=n. Move the stub function to the header file and make it inline so that callers don't have to worry about linking against this symbol. rtcdev isn't used outside of this ifdef so it's not required to be redefined to NULL. Drop that while touching this area. Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20200124055849.154411-4-swboyd@chromium.org |
||
|
Stephen Boyd
|
7c94caca87 |
alarmtimer: Use wakeup source from alarmtimer platform device
Use the wakeup source that can be associated with the 'alarmtimer' platform device instead of registering another one by hand. Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Douglas Anderson <dianders@chromium.org> Link: https://lore.kernel.org/r/20200124055849.154411-3-swboyd@chromium.org |
||
|
Stephen Boyd
|
c79108bd19 |
alarmtimer: Make alarmtimer platform device child of RTC device
The alarmtimer_suspend() function will fail if an RTC device is on a bus such as SPI or i2c and that RTC device registers and probes after alarmtimer_init() registers and probes the 'alarmtimer' platform device. This is because system wide suspend suspends devices in the reverse order of their probe. When alarmtimer_suspend() attempts to program the RTC for a wakeup it will try to program an RTC device on a bus that has already been suspended. Move the alarmtimer device registration to happen when the RTC which is used for wakeup is registered. Register the 'alarmtimer' platform device as a child of the RTC device too, so that it can be guaranteed that the RTC device won't be suspended when alarmtimer_suspend() is called. Reported-by: Douglas Anderson <dianders@chromium.org> Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Douglas Anderson <dianders@chromium.org> Link: https://lore.kernel.org/r/20200124055849.154411-2-swboyd@chromium.org |
||
|
Stephen Boyd
|
6b088cefbe |
alarmtimer: Update alarmtimer_get_rtcdev() docs to reflect reality
This function doesn't do anything like this comment says when an RTC device
hasn't been chosen. It looks like we used to do something like that before
commit
|