The code that checks recursion will work to only do the recursion check once
if there's nested checks. The top one will do the check, the other nested
checks will see recursion was already checked and return zero for its "bit".
On the return side, nothing will be done if the "bit" is zero.
The problem is that zero is returned for the "good" bit when in NMI context.
This will set the bit for NMIs making it look like *all* NMI tracing is
recursing, and prevent tracing of anything in NMI context!
The simple fix is to return "bit + 1" and subtract that bit on the end to
get the real bit.
Cc: stable@vger.kernel.org
Fixes: edc15cafcb ("tracing: Avoid unnecessary multiple recursion checks")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
The nesting count of trace_printk allows for 4 levels of nesting. The
nesting counter starts at zero and is incremented before being used to
retrieve the current context's buffer. But the index to the buffer uses the
nesting counter after it was incremented, and not its original number,
which in needs to do.
Link: https://lkml.kernel.org/r/20201029161905.4269-1-hqjagain@gmail.com
Cc: stable@vger.kernel.org
Fixes: 3d9622c12c ("tracing: Add barrier to trace_printk() buffer nesting modification")
Signed-off-by: Qiujun Huang <hqjagain@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Pull timer fixes from Thomas Gleixner:
"A few fixes for timers/timekeeping:
- Prevent undefined behaviour in the timespec64_to_ns() conversion
which is used for converting user supplied time input to
nanoseconds. It lacked overflow protection.
- Mark sched_clock_read_begin/retry() to prevent recursion in the
tracer
- Remove unused debug functions in the hrtimer and timerlist code"
* tag 'timers-urgent-2020-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
time: Prevent undefined behaviour in timespec64_to_ns()
timers: Remove unused inline funtion debug_timer_free()
hrtimer: Remove unused inline function debug_hrtimer_free()
time/sched_clock: Mark sched_clock_read_begin/retry() as notrace
Pull smp fix from Thomas Gleixner:
"A single fix for stop machine.
Mark functions no trace to prevent a crash caused by recursion when
enabling or disabling a tracer on RISC-V (probably all architectures
which patch through stop machine)"
* tag 'smp-urgent-2020-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
stop_machine, rcu: Mark functions as notrace
Pull locking fixes from Thomas Gleixner:
"A couple of locking fixes:
- Fix incorrect failure injection handling in the fuxtex code
- Prevent a preemption warning in lockdep when tracking
local_irq_enable() and interrupts are already enabled
- Remove more raw_cpu_read() usage from lockdep which causes state
corruption on !X86 architectures.
- Make the nr_unused_locks accounting in lockdep correct again"
* tag 'locking-urgent-2020-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
lockdep: Fix nr_unused_locks accounting
locking/lockdep: Remove more raw_cpu_read() usage
futex: Fix incorrect should_fail_futex() handling
lockdep: Fix preemption WARN for spurious IRQ-enable
Pull more flexible-array member conversions from Gustavo A. R. Silva:
"Replace zero-length arrays with flexible-array members"
* tag 'flexible-array-conversions-5.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gustavoars/linux:
printk: ringbuffer: Replace zero-length array with flexible-array member
net/smc: Replace zero-length array with flexible-array member
net/mlx5: Replace zero-length array with flexible-array member
mei: hw: Replace zero-length array with flexible-array member
gve: Replace zero-length array with flexible-array member
Bluetooth: btintel: Replace zero-length array with flexible-array member
scsi: target: tcmu: Replace zero-length array with flexible-array member
ima: Replace zero-length array with flexible-array member
enetc: Replace zero-length array with flexible-array member
fs: Replace zero-length array with flexible-array member
Bluetooth: Replace zero-length array with flexible-array member
params: Replace zero-length array with flexible-array member
tracepoint: Replace zero-length array with flexible-array member
platform/chrome: cros_ec_proto: Replace zero-length array with flexible-array member
platform/chrome: cros_ec_commands: Replace zero-length array with flexible-array member
mailbox: zynqmp-ipi-message: Replace zero-length array with flexible-array member
dmaengine: ti-cppi5: Replace zero-length array with flexible-array member
Almost all machines use GENERIC_CLOCKEVENTS, so it feels wrong to
require each one to select that symbol manually.
Instead, enable it whenever CONFIG_LEGACY_TIMER_TICK is disabled as
a simplification. It should be possible to select both
GENERIC_CLOCKEVENTS and LEGACY_TIMER_TICK from an architecture now
and decide at runtime between the two.
