| Age | Commit message (Collapse) | Author |
|---|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Thomas Gleixner:
- Cleanup and improvement of NUMA balancing
- Refactoring and improvements to the PELT (Per Entity Load Tracking)
code
- Watchdog simplification and related cleanups
- The usual pile of small incremental fixes and improvements
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
watchdog: Reduce message verbosity
stop_machine: Reflow cpu_stop_queue_two_works()
sched/numa: Move task_numa_placement() closer to numa_migrate_preferred()
sched/numa: Use group_weights to identify if migration degrades locality
sched/numa: Update the scan period without holding the numa_group lock
sched/numa: Remove numa_has_capacity()
sched/numa: Modify migrate_swap() to accept additional parameters
sched/numa: Remove unused task_capacity from 'struct numa_stats'
sched/numa: Skip nodes that are at 'hoplimit'
sched/debug: Reverse the order of printing faults
sched/numa: Use task faults only if numa_group is not yet set up
sched/numa: Set preferred_node based on best_cpu
sched/numa: Simplify load_too_imbalanced()
sched/numa: Evaluate move once per node
sched/numa: Remove redundant field
sched/debug: Show the sum wait time of a task group
sched/fair: Remove #ifdefs from scale_rt_capacity()
sched/core: Remove get_cpu() from sched_fork()
sched/cpufreq: Clarify sugov_get_util()
sched/sysctl: Remove unused sched_time_avg_ms sysctl
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fix from Thomas Gleixner:
"A single bugfix to prevent a pinned thread which queues stomp machine
work to be preempted by the stopper thread on its CPU which causes a
live lock as it is unable to wake the second CPUs stopper thread"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
stop_machine: Atomically queue and wake stopper threads
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RCU updates from Thomas Gleixner:
"A large update to RCU:
Preparatory work for consolidating the RCU flavors:
- Introduce grace-period sequence numbers to the RCU-bh, RCU-preempt,
and RCU-sched flavors, replacing the old ->gpnum and ->completed
pair of fields.
This change allows lockless code to obtain the complete
grace-period state with a single READ_ONCE(), which is needed to
maintain tolerable lock contention during the upcoming
consolidation of the three RCU flavors.
Note that grace-period sequence numbers are already used by
rcu_barrier(), expedited RCU grace periods, and SRCU, and are thus
already heavily used and well-tested. Joel Fernandes contributed a
number of excellent fixes and improvements.
- Clean up some grace-period-reporting loose ends, including
improving the handling of quiescent states from offline CPUs and
fixing some false-positive WARN_ON_ONCE() invocations.
(Strictly speaking, the WARN_ON_ONCE() invocations were quite
correct, but their invariants were (harmlessly) violated by the
earlier sloppy handling of quiescent states from offline CPUs.)
In addition, improve grace-period forward-progress guarantees so as
to allow removal of fail-safe checks that required otherwise
needless lock acquisitions. Finally, add more diagnostics to help
debug the upcoming consolidation of the RCU-bh, RCU-preempt, and
RCU-sched flavors.
The rest:
- SRCU updates
- Updates to rcutorture and associated scripting.
- The usual pile of miscellaneous fixes"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (118 commits)
rcutorture: Fix rcu_barrier successes counter
rcutorture: Add support to detect if boost kthread prio is too low
rcutorture: Use monotonic timestamp for stall detection
rcutorture: Make boost test more robust
rcutorture: Disable RT throttling for boost tests
rcutorture: Emphasize testing of single reader protection type
rcutorture: Handle extended read-side critical sections
rcutorture: Make rcu_torture_timer() use rcu_torture_one_read()
rcutorture: Use per-CPU random state for rcu_torture_timer()
rcutorture: Use atomic increment for n_rcu_torture_timers
rcutorture: Extract common code from rcu_torture_reader()
rcuperf: Remove unused torturing_tasks() function
rcu: Remove rcutorture test version and sequence number
rcutorture: Change units of onoff_interval to jiffies
rcu: Assign higher prio to RCU threads if rcutorture is built-in
rculist: Improve documentation for list_for_each_entry_from_rcu()
srcu: Add grace-period number to rcutorture statistics printout
rcu: Print stall-warning NMI dyntick state in hexadecimal
MAINTAINERS: Update RCU, SRCU, and TORTURE-TEST entries
rcu: Make rcu_seq_diff() more exact
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull genirq updates from Thomas Gleixner:
"The irq departement provides:
- A synchronization fix for free_irq() to synchronize just the
removed interrupt thread on shared interrupt lines.
- Consolidate the multi low level interrupt entry handling and mvoe
it to the generic code instead of adding yet another copy for
RISC-V
- Refactoring of the ARM LPI allocator and LPI exposure to the
hypervisor
- Yet another interrupt chip driver for the JZ4725B SoC
- Speed up for /proc/interrupts as people seem to love reading this
file with high frequency
- Miscellaneous fixes and updates"
* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
irqchip/gic-v3-its: Make its_lock a raw_spin_lock_t
genirq/irqchip: Remove MULTI_IRQ_HANDLER as it's now obselete
openrisc: Use the new GENERIC_IRQ_MULTI_HANDLER
arm64: Use the new GENERIC_IRQ_MULTI_HANDLER
ARM: Convert to GENERIC_IRQ_MULTI_HANDLER
irqchip: Port the ARM IRQ drivers to GENERIC_IRQ_MULTI_HANDLER
irqchip/gic-v3-its: Reduce minimum LPI allocation to 1 for PCI devices
dt-bindings: irqchip: renesas-irqc: Document r8a77980 support
dt-bindings: irqchip: renesas-irqc: Document r8a77470 support
irqchip/ingenic: Add support for the JZ4725B SoC
irqchip/stm32: Add exti0 translation for stm32mp1
genirq: Remove redundant NULL pointer check in __free_irq()
irqchip/gic-v3-its: Honor hypervisor enforced LPI range
irqchip/gic-v3: Expose GICD_TYPER in the rdist structure
irqchip/gic-v3-its: Drop chunk allocation compatibility
irqchip/gic-v3-its: Move minimum LPI requirements to individual busses
irqchip/gic-v3-its: Use full range of LPIs
irqchip/gic-v3-its: Refactor LPI allocator
genirq: Synchronize only with single thread on free_irq()
genirq: Update code comments wrt recycled thread_mask
...
|
|
This is purely a preparatory patch for upcoming changes during the 4.19
merge window.
We have a function called "boot_cpu_state_init()" that isn't really
about the bootup cpu state: that is done much earlier by the similarly
named "boot_cpu_init()" (note lack of "state" in name).
This function initializes some hotplug CPU state, and needs to run after
the percpu data has been properly initialized. It even has a comment to
that effect.
Except it _doesn't_ actually run after the percpu data has been properly
initialized. On x86 it happens to do that, but on at least arm and
arm64, the percpu base pointers are initialized by the arch-specific
'smp_prepare_boot_cpu()' hook, which ran _after_ boot_cpu_state_init().
This had some unexpected results, and in particular we have a patch
pending for the merge window that did the obvious cleanup of using
'this_cpu_write()' in the cpu hotplug init code:
- per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+ this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
which is obviously the right thing to do. Except because of the
ordering issue, it actually failed miserably and unexpectedly on arm64.
So this just fixes the ordering, and changes the name of the function to
be 'boot_cpu_hotplug_init()' to make it obvious that it's about cpu
hotplug state, because the core CPU state was supposed to have already
been done earlier.
