Pull irqchip updates for 4.14-rc5 from Marc Zyngier:
- Fix unfortunate mistake in the GICv3 ITS binding example
- Two fixes for the recently merged GICv4 support
- GICv3 ITS 52bit PA fixes
- Generic irqchip mask-ack fix, and its application to the tango irqchip
Pull perf fixes from Ingo Molnar:
"Some tooling fixes plus three kernel fixes: a memory leak fix, a
statistics fix and a crash fix"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel/uncore: Fix memory leaks on allocation failures
perf/core: Fix cgroup time when scheduling descendants
perf/core: Avoid freeing static PMU contexts when PMU is unregistered
tools include uapi bpf.h: Sync kernel ABI header with tooling header
perf pmu: Unbreak perf record for arm/arm64 with events with explicit PMU
perf script: Add missing separator for "-F ip,brstack" (and brstackoff)
perf callchain: Compare dsos (as well) for CCKEY_FUNCTION
Pull locking fixes from Ingo Molnar:
"Two lockdep fixes for bugs introduced by the cross-release dependency
tracking feature - plus a commit that disables it because performance
regressed in an absymal fashion on some systems"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/lockdep: Disable cross-release features for now
locking/selftest: Avoid false BUG report
locking/lockdep: Fix stacktrace mess
Pull irq fixes from Ingo Molnar:
"A CPU hotplug related fix, plus two related sanity checks"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq/cpuhotplug: Enforce affinity setting on startup of managed irqs
genirq/cpuhotplug: Add sanity check for effective affinity mask
genirq: Warn when effective affinity is not updated
Use a simplified is_valid_access() callback when verifier
is used for program analysis by non-host JITs. This allows
us to teach the verifier about packet start and packet end
offsets for direct packet access.
We can extend the callback as needed but for most packet
processing needs there isn't much more the offloads may
require.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Any usage of the irq_gc_mask_disable_reg_and_ack() function has
been replaced with the desired functionality.
The incorrect and ambiguously named function is removed here to
prevent accidental misuse.
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
The irq_gc_mask_disable_reg_and_ack() function name implies that it
provides the combined functions of irq_gc_mask_disable_reg() and
irq_gc_ack(). However, the implementation does not actually do
that since it writes the mask instead of the disable register. It
also does not maintain the mask cache which makes it inappropriate
to use with other masking functions.
In addition, commit 659fb32d1b ("genirq: replace irq_gc_ack() with
{set,clr}_bit variants (fwd)") effectively renamed irq_gc_ack() to
irq_gc_ack_set_bit() so this function probably should have also been
renamed at that time.
The generic chip code currently provides three functions for use
with the irq_mask member of the irq_chip structure and two functions
for use with the irq_ack member of the irq_chip structure. These
functions could be combined into six functions for use with the
irq_mask_ack member of the irq_chip structure. However, since only
one of the combinations is currently used, only the function
irq_gc_mask_disable_and_ack_set() is added by this commit.
The '_reg' and '_bit' portions of the base function name were left
out of the new combined function name in an attempt to keep the
function name length manageable with the 80 character source code
line length while still allowing the distinct aspects of each
combination to be captured by the name.
If other combinations are desired in the future please add them to
the irq generic chip library at that time.
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
After trace_selftest_startup_sched_switch is removed, trace_test_buffer()
is only used sometimes, leading to this warning:
kernel/trace/trace_selftest.c:62:12: error: 'trace_test_buffer' defined but not used [-Werror=unused-function]
There is no simple #ifdef condition that captures well whether the
function is in fact used or not, so marking it as __maybe_unused is
probably the best way to shut up the warning. The function will then
be silently dropped when there is no user.
Link: http://lkml.kernel.org/r/20171013142227.1273469-1-arnd@arndb.de
Fixes: d8c4deee6d ("tracing: Remove obsolete sched_switch tracer selftest")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
The variable printk_safe_irq_ready is set and never cleared at system
boot up, when there's only one CPU active. It is set before other
CPUs come on line. Also, it is extremely unlikely that an NMI would
trigger this early in boot up (which I wonder why we even have this
variable at all).
