When delivering a signal to a task that is using rseq, we call into
__rseq_handle_notify_resume() so that the registers pushed in the
sigframe are updated to reflect the state of the restartable sequence
(for example, ensuring that the signal returns to the abort handler if
necessary).
However, if the rseq management fails due to an unrecoverable fault when
accessing userspace or certain combinations of RSEQ_CS_* flags, then we
will attempt to deliver a SIGSEGV. This has the potential for infinite
recursion if the rseq code continuously fails on signal delivery.
Avoid this problem by using force_sigsegv() instead of force_sig(), which
is explicitly designed to reset the SEGV handler to SIG_DFL in the case
of a recursive fault. In doing so, remove rseq_signal_deliver() from the
internal rseq API and have an optional struct ksignal * parameter to
rseq_handle_notify_resume() instead.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: peterz@infradead.org
Cc: paulmck@linux.vnet.ibm.com
Cc: boqun.feng@gmail.com
Link: https://lkml.kernel.org/r/1529664307-983-1-git-send-email-will.deacon@arm.com
During a context switch, we first switch_mm() to the next task's mm,
then switch_to() that new task. This means that vmalloc'd regions which
had previously been faulted in can transiently disappear in the context
of the prev task.
Functions instrumented by KCOV may try to access a vmalloc'd kcov_area
during this window, and as the fault handling code is instrumented, this
results in a recursive fault.
We must avoid accessing any kcov_area during this window. We can do so
with a new flag in kcov_mode, set prior to switching the mm, and cleared
once the new task is live. Since task_struct::kcov_mode isn't always a
specific enum kcov_mode value, this is made an unsigned int.
The manipulation is hidden behind kcov_{prepare,finish}_switch() helpers,
which are empty for !CONFIG_KCOV kernels.
The code uses macros because I can't use static inline functions without a
circular include dependency between <linux/sched.h> and <linux/kcov.h>,
since the definition of task_struct uses things defined in <linux/kcov.h>
Link: http://lkml.kernel.org/r/20180504135535.53744-4-mark.rutland@arm.com
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The changes to automatically test for working stack protector compiler
support in the Kconfig files removed the special STACKPROTECTOR_AUTO
option that picked the strongest stack protector that the compiler
supported.
That was all a nice cleanup - it makes no sense to have the AUTO case
now that the Kconfig phase can just determine the compiler support
directly.
HOWEVER.
It also meant that doing "make oldconfig" would now _disable_ the strong
stackprotector if you had AUTO enabled, because in a legacy config file,
the sane stack protector configuration would look like
CONFIG_HAVE_CC_STACKPROTECTOR=y
# CONFIG_CC_STACKPROTECTOR_NONE is not set
# CONFIG_CC_STACKPROTECTOR_REGULAR is not set
# CONFIG_CC_STACKPROTECTOR_STRONG is not set
CONFIG_CC_STACKPROTECTOR_AUTO=y
and when you ran this through "make oldconfig" with the Kbuild changes,
it would ask you about the regular CONFIG_CC_STACKPROTECTOR (that had
been renamed from CONFIG_CC_STACKPROTECTOR_REGULAR to just
CONFIG_CC_STACKPROTECTOR), but it would think that the STRONG version
used to be disabled (because it was really enabled by AUTO), and would
disable it in the new config, resulting in:
CONFIG_HAVE_CC_STACKPROTECTOR=y
CONFIG_CC_HAS_STACKPROTECTOR_NONE=y
CONFIG_CC_STACKPROTECTOR=y
# CONFIG_CC_STACKPROTECTOR_STRONG is not set
CONFIG_CC_HAS_SANE_STACKPROTECTOR=y
That's dangerously subtle - people could suddenly find themselves with
the weaker stack protector setup without even realizing.
The solution here is to just rename not just the old RECULAR stack
protector option, but also the strong one. This does that by just
removing the CC_ prefix entirely for the user choices, because it really
is not about the compiler support (the compiler support now instead
automatially impacts _visibility_ of the options to users).
