In order for the scheduler to be frequency invariant we measure the
ratio between the maximum CPU frequency and the actual CPU frequency.
During long tickless periods of time the calculations that keep track
of that might overflow, in the function scale_freq_tick():
if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
goto error;
eventually forcing the kernel to disable the feature for all CPUs,
and show the warning message:
"Scheduler frequency invariance went wobbly, disabling!".
Let's avoid that by limiting the frequency invariant calculations
to CPUs with regular tick.
Fixes: e2b0d619b4 ("x86, sched: check for counters overflow in frequency invariant accounting")
Suggested-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Signed-off-by: Yair Podemsky <ypodemsk@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Acked-by: Giovanni Gherdovich <ggherdovich@suse.cz>
Link: https://lore.kernel.org/r/20221130125121.34407-1-ypodemsk@redhat.com
The max CPU capacity is the same for all CPUs sharing frequency domain.
There is a way to avoid heavy operations in a loop for each CPU by
leveraging this knowledge. Thus, simplify the looping code in the
sugov_next_freq_shared() and drop heavy multiplications. Instead, use
simple max() to get the highest utilization from these CPUs.
This is useful for platforms with many (4 or 6) little CPUs. We avoid
heavy 2*PD_CPU_NUM multiplications in that loop, which is called billions
of times, since it's not limited by the schedutil time delta filter in
sugov_should_update_freq(). When there was no need to change frequency
the code bailed out, not updating the sg_policy::last_freq_update_time.
Then every visit after delta_ns time longer than the
sg_policy::freq_update_delay_ns goes through and triggers the next
frequency calculation code. Although, if the next frequency, as outcome
of that, would be the same as current frequency, we won't update the
sg_policy::last_freq_update_time and the story will be repeated (in
a very short period, sometimes a few microseconds).
The max CPU capacity must be fetched every time we are called, due to
difficulties during the policy setup, where we are not able to get the
normalized CPU capacity at the right time.
The fetched CPU capacity value is than used in sugov_iowait_apply() to
calculate the right boost. This required a few changes in the local
functions and arguments. The capacity value should hopefully be fetched
once when needed and then passed over CPU registers to those functions.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20221208160256.859-2-lukasz.luba@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Patrick Bellasi <patrick.bellasi@arm.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
ttwu_do_activate() is used for a complete wakeup, in which we will
activate_task() and use ttwu_do_wakeup() to mark the task runnable
and perform wakeup-preemption, also call class->task_woken() callback
and update the rq->idle_stamp.
Since ttwu_runnable() is not a complete wakeup, don't need all those
done in ttwu_do_wakeup(), so we can move those to ttwu_do_activate()
to simplify ttwu_do_wakeup(), making it only mark the task runnable
to be reused in ttwu_runnable() and try_to_wake_up().
This patch should not have any functional changes.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20221223103257.4962-2-zhouchengming@bytedance.com
ttwu_runnable() is used as a fast wakeup path when the wakee task
is running on CPU or runnable on RQ, in both cases we can just
set its state to TASK_RUNNING to prevent a sleep.
If the wakee task is on_cpu running, we don't need to update_rq_clock()
or check_preempt_curr().
But if the wakee task is on_rq && !on_cpu (e.g. an IRQ hit before
the task got to schedule() and the task been preempted), we should
check_preempt_curr() to see if it can preempt the current running.
This also removes the class->task_woken() callback from ttwu_runnable(),
which wasn't required per the RT/DL implementations: any required push
operation would have been queued during class->set_next_task() when p
got preempted.
ttwu_runnable() also loses the update to rq->idle_stamp, as by definition
the rq cannot be idle in this scenario.
Suggested-by: Valentin Schneider <vschneid@redhat.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20221223103257.4962-1-zhouchengming@bytedance.com
The show_pwq() function dumps out a pool_workqueue structure's activity,
including the pending work-queue handlers:
Showing busy workqueues and worker pools:
workqueue events: flags=0x0
pwq 0: cpus=0 node=0 flags=0x1 nice=0 active=10/256 refcnt=11
in-flight: 7:test_work_func, 64:test_work_func, 249:test_work_func
pending: test_work_func, test_work_func, test_work_func1, test_work_func1, test_work_func1, test_work_func1, test_work_func1
When large systems are facing certain types of hang conditions, it is not
unusual for this "pending" list to contain runs of hundreds of identical
function names. This "wall of text" is difficult to read, and worse yet,
it can be interleaved with other output such as stack traces.
Therefore, make show_pwq() use run-length encoding so that the above
printout instead looks like this:
Showing busy workqueues and worker pools:
workqueue events: flags=0x0
pwq 0: cpus=0 node=0 flags=0x1 nice=0 active=10/256 refcnt=11
in-flight: 7:test_work_func, 64:test_work_func, 249:test_work_func
pending: 2*test_work_func, 5*test_work_func1
When no comma would be printed, including the WORK_STRUCT_LINKED case,
a new run is started unconditionally.