Also mark the printk_safe_irq_ready as read mostly, as it is set at
system boot up, and never touched again.
Link: http://lkml.kernel.org/r/20171011124647.7781f98f@gandalf.local.home
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Pull livepatching fix from Jiri Kosina:
- bugfix for handling of coming modules (incorrect handling of failure)
from Joe Lawrence
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching:
livepatch: unpatch all klp_objects if klp_module_coming fails
Merge waitid() fix from Kees Cook.
I'd have hoped that the unsafe_{get|put}_user() naming would have
avoided these kinds of stupid bugs, but no such luck.
* waitid-fix:
waitid(): Add missing access_ok() checks
Variable old_flags is being assigned but is never read; it is redundant
and can be removed.
Cleans up clang warning: Value stored to 'old_flags' is never read
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
When an incoming module is considered for livepatching by
klp_module_coming(), it iterates over multiple patches and multiple
kernel objects in this order:
list_for_each_entry(patch, &klp_patches, list) {
klp_for_each_object(patch, obj) {
which means that if one of the kernel objects fails to patch,
klp_module_coming()'s error path needs to unpatch and cleanup any kernel
objects that were already patched by a previous patch.
Reported-by: Miroslav Benes <mbenes@suse.cz>
Suggested-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
This reverts commit fbb1fb4ad4.
This was not the proper fix, lets cleanly revert it, so that
following patch can be carried to stable versions.
sock_cgroup_ptr() callers do not expect a NULL return value.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Filters should be cleared of init functions during freeing of init
memory when the ftrace dyn records are released. However in current
code, the filters are left as is. This patch clears the hashes of the
saved init functions when the init memory is freed. This fixes the
following issue reproducible with the following sequence of commands for
a test module:
================================================
void bar(void)
{
printk(KERN_INFO "bar!\n");
}
void foo(void)
{
printk(KERN_INFO "foo!\n");
bar();
}
static int __init hello_init(void)
{
printk(KERN_INFO "Hello world!\n");
foo();
return 0;
}
static void __exit hello_cleanup(void)
{
printk(KERN_INFO "Cleaning up module.\n");
}
module_init(hello_init);
module_exit(hello_cleanup);
================================================
Commands:
echo '*:mod:test' > /d/tracing/set_ftrace_filter
echo function > /d/tracing/current_tracer
modprobe test
rmmod test
sleep 1
modprobe test
cat /d/tracing/set_ftrace_filter
Behavior without patch: Init function is still in the filter
Expected behavior: Shouldn't have any of the filters set
Link: http://lkml.kernel.org/r/20171009192931.56401-1-joelaf@google.com
Signed-off-by: Joel Fernandes <joelaf@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Pull seccomp fixlet from Kees Cook:
"Minor seccomp fix for v4.14-rc5. I debated sending this at all for
v4.14, but since it fixes a minor issue in the prior fix, which also
went to -stable, it seemed better to just get all of it cleaned up
right now.
- fix missed "static" to avoid Sparse warning (Colin King)"
* tag 'seccomp-v4.14-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
seccomp: make function __get_seccomp_filter static
Verifier log buffer can be quite large (up to 16MB currently).
As Eric Dumazet points out if we allow multiple verification
requests to proceed simultaneously, malicious user may use the
verifier as a way of allocating large amounts of unswappable
memory to OOM the host.
Switch to a strategy of allocating a smaller buffer (1024B)
and writing it out into the user buffer after every print.
While at it remove the old BUG_ON().
This is in preparation of the global verifier lock removal.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The biggest piece of global state protected by the verifier lock
is the verifier_log. Move that log to struct bpf_verifier_env.
struct bpf_verifier_env has to be passed now to all invocations
of verbose().
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function __get_seccomp_filter is local to the source and does
not need to be in global scope, so make it static.
Cleans up sparse warning:
symbol '__get_seccomp_filter' was not declared. Should it be static?