This results in "make oldconfig" actually asking the user for their
choice, so that we don't have any silent subtle security model changes.
The end result would generally look like this:
CONFIG_HAVE_CC_STACKPROTECTOR=y
CONFIG_CC_HAS_STACKPROTECTOR_NONE=y
CONFIG_STACKPROTECTOR=y
CONFIG_STACKPROTECTOR_STRONG=y
CONFIG_CC_HAS_SANE_STACKPROTECTOR=y
where the "CC_" versions really are about internal compiler
infrastructure, not the user selections.
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull KVM updates from Paolo Bonzini:
"Small update for KVM:
ARM:
- lazy context-switching of FPSIMD registers on arm64
- "split" regions for vGIC redistributor
s390:
- cleanups for nested
- clock handling
- crypto
- storage keys
- control register bits
x86:
- many bugfixes
- implement more Hyper-V super powers
- implement lapic_timer_advance_ns even when the LAPIC timer is
emulated using the processor's VMX preemption timer.
- two security-related bugfixes at the top of the branch"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (79 commits)
kvm: fix typo in flag name
kvm: x86: use correct privilege level for sgdt/sidt/fxsave/fxrstor access
KVM: x86: pass kvm_vcpu to kvm_read_guest_virt and kvm_write_guest_virt_system
KVM: x86: introduce linear_{read,write}_system
kvm: nVMX: Enforce cpl=0 for VMX instructions
kvm: nVMX: Add support for "VMWRITE to any supported field"
kvm: nVMX: Restrict VMX capability MSR changes
KVM: VMX: Optimize tscdeadline timer latency
KVM: docs: nVMX: Remove known limitations as they do not exist now
KVM: docs: mmu: KVM support exposing SLAT to guests
kvm: no need to check return value of debugfs_create functions
kvm: Make VM ioctl do valloc for some archs
kvm: Change return type to vm_fault_t
KVM: docs: mmu: Fix link to NPT presentation from KVM Forum 2008
kvm: x86: Amend the KVM_GET_SUPPORTED_CPUID API documentation
KVM: x86: hyperv: declare KVM_CAP_HYPERV_TLBFLUSH capability
KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}_EX implementation
KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} implementation
KVM: introduce kvm_make_vcpus_request_mask() API
KVM: x86: hyperv: do rep check for each hypercall separately
...
Expose a new system call allowing each thread to register one userspace
memory area to be used as an ABI between kernel and user-space for two
purposes: user-space restartable sequences and quick access to read the
current CPU number value from user-space.
* Restartable sequences (per-cpu atomics)
Restartables sequences allow user-space to perform update operations on
per-cpu data without requiring heavy-weight atomic operations.
The restartable critical sections (percpu atomics) work has been started
by Paul Turner and Andrew Hunter. It lets the kernel handle restart of
critical sections. [1] [2] The re-implementation proposed here brings a
few simplifications to the ABI which facilitates porting to other
architectures and speeds up the user-space fast path.
Here are benchmarks of various rseq use-cases.
Test hardware:
arm32: ARMv7 Processor rev 4 (v7l) "Cubietruck", 2-core
x86-64: Intel E5-2630 v3@2.40GHz, 16-core, hyperthreading
The following benchmarks were all performed on a single thread.
* Per-CPU statistic counter increment
getcpu+atomic (ns/op) rseq (ns/op) speedup
arm32: 344.0 31.4 11.0
x86-64: 15.3 2.0 7.7
* LTTng-UST: write event 32-bit header, 32-bit payload into tracer
per-cpu buffer
getcpu+atomic (ns/op) rseq (ns/op) speedup
arm32: 2502.0 2250.0 1.1
x86-64: 117.4 98.0 1.2
* liburcu percpu: lock-unlock pair, dereference, read/compare word
getcpu+atomic (ns/op) rseq (ns/op) speedup
arm32: 751.0 128.5 5.8
x86-64: 53.4 28.6 1.9
* jemalloc memory allocator adapted to use rseq
Using rseq with per-cpu memory pools in jemalloc at Facebook (based on
rseq 2016 implementation):
The production workload response-time has 1-2% gain avg. latency, and
the P99 overall latency drops by 2-3%.