Marked for stable, since the (not yet merged) patch that will show this
problem is marked for stable.
Reported-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Mian Yousaf Kaukab <yousaf.kaukab@suse.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Like cpumap teardown, the devmap teardown code also flush remaining
xdp_frames, via bq_xmit_all() in case map entry is removed. The code
can call xdp_return_frame_rx_napi, from the the wrong context, in-case
ndo_xdp_xmit() fails.
Fixes: 389ab7f01af9 ("xdp: introduce xdp_return_frame_rx_napi")
Fixes: 735fc4054b3a ("xdp: change ndo_xdp_xmit API to support bulking")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
When removing a cpumap entry, a number of syncronization steps happen.
Eventually the teardown code __cpu_map_entry_free is invoked from/via
call_rcu.
The teardown code __cpu_map_entry_free() flushes remaining xdp_frames,
by invoking bq_flush_to_queue, which calls xdp_return_frame_rx_napi().
The issues is that the teardown code is not running in the RX NAPI
code path. Thus, it is not allowed to invoke the NAPI variant of
xdp_return_frame.
This bug was found and triggered by using the --stress-mode option to
the samples/bpf program xdp_redirect_cpu. It is hard to trigger,
because the ptr_ring have to be full and cpumap bulk queue max
contains 8 packets, and a remote CPU is racing to empty the ptr_ring
queue.
Fixes: 389ab7f01af9 ("xdp: introduce xdp_return_frame_rx_napi")
Tested-by: Jean-Tsung Hsiao <jhsiao@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
In bpf_tcp_sendmsg() the sk_alloc_sg() may fail. In the case of
ENOMEM, it may also mean that we've partially filled the scatterlist
entries with pages. Later jumping to sk_stream_wait_memory()
we could further fail with an error for several reasons, however
we miss to call free_start_sg() if the local sk_msg_buff was used.
Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
While working on bpf_tcp_sendmsg() code, I noticed that when a
sk->sk_err is set we error out with err = sk->sk_err. However
this is problematic since sk->sk_err is a positive error value
and therefore we will neither go into sk_stream_error() nor will
we report an error back to user space. I had this case with EPIPE
and user space was thinking sendmsg() succeeded since EPIPE is
a positive value, thinking we submitted 32 bytes. Fix it by
negating the sk->sk_err value.
Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core
Pull irqchip updates from Marc Zyngier:
- GICv3 ITS LPI allocation revamp
- GICv3 support for hypervisor-enforced LPI range
- GICv3 ITS conversion to raw spinlock
|
|
When cpu_stop_queue_work() releases the lock for the stopper
thread that was queued into its wake queue, preemption is
enabled, which leads to the following deadlock:
CPU0 CPU1
sched_setaffinity(0, ...)
__set_cpus_allowed_ptr()
stop_one_cpu(0, ...) stop_two_cpus(0, 1, ...)
cpu_stop_queue_work(0, ...) cpu_stop_queue_two_works(0, ..., 1, ...)
-grabs lock for migration/0-
-spins with preemption disabled,
waiting for migration/0's lock to be
released-
-adds work items for migration/0
and queues migration/0 to its
wake_q-
-releases lock for migration/0
and preemption is enabled-
-current thread is preempted,
and __set_cpus_allowed_ptr
has changed the thread's
cpu allowed mask to CPU1 only-
-acquires migration/0 and migration/1's
locks-
-adds work for migration/0 but does not
add migration/0 to wake_q, since it is
already in a wake_q-
-adds work for migration/1 and adds
migration/1 to its wake_q-
-releases migration/0 and migration/1's
locks, wakes migration/1, and enables
preemption-
-since migration/1 is requested to run,
migration/1 begins to run and waits on
migration/0, but migration/0 will never
be able to run, since the thread that
can wake it is affine to CPU1-
Disable preemption in cpu_stop_queue_work() before queueing works for
stopper threads, and queueing the stopper thread in the wake queue, to
ensure that the operation of queueing the works and waking the stopper
threads is atomic.
Fixes: 0b26351b910f ("stop_machine, sched: Fix migrate_swap() vs. active_balance() deadlock")
Signed-off-by: Prasad Sodagudi <psodagud@codeaurora.org>
Signed-off-by: Isaac J. Manjarres <isaacm@codeaurora.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: peterz@infradead.org
Cc: matt@codeblueprint.co.uk
Cc: bigeasy@linutronix.de
Cc: gregkh@linuxfoundation.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1533329766-4856-1-git-send-email-isaacm@codeaurora.org
Co-Developed-by: Isaac J. Manjarres <isaacm@codeaurora.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer fixes from Thomas Gleixner:
"Two oneliners addressing NOHZ failures:
- Use a bitmask to check for the pending timer softirq and not the
bit number. The existing code using the bit number checked for
the wrong bit, which caused timers to either expire late or stop
completely.
- Make the nohz evaluation on interrupt exit more robust. The
existing code did not re-arm the hardware when interrupting a
running softirq in task context (ksoftirqd or tail of
local_bh_enable()), which caused timers to either expire late
or stop completely"
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
nohz: Fix missing tick reprogram when interrupting an inline softirq
nohz: Fix local_timer_softirq_pending()
|
|
The full nohz tick is reprogrammed in irq_exit() only if the exit is not in
a nesting interrupt. This stands as an optimization: whether a hardirq or a
softirq is interrupted, the tick is going to be reprogrammed when necessary
at the end of the inner interrupt, with even potential new updates on the
timer queue.
When soft interrupts are interrupted, it's assumed that they are executing
on the tail of an interrupt return. In that case tick_nohz_irq_exit() is
called after softirq processing to take care of the tick reprogramming.
But the assumption is wrong: softirqs can be processed inline as well, ie:
outside of an interrupt, like in a call to local_bh_enable() or from
ksoftirqd.
Inline softirqs don't reprogram the tick once they are done, as opposed to
interrupt tail softirq processing. So if a tick interrupts an inline
softirq processing, the next timer will neither be reprogrammed from the
interrupting tick's irq_exit() nor after the interrupted softirq
processing. This situation may leave the tick unprogrammed while timers are
armed.
To fix this, simply keep reprogramming the tick even if a softirq has been
interrupted. That can be optimized further, but for now correctness is more
important.
Note that new timers enqueued in nohz_full mode after a softirq gets
interrupted will still be handled just fine through self-IPIs triggered by
the timer code.
Reported-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Cc: stable@vger.kernel.org # 4.14+
Link: https://lkml.kernel.org/r/1533303094-15855-1-git-send-email-frederic@kernel.org
|
|
The support of force threading interrupts which are set up with both a
primary and a threaded handler wreckaged the setup of regular requested
threaded interrupts (primary handler == NULL).
The reason is that it does not check whether the primary handler is set to
the default handler which wakes the handler thread. Instead it replaces the
thread handler with the primary handler as it would do with force threaded
interrupts which have been requested via request_irq(). So both the primary
and the thread handler become the same which then triggers the warnon that
the thread handler tries to wakeup a not configured secondary thread.
Fortunately this only happens when the driver omits the IRQF_ONESHOT flag
when requesting the threaded interrupt, which is normaly caught by the
sanity checks when force irq threading is disabled.
Fix it by skipping the force threading setup when a regular threaded
interrupt is requested. As a consequence the interrupt request which lacks
the IRQ_ONESHOT flag is rejected correctly instead of silently wreckaging
it.