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Fixes: 66a733ea6b ("seccomp: fix the usage of get/put_seccomp_filter() in seccomp_get_filter()")
Cc: stable@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Josef reported a HARDIRQ-safe -> HARDIRQ-unsafe lock order detected by
lockdep:
[ 1270.472259] WARNING: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected
[ 1270.472783] 4.14.0-rc1-xfstests-12888-g76833e8 #110 Not tainted
[ 1270.473240] -----------------------------------------------------
[ 1270.473710] kworker/u5:2/5157 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
[ 1270.474239] (&(&lock->wait_lock)->rlock){+.+.}, at: [<ffffffff8da253d2>] __mutex_unlock_slowpath+0xa2/0x280
[ 1270.474994]
[ 1270.474994] and this task is already holding:
[ 1270.475440] (&pool->lock/1){-.-.}, at: [<ffffffff8d2992f6>] worker_thread+0x366/0x3c0
[ 1270.476046] which would create a new lock dependency:
[ 1270.476436] (&pool->lock/1){-.-.} -> (&(&lock->wait_lock)->rlock){+.+.}
[ 1270.476949]
[ 1270.476949] but this new dependency connects a HARDIRQ-irq-safe lock:
[ 1270.477553] (&pool->lock/1){-.-.}
...
[ 1270.488900] to a HARDIRQ-irq-unsafe lock:
[ 1270.489327] (&(&lock->wait_lock)->rlock){+.+.}
...
[ 1270.494735] Possible interrupt unsafe locking scenario:
[ 1270.494735]
[ 1270.495250] CPU0 CPU1
[ 1270.495600] ---- ----
[ 1270.495947] lock(&(&lock->wait_lock)->rlock);
[ 1270.496295] local_irq_disable();
[ 1270.496753] lock(&pool->lock/1);
[ 1270.497205] lock(&(&lock->wait_lock)->rlock);
[ 1270.497744] <Interrupt>
[ 1270.497948] lock(&pool->lock/1);
, which will cause a irq inversion deadlock if the above lock scenario
happens.
The root cause of this safe -> unsafe lock order is the
mutex_unlock(pool->manager_arb) in manage_workers() with pool->lock
held.
Unlocking mutex while holding an irq spinlock was never safe and this
problem has been around forever but it never got noticed because the
only time the mutex is usually trylocked while holding irqlock making
actual failures very unlikely and lockdep annotation missed the
condition until the recent b9c16a0e1f ("locking/mutex: Fix
lockdep_assert_held() fail").
Using mutex for pool->manager_arb has always been a bit of stretch.
It primarily is an mechanism to arbitrate managership between workers
which can easily be done with a pool flag. The only reason it became
a mutex is that pool destruction path wants to exclude parallel
managing operations.
This patch replaces the mutex with a new pool flag POOL_MANAGER_ACTIVE
and make the destruction path wait for the current manager on a wait
queue.
v2: Drop unnecessary flag clearing before pool destruction as
suggested by Boqun.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: stable@vger.kernel.org
The fanotify interface allows user space daemons to make access
control decisions. Under common criteria requirements, we need to
optionally record decisions based on policy. This patch adds a bit mask,
FAN_AUDIT, that a user space daemon can 'or' into the response decision
which will tell the kernel that it made a decision and record it.
It would be used something like this in user space code:
response.response = FAN_DENY | FAN_AUDIT;
write(fd, &response, sizeof(struct fanotify_response));
When the syscall ends, the audit system will record the decision as a
AUDIT_FANOTIFY auxiliary record to denote that the reason this event
occurred is the result of an access control decision from fanotify
rather than DAC or MAC policy.
A sample event looks like this:
type=PATH msg=audit(1504310584.332:290): item=0 name="./evil-ls"
inode=1319561 dev=fc:03 mode=0100755 ouid=1000 ogid=1000 rdev=00:00
obj=unconfined_u:object_r:user_home_t:s0 nametype=NORMAL
type=CWD msg=audit(1504310584.332:290): cwd="/home/sgrubb"
type=SYSCALL msg=audit(1504310584.332:290): arch=c000003e syscall=2
success=no exit=-1 a0=32cb3fca90 a1=0 a2=43 a3=8 items=1 ppid=901
pid=959 auid=1000 uid=1000 gid=1000 euid=1000 suid=1000
fsuid=1000 egid=1000 sgid=1000 fsgid=1000 tty=pts1 ses=3 comm="bash"
exe="/usr/bin/bash" subj=unconfined_u:unconfined_r:unconfined_t:
s0-s0:c0.c1023 key=(null)
type=FANOTIFY msg=audit(1504310584.332:290): resp=2
Prior to using the audit flag, the developer needs to call
fanotify_init or'ing in FAN_ENABLE_AUDIT to ensure that the kernel
supports auditing. The calling process must also have the CAP_AUDIT_WRITE
capability.