* Reading the current CPU number
Speeding up reading the current CPU number on which the caller thread is
running is done by keeping the current CPU number up do date within the
cpu_id field of the memory area registered by the thread. This is done
by making scheduler preemption set the TIF_NOTIFY_RESUME flag on the
current thread. Upon return to user-space, a notify-resume handler
updates the current CPU value within the registered user-space memory
area. User-space can then read the current CPU number directly from
memory.
Keeping the current cpu id in a memory area shared between kernel and
user-space is an improvement over current mechanisms available to read
the current CPU number, which has the following benefits over
alternative approaches:
- 35x speedup on ARM vs system call through glibc
- 20x speedup on x86 compared to calling glibc, which calls vdso
executing a "lsl" instruction,
- 14x speedup on x86 compared to inlined "lsl" instruction,
- Unlike vdso approaches, this cpu_id value can be read from an inline
assembly, which makes it a useful building block for restartable
sequences.
- The approach of reading the cpu id through memory mapping shared
between kernel and user-space is portable (e.g. ARM), which is not the
case for the lsl-based x86 vdso.
On x86, yet another possible approach would be to use the gs segment
selector to point to user-space per-cpu data. This approach performs
similarly to the cpu id cache, but it has two disadvantages: it is
not portable, and it is incompatible with existing applications already
using the gs segment selector for other purposes.
Benchmarking various approaches for reading the current CPU number:
ARMv7 Processor rev 4 (v7l)
Machine model: Cubietruck
- Baseline (empty loop): 8.4 ns
- Read CPU from rseq cpu_id: 16.7 ns
- Read CPU from rseq cpu_id (lazy register): 19.8 ns
- glibc 2.19-0ubuntu6.6 getcpu: 301.8 ns
- getcpu system call: 234.9 ns
x86-64 Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz:
- Baseline (empty loop): 0.8 ns
- Read CPU from rseq cpu_id: 0.8 ns
- Read CPU from rseq cpu_id (lazy register): 0.8 ns
- Read using gs segment selector: 0.8 ns
- "lsl" inline assembly: 13.0 ns
- glibc 2.19-0ubuntu6 getcpu: 16.6 ns
- getcpu system call: 53.9 ns
- Speed (benchmark taken on v8 of patchset)
Running 10 runs of hackbench -l 100000 seems to indicate, contrary to
expectations, that enabling CONFIG_RSEQ slightly accelerates the
scheduler:
Configuration: 2 sockets * 8-core Intel(R) Xeon(R) CPU E5-2630 v3 @
2.40GHz (directly on hardware, hyperthreading disabled in BIOS, energy
saving disabled in BIOS, turboboost disabled in BIOS, cpuidle.off=1
kernel parameter), with a Linux v4.6 defconfig+localyesconfig,
restartable sequences series applied.
* CONFIG_RSEQ=n
avg.: 41.37 s
std.dev.: 0.36 s
* CONFIG_RSEQ=y
avg.: 40.46 s
std.dev.: 0.33 s
- Size
On x86-64, between CONFIG_RSEQ=n/y, the text size increase of vmlinux is
567 bytes, and the data size increase of vmlinux is 5696 bytes.