This output is more readable, places less stress on the hardware,
firmware, and software on the console-log path, and reduces interference
with other output.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The following kernel panic can be triggered when a task with pid=1 attaches
a prog that attempts to send killing signal to itself, also see [1] for more
details:
Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
CPU: 3 PID: 1 Comm: systemd Not tainted 6.1.0-09652-g59fe41b5255f #148
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x100/0x178 lib/dump_stack.c:106
panic+0x2c4/0x60f kernel/panic.c:275
do_exit.cold+0x63/0xe4 kernel/exit.c:789
do_group_exit+0xd4/0x2a0 kernel/exit.c:950
get_signal+0x2460/0x2600 kernel/signal.c:2858
arch_do_signal_or_restart+0x78/0x5d0 arch/x86/kernel/signal.c:306
exit_to_user_mode_loop kernel/entry/common.c:168 [inline]
exit_to_user_mode_prepare+0x15f/0x250 kernel/entry/common.c:203
__syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline]
syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:296
do_syscall_64+0x44/0xb0 arch/x86/entry/common.c:86
entry_SYSCALL_64_after_hwframe+0x63/0xcd
So skip task with pid=1 in bpf_send_signal_common() to avoid the panic.
[1] https://lore.kernel.org/bpf/20221222043507.33037-1-sunhao.th@gmail.com
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20230106084838.12690-1-sunhao.th@gmail.com
The verifier skips invalid kfunc call in check_kfunc_call(), which
would be captured in fixup_kfunc_call() if such insn is not eliminated
by dead code elimination. However, this can lead to the following
warning in backtrack_insn(), also see [1]:
------------[ cut here ]------------
verifier backtracking bug
WARNING: CPU: 6 PID: 8646 at kernel/bpf/verifier.c:2756 backtrack_insn
kernel/bpf/verifier.c:2756
__mark_chain_precision kernel/bpf/verifier.c:3065
mark_chain_precision kernel/bpf/verifier.c:3165
adjust_reg_min_max_vals kernel/bpf/verifier.c:10715
check_alu_op kernel/bpf/verifier.c:10928
do_check kernel/bpf/verifier.c:13821 [inline]
do_check_common kernel/bpf/verifier.c:16289
[...]
So make backtracking conservative with this by returning ENOTSUPP.
[1] https://lore.kernel.org/bpf/CACkBjsaXNceR8ZjkLG=dT3P=4A8SBsg0Z5h5PWLryF5=ghKq=g@mail.gmail.com/
Reported-by: syzbot+4da3ff23081bafe74fc2@syzkaller.appspotmail.com
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20230104014709.9375-1-sunhao.th@gmail.com
Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf, wifi, and netfilter.
Current release - regressions:
- bpf: fix nullness propagation for reg to reg comparisons, avoid
null-deref
- inet: control sockets should not use current thread task_frag
- bpf: always use maximal size for copy_array()
- eth: bnxt_en: don't link netdev to a devlink port for VFs
Current release - new code bugs:
- rxrpc: fix a couple of potential use-after-frees
- netfilter: conntrack: fix IPv6 exthdr error check
- wifi: iwlwifi: fw: skip PPAG for JF, avoid FW crashes
- eth: dsa: qca8k: various fixes for the in-band register access
- eth: nfp: fix schedule in atomic context when sync mc address
- eth: renesas: rswitch: fix getting mac address from device tree
- mobile: ipa: use proper endpoint mask for suspend
Previous releases - regressions:
- tcp: add TIME_WAIT sockets in bhash2, fix regression caught by
Jiri / python tests
- net: tc: don't intepret cls results when asked to drop, fix
oob-access
- vrf: determine the dst using the original ifindex for multicast
- eth: bnxt_en:
- fix XDP RX path if BPF adjusted packet length
- fix HDS (header placement) and jumbo thresholds for RX packets
- eth: ice: xsk: do not use xdp_return_frame() on tx_buf->raw_buf,
avoid memory corruptions
Previous releases - always broken:
- ulp: prevent ULP without clone op from entering the LISTEN status
- veth: fix race with AF_XDP exposing old or uninitialized
descriptors
- bpf:
- pull before calling skb_postpull_rcsum() (fix checksum support
and avoid a WARN())
- fix panic due to wrong pageattr of im->image (when livepatch and
kretfunc coexist)
- keep a reference to the mm, in case the task is dead
- mptcp: fix deadlock in fastopen error path
- netfilter:
- nf_tables: perform type checking for existing sets
- nf_tables: honor set timeout and garbage collection updates
- ipset: fix hash:net,port,net hang with /0 subnet
- ipset: avoid hung task warning when adding/deleting entries
- selftests: net:
- fix cmsg_so_mark.sh test hang on non-x86 systems
- fix the arp_ndisc_evict_nocarrier test for IPv6
- usb: rndis_host: secure rndis_query check against int overflow
- eth: r8169: fix dmar pte write access during suspend/resume with
WOL
- eth: lan966x: fix configuration of the PCS
- eth: sparx5: fix reading of the MAC address
- eth: qed: allow sleep in qed_mcp_trace_dump()
- eth: hns3:
- fix interrupts re-initialization after VF FLR