Signed-off-by: sgrubb <sgrubb@redhat.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Outside of the locking code itself, {read,spin,write}_can_lock() have no
users in tree. Apparmor (the last remaining user of write_can_lock()) got
moved over to lockdep by the previous patch.
This patch removes the use of {read,spin,write}_can_lock() from the
BUILD_LOCK_OPS macro, deferring to the trylock operation for testing the
lock status, and subsequently removes the unused macros altogether. They
aren't guaranteed to work in a concurrent environment and can give
incorrect results in the case of qrwlock.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1507055129-12300-2-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a CPU lowers its priority (schedules out a high priority task for a
lower priority one), a check is made to see if any other CPU has overloaded
RT tasks (more than one). It checks the rto_mask to determine this and if so
it will request to pull one of those tasks to itself if the non running RT
task is of higher priority than the new priority of the next task to run on
the current CPU.
When we deal with large number of CPUs, the original pull logic suffered
from large lock contention on a single CPU run queue, which caused a huge
latency across all CPUs. This was caused by only having one CPU having
overloaded RT tasks and a bunch of other CPUs lowering their priority. To
solve this issue, commit:
b6366f048e ("sched/rt: Use IPI to trigger RT task push migration instead of pulling")
changed the way to request a pull. Instead of grabbing the lock of the
overloaded CPU's runqueue, it simply sent an IPI to that CPU to do the work.
Although the IPI logic worked very well in removing the large latency build
up, it still could suffer from a large number of IPIs being sent to a single
CPU. On a 80 CPU box, I measured over 200us of processing IPIs. Worse yet,
when I tested this on a 120 CPU box, with a stress test that had lots of
RT tasks scheduling on all CPUs, it actually triggered the hard lockup
detector! One CPU had so many IPIs sent to it, and due to the restart
mechanism that is triggered when the source run queue has a priority status
change, the CPU spent minutes! processing the IPIs.
Thinking about this further, I realized there's no reason for each run queue
to send its own IPI. As all CPUs with overloaded tasks must be scanned
regardless if there's one or many CPUs lowering their priority, because
there's no current way to find the CPU with the highest priority task that
can schedule to one of these CPUs, there really only needs to be one IPI
being sent around at a time.
This greatly simplifies the code!
The new approach is to have each root domain have its own irq work, as the
rto_mask is per root domain. The root domain has the following fields
attached to it:
rto_push_work - the irq work to process each CPU set in rto_mask
rto_lock - the lock to protect some of the other rto fields
rto_loop_start - an atomic that keeps contention down on rto_lock
the first CPU scheduling in a lower priority task
is the one to kick off the process.
rto_loop_next - an atomic that gets incremented for each CPU that
schedules in a lower priority task.
rto_loop - a variable protected by rto_lock that is used to
compare against rto_loop_next
rto_cpu - The cpu to send the next IPI to, also protected by
the rto_lock.
When a CPU schedules in a lower priority task and wants to make sure
overloaded CPUs know about it. It increments the rto_loop_next. Then it
atomically sets rto_loop_start with a cmpxchg. If the old value is not "0",
then it is done, as another CPU is kicking off the IPI loop. If the old
value is "0", then it will take the rto_lock to synchronize with a possible
IPI being sent around to the overloaded CPUs.
If rto_cpu is greater than or equal to nr_cpu_ids, then there's either no
IPI being sent around, or one is about to finish. Then rto_cpu is set to the
first CPU in rto_mask and an IPI is sent to that CPU. If there's no CPUs set
in rto_mask, then there's nothing to be done.
When the CPU receives the IPI, it will first try to push any RT tasks that is
queued on the CPU but can't run because a higher priority RT task is
currently running on that CPU.