For the clockevents arch-support.txt file, this means that additional
architectures are marked as TODO when they have at least one machine
that still uses LEGACY_TIMER_TICK, rather than being marked 'ok' when
at least one machine has been converted. This means that both m68k and
arm (for riscpc) revert to TODO.
At this point, we could just always enable CONFIG_GENERIC_CLOCKEVENTS
rather than leaving it off when not needed. I built an m68k
defconfig kernel (using gcc-10.1.0) and found that this would add
around 5.5KB in kernel image size:
text data bss dec hex filename
3861936 1092236 196656 5150828 4e986c obj-m68k/vmlinux-no-clockevent
3866201 1093832 196184 5156217 4ead79 obj-m68k/vmlinux-clockevent
On Arm (MACH_RPC), that difference appears to be twice as large,
around 11KB on top of an 6MB vmlinux.
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
There are no more users of xtime_update aside from legacy_timer_tick(),
so fold it into that function and remove the declaration.
update_process_times() is now only called inside of the kernel/time/
code, so the declaration can be moved there.
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
All platforms that currently do not use generic clockevents roughly call
the same set of functions in their timer interrupts: xtime_update(),
update_process_times() and profile_tick(), sometimes in a different
sequence.
Add a helper function that performs all three of them, to make the
callers more uniform and simplify the interface.
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
With Arm EBSA110 gone, nothing uses it any more, so the corresponding
code and the Kconfig option can be removed.
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
If a hashtab is accessed in both non-NMI and NMI context, the system may
deadlock on bucket->lock. Fix this issue with percpu counter map_locked.
map_locked rejects concurrent access to the same bucket from the same CPU.
To reduce memory overhead, map_locked is not added per bucket. Instead,
8 percpu counters are added to each hashtab. buckets are assigned to these
counters based on the lower bits of its hash.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201029071925.3103400-3-songliubraving@fb.com
Pull power management fixes from Rafael Wysocki:
"These fix a few issues related to running intel_pstate in the passive
mode with HWP enabled, correct the handling of the max_cstate module
parameter in intel_idle and make a few janitorial changes.
Specifics:
- Modify Kconfig to prevent configuring either the "conservative" or
the "ondemand" governor as the default cpufreq governor if
intel_pstate is selected, in which case "schedutil" is the default
choice for the default governor setting (Rafael Wysocki).
- Modify the cpufreq core, intel_pstate and the schedutil governor to
avoid missing updates of the HWP max limit when intel_pstate
operates in the passive mode with HWP enabled (Rafael Wysocki).
- Fix max_cstate module parameter handling in intel_idle for
processor models with C-state tables coming from ACPI (Chen Yu).
- Clean up assorted pieces of power management code (Jackie Zamow,
Tom Rix, Zhang Qilong)"
* tag 'pm-5.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
cpufreq: schedutil: Always call driver if CPUFREQ_NEED_UPDATE_LIMITS is set
cpufreq: Introduce cpufreq_driver_test_flags()
cpufreq: speedstep: remove unneeded semicolon
PM: sleep: fix typo in kernel/power/process.c
intel_idle: Fix max_cstate for processor models without C-state tables
cpufreq: intel_pstate: Avoid missing HWP max updates in passive mode
cpufreq: Introduce CPUFREQ_NEED_UPDATE_LIMITS driver flag
cpufreq: Avoid configuring old governors as default with intel_pstate
cpufreq: e_powersaver: remove unreachable break
Chris reported that commit 24d5a3bffef1 ("lockdep: Fix
usage_traceoverflow") breaks the nr_unused_locks validation code
triggered by /proc/lockdep_stats.
By fully splitting LOCK_USED and LOCK_USED_READ it becomes a bad
indicator for accounting nr_unused_locks; simplyfy by using any first
bit.
Fixes: 24d5a3bffef1 ("lockdep: Fix usage_traceoverflow")
Reported-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://lkml.kernel.org/r/20201027124834.GL2628@hirez.programming.kicks-ass.net
I initially thought raw_cpu_read() was OK, since if it is !0 we have
IRQs disabled and can't get migrated, so if we get migrated both CPUs
must have 0 and it doesn't matter which 0 we read.
And while that is true; it isn't the whole store, on pretty much all
architectures (except x86) this can result in computing the address for
one CPU, getting migrated, the old CPU continuing execution with another
task (possibly setting recursion) and then the new CPU reading the value
of the old CPU, which is no longer 0.