Fixes: 2a1d3ab8986d ("genirq: Handle force threading of irqs with primary and thread handler")
Reported-by: Kurt Kanzenbach <kurt.kanzenbach@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Kurt Kanzenbach <kurt.kanzenbach@linutronix.de>
Cc: stable@vger.kernel.org
|
|
Code is emitting the following error message during boot on systems
without PMU hardware support while probing NMI capability.
NMI watchdog: Perf event create on CPU 0 failed with -2
This error is emitted as the perf subsystem returns -ENOENT due to lack of
PMUs in the system.
It is followed by the warning that NMI watchdog is disabled:
NMI watchdog: Perf NMI watchdog permanently disabled
While NMI disabled information is useful for ordinary users, seeing a PERF
event create failed with error code -2 is not.
Reduce the message severity to debug so that if debugging is still possible
in case the error code returned by perf is required for analysis.
Signed-off-by: Sinan Kaya <okaya@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Don Zickus <dzickus@redhat.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=599368
Link: https://lkml.kernel.org/r/20180803060943.2643-1-okaya@kernel.org
|
|
Now that every user of MULTI_IRQ_HANDLER has been convereted over to use
GENERIC_IRQ_MULTI_HANDLER remove the references to MULTI_IRQ_HANDLER.
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux@armlinux.org.uk
Cc: catalin.marinas@arm.com
Cc: Will Deacon <will.deacon@arm.com>
Cc: jonas@southpole.se
Cc: stefan.kristiansson@saunalahti.fi
Cc: shorne@gmail.com
Cc: jason@lakedaemon.net
Cc: marc.zyngier@arm.com
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: nicolas.pitre@linaro.org
Cc: vladimir.murzin@arm.com
Cc: keescook@chromium.org
Cc: jinb.park7@gmail.com
Cc: yamada.masahiro@socionext.com
Cc: alexandre.belloni@bootlin.com
Cc: pombredanne@nexb.com
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: kstewart@linuxfoundation.org
Cc: jhogan@kernel.org
Cc: mark.rutland@arm.com
Cc: ard.biesheuvel@linaro.org
Cc: james.morse@arm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: openrisc@lists.librecores.org
Link: https://lkml.kernel.org/r/20180622170126.6308-6-palmer@sifive.com
|
|
The code flow in cpu_stop_queue_two_works() is a little arcane; fix this by
lifting the preempt_disable() to the top to create more natural nesting wrt
the spinlocks and make the wake_up_q() and preempt_enable() unconditional
at the end.
Furthermore, enable preemption in the -EDEADLK case, such that we spin-wait
with preemption enabled.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: isaacm@codeaurora.org
Cc: matt@codeblueprint.co.uk
Cc: psodagud@codeaurora.org
Cc: gregkh@linuxfoundation.org
Cc: pkondeti@codeaurora.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180730112140.GH2494@hirez.programming.kicks-ass.net
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit
Pull audit fix from Paul Moore:
"A single small audit fix to guard against memory allocation failures
when logging information about a kernel module load.
It's small, easy to understand, and self-contained; while nothing is
zero risk, this should be pretty low"
* tag 'audit-pr-20180731' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit:
audit: fix potential null dereference 'context->module.name'
|
|
local_timer_softirq_pending() checks whether the timer softirq is
pending with: local_softirq_pending() & TIMER_SOFTIRQ.
This is wrong because TIMER_SOFTIRQ is the softirq number and not a
bitmask. So the test checks for the wrong bit.
Use BIT(TIMER_SOFTIRQ) instead.
Fixes: 5d62c183f9e9 ("nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick()")
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Cc: bigeasy@linutronix.de
Cc: peterz@infradead.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180731161358.29472-1-anna-maria@linutronix.de
|
|
Pull networking fixes from David Miller:
"Several smallish fixes, I don't think any of this requires another -rc
but I'll leave that up to you:
1) Don't leak uninitialzed bytes to userspace in xfrm_user, from Eric
Dumazet.
2) Route leak in xfrm_lookup_route(), from Tommi Rantala.
3) Premature poll() returns in AF_XDP, from Björn Töpel.
4) devlink leak in netdevsim, from Jakub Kicinski.
5) Don't BUG_ON in fib_compute_spec_dst, the condition can
legitimately happen. From Lorenzo Bianconi.
6) Fix some spectre v1 gadgets in generic socket code, from Jeremy
Cline.
7) Don't allow user to bind to out of range multicast groups, from
Dmitry Safonov with a follow-up by Dmitry Safonov.
8) Fix metrics leak in fib6_drop_pcpu_from(), from Sabrina Dubroca"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits)
netlink: Don't shift with UB on nlk->ngroups
net/ipv6: fix metrics leak
xen-netfront: wait xenbus state change when load module manually
can: ems_usb: Fix memory leak on ems_usb_disconnect()
openvswitch: meter: Fix setting meter id for new entries
netlink: Do not subscribe to non-existent groups
NET: stmmac: align DMA stuff to largest cache line length
tcp_bbr: fix bw probing to raise in-flight data for very small BDPs
net: socket: Fix potential spectre v1 gadget in sock_is_registered
net: socket: fix potential spectre v1 gadget in socketcall
net: mdio-mux: bcm-iproc: fix wrong getter and setter pair
ipv4: remove BUG_ON() from fib_compute_spec_dst
enic: handle mtu change for vf properly
net: lan78xx: fix rx handling before first packet is send
nfp: flower: fix port metadata conversion bug
bpf: use GFP_ATOMIC instead of GFP_KERNEL in bpf_parse_prog()
bpf: fix bpf_skb_load_bytes_relative pkt length check
perf build: Build error in libbpf missing initialization
net: ena: Fix use of uninitialized DMA address bits field
bpf: btf: Use exact btf value_size match in map_check_btf()
...
|
|
The variable 'context->module.name' may be null pointer when
kmalloc return null, so it's better to check it before using
to avoid null dereference.
Another one more thing this patch does is using kstrdup instead
of (kmalloc + strcpy), and signal a lost record via audit_log_lost.
Cc: stable@vger.kernel.org # 4.11
Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn>
Reviewed-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Ingo Molnar:
"Misc fixes:
- a deadline scheduler related bug fix which triggered a kernel
warning
- an RT_RUNTIME_SHARE fix
- a stop_machine preemption fix
- a potential NULL dereference fix in sched_domain_debug_one()"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/rt: Restore rt_runtime after disabling RT_RUNTIME_SHARE
sched/deadline: Update rq_clock of later_rq when pushing a task
stop_machine: Disable preemption after queueing stopper threads
sched/topology: Check variable group before dereferencing it
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
"Misc fixes:
- AMD IBS data corruptor fix (uncovered by UBSAN)
- an Intel PEBS entry unwind error fix
- a HW-tracing crash fix
- a MAINTAINERS update"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/core: Fix crash when using HW tracing kernel filters
perf/x86/intel: Fix unwind errors from PEBS entries (mk-II)
MAINTAINERS: Add Naveen N. Rao as kprobes co-maintainer
perf/x86/amd/ibs: Don't access non-started event
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking fixes from Ingo Molnar:
"A paravirt UP-patching fix, and an I2C MUX driver lockdep warning fix"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/pvqspinlock/x86: Use LOCK_PREFIX in __pv_queued_spin_unlock() assembly code
i2c/mux, locking/core: Annotate the nested rt_mutex usage
locking/rtmutex: Allow specifying a subclass for nested locking
|
|
Daniel Borkmann says:
====================
pull-request: bpf 2018-07-28
The following pull-request contains BPF updates for your *net* tree.