Then it takes the rto_lock and looks for the next CPU in the rto_mask. If it
finds one, it simply sends an IPI to that CPU and the process continues.
If there's no more CPUs in the rto_mask, then rto_loop is compared with
rto_loop_next. If they match, everything is done and the process is over. If
they do not match, then a CPU scheduled in a lower priority task as the IPI
was being passed around, and the process needs to start again. The first CPU
in rto_mask is sent the IPI.
This change removes this duplication of work in the IPI logic, and greatly
lowers the latency caused by the IPIs. This removed the lockup happening on
the 120 CPU machine. It also simplifies the code tremendously. What else
could anyone ask for?
Thanks to Peter Zijlstra for simplifying the rto_loop_start atomic logic and
supplying me with the rto_start_trylock() and rto_start_unlock() helper
functions.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Wood <swood@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170424114732.1aac6dc4@gandalf.local.home
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The "goto force_balance" here is intended to mitigate the fact that
avg_load calculations can result in bad placement decisions when
priority is asymmetrical.
The original commit that adds it:
fab476228b ("sched: Force balancing on newidle balance if local group has capacity")
explains:
Under certain situations, such as a niced down task (i.e. nice =
-15) in the presence of nr_cpus NICE0 tasks, the niced task lands
on a sched group and kicks away other tasks because of its large
weight. This leads to sub-optimal utilization of the
machine. Even though the sched group has capacity, it does not
pull tasks because sds.this_load >> sds.max_load, and f_b_g()
returns NULL.
A similar but inverted issue also affects ARM big.LITTLE (asymmetrical CPU
capacity) systems - consider 8 always-running, same-priority tasks on a
system with 4 "big" and 4 "little" CPUs. Suppose that 5 of them end up on
the "big" CPUs (which will be represented by one sched_group in the DIE
sched_domain) and 3 on the "little" (the other sched_group in DIE), leaving
one CPU unused. Because the "big" group has a higher group_capacity its
avg_load may not present an imbalance that would cause migrating a
task to the idle "little".
The force_balance case here solves the problem but currently only for
CPU_NEWLY_IDLE balances, which in theory might never happen on the
unused CPU. Including CPU_IDLE in the force_balance case means
there's an upper bound on the time before we can attempt to solve the
underutilization: after DIE's sd->balance_interval has passed the
next nohz balance kick will help us out.
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170807163900.25180-1-brendan.jackman@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We use task_util() in find_idlest_group() via capacity_spare_wake().
This task_util() updated in wake_cap(). However wake_cap() is not the
only reason for ending up in find_idlest_group() - we could have been sent
there by wake_wide(). So explicitly sync the task util with prev_cpu
when we are about to head to find_idlest_group().
We could simply do this at the beginning of
select_task_rq_fair() (i.e. irrespective of whether we're heading to
select_idle_sibling() or find_idlest_group() & co), but I didn't want to
slow down the select_idle_sibling() path more than necessary.
Don't do this during fork balancing, we won't need the task_util and
we'd just clobber the last_update_time, which is supposed to be 0.
Signed-off-by: Brendan Jackman <brendan.jackman@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andres Oportus <andresoportus@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: http://lkml.kernel.org/r/20170808095519.10077-1-brendan.jackman@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
As a first step this patch makes cfs_tasks list as MRU one.
It means, that when a next task is picked to run on physical
CPU it is moved to the front of the list.
Therefore, the cfs_tasks list is more or less sorted (except
woken tasks) starting from recently given CPU time tasks toward
tasks with max wait time in a run-queue, i.e. MRU list.
Second, as part of the load balance operation, this approach
starts detach_tasks()/detach_one_task() from the tail of the
queue instead of the head, giving some advantages:
- tends to pick a task with highest wait time;
- tasks located in the tail are less likely cache-hot,
therefore the can_migrate_task() decision is higher.
hackbench illustrates slightly better performance. For example
doing 1000 samples and 40 groups on i5-3320M CPU, it shows below
figures:
default: 0.657 avg
patched: 0.646 avg
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Link: http://lkml.kernel.org/r/20170913102430.8985-2-urezki@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
On AMD Family17h-based (EPYC) system, a logical NUMA node can contain
upto 8 cores (16 threads) with the following topology.