Similer to:
baffd723e4 ("lockdep: Revert "lockdep: Use raw_cpu_*() for per-cpu variables"")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201026152256.GB2651@hirez.programming.kicks-ass.net
Commit 3193c0836 ("bpf: Disable GCC -fgcse optimization for
___bpf_prog_run()") introduced a __no_fgcse macro that expands to a
function scope __attribute__((optimize("-fno-gcse"))), to disable a
GCC specific optimization that was causing trouble on x86 builds, and
was not expected to have any positive effect in the first place.
However, as the GCC manual documents, __attribute__((optimize))
is not for production use, and results in all other optimization
options to be forgotten for the function in question. This can
cause all kinds of trouble, but in one particular reported case,
it causes -fno-asynchronous-unwind-tables to be disregarded,
resulting in .eh_frame info to be emitted for the function.
This reverts commit 3193c0836, and instead, it disables the -fgcse
optimization for the entire source file, but only when building for
X86 using GCC with CONFIG_BPF_JIT_ALWAYS_ON disabled. Note that the
original commit states that CONFIG_RETPOLINE=n triggers the issue,
whereas CONFIG_RETPOLINE=y performs better without the optimization,
so it is kept disabled in both cases.
Fixes: 3193c0836f ("bpf: Disable GCC -fgcse optimization for ___bpf_prog_run()")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/lkml/CAMuHMdUg0WJHEcq6to0-eODpXPOywLot6UD2=GFHpzoj_hCoBQ@mail.gmail.com/
Link: https://lore.kernel.org/bpf/20201028171506.15682-2-ardb@kernel.org
Because sugov_update_next_freq() may skip a frequency update even if
the need_freq_update flag has been set for the policy at hand, policy
limits updates may not take effect as expected.
For example, if the intel_pstate driver operates in the passive mode
with HWP enabled, it needs to update the HWP min and max limits when
the policy min and max limits change, respectively, but that may not
happen if the target frequency does not change along with the limit
at hand. In particular, if the policy min is changed first, causing
the target frequency to be adjusted to it, and the policy max limit
is changed later to the same value, the HWP max limit will not be
updated to follow it as expected, because the target frequency is
still equal to the policy min limit and it will not change until
that limit is updated.
To address this issue, modify get_next_freq() to let the driver
callback run if the CPUFREQ_NEED_UPDATE_LIMITS cpufreq driver flag
is set regardless of whether or not the new frequency to set is
equal to the previous one.
Fixes: f6ebbcf08f ("cpufreq: intel_pstate: Implement passive mode with HWP enabled")
Reported-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Cc: 5.9+ <stable@vger.kernel.org> # 5.9+: 1c534352f4 cpufreq: Introduce CPUFREQ_NEED_UPDATE_LIMITS ...
Cc: 5.9+ <stable@vger.kernel.org> # 5.9+: a62f68f5ca cpufreq: Introduce cpufreq_driver_test_flags()
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
If a module fails to load due to an error in prepare_coming_module(),
the following error handling in load_module() runs with
MODULE_STATE_COMING in module's state. Fix it by correctly setting
MODULE_STATE_GOING under "bug_cleanup" label.
Signed-off-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
A limited nunmber of architectures support hugetlbfs sizes that do not
align with the page-tables (ARM64, Power, Sparc64). Add support for
this to the generic perf_get_page_size() implementation, and also
allow an architecture to override this implementation.
This latter is only needed when it uses non-page-table aligned huge
pages in its kernel map.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
When studying code layout, it is useful to capture the page size of the
sampled code address.
Add a new sample type for code page size.
The new sample type requires collecting the ip. The code page size can
be calculated from the NMI-safe perf_get_page_size().
For large PEBS, it's very unlikely that the mapping is gone for the
earlier PEBS records. Enable the feature for the large PEBS. The worst
case is that page-size '0' is returned.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-5-kan.liang@linux.intel.com
Current perf can report both virtual addresses and physical addresses,
but not the MMU page size. Without the MMU page size information of the
utilized page, users cannot decide whether to promote/demote large pages
to optimize memory usage.
Add a new sample type for the data MMU page size.
Current perf already has a facility to collect data virtual addresses.
A page walker is required to walk the pages tables and calculate the
MMU page size from a given virtual address.
On some platforms, e.g., X86, the page walker is invoked in an NMI
handler. So the page walker must be NMI-safe and low overhead. Besides,
the page walker should work for both user and kernel virtual address.
The existing generic page walker, e.g., walk_page_range_novma(), is a
little bit complex and doesn't guarantee the NMI-safe. The follow_page()
is only for user-virtual address.