The main changes are:
1) API fixes for libbpf's BTF mapping of map key/value types in order
to make them compatible with iproute2's BPF_ANNOTATE_KV_PAIR()
markings, from Martin.
2) Fix AF_XDP to not report POLLIN prematurely by using the non-cached
consumer pointer of the RX queue, from Björn.
3) Fix __xdp_return() to check for NULL pointer after the rhashtable
lookup that retrieves the allocator object, from Taehee.
4) Fix x86-32 JIT to adjust ebp register in prologue and epilogue
by 4 bytes which got removed from overall stack usage, from Wang.
5) Fix bpf_skb_load_bytes_relative() length check to use actual
packet length, from Daniel.
6) Fix uninitialized return code in libbpf bpf_perf_event_read_simple()
handler, from Thomas.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Merge misc fixes from Andrew Morton:
"11 fixes"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
kvm, mm: account shadow page tables to kmemcg
zswap: re-check zswap_is_full() after do zswap_shrink()
include/linux/eventfd.h: include linux/errno.h
mm: fix vma_is_anonymous() false-positives
mm: use vma_init() to initialize VMAs on stack and data segments
mm: introduce vma_init()
mm: fix exports that inadvertently make put_page() EXPORT_SYMBOL_GPL
ipc/sem.c: prevent queue.status tearing in semop
mm: disallow mappings that conflict for devm_memremap_pages()
kasan: only select SLUB_DEBUG with SYSFS=y
delayacct: fix crash in delayacct_blkio_end() after delayacct init failure
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing fixes from Steven Rostedt:
"Various fixes to the tracing infrastructure:
- Fix double free when the reg() call fails in
event_trigger_callback()
- Fix anomoly of snapshot causing tracing_on flag to change
- Add selftest to test snapshot and tracing_on affecting each other
- Fix setting of tracepoint flag on error that prevents probes from
being deleted.
- Fix another possible double free that is similar to
event_trigger_callback()
- Quiet a gcc warning of a false positive unused variable
- Fix crash of partial exposed task->comm to trace events"
* tag 'trace-v4.18-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
kthread, tracing: Don't expose half-written comm when creating kthreads
tracing: Quiet gcc warning about maybe unused link variable
tracing: Fix possible double free in event_enable_trigger_func()
tracing/kprobes: Fix trace_probe flags on enable_trace_kprobe() failure
selftests/ftrace: Add snapshot and tracing_on test case
ring_buffer: tracing: Inherit the tracing setting to next ring buffer
tracing: Fix double free of event_trigger_data
|
|
Not all VMAs allocated with vm_area_alloc(). Some of them allocated on
stack or in data segment.
The new helper can be use to initialize VMA properly regardless where it
was allocated.
Link: http://lkml.kernel.org/r/20180724121139.62570-2-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Commit e76384884344 ("mm: introduce MEMORY_DEVICE_FS_DAX and
CONFIG_DEV_PAGEMAP_OPS") added two EXPORT_SYMBOL_GPL() symbols, but
these symbols are required by the inlined put_page(), thus accidentally
making put_page() a GPL export only. This breaks OpenAFS (at least).
Mark them EXPORT_SYMBOL() instead.
Link: http://lkml.kernel.org/r/153128611970.2928.11310692420711601254.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: e76384884344 ("mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: Joe Gorse <jhgorse@gmail.com>
Reported-by: John Hubbard <jhubbard@nvidia.com>
Tested-by: Joe Gorse <jhgorse@gmail.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Mark Vitale <mvitale@sinenomine.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
When pmem namespaces created are smaller than section size, this can
cause an issue during removal and gpf was observed:
general protection fault: 0000 1 SMP PTI
CPU: 36 PID: 3941 Comm: ndctl Tainted: G W 4.14.28-1.el7uek.x86_64 #2
task: ffff88acda150000 task.stack: ffffc900233a4000
RIP: 0010:__put_page+0x56/0x79
Call Trace:
devm_memremap_pages_release+0x155/0x23a
release_nodes+0x21e/0x260
devres_release_all+0x3c/0x48
device_release_driver_internal+0x15c/0x207
device_release_driver+0x12/0x14
unbind_store+0xba/0xd8
drv_attr_store+0x27/0x31
sysfs_kf_write+0x3f/0x46
kernfs_fop_write+0x10f/0x18b
__vfs_write+0x3a/0x16d
vfs_write+0xb2/0x1a1
SyS_write+0x55/0xb9
do_syscall_64+0x79/0x1ae
entry_SYSCALL_64_after_hwframe+0x3d/0x0
Add code to check whether we have a mapping already in the same section
and prevent additional mappings from being created if that is the case.
Link: http://lkml.kernel.org/r/152909478401.50143.312364396244072931.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Robert Elliott <elliott@hpe.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
The current map_check_btf() in BPF_MAP_TYPE_ARRAY rejects
'> map->value_size' to ensure map_seq_show_elem() will not
access things beyond an array element.
Yonghong suggested that using '!=' is a more correct
check. The 8 bytes round_up on value_size is stored
in array->elem_size. Hence, using '!=' on map->value_size
is a proper check.
This patch also adds new tests to check the btf array
key type and value type. Two of these new tests verify
the btf's value_size (the change in this patch).
It also fixes two existing tests that wrongly encoded
a btf's type size (pprint_test) and the value_type_id (in one
of the raw_tests[]). However, that do not affect these two
BTF verification tests before or after this test changes.
These two tests mainly failed at array creation time after
this patch.
Fixes: a26ca7c982cb ("bpf: btf: Add pretty print support to the basic arraymap")
Suggested-by: Yonghong Song <yhs@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
There is a window for racing when printing directly to task->comm,
allowing other threads to see a non-terminated string. The vsnprintf
function fills the buffer, counts the truncated chars, then finally
writes the \0 at the end.
creator other
vsnprintf:
fill (not terminated)
count the rest trace_sched_waking(p):
... memcpy(comm, p->comm, TASK_COMM_LEN)
write \0
The consequences depend on how 'other' uses the string. In our case,
it was copied into the tracing system's saved cmdlines, a buffer of
adjacent TASK_COMM_LEN-byte buffers (note the 'n' where 0 should be):
crash-arm64> x/1024s savedcmd->saved_cmdlines | grep 'evenk'
0xffffffd5b3818640: "irq/497-pwr_evenkworker/u16:12"
...and a strcpy out of there would cause stack corruption:
[224761.522292] Kernel panic - not syncing: stack-protector:
Kernel stack is corrupted in: ffffff9bf9783c78
crash-arm64> kbt | grep 'comm\|trace_print_context'
#6 0xffffff9bf9783c78 in trace_print_context+0x18c(+396)
comm (char [16]) = "irq/497-pwr_even"
crash-arm64> rd 0xffffffd4d0e17d14 8
ffffffd4d0e17d14: 2f71726900000000 5f7277702d373934 ....irq/497-pwr_
ffffffd4d0e17d24: 726f776b6e657665 3a3631752f72656b evenkworker/u16:
ffffffd4d0e17d34: f9780248ff003231 cede60e0ffffff9b 12..H.x......`..
ffffffd4d0e17d44: cede60c8ffffffd4 00000fffffffffd4 .....`..........
The workaround in e09e28671 (use strlcpy in __trace_find_cmdline) was
likely needed because of this same bug.