----------------------------
C0 | T0 T1 | || | T0 T1 | C4
--------| || |--------
C1 | T0 T1 | L3 || L3 | T0 T1 | C5
--------| || |--------
C2 | T0 T1 | #0 || #1 | T0 T1 | C6
--------| || |--------
C3 | T0 T1 | || | T0 T1 | C7
----------------------------
Here, there are 2 last-level (L3) caches per logical NUMA node.
A socket can contain upto 4 NUMA nodes, and a system can support
upto 2 sockets. With full system configuration, current scheduler
creates 4 sched domains:
domain0 SMT (span a core)
domain1 MC (span a last-level-cache)
domain2 NUMA (span a socket: 4 nodes)
domain3 NUMA (span a system: 8 nodes)
Note that there is no domain to represent cpus spaning a logical
NUMA node. With this hierarchy of sched domains, the scheduler does
not balance properly in the following cases:
Case1:
When running 8 tasks, a properly balanced system should
schedule a task per logical NUMA node. This is not the case for
the current scheduler.
Case2:
In some cases, threads are scheduled on the same cpu, while other
cpus are idle. This results in run-to-run inconsistency. For example:
taskset -c 0-7 sysbench --num-threads=8 --test=cpu \
--cpu-max-prime=100000 run
Total execution time ranges from 25.1s to 33.5s depending on threads
placement, where 25.1s is when all 8 threads are balanced properly
on 8 cpus.
Introducing NUMA identity node sched domain, which is based on how
SRAT/SLIT table define a logical NUMA node. This results in the following
hierarchy of sched domains on the same system described above.
domain0 SMT (span a core)
domain1 MC (span a last-level-cache)
domain2 NODE (span a logical NUMA node)
domain3 NUMA (span a socket: 4 nodes)
domain4 NUMA (span a system: 8 nodes)
This fixes the improper load balancing cases mentioned above.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bp@suse.de
Link: http://lkml.kernel.org/r/1504768805-46716-1-git-send-email-suravee.suthikulpanit@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The normal x86_topology on NHM+ machines degenerates because the MC
and CPU domains are of the same size, therefore MC inherits
SD_PREFER_SIBLING from CPU (which then gets taken out). The result is
that we'll spread tasks across the first NUMA level in order to
maximize cache utilization.
However, for the x86_numa_in_package_topology we loose the CPU domain,
and we'll not have SD_PREFER_SIBLING set anywhere, giving a distinct
difference in behaviour.
Commit:
8e7fbcbc22 ("sched: Remove stale power aware scheduling remnants and dysfunctional knobs")
made a fail by not preserving the SD_PREFER_SIBLING for the !power_saving
case on both CPU and MC.
Then commit:
6956dc568f ("sched/numa: Add SD_PERFER_SIBLING to CPU domain")
adds it back to the CPU but not MC.
Restore that now, such that we get consistent spreading behaviour wrt
L3 and NUMA.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fix a bug introduced in:
72f9f3fdc9 ("sched/deadline: Remove dl_new from struct sched_dl_entity")
After that commit, when switching to -deadline if the scheduling
deadline of a task is in the past then switched_to_dl() calls
setup_new_entity() to properly initialize the scheduling deadline
and runtime.
The problem is that the task is enqueued _before_ having its parameters
initialized by setup_new_entity(), and this can cause problems.
For example, a task with its out-of-date deadline in the past will
potentially be enqueued as the highest priority one; however, its
adjusted deadline may not be the earliest one.
This patch fixes the problem by initializing the task's parameters before
enqueuing it.
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1504778971-13573-3-git-send-email-luca.abeni@santannapisa.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While load_balance() masks the source CPUs against active_mask, it had
a hole against the destination CPU. Ensure the destination CPU is also
part of the 'domain-mask & active-mask' set.
Reported-by: Levin, Alexander (Sasha Levin) <alexander.levin@verizon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 77d1dfda0e ("sched/topology, cpuset: Avoid spurious/wrong domain rebuilds")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