Add a new function perf_get_page_size() to walk the page tables and
calculate the MMU page size. In the function:
- Interrupts have to be disabled to prevent any teardown of the page
tables.
- For user space threads, the current->mm is used for the page walker.
For kernel threads and the like, the current->mm is NULL. The init_mm
is used for the page walker. The active_mm is not used here, because
it can be NULL.
Quote from Peter Zijlstra,
"context_switch() can set prev->active_mm to NULL when it transfers it
to @next. It does this before @current is updated. So an NMI that
comes in between this active_mm swizzling and updating @current will
see !active_mm."
- The MMU page size is calculated from the page table level.
The method should work for all architectures, but it has only been
verified on X86. Should there be some architectures, which support perf,
where the method doesn't work, it can be fixed later separately.
Reporting the wrong page size would not be fatal for the architecture.
Some under discussion features may impact the method in the future.
Quote from Dave Hansen,
"There are lots of weird things folks are trying to do with the page
tables, like Address Space Isolation. For instance, if you get a
perf NMI when running userspace, current->mm->pgd is *different* than
the PGD that was in use when userspace was running. It's close enough
today, but it might not stay that way."
If the case happens later, lots of consecutive page walk errors will
happen. The worst case is that lots of page-size '0' are returned, which
would not be fatal.
In the perf tool, a check is implemented to detect this case. Once it
happens, a kernel patch could be implemented accordingly then.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-2-kan.liang@linux.intel.com
In the case of a thread wakeup, wake_affine determines whether a core
will be chosen for the thread on the socket where the thread ran
previously or on the socket of the waker. This is done primarily by
comparing the load of the core where th thread ran previously (prev)
and the load of the waker (this).
commit 11f10e5420 ("sched/fair: Use load instead of runnable load
in wakeup path") changed the load computation from the runnable load
to the load average, where the latter includes the load of threads
that have already blocked on the core.
When a short-running daemon processes happens to run on prev, this
change raised the situation that prev could appear to have a greater
load than this, even when prev is actually idle. When prev and this
are on the same socket, the idle prev is detected later, in
select_idle_sibling. But if that does not hold, prev is completely
ignored, causing the waking thread to move to the socket of the waker.
In the case of N mostly active threads on N cores, this triggers other
migrations and hurts performance.
In contrast, before commit 11f10e5420, the load on an idle core
was 0, and in the case of a non-idle waker core, the effect of
wake_affine was to select prev as the target for searching for a core
for the waking thread.
To avoid unnecessary migrations, extend wake_affine_idle to check
whether the core where the thread previously ran is currently idle,
and if so simply return that core as the target.
[1] commit 11f10e5420 ("sched/fair: Use load instead of runnable
load in wakeup path")
This particularly has an impact when using the ondemand power manager,
where kworkers run every 0.004 seconds on all cores, increasing the
likelihood that an idle core will be considered to have a load.
The following numbers were obtained with the benchmarking tool
hyperfine (https://github.com/sharkdp/hyperfine) on the NAS parallel
benchmarks (https://www.nas.nasa.gov/publications/npb.html). The
tests were run on an 80-core Intel(R) Xeon(R) CPU E7-8870 v4 @
2.10GHz. Active (intel_pstate) and passive (intel_cpufreq) power
management were used. Times are in seconds. All experiments use all
160 hardware threads.
v5.9/intel-pstate v5.9+patch/intel-pstate
bt.C.c 24.725724+-0.962340 23.349608+-1.607214
lu.C.x 29.105952+-4.804203 25.249052+-5.561617
sp.C.x 31.220696+-1.831335 30.227760+-2.429792
ua.C.x 26.606118+-1.767384 25.778367+-1.263850
v5.9/ondemand v5.9+patch/ondemand
bt.C.c 25.330360+-1.028316 23.544036+-1.020189
lu.C.x 35.872659+-4.872090 23.719295+-3.883848
sp.C.x 32.141310+-2.289541 29.125363+-0.872300
ua.C.x 29.024597+-1.667049 25.728888+-1.539772
On the smaller data sets (A and B) and on the other NAS benchmarks
there is no impact on performance.
This also has a major impact on the splash2x.volrend benchmark of the
parsec benchmark suite that goes from 1m25 without this patch to 0m45,
in active (intel_pstate) mode.
Fixes: 11f10e5420 ("sched/fair: Use load instead of runnable load in wakeup path")
Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lkml.kernel.org/r/1603372550-14680-1-git-send-email-Julia.Lawall@inria.fr
Florian reported that all of kernel/sched/ is rebuild when
CONFIG_BLK_DEV_INITRD is changed, which, while not a bug is
unexpected. This is due to us including vmlinux.lds.h.