Solved by vsnprintf:ing to a local buffer, then using set_task_comm().
This way, there won't be a window where comm is not terminated.
Link: http://lkml.kernel.org/r/20180726071539.188015-1-snild@sony.com
Cc: stable@vger.kernel.org
Fixes: bc0c38d139ec7 ("ftrace: latency tracer infrastructure")
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Snild Dolkow <snild@sony.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Commit 57ea2a34adf4 ("tracing/kprobes: Fix trace_probe flags on
enable_trace_kprobe() failure") added an if statement that depends on another
if statement that gcc doesn't see will initialize the "link" variable and
gives the warning:
"warning: 'link' may be used uninitialized in this function"
It is really a false positive, but to quiet the warning, and also to make
sure that it never actually is used uninitialized, initialize the "link"
variable to NULL and add an if (!WARN_ON_ONCE(!link)) where the compiler
thinks it could be used uninitialized.
Cc: stable@vger.kernel.org
Fixes: 57ea2a34adf4 ("tracing/kprobes: Fix trace_probe flags on enable_trace_kprobe() failure")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
There was a case that triggered a double free in event_trigger_callback()
due to the called reg() function freeing the trigger_data and then it
getting freed again by the error return by the caller. The solution there
was to up the trigger_data ref count.
Code inspection found that event_enable_trigger_func() has the same issue,
but is not as easy to trigger (requires harder to trigger failures). It
needs to be solved slightly different as it needs more to clean up when the
reg() function fails.
Link: http://lkml.kernel.org/r/20180725124008.7008e586@gandalf.local.home
Cc: stable@vger.kernel.org
Fixes: 7862ad1846e99 ("tracing: Add 'enable_event' and 'disable_event' event trigger commands")
Reivewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
If enable_trace_kprobe fails to enable the probe in enable_k(ret)probe
it returns an error, but does not unset the tp flags it set previously.
This results in a probe being considered enabled and failures like being
unable to remove the probe through kprobe_events file since probes_open()
expects every probe to be disabled.
Link: http://lkml.kernel.org/r/20180725102826.8300-1-asavkov@redhat.com
Link: http://lkml.kernel.org/r/20180725142038.4765-1-asavkov@redhat.com
Cc: Ingo Molnar <mingo@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 41a7dd420c57 ("tracing/kprobes: Support ftrace_event_file base multibuffer")
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Artem Savkov <asavkov@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Maintain the tracing on/off setting of the ring_buffer when switching
to the trace buffer snapshot.
Taking a snapshot is done by swapping the backup ring buffer
(max_tr_buffer). But since the tracing on/off setting is defined
by the ring buffer, when swapping it, the tracing on/off setting
can also be changed. This causes a strange result like below:
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 0 > tracing_on
/sys/kernel/debug/tracing # cat tracing_on
0
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
0
We don't touch tracing_on, but snapshot changes tracing_on
setting each time. This is an anomaly, because user doesn't know
that each "ring_buffer" stores its own tracing-enable state and
the snapshot is done by swapping ring buffers.
Link: http://lkml.kernel.org/r/153149929558.11274.11730609978254724394.stgit@devbox
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Tom Zanussi <tom.zanussi@linux.intel.com>
Cc: Hiraku Toyooka <hiraku.toyooka@cybertrust.co.jp>
Cc: stable@vger.kernel.org
Fixes: debdd57f5145 ("tracing: Make a snapshot feature available from userspace")
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
[ Updated commit log and comment in the code ]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Running the following:
# cd /sys/kernel/debug/tracing
# echo 500000 > buffer_size_kb
[ Or some other number that takes up most of memory ]
# echo snapshot > events/sched/sched_switch/trigger
Triggers the following bug:
------------[ cut here ]------------
kernel BUG at mm/slub.c:296!
invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC PTI
CPU: 6 PID: 6878 Comm: bash Not tainted 4.18.0-rc6-test+ #1066
Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016
RIP: 0010:kfree+0x16c/0x180
Code: 05 41 0f b6 72 51 5b 5d 41 5c 4c 89 d7 e9 ac b3 f8 ff 48 89 d9 48 89 da 41 b8 01 00 00 00 5b 5d 41 5c 4c 89 d6 e9 f4 f3 ff ff <0f> 0b 0f 0b 48 8b 3d d9 d8 f9 00 e9 c1 fe ff ff 0f 1f 40 00 0f 1f
RSP: 0018:ffffb654436d3d88 EFLAGS: 00010246
RAX: ffff91a9d50f3d80 RBX: ffff91a9d50f3d80 RCX: ffff91a9d50f3d80
RDX: 00000000000006a4 RSI: ffff91a9de5a60e0 RDI: ffff91a9d9803500
RBP: ffffffff8d267c80 R08: 00000000000260e0 R09: ffffffff8c1a56be
R10: fffff0d404543cc0 R11: 0000000000000389 R12: ffffffff8c1a56be
R13: ffff91a9d9930e18 R14: ffff91a98c0c2890 R15: ffffffff8d267d00
FS: 00007f363ea64700(0000) GS:ffff91a9de580000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055c1cacc8e10 CR3: 00000000d9b46003 CR4: 00000000001606e0
Call Trace:
event_trigger_callback+0xee/0x1d0
event_trigger_write+0xfc/0x1a0
__vfs_write+0x33/0x190
? handle_mm_fault+0x115/0x230
? _cond_resched+0x16/0x40
vfs_write+0xb0/0x190
ksys_write+0x52/0xc0
do_syscall_64+0x5a/0x160
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7f363e16ab50
Code: 73 01 c3 48 8b 0d 38 83 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 79 db 2c 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 1e e3 01 00 48 89 04 24
RSP: 002b:00007fff9a4c6378 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000009 RCX: 00007f363e16ab50
RDX: 0000000000000009 RSI: 000055c1cacc8e10 RDI: 0000000000000001
RBP: 000055c1cacc8e10 R08: 00007f363e435740 R09: 00007f363ea64700
R10: 0000000000000073 R11: 0000000000000246 R12: 0000000000000009
R13: 0000000000000001 R14: 00007f363e4345e0 R15: 00007f363e4303c0
Modules linked in: ip6table_filter ip6_tables snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device i915 snd_pcm snd_timer i2c_i801 snd soundcore i2c_algo_bit drm_kms_helper
86_pkg_temp_thermal video kvm_intel kvm irqbypass wmi e1000e
---[ end trace d301afa879ddfa25 ]---
The cause is because the register_snapshot_trigger() call failed to
allocate the snapshot buffer, and then called unregister_trigger()
which freed the data that was passed to it. Then on return to the
function that called register_snapshot_trigger(), as it sees it
failed to register, it frees the trigger_data again and causes
a double free.
By calling event_trigger_init() on the trigger_data (which only ups
the reference counter for it), and then event_trigger_free() afterward,
the trigger_data would not get freed by the registering trigger function
as it would only up and lower the ref count for it. If the register
trigger function fails, then the event_trigger_free() called after it
will free the trigger data normally.