[1] https://lwn.net/Articles/650333/
[2] http://www.linuxplumbersconf.org/2013/ocw/system/presentations/1695/original/LPC%20-%20PerCpu%20Atomics.pdf
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Andrew Hunter <ahh@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20151027235635.16059.11630.stgit@pjt-glaptop.roam.corp.google.com
Link: http://lkml.kernel.org/r/20150624222609.6116.86035.stgit@kitami.mtv.corp.google.com
Link: https://lkml.kernel.org/r/20180602124408.8430-3-mathieu.desnoyers@efficios.com
Pull scheduler updates from Ingo Molnar:
- power-aware scheduling improvements (Patrick Bellasi)
- NUMA balancing improvements (Mel Gorman)
- vCPU scheduling fixes (Rohit Jain)
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/fair: Update util_est before updating schedutil
sched/cpufreq: Modify aggregate utilization to always include blocked FAIR utilization
sched/deadline/Documentation: Add overrun signal and GRUB-PA documentation
sched/core: Distinguish between idle_cpu() calls based on desired effect, introduce available_idle_cpu()
sched/wait: Include <linux/wait.h> in <linux/swait.h>
sched/numa: Stagger NUMA balancing scan periods for new threads
sched/core: Don't schedule threads on pre-empted vCPUs
sched/fair: Avoid calling sync_entity_load_avg() unnecessarily
sched/fair: Rearrange select_task_rq_fair() to optimize it
Pull RCU updates from Ingo Molnar:
- updates to the handling of expedited grace periods
- updates to reduce lock contention in the rcu_node combining tree
[ These are in preparation for the consolidation of RCU-bh,
RCU-preempt, and RCU-sched into a single flavor, which was
requested by Linus in response to a security flaw whose root cause
included confusion between the multiple flavors of RCU ]
- torture-test updates that save their users some time and effort
- miscellaneous fixes
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
rcu/x86: Provide early rcu_cpu_starting() callback
torture: Make kvm-find-errors.sh find build warnings
rcutorture: Abbreviate kvm.sh summary lines
rcutorture: Print end-of-test state in kvm.sh summary
rcutorture: Print end-of-test state
torture: Fold parse-torture.sh into parse-console.sh
torture: Add a script to edit output from failed runs
rcu: Update list of rcu_future_grace_period() trace events
rcu: Drop early GP request check from rcu_gp_kthread()
rcu: Simplify and inline cpu_needs_another_gp()
rcu: The rcu_gp_cleanup() function does not need cpu_needs_another_gp()
rcu: Make rcu_start_this_gp() check for out-of-range requests
rcu: Add funnel locking to rcu_start_this_gp()
rcu: Make rcu_start_future_gp() caller select grace period
rcu: Inline rcu_start_gp_advanced() into rcu_start_future_gp()
rcu: Clear request other than RCU_GP_FLAG_INIT at GP end
rcu: Cleanup, don't put ->completed into an int
rcu: Switch __rcu_process_callbacks() to rcu_accelerate_cbs()
rcu: Avoid __call_rcu_core() root rcu_node ->lock acquisition
rcu: Make rcu_migrate_callbacks wake GP kthread when needed
...
Merge speculative store buffer bypass fixes from Thomas Gleixner:
- rework of the SPEC_CTRL MSR management to accomodate the new fancy
SSBD (Speculative Store Bypass Disable) bit handling.
- the CPU bug and sysfs infrastructure for the exciting new Speculative
Store Bypass 'feature'.
- support for disabling SSB via LS_CFG MSR on AMD CPUs including
Hyperthread synchronization on ZEN.
- PRCTL support for dynamic runtime control of SSB
- SECCOMP integration to automatically disable SSB for sandboxed
processes with a filter flag for opt-out.
- KVM integration to allow guests fiddling with SSBD including the new
software MSR VIRT_SPEC_CTRL to handle the LS_CFG based oddities on
AMD.
- BPF protection against SSB
.. this is just the core and x86 side, other architecture support will
come separately.