Jakub explained that the problem is that we put the alignment
requirement on the type instead of on a variable. Type alignment is a
minimum, the compiler is free to pick any larger alignment for a
specific instance of the type (eg. the variable).
So force the type alignment on all individual variable definitions and
remove the undesired dependency on vmlinux.lds.h.
Fixes: 85c2ce9104 ("sched, vmlinux.lds: Increase STRUCT_ALIGNMENT to 64 bytes for GCC-4.9")
Reported-by: Florian Fainelli <f.fainelli@gmail.com>
Suggested-by: Jakub Jelinek <jakub@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
do_sched_yield() invokes schedule() with interrupts disabled which is
not allowed. This goes back to the pre git era to commit a6efb709806c
("[PATCH] irqlock patch 2.5.27-H6") in the history tree.
Reenable interrupts and remove the misleading comment which "explains" it.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/87r1pt7y5c.fsf@nanos.tec.linutronix.de
Add comments and memory barrier to kthread_use_mm and kthread_unuse_mm
to allow the effect of membarrier(2) to apply to kthreads accessing
user-space memory as well.
Given that no prior kthread use this guarantee and that it only affects
kthreads, adding this guarantee does not affect user-space ABI.
Refine the check in membarrier_global_expedited to exclude runqueues
running the idle thread rather than all kthreads from the IPI cpumask.
Now that membarrier_global_expedited can IPI kthreads, the scheduler
also needs to update the runqueue's membarrier_state when entering lazy
TLB state.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201020134715.13909-3-mathieu.desnoyers@efficios.com
exit_mm should issue memory barriers after user-space memory accesses,
before clearing current->mm, to order user-space memory accesses
performed prior to exit_mm before clearing tsk->mm, which has the
effect of skipping the membarrier private expedited IPIs.
exit_mm should also update the runqueue's membarrier_state so
membarrier global expedited IPIs are not sent when they are not
needed.
The membarrier system call can be issued concurrently with do_exit
if we have thread groups created with CLONE_VM but not CLONE_THREAD.
Here is the scenario I have in mind:
Two thread groups are created, A and B. Thread group B is created by
issuing clone from group A with flag CLONE_VM set, but not CLONE_THREAD.
Let's assume we have a single thread within each thread group (Thread A
and Thread B).
The AFAIU we can have:
Userspace variables:
int x = 0, y = 0;
CPU 0 CPU 1
Thread A Thread B
(in thread group A) (in thread group B)
x = 1
barrier()
y = 1
exit()
exit_mm()
current->mm = NULL;
r1 = load y
membarrier()
skips CPU 0 (no IPI) because its current mm is NULL
r2 = load x
BUG_ON(r1 == 1 && r2 == 0)
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201020134715.13909-2-mathieu.desnoyers@efficios.com
It is possible for find_new_ilb() to select the current CPU, however,
this only happens from newidle balancing, in which case need_resched()
will be true, and consequently nohz_csd_func() will not trigger the
softirq.
Exclude the current CPU from becoming an ILB target.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Add CPUPRI_HIGHER above the RT99 priority to denote the CPU is in use
by higher priority tasks (specifically deadline).
XXX: we should probably drive PUSH-PULL from cpupri, that would
automagically result in an RT-PUSH when DL sets cpupri to CPUPRI_HIGHER.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
pri_to_cpu[CPUPRI_IDLE=0] isn't used since cpupri_set(..., newpri) is
never called with newpri = MAX_PRIO (140).
Current mapping:
p->rt_priority p->prio newpri cpupri
-1 -1 (CPUPRI_INVALID)
140 0 (CPUPRI_IDLE)
100 1 (CPUPRI_NORMAL)
1 98 98 3
...
49 50 50 51
50 49 49 52
...
99 0 0 101
Even when cpupri was introduced with commit 6e0534f278 ("sched: use a
2-d bitmap for searching lowest-pri CPU") in v2.6.27, only
(1) CPUPRI_INVALID (-1),
(2) MAX_RT_PRIO (100),
(3) an RT prio (RT1..RT99)
were used as newprio in cpupri_set(..., newpri) -> convert_prio(newpri).
MAX_RT_PRIO is used only in dec_rt_tasks() -> dec_rt_prio() ->
dec_rt_prio_smp() -> cpupri_set() in case of !rt_rq->rt_nr_running.
I.e. it stands for a non-rt task, including the IDLE task.