Link: http://lkml.kernel.org/r/20180724191331.738eb819@gandalf.local.home
Cc: stable@vger.kerne.org
Fixes: 93e31ffbf417 ("tracing: Add 'snapshot' event trigger command")
Reported-by: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
In function perf_event_parse_addr_filter(), the path::dentry of each struct
perf_addr_filter is left unassigned (as it should be) when the pattern
being parsed is related to kernel space. But in function
perf_addr_filter_match() the same dentries are given to d_inode() where
the value is not expected to be NULL, resulting in the following splat:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000058
pc : perf_event_mmap+0x2fc/0x5a0
lr : perf_event_mmap+0x2c8/0x5a0
Process uname (pid: 2860, stack limit = 0x000000001cbcca37)
Call trace:
perf_event_mmap+0x2fc/0x5a0
mmap_region+0x124/0x570
do_mmap+0x344/0x4f8
vm_mmap_pgoff+0xe4/0x110
vm_mmap+0x2c/0x40
elf_map+0x60/0x108
load_elf_binary+0x450/0x12c4
search_binary_handler+0x90/0x290
__do_execve_file.isra.13+0x6e4/0x858
sys_execve+0x3c/0x50
el0_svc_naked+0x30/0x34
This patch is fixing the problem by introducing a new check in function
perf_addr_filter_match() to see if the filter's dentry is NULL.
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: miklos@szeredi.hu
Cc: namhyung@kernel.org
Cc: songliubraving@fb.com
Fixes: 9511bce9fe8e ("perf/core: Fix bad use of igrab()")
Link: http://lkml.kernel.org/r/1531782831-1186-1-git-send-email-mathieu.poirier@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Vince reported the perf_fuzzer giving various unwinder warnings and
Josh reported:
> Deja vu. Most of these are related to perf PEBS, similar to the
> following issue:
>
> b8000586c90b ("perf/x86/intel: Cure bogus unwind from PEBS entries")
>
> This is basically the ORC version of that. setup_pebs_sample_data() is
> assembling a franken-pt_regs which ORC isn't happy about. RIP is
> inconsistent with some of the other registers (like RSP and RBP).
And where the previous unwinder only needed BP,SP ORC also requires
IP. But we cannot spoof IP because then the sample will get displaced,
entirely negating the point of PEBS.
So cure the whole thing differently by doing the unwind early; this
does however require a means to communicate we did the unwind early.
We (ab)use an unused sample_type bit for this, which we set on events
that fill out the data->callchain before the normal
perf_prepare_sample().
Debugged-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Tested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Tested-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
numa_migrate_preferred() is called periodically or when task preferred
node changes. Preferred node evaluations happen once per scan sequence.
If the scan completion happens just after the periodic NUMA migration,
then we try to migrate to the preferred node and the preferred node might
change, needing another node migration.
Avoid this by checking for scan sequence completion only when checking
for periodic migration.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25862.6 26158.1 1.14258
1 74357 72725 -2.19482
Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
8 117019 113992 -2.58
1 179095 174947 -2.31
(numbers from v1 based on v4.17-rc5)
Testcase Time: Min Max Avg StdDev
numa01.sh Real: 449.46 770.77 615.22 101.70
numa01.sh Sys: 132.72 208.17 170.46 24.96
numa01.sh User: 39185.26 60290.89 50066.76 6807.84
numa02.sh Real: 60.85 61.79 61.28 0.37
numa02.sh Sys: 15.34 24.71 21.08 3.61
numa02.sh User: 5204.41 5249.85 5231.21 17.60
numa03.sh Real: 785.50 916.97 840.77 44.98
numa03.sh Sys: 108.08 133.60 119.43 8.82
numa03.sh User: 61422.86 70919.75 64720.87 3310.61
numa04.sh Real: 429.57 587.37 480.80 57.40
numa04.sh Sys: 240.61 321.97 290.84 33.58
numa04.sh User: 34597.65 40498.99 37079.48 2060.72
numa05.sh Real: 392.09 431.25 414.65 13.82
numa05.sh Sys: 229.41 372.48 297.54 53.14
numa05.sh User: 33390.86 34697.49 34222.43 556.42
Testcase Time: Min Max Avg StdDev %Change
numa01.sh Real: 424.63 566.18 498.12 59.26 23.50%
numa01.sh Sys: 160.19 256.53 208.98 37.02 -18.4%
numa01.sh User: 37320.00 46225.58 42001.57 3482.45 19.20%
numa02.sh Real: 60.17 62.47 60.91 0.85 0.607%
numa02.sh Sys: 15.30 22.82 17.04 2.90 23.70%
numa02.sh User: 5202.13 5255.51 5219.08 20.14 0.232%
numa03.sh Real: 823.91 844.89 833.86 8.46 0.828%
numa03.sh Sys: 130.69 148.29 140.47 6.21 -14.9%
numa03.sh User: 62519.15 64262.20 63613.38 620.05 1.740%
numa04.sh Real: 515.30 603.74 548.56 30.93 -12.3%
numa04.sh Sys: 459.73 525.48 489.18 21.63 -40.5%
numa04.sh User: 40561.96 44919.18 42047.87 1526.85 -11.8%
numa05.sh Real: 396.58 454.37 421.13 19.71 -1.53%
numa05.sh Sys: 208.72 422.02 348.90 73.60 -14.7%
numa05.sh User: 33124.08 36109.35 34846.47 1089.74 -1.79%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-20-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
On NUMA_BACKPLANE and NUMA_GLUELESS_MESH systems, tasks/memory should be
consolidated to the closest group of nodes. In such a case, relying on
group_fault metric may not always help to consolidate. There can always
be a case where a node closer to the preferred node may have lesser
faults than a node further away from the preferred node. In such a case,
moving to node with more faults might avoid numa consolidation.
Using group_weight would help to consolidate task/memory around the
preferred_node.
While here, to be on the conservative side, don't override migrate thread
degrades locality logic for CPU_NEWLY_IDLE load balancing.
Note: Similar problems exist with should_numa_migrate_memory and will be
dealt separately.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25645.4 25960 1.22
1 72142 73550 1.95
Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
8 110199 120071 8.958
1 176303 176249 -0.03
(numbers from v1 based on v4.17-rc5)
Testcase Time: Min Max Avg StdDev
numa01.sh Real: 490.04 774.86 596.26 96.46
numa01.sh Sys: 151.52 242.88 184.82 31.71
numa01.sh User: 41418.41 60844.59 48776.09 6564.27
numa02.sh Real: 60.14 62.94 60.98 1.00
numa02.sh Sys: 16.11 30.77 21.20 5.28
numa02.sh User: 5184.33 5311.09 5228.50 44.24
numa03.sh Real: 790.95 856.35 826.41 24.11
numa03.sh Sys: 114.93 118.85 117.05 1.63
numa03.sh User: 60990.99 64959.28 63470.43 1415.44
numa04.sh Real: 434.37 597.92 504.87 59.70
numa04.sh Sys: 237.63 397.40 289.74 55.98
numa04.sh User: 34854.87 41121.83 38572.52 2615.84
numa05.sh Real: 386.77 448.90 417.22 22.79
numa05.sh Sys: 149.23 379.95 303.04 79.55
numa05.sh User: 32951.76 35959.58 34562.18 1034.05
Testcase Time: Min Max Avg StdDev %Change
numa01.sh Real: 493.19 672.88 597.51 59.38 -0.20%
numa01.sh Sys: 150.09 245.48 207.76 34.26 -11.0%
numa01.sh User: 41928.51 53779.17 48747.06 3901.39 0.059%
numa02.sh Real: 60.63 62.87 61.22 0.83 -0.39%
numa02.sh Sys: 16.64 27.97 20.25 4.06 4.691%
numa02.sh User: 5222.92 5309.60 5254.03 29.98 -0.48%
numa03.sh Real: 821.52 902.15 863.60 32.41 -4.30%
numa03.sh Sys: 112.04 130.66 118.35 7.08 -1.09%
numa03.sh User: 62245.16 69165.14 66443.04 2450.32 -4.47%
numa04.sh Real: 414.53 519.57 476.25 37.00 6.009%
numa04.sh Sys: 181.84 335.67 280.41 54.07 3.327%
numa04.sh User: 33924.50 39115.39 37343.78 1934.26 3.290%
numa05.sh Real: 408.30 441.45 417.90 12.05 -0.16%
numa05.sh Sys: 233.41 381.60 295.58 57.37 2.523%
numa05.sh User: 33301.31 35972.50 34335.19 938.94 0.661%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-16-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
The metrics for updating scan periods are local or task specific.