* 'speck-v20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
bpf: Prevent memory disambiguation attack
x86/bugs: Rename SSBD_NO to SSB_NO
KVM: SVM: Implement VIRT_SPEC_CTRL support for SSBD
x86/speculation, KVM: Implement support for VIRT_SPEC_CTRL/LS_CFG
x86/bugs: Rework spec_ctrl base and mask logic
x86/bugs: Remove x86_spec_ctrl_set()
x86/bugs: Expose x86_spec_ctrl_base directly
x86/bugs: Unify x86_spec_ctrl_{set_guest,restore_host}
x86/speculation: Rework speculative_store_bypass_update()
x86/speculation: Add virtualized speculative store bypass disable support
x86/bugs, KVM: Extend speculation control for VIRT_SPEC_CTRL
x86/speculation: Handle HT correctly on AMD
x86/cpufeatures: Add FEATURE_ZEN
x86/cpufeatures: Disentangle SSBD enumeration
x86/cpufeatures: Disentangle MSR_SPEC_CTRL enumeration from IBRS
x86/speculation: Use synthetic bits for IBRS/IBPB/STIBP
KVM: SVM: Move spec control call after restore of GS
x86/cpu: Make alternative_msr_write work for 32-bit code
x86/bugs: Fix the parameters alignment and missing void
x86/bugs: Make cpu_show_common() static
...
- Updates to the handling of expedited grace periods, perhaps most
notably parallelizing their initialization. Other changes
include fixes from Boqun Feng.
- Miscellaneous fixes. These include an nvme fix from Nitzan Carmi
that I am carrying because it depends on a new SRCU function
cleanup_srcu_struct_quiesced(). This branch also includes fixes
from Byungchul Park and Yury Norov.
- Updates to reduce lock contention in the rcu_node combining tree.
These are in preparation for the consolidation of RCU-bh,
RCU-preempt, and RCU-sched into a single flavor, which was
requested by Linus Torvalds in response to a security flaw
whose root cause included confusion between the multiple flavors
of RCU.
- Torture-test updates that save their users some time and effort.
Conflicts:
drivers/nvme/host/core.c
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For certain use cases it is desired to enforce mitigations so they cannot
be undone afterwards. That's important for loader stubs which want to
prevent a child from disabling the mitigation again. Will also be used for
seccomp(). The extra state preserving of the prctl state for SSB is a
preparatory step for EBPF dymanic speculation control.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Gaurav reported a perceived problem with TASK_PARKED, which turned out
to be a broken wait-loop pattern in __kthread_parkme(), but the
reported issue can (and does) in fact happen for states that do not do
condition based sleeps.
When the 'current->state = TASK_RUNNING' store of a previous
(concurrent) try_to_wake_up() collides with the setting of a 'special'
sleep state, we can loose the sleep state.
Normal condition based wait-loops are immune to this problem, but for
sleep states that are not condition based are subject to this problem.
There already is a fix for TASK_DEAD. Abstract that and also apply it
to TASK_STOPPED and TASK_TRACED, both of which are also without
condition based wait-loop.
Reported-by: Gaurav Kohli <gkohli@codeaurora.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For some as yet not understood reason, Tony gets unaligned access
traps on IA64 because of:
struct util_est ue = READ_ONCE(p->se.avg.util_est);
and:
WRITE_ONCE(p->se.avg.util_est, ue);
introduced by commit:
d519329f72 ("sched/fair: Update util_est only on util_avg updates")
Normally those two fields should end up on an 8-byte aligned location,
but UP and RANDSTRUCT can mess that up so enforce the alignment
explicitly.
Also make the alignment on sched_avg unconditional, as it is really
about data locality, not false-sharing.
With or without this patch the layout for sched_avg on a
ia64-defconfig build looks like:
$ pahole -EC sched_avg ia64-defconfig/kernel/sched/core.o
die__process_function: tag not supported (INVALID)!