Commit 57785df5ac ("sched: Fix task priority bug") removed code in
v2.6.33 which did set the priority of the IDLE task to MAX_PRIO.
Although this happened after the introduction of cpupri, it didn't have
an effect on the values used for cpupri_set(..., newpri).
Remove CPUPRI_IDLE and adapt the cpupri implementation accordingly.
This will save a useless for loop with an atomic_read in
cpupri_find_fitness() calling __cpupri_find().
New mapping:
p->rt_priority p->prio newpri cpupri
-1 -1 (CPUPRI_INVALID)
100 0 (CPUPRI_NORMAL)
1 98 98 2
...
49 50 50 50
50 49 49 51
...
99 0 0 100
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200922083934.19275-2-dietmar.eggemann@arm.com
When change sched_rt_{runtime, period}_us, we validate that the new
settings should at least accommodate the currently allocated -dl
bandwidth:
sched_rt_handler()
--> sched_dl_bandwidth_validate()
{
new_bw = global_rt_runtime()/global_rt_period();
for_each_possible_cpu(cpu) {
dl_b = dl_bw_of(cpu);
if (new_bw < dl_b->total_bw) <-------
ret = -EBUSY;
}
}
But under CONFIG_SMP, dl_bw is per root domain , but not per CPU,
dl_b->total_bw is the allocated bandwidth of the whole root domain.
Instead, we should compare dl_b->total_bw against "cpus*new_bw",
where 'cpus' is the number of CPUs of the root domain.
Also, below annotation(in kernel/sched/sched.h) implied implementation
only appeared in SCHED_DEADLINE v2[1], then deadline scheduler kept
evolving till got merged(v9), but the annotation remains unchanged,
meaningless and misleading, update it.
* With respect to SMP, the bandwidth is given on a per-CPU basis,
* meaning that:
* - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
* - dl_total_bw array contains, in the i-eth element, the currently
* allocated bandwidth on the i-eth CPU.
[1]: https://lore.kernel.org/lkml/1267385230.13676.101.camel@Palantir/
Fixes: 332ac17ef5 ("sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks")
Signed-off-by: Peng Liu <iwtbavbm@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/db6bbda316048cda7a1bbc9571defde193a8d67e.1602171061.git.iwtbavbm@gmail.com
If the arch supports TIF_NOTIFY_SIGNAL, then use that for TWA_SIGNAL as
it's more efficient than using the signal delivery method. This is
especially true on threaded applications, where ->sighand is shared across
threads, but it's also lighter weight on non-shared cases.
io_uring is a heavy consumer of TWA_SIGNAL based task_work. A test with
threads shows a nice improvement running an io_uring based echo server.
stock kernel:
0.01% <= 0.1 milliseconds
95.86% <= 0.2 milliseconds
98.27% <= 0.3 milliseconds
99.71% <= 0.4 milliseconds
100.00% <= 0.5 milliseconds
100.00% <= 0.6 milliseconds
100.00% <= 0.7 milliseconds
100.00% <= 0.8 milliseconds
100.00% <= 0.9 milliseconds
100.00% <= 1.0 milliseconds
100.00% <= 1.1 milliseconds
100.00% <= 2 milliseconds
100.00% <= 3 milliseconds
100.00% <= 3 milliseconds
1378930.00 requests per second
~1600% CPU
1.38M requests/second, and all 16 CPUs are maxed out.
patched kernel:
0.01% <= 0.1 milliseconds
98.24% <= 0.2 milliseconds
99.47% <= 0.3 milliseconds
99.99% <= 0.4 milliseconds
100.00% <= 0.5 milliseconds
100.00% <= 0.6 milliseconds
100.00% <= 0.7 milliseconds
100.00% <= 0.8 milliseconds
100.00% <= 0.9 milliseconds
100.00% <= 1.2 milliseconds
1666111.38 requests per second
~1450% CPU
1.67M requests/second, and we're no longer just hammering on the sighand
lock. The original reporter states:
"For 5.7.15 my benchmark achieves 1.6M qps and system cpu is at ~80%.
for 5.7.16 or later it achieves only 1M qps and the system cpu is is
at ~100%"
with the only difference there being that TWA_SIGNAL is used
unconditionally in 5.7.16, since it's required to be able to handle the
inability to run task_work if the application is waiting in the kernel
already on an event that needs task_work run to be satisfied. Also see
commit 0ba9c9edcd.