Currently this update happens under the numa_group lock, which seems
unnecessary. Hence move this update outside the lock.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25355.9 25645.4 1.141
1 72812 72142 -0.92
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-15-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
task_numa_find_cpu() helps to find the CPU to swap/move the task to.
It's guarded by numa_has_capacity(). However node not having capacity
shouldn't deter a task swapping if it helps NUMA placement.
Further load_too_imbalanced(), which evaluates possibilities of move/swap,
provides similar checks as numa_has_capacity.
Hence remove numa_has_capacity() to enhance possibilities of task
swapping even if load is imbalanced.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25657.9 25804.1 0.569
1 74435 73413 -1.37
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rik van Riel <riel@surriel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-13-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
There are checks in migrate_swap_stop() that check if the task/CPU
combination is as per migrate_swap_arg before migrating.
However atleast one of the two tasks to be swapped by migrate_swap() could
have migrated to a completely different CPU before updating the
migrate_swap_arg. The new CPU where the task is currently running could
be a different node too. If the task has migrated, numa balancer might
end up placing a task in a wrong node. Instead of achieving node
consolidation, it may end up spreading the load across nodes.
To avoid that pass the CPUs as additional parameters.
While here, place migrate_swap under CONFIG_NUMA_BALANCING.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25377.3 25226.6 -0.59
1 72287 73326 1.437
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-10-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
The task_capacity field in 'struct numa_stats' is redundant.
Also move nr_running for better packing within the struct.
No functional changes.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25308.6 25377.3 0.271
1 72964 72287 -0.92
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Rik van Riel <riel@surriel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-9-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
When comparing two nodes at a distance of 'hoplimit', we should consider
nodes only up to 'hoplimit'. Currently we also consider nodes at 'oplimit'
distance too. Hence two nodes at a distance of 'hoplimit' will have same
groupweight. Fix this by skipping nodes at hoplimit.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25375.3 25308.6 -0.26
1 72617 72964 0.477
Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
8 113372 108750 -4.07684
1 177403 183115 3.21979
(numbers from v1 based on v4.17-rc5)
Testcase Time: Min Max Avg StdDev
numa01.sh Real: 478.45 565.90 515.11 30.87
numa01.sh Sys: 207.79 271.04 232.94 21.33
numa01.sh User: 39763.93 47303.12 43210.73 2644.86
numa02.sh Real: 60.00 61.46 60.78 0.49
numa02.sh Sys: 15.71 25.31 20.69 3.42
numa02.sh User: 5175.92 5265.86 5235.97 32.82
numa03.sh Real: 776.42 834.85 806.01 23.22
numa03.sh Sys: 114.43 128.75 121.65 5.49
numa03.sh User: 60773.93 64855.25 62616.91 1576.39
numa04.sh Real: 456.93 511.95 482.91 20.88
numa04.sh Sys: 178.09 460.89 356.86 94.58
numa04.sh User: 36312.09 42553.24 39623.21 2247.96
numa05.sh Real: 393.98 493.48 436.61 35.59
numa05.sh Sys: 164.49 329.15 265.87 61.78
numa05.sh User: 33182.65 36654.53 35074.51 1187.71
Testcase Time: Min Max Avg StdDev %Change
numa01.sh Real: 414.64 819.20 556.08 147.70 -7.36%
numa01.sh Sys: 77.52 205.04 139.40 52.05 67.10%
numa01.sh User: 37043.24 61757.88 45517.48 9290.38 -5.06%
numa02.sh Real: 60.80 63.32 61.63 0.88 -1.37%
numa02.sh Sys: 17.35 39.37 25.71 7.33 -19.5%
numa02.sh User: 5213.79 5374.73 5268.90 55.09 -0.62%
numa03.sh Real: 780.09 948.64 831.43 63.02 -3.05%
numa03.sh Sys: 104.96 136.92 116.31 11.34 4.591%
numa03.sh User: 60465.42 73339.78 64368.03 4700.14 -2.72%
numa04.sh Real: 412.60 681.92 521.29 96.64 -7.36%
numa04.sh Sys: 210.32 314.10 251.77 37.71 41.74%
numa04.sh User: 34026.38 45581.20 38534.49 4198.53 2.825%
numa05.sh Real: 394.79 439.63 411.35 16.87 6.140%
numa05.sh Sys: 238.32 330.09 292.31 38.32 -9.04%
numa05.sh User: 33456.45 34876.07 34138.62 609.45 2.741%
While there is a regression with this change, this change is needed from a
correctness perspective. Also it helps consolidation as seen from perf bench
output.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-8-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Fix the order in which the private and shared numa faults are getting
printed.
No functional changes.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25215.7 25375.3 0.63
1 72107 72617 0.70
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-7-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
When numa_group faults are available, task_numa_placement only uses
numa_group faults to evaluate preferred node. However it still accounts
task faults and even evaluates the preferred node just based on task
faults just to discard it in favour of preferred node chosen on the
basis of numa_group.
Instead use task faults only if numa_group is not set.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25549.6 25215.7 -1.30
1 73190 72107 -1.47
Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
8 113437 113372 -0.05
1 196130 177403 -9.54
(numbers from v1 based on v4.17-rc5)
Testcase Time: Min Max Avg StdDev
numa01.sh Real: 506.35 794.46 599.06 104.26
numa01.sh Sys: 150.37 223.56 195.99 24.94
numa01.sh User: 43450.69 61752.04 49281.50 6635.33
numa02.sh Real: 60.33 62.40 61.31 0.90
numa02.sh Sys: 18.12 31.66 24.28 5.89
numa02.sh User: 5203.91 5325.32 5260.29 49.98
numa03.sh Real: 696.47 853.62 745.80 57.28
numa03.sh Sys: 85.68 123.71 97.89 13.48
numa03.sh User: 55978.45 66418.63 59254.94 3737.97
numa04.sh Real: 444.05 514.83 497.06 26.85
numa04.sh Sys: 230.39 375.79 316.23 48.58
numa04.sh User: 35403.12 41004.10 39720.80 2163.08
numa05.sh Real: 423.09 460.41 439.57 13.92
numa05.sh Sys: 287.38 480.15 369.37 68.52
numa05.sh User: 34732.12 38016.80 36255.85 1070.51
Testcase Time: Min Max Avg StdDev %Change
numa01.sh Real: 478.45 565.90 515.11 30.87 16.29%
numa01.sh Sys: 207.79 271.04 232.94 21.33 -15.8%
numa01.sh User: 39763.93 47303.12 43210.73 2644.86 14.04%
numa02.sh Real: 60.00 61.46 60.78 0.49 0.871%
numa02.sh Sys: 15.71 25.31 20.69 3.42 17.35%
numa02.sh User: 5175.92 5265.86 5235.97 32.82 0.464%
numa03.sh Real: 776.42 834.85 806.01 23.22 -7.47%
numa03.sh Sys: 114.43 128.75 121.65 5.49 -19.5%
numa03.sh User: 60773.93 64855.25 62616.91 1576.39 -5.36%
numa04.sh Real: 456.93 511.95 482.91 20.88 2.930%
numa04.sh Sys: 178.09 460.89 356.86 94.58 -11.3%
numa04.sh User: 36312.09 42553.24 39623.21 2247.96 0.246%
numa05.sh Real: 393.98 493.48 436.61 35.59 0.677%
numa05.sh Sys: 164.49 329.15 265.87 61.78 38.92%
numa05.sh User: 33182.65 36654.53 35074.51 1187.71 3.368%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-6-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Currently preferred node is set to dst_nid which is the last node in the
iteration whose group weight or task weight is greater than the current
node. However it doesn't guarantee that dst_nid has the numa capacity
to move. It also doesn't guarantee that dst_nid has the best_cpu which
is the CPU/node ideal for node migration.