struct sched_avg {
/* typedef u64 */ long long unsigned int last_update_time; /* 0 8 */
/* typedef u64 */ long long unsigned int load_sum; /* 8 8 */
/* typedef u64 */ long long unsigned int runnable_load_sum; /* 16 8 */
/* typedef u32 */ unsigned int util_sum; /* 24 4 */
/* typedef u32 */ unsigned int period_contrib; /* 28 4 */
long unsigned int load_avg; /* 32 8 */
long unsigned int runnable_load_avg; /* 40 8 */
long unsigned int util_avg; /* 48 8 */
struct util_est {
unsigned int enqueued; /* 56 4 */
unsigned int ewma; /* 60 4 */
} util_est; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
/* size: 64, cachelines: 1, members: 9 */
};
Reported-and-Tested-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Norbert Manthey <nmanthey@amazon.de>
Cc: Patrick Bellasi <patrick.bellasi@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony <tony.luck@intel.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Fixes: d519329f72 ("sched/fair: Update util_est only on util_avg updates")
Link: http://lkml.kernel.org/r/20180405080521.GG4129@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The util_avg signal computed by PELT is too variable for some use-cases.
For example, a big task waking up after a long sleep period will have its
utilization almost completely decayed. This introduces some latency before
schedutil will be able to pick the best frequency to run a task.
The same issue can affect task placement. Indeed, since the task
utilization is already decayed at wakeup, when the task is enqueued in a
CPU, this can result in a CPU running a big task as being temporarily
represented as being almost empty. This leads to a race condition where
other tasks can be potentially allocated on a CPU which just started to run
a big task which slept for a relatively long period.
Moreover, the PELT utilization of a task can be updated every [ms], thus
making it a continuously changing value for certain longer running
tasks. This means that the instantaneous PELT utilization of a RUNNING
task is not really meaningful to properly support scheduler decisions.
For all these reasons, a more stable signal can do a better job of
representing the expected/estimated utilization of a task/cfs_rq.
Such a signal can be easily created on top of PELT by still using it as
an estimator which produces values to be aggregated on meaningful
events.
This patch adds a simple implementation of util_est, a new signal built on
top of PELT's util_avg where:
util_est(task) = max(task::util_avg, f(task::util_avg@dequeue))
This allows to remember how big a task has been reported by PELT in its
previous activations via f(task::util_avg@dequeue), which is the new
_task_util_est(struct task_struct*) function added by this patch.
If a task should change its behavior and it runs longer in a new
activation, after a certain time its util_est will just track the
original PELT signal (i.e. task::util_avg).
The estimated utilization of cfs_rq is defined only for root ones.
That's because the only sensible consumer of this signal are the
scheduler and schedutil when looking for the overall CPU utilization
due to FAIR tasks.
For this reason, the estimated utilization of a root cfs_rq is simply
defined as:
util_est(cfs_rq) = max(cfs_rq::util_avg, cfs_rq::util_est::enqueued)
where:
cfs_rq::util_est::enqueued = sum(_task_util_est(task))
for each RUNNABLE task on that root cfs_rq
It's worth noting that the estimated utilization is tracked only for
objects of interests, specifically:
- Tasks: to better support tasks placement decisions
- root cfs_rqs: to better support both tasks placement decisions as
well as frequencies selection
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com>
Cc: Steve Muckle <smuckle@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Todd Kjos <tkjos@android.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Link: http://lkml.kernel.org/r/20180309095245.11071-2-patrick.bellasi@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The select_idle_sibling() (SIS) rewrite in commit:
10e2f1acd0 ("sched/core: Rewrite and improve select_idle_siblings()")
... replaced a domain iteration with a search that broadly speaking
does a wrapped walk of the scheduler domain sharing a last-level-cache.
While this had a number of improvements, one consequence is that two tasks
that share a waker/wakee relationship push each other around a socket. Even
though two tasks may be active, all cores are evenly used. This is great from
a search perspective and spreads a load across individual cores, but it has
adverse consequences for cpufreq. As each CPU has relatively low utilisation,
cpufreq may decide the utilisation is too low to used a higher P-state and
overall computation throughput suffers.
While individual cpufreq and cpuidle drivers may compensate by artifically
boosting P-state (at c0) or avoiding lower C-states (during idle), it does
not help if hardware-based cpufreq (e.g. HWP) is used.