Reported-by: Roman Gershman <romger@amazon.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20201026203230.386348-5-axboe@kernel.dk
Add TIF_NOTIFY_SIGNAL handling in the generic entry code, which if set,
will return true if signal_pending() is used in a wait loop. That causes an
exit of the loop so that notify_signal tracehooks can be run. If the wait
loop is currently inside a system call, the system call is restarted once
task_work has been processed.
In preparation for only having arch_do_signal() handle syscall restarts if
_TIF_SIGPENDING isn't set, rename it to arch_do_signal_or_restart(). Pass
in a boolean that tells the architecture specific signal handler if it
should attempt to get a signal, or just process a potential syscall
restart.
For !CONFIG_GENERIC_ENTRY archs, add the TIF_NOTIFY_SIGNAL handling to
get_signal(). This is done to minimize the needed architecture changes to
support this feature.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20201026203230.386348-3-axboe@kernel.dk
This is in preparation for maintaining signal_pending() as the decider of
whether or not a schedule() loop should be broken, or continue sleeping.
This is different than the core signal use cases, which really need to know
whether an actual signal is pending or not. task_sigpending() returns
non-zero if TIF_SIGPENDING is set.
Only core kernel use cases should care about the distinction between
the two, make sure those use the task_sigpending() helper.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20201026203230.386348-2-axboe@kernel.dk
Commit e679654a70 ("bpf: Fix a rcu_sched stall issue with
bpf task/task_file iterator") tries to fix rcu stalls warning
which is caused by bpf task_file iterator when running
"bpftool prog".
rcu: INFO: rcu_sched self-detected stall on CPU
rcu: \x097-....: (20999 ticks this GP) idle=302/1/0x4000000000000000 softirq=1508852/1508852 fqs=4913
\x09(t=21031 jiffies g=2534773 q=179750)
NMI backtrace for cpu 7
CPU: 7 PID: 184195 Comm: bpftool Kdump: loaded Tainted: G W 5.8.0-00004-g68bfc7f8c1b4 #6
Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A17 05/03/2019
Call Trace:
<IRQ>
dump_stack+0x57/0x70
nmi_cpu_backtrace.cold+0x14/0x53
? lapic_can_unplug_cpu.cold+0x39/0x39
nmi_trigger_cpumask_backtrace+0xb7/0xc7
rcu_dump_cpu_stacks+0xa2/0xd0
rcu_sched_clock_irq.cold+0x1ff/0x3d9
? tick_nohz_handler+0x100/0x100
update_process_times+0x5b/0x90
tick_sched_timer+0x5e/0xf0
__hrtimer_run_queues+0x12a/0x2a0
hrtimer_interrupt+0x10e/0x280
__sysvec_apic_timer_interrupt+0x51/0xe0
asm_call_on_stack+0xf/0x20
</IRQ>
sysvec_apic_timer_interrupt+0x6f/0x80
...
task_file_seq_next+0x52/0xa0
bpf_seq_read+0xb9/0x320
vfs_read+0x9d/0x180
ksys_read+0x5f/0xe0
do_syscall_64+0x38/0x60
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The fix is to limit the number of bpf program runs to be
one million. This fixed the program in most cases. But
we also found under heavy load, which can increase the wallclock
time for bpf_seq_read(), the warning may still be possible.
For example, calling bpf_delay() in the "while" loop of
bpf_seq_read(), which will introduce artificial delay,
the warning will show up in my qemu run.
static unsigned q;
volatile unsigned *p = &q;
volatile unsigned long long ll;
static void bpf_delay(void)
{
int i, j;
for (i = 0; i < 10000; i++)
for (j = 0; j < 10000; j++)
ll += *p;
}
There are two ways to fix this issue. One is to reduce the above
one million threshold to say 100,000 and hopefully rcu warning will
not show up any more. Another is to introduce a target feature
which enables bpf_seq_read() calling cond_resched().
This patch took second approach as the first approach may cause
more -EAGAIN failures for read() syscalls. Note that not all bpf_iter
targets can permit cond_resched() in bpf_seq_read() as some, e.g.,
netlink seq iterator, rcu read lock critical section spans through
seq_ops->next() -> seq_ops->show() -> seq_ops->next().
For the kernel code with the above hack, "bpftool p" roughly takes
38 seconds to finish on my VM with 184 bpf program runs.
Using the following command, I am able to collect the number of
context switches:
perf stat -e context-switches -- ./bpftool p >& log
Without this patch,
69 context-switches
With this patch,
75 context-switches
This patch added additional 6 context switches, roughly every 6 seconds
to reschedule, to avoid lengthy no-rescheduling which may cause the
above RCU warnings.