Lets consider faults on a 4 node system with group weight numbers
in different nodes being in 0 < 1 < 2 < 3 proportion. Consider the task
is running on 3 and 0 is its preferred node but its capacity is full.
Consider nodes 1, 2 and 3 have capacity. Then the task should be
migrated to node 1. Currently the task gets moved to node 2. env.dst_nid
points to the last node whose faults were greater than current node.
Modify to set the preferred node based of best_cpu. Earlier setting
preferred node was skipped if nr_active_nodes is 1. This could result in
the task being moved out of the preferred node to a random node during
regular load balancing.
Also while modifying task_numa_migrate(), use sched_setnuma to set
preferred node. This ensures out numa accounting is correct.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25122.9 25549.6 1.698
1 73850 73190 -0.89
Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
8 105930 113437 7.08676
1 178624 196130 9.80047
(numbers from v1 based on v4.17-rc5)
Testcase Time: Min Max Avg StdDev
numa01.sh Real: 435.78 653.81 534.58 83.20
numa01.sh Sys: 121.93 187.18 145.90 23.47
numa01.sh User: 37082.81 51402.80 43647.60 5409.75
numa02.sh Real: 60.64 61.63 61.19 0.40
numa02.sh Sys: 14.72 25.68 19.06 4.03
numa02.sh User: 5210.95 5266.69 5233.30 20.82
numa03.sh Real: 746.51 808.24 780.36 23.88
numa03.sh Sys: 97.26 108.48 105.07 4.28
numa03.sh User: 58956.30 61397.05 60162.95 1050.82
numa04.sh Real: 465.97 519.27 484.81 19.62
numa04.sh Sys: 304.43 359.08 334.68 20.64
numa04.sh User: 37544.16 41186.15 39262.44 1314.91
numa05.sh Real: 411.57 457.20 433.29 16.58
numa05.sh Sys: 230.05 435.48 339.95 67.58
numa05.sh User: 33325.54 36896.31 35637.84 1222.64
Testcase Time: Min Max Avg StdDev %Change
numa01.sh Real: 506.35 794.46 599.06 104.26 -10.76%
numa01.sh Sys: 150.37 223.56 195.99 24.94 -25.55%
numa01.sh User: 43450.69 61752.04 49281.50 6635.33 -11.43%
numa02.sh Real: 60.33 62.40 61.31 0.90 -0.195%
numa02.sh Sys: 18.12 31.66 24.28 5.89 -21.49%
numa02.sh User: 5203.91 5325.32 5260.29 49.98 -0.513%
numa03.sh Real: 696.47 853.62 745.80 57.28 4.6339%
numa03.sh Sys: 85.68 123.71 97.89 13.48 7.3347%
numa03.sh User: 55978.45 66418.63 59254.94 3737.97 1.5323%
numa04.sh Real: 444.05 514.83 497.06 26.85 -2.464%
numa04.sh Sys: 230.39 375.79 316.23 48.58 5.8343%
numa04.sh User: 35403.12 41004.10 39720.80 2163.08 -1.153%
numa05.sh Real: 423.09 460.41 439.57 13.92 -1.428%
numa05.sh Sys: 287.38 480.15 369.37 68.52 -7.964%
numa05.sh User: 34732.12 38016.80 36255.85 1070.51 -1.704%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-5-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Currently load_too_imbalance() cares about the slope of imbalance.
It doesn't care of the direction of the imbalance.
However this may not work if nodes that are being compared have
dissimilar capacities. Few nodes might have more cores than other nodes
in the system. Also unlike traditional load balance at a NUMA sched
domain, multiple requests to migrate from the same source node to same
destination node may run in parallel. This can cause huge load
imbalance. This is specially true on a larger machines with either large
cores per node or more number of nodes in the system. Hence allow
move/swap only if the imbalance is going to reduce.
Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS LAST_PATCH WITH_PATCH %CHANGE
16 25058.2 25122.9 0.25
1 72950 73850 1.23
(numbers from v1 based on v4.17-rc5)
Testcase Time: Min Max Avg StdDev
numa01.sh Real: 516.14 892.41 739.84 151.32
numa01.sh Sys: 153.16 192.99 177.70 14.58
numa01.sh User: 39821.04 69528.92 57193.87 10989.48
numa02.sh Real: 60.91 62.35 61.58 0.63
numa02.sh Sys: 16.47 26.16 21.20 3.85
numa02.sh User: 5227.58 5309.61 5265.17 31.04
numa03.sh Real: 739.07 917.73 795.75 64.45
numa03.sh Sys: 94.46 136.08 109.48 14.58
numa03.sh User: 57478.56 72014.09 61764.48 5343.69
numa04.sh Real: 442.61 715.43 530.31 96.12
numa04.sh Sys: 224.90 348.63 285.61 48.83
numa04.sh User: 35836.84 47522.47 40235.41 3985.26
numa05.sh Real: 386.13 489.17 434.94 43.59
numa05.sh Sys: 144.29 438.56 278.80 105.78
numa05.sh User: 33255.86 36890.82 34879.31 1641.98
Testcase Time: Min Max Avg StdDev %Change
numa01.sh Real: 435.78 653.81 534.58 83.20 38.39%
numa01.sh Sys: 121.93 187.18 145.90 23.47 21.79%
numa01.sh User: 37082.81 51402.80 43647.60 5409.75 31.03%
numa02.sh Real: 60.64 61.63 61.19 0.40 0.637%
numa02.sh Sys: 14.72 25.68 19.06 4.03 11.22%
numa02.sh User: 5210.95 5266.69 5233.30 20.82 0.608%
numa03.sh Real: 746.51 808.24 780.36 23.88 1.972%
numa03.sh Sys: 97.26 108.48 105.07 4.28 4.197%
numa03.sh User: 58956.30 61397.05 60162.95 1050.82 2.661%
numa04.sh Real: 465.97 519.27 484.81 19.62 9.385%
numa04.sh Sys: 304.43 359.08 334.68 20.64 -14.6%
numa04.sh User: 37544.16 41186.15 39262.44 1314.91 2.478%
numa05.sh Real: 411.57 457.20 433.29 16.58 0.380%
numa05.sh Sys: 230.05 435.48 339.95 67.58 -17.9%
numa05.sh User: 33325.54 36896.31 35637.84 1222.64 -2.12%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-4-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