This patch tracks a recently used CPU based on what CPU a task was running
on when it last was a waker a CPU it was recently using when a task is a
wakee. During SIS, the recently used CPU is used as a target if it's still
allowed by the task and is idle.
The benefit may be non-obvious so consider an example of two tasks
communicating back and forth. Task A may be an application doing IO where
task B is a kworker or kthread like journald. Task A may issue IO, wake
B and B wakes up A on completion. With the existing scheme this may look
like the following (potentially different IDs if SMT is in use but similar
principal applies).
A (cpu 0) wake B (wakes on cpu 1)
B (cpu 1) wake A (wakes on cpu 2)
A (cpu 2) wake B (wakes on cpu 3)
etc.
A careful reader may wonder why CPU 0 was not idle when B wakes A the
first time and it's simply due to the fact that A can be rescheduled to
another CPU and the pattern is that prev == target when B tries to wakeup A
and the information about CPU 0 has been lost.
With this patch, the pattern is more likely to be:
A (cpu 0) wake B (wakes on cpu 1)
B (cpu 1) wake A (wakes on cpu 0)
A (cpu 0) wake B (wakes on cpu 1)
etc
i.e. two communicating casts are more likely to use just two cores instead
of all available cores sharing a LLC.
The most dramatic speedup was noticed on dbench using the XFS filesystem on
UMA as clients interact heavily with workqueues in that configuration. Note
that a similar speedup is not observed on ext4 as the wakeup pattern
is different:
4.15.0-rc9 4.15.0-rc9
waprev-v1 biasancestor-v1
Hmean 1 287.54 ( 0.00%) 817.01 ( 184.14%)
Hmean 2 1268.12 ( 0.00%) 1781.24 ( 40.46%)
Hmean 4 1739.68 ( 0.00%) 1594.47 ( -8.35%)
Hmean 8 2464.12 ( 0.00%) 2479.56 ( 0.63%)
Hmean 64 1455.57 ( 0.00%) 1434.68 ( -1.44%)
The results can be less dramatic on NUMA where automatic balancing interferes
with the test. It's also known that network benchmarks running on localhost
also benefit quite a bit from this patch (roughly 10% on netperf RR for UDP
and TCP depending on the machine). Hackbench also seens small improvements
(6-11% depending on machine and thread count). The facebook schbench was also
tested but in most cases showed little or no different to wakeup latencies.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20180130104555.4125-5-mgorman@techsingularity.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle were:
- Implement frequency/CPU invariance and OPP selection for
SCHED_DEADLINE (Juri Lelli)
- Tweak the task migration logic for better multi-tasking
workload scalability (Mel Gorman)
- Misc cleanups, fixes and improvements"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/deadline: Make bandwidth enforcement scale-invariant
sched/cpufreq: Move arch_scale_{freq,cpu}_capacity() outside of #ifdef CONFIG_SMP
sched/cpufreq: Remove arch_scale_freq_capacity()'s 'sd' parameter
sched/cpufreq: Always consider all CPUs when deciding next freq
sched/cpufreq: Split utilization signals
sched/cpufreq: Change the worker kthread to SCHED_DEADLINE
sched/deadline: Move CPU frequency selection triggering points
sched/cpufreq: Use the DEADLINE utilization signal
sched/deadline: Implement "runtime overrun signal" support
sched/fair: Only immediately migrate tasks due to interrupts if prev and target CPUs share cache
sched/fair: Correct obsolete comment about cpufreq_update_util()
sched/fair: Remove impossible condition from find_idlest_group_cpu()
sched/cpufreq: Don't pass flags to sugov_set_iowait_boost()
sched/cpufreq: Initialize sg_cpu->flags to 0
sched/fair: Consider RT/IRQ pressure in capacity_spare_wake()
sched/fair: Use 'unsigned long' for utilization, consistently
sched/core: Rework and clarify prepare_lock_switch()
sched/fair: Remove unused 'curr' parameter from wakeup_gran
sched/headers: Constify object_is_on_stack()