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20201028061054.1411116-1-yhs@fb.com
Coredump logics needs to report not only the registers of the dumping
thread, but (since 2.5.43) those of other threads getting killed.
Doing that might require extra state saved on the stack in asm glue at
kernel entry; signal delivery logics does that (we need to be able to
save sigcontext there, at the very least) and so does seccomp.
That covers all callers of do_coredump(). Secondary threads get hit with
SIGKILL and caught as soon as they reach exit_mm(), which normally happens
in signal delivery, so those are also fine most of the time. Unfortunately,
it is possible to end up with secondary zapped when it has already entered
exit(2) (or, worse yet, is oopsing). In those cases we reach exit_mm()
when mm->core_state is already set, but the stack contents is not what
we would have in signal delivery.
At least on two architectures (alpha and m68k) it leads to infoleaks - we
end up with a chunk of kernel stack written into coredump, with the contents
consisting of normal C stack frames of the call chain leading to exit_mm()
instead of the expected copy of userland registers. In case of alpha we
leak 312 bytes of stack. Other architectures (including the regset-using
ones) might have similar problems - the normal user of regsets is ptrace
and the state of tracee at the time of such calls is special in the same
way signal delivery is.
Note that had the zapper gotten to the exiting thread slightly later,
it wouldn't have been included into coredump anyway - we skip the threads
that have already cleared their ->mm. So let's pretend that zapper always
loses the race. IOW, have exit_mm() only insert into the dumper list if
we'd gotten there from handling a fatal signal[*]
As the result, the callers of do_exit() that have *not* gone through get_signal()
are not seen by coredump logics as secondary threads. Which excludes voluntary
exit()/oopsen/traps/etc. The dumper thread itself is unaffected by that,
so seccomp is fine.
[*] originally I intended to add a new flag in tsk->flags, but ebiederman pointed
out that PF_SIGNALED is already doing just what we need.
Cc: stable@vger.kernel.org
Fixes: d89f3847def4 ("[PATCH] thread-aware coredumps, 2.5.43-C3")
History-tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull tracing fix from Steven Rostedt:
"Fix synthetic event "strcat" overrun
New synthetic event code used strcat() and miscalculated the ending,
causing the concatenation to write beyond the allocated memory.
Instead of using strncat(), the code is switched over to seq_buf which
has all the mechanisms in place to protect against writing more than
what is allocated, and cleans up the code a bit"
* tag 'trace-v5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing, synthetic events: Replace buggy strcat() with seq_buf operations
If should_futex_fail() returns true in futex_wake_pi(), then the 'ret'
variable is set to -EFAULT and then immediately overwritten. So the failure
injection is non-functional.
Fix it by actually leaving the function and returning -EFAULT.
The Fixes tag is kinda blury because the initial commit which introduced
failure injection was already sloppy, but the below mentioned commit broke
it completely.
[ tglx: Massaged changelog ]
Fixes: 6b4f4bc9cb ("locking/futex: Allow low-level atomic operations to return -EAGAIN")
Signed-off-by: Mateusz Nosek <mateusznosek0@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200927000858.24219-1-mateusznosek0@gmail.com
When there are no audit rules registered, mandatory records (config,
etc.) are missing their accompanying records (syscall, proctitle, etc.).
This is due to audit context dummy set on syscall entry based on absence
of rules that signals that no other records are to be printed. Clear the dummy
bit if any record is generated, open coding this in audit_log_start().
The proctitle context and dummy checks are pointless since the
proctitle record will not be printed if no syscall records are printed.
The fds array is reset to -1 after the first syscall to indicate it
isn't valid any more, but was never set to -1 when the context was
allocated to indicate it wasn't yet valid.
Check ctx->pwd in audit_log_name().
The audit_inode* functions can be called without going through
getname_flags() or getname_kernel() that sets audit_names and cwd, so
set the cwd in audit_alloc_name() if it has not already been done so due to
audit_names being valid and purge all other audit_getcwd() calls.
Revert the LSM dump_common_audit_data() LSM_AUDIT_DATA_* cases from the
ghak96 patch since they are no longer necessary due to cwd coverage in
audit_alloc_name().
Thanks to bauen1 <j2468h@googlemail.com> for reporting LSM situations in
which context->cwd is not valid, inadvertantly fixed by the ghak96 patch.
Please see upstream github issue
https://github.com/linux-audit/audit-kernel/issues/120
This is also related to upstream github issue
https://github.com/linux-audit/audit-kernel/issues/96
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