- fix handling of promisc when MAC addr table gets full
- refine the handling for VF heartbeat
- eth: mlx5:
- properly handle ingress QinQ-tagged packets on VST
- fix io_eq_size and event_eq_size params validation on big endian
- fix RoCE setting at HCA level if not supported at all
- don't turn CQE compression on by default for IPoIB
- eth: ena:
- fix toeplitz initial hash key value
- account for the number of XDP-processed bytes in interface stats
- fix rx_copybreak value update
Misc:
- ethtool: harden phy stat handling against buggy drivers
- docs: netdev: convert maintainer's doc from FAQ to a normal
document"
* tag 'net-6.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (112 commits)
caif: fix memory leak in cfctrl_linkup_request()
inet: control sockets should not use current thread task_frag
net/ulp: prevent ULP without clone op from entering the LISTEN status
qed: allow sleep in qed_mcp_trace_dump()
MAINTAINERS: Update maintainers for ptp_vmw driver
usb: rndis_host: Secure rndis_query check against int overflow
net: dpaa: Fix dtsec check for PCS availability
octeontx2-pf: Fix lmtst ID used in aura free
drivers/net/bonding/bond_3ad: return when there's no aggregator
netfilter: ipset: Rework long task execution when adding/deleting entries
netfilter: ipset: fix hash:net,port,net hang with /0 subnet
net: sparx5: Fix reading of the MAC address
vxlan: Fix memory leaks in error path
net: sched: htb: fix htb_classify() kernel-doc
net: sched: cbq: dont intepret cls results when asked to drop
net: sched: atm: dont intepret cls results when asked to drop
dt-bindings: net: marvell,orion-mdio: Fix examples
dt-bindings: net: sun8i-emac: Add phy-supply property
net: ipa: use proper endpoint mask for suspend
selftests: net: return non-zero for failures reported in arp_ndisc_evict_nocarrier
...
When clocksource_watchdog() detects excessive clocksource skew compared
to the watchdog clocksource, it marks the clocksource under test as
unstable and prints several lines worth of message. But that message
is unclear to anyone unfamiliar with the code:
clocksource: timekeeping watchdog on CPU2: Marking clocksource 'wdtest-ktime' as unstable because the skew is too large:
clocksource: 'kvm-clock' wd_nsec: 400744390 wd_now: 612625c2c wd_last: 5fa7f7c66 mask: ffffffffffffffff
clocksource: 'wdtest-ktime' cs_nsec: 600744034 cs_now: 173081397a292d4f cs_last: 17308139565a8ced mask: ffffffffffffffff
clocksource: 'kvm-clock' (not 'wdtest-ktime') is current clocksource.
Therefore, add the following line near the end of that message:
Clocksource 'wdtest-ktime' skewed 199999644 ns (199 ms) over watchdog 'kvm-clock' interval of 400744390 ns (400 ms)
This new line clearly indicates the amount of skew between the two
clocksources, along with the duration of the time interval over which
the skew occurred, both in nanoseconds and milliseconds.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: John Stultz <jstultz@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Feng Tang <feng.tang@intel.com>
Time stamps are added to the output in kernels built with
CONFIG_PRINTK_TIME=y, which causes misaligned output. Therefore,
replace pr_cont() with pr_err(), which fixes alignment and gets
rid of a couple of despised pr_cont() calls.
Before:
[ 37.567343] rcu: INFO: rcu_preempt self-detected stall on CPU
[ 37.567839] rcu: 0-....: (1500 ticks this GP) idle=***
[ 37.568270] (t=1501 jiffies g=4717 q=28 ncpus=4)
[ 37.568668] CPU: 0 PID: 313 Comm: test0 Not tainted 6.1.0-rc4 #8
After:
[ 36.762074] rcu: INFO: rcu_preempt self-detected stall on CPU
[ 36.762543] rcu: 0-....: (1499 ticks this GP) idle=***
[ 36.763003] rcu: (t=1500 jiffies g=5097 q=27 ncpus=4)
[ 36.763522] CPU: 0 PID: 313 Comm: test0 Not tainted 6.1.0-rc4 #9
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Because RCU CPU stall warnings are driven from the scheduling-clock
interrupt handler, a workload consisting of a very large number of
short-duration hardware interrupts can result in misleading stall-warning
messages. On systems supporting only a single level of interrupts,
that is, where interrupts handlers cannot be interrupted, this can
produce misleading diagnostics. The stack traces will show the
innocent-bystander interrupted task, not the interrupts that are
at the very least exacerbating the stall.
This situation can be improved by displaying the number of interrupts
and the CPU time that they have consumed. Diagnosing other types
of stalls can be eased by also providing the count of softirqs and
the CPU time that they consumed as well as the number of context
switches and the task-level CPU time consumed.
Consider the following output given this change:
rcu: INFO: rcu_preempt self-detected stall on CPU
rcu: 0-....: (1250 ticks this GP) <omitted>
rcu: hardirqs softirqs csw/system
rcu: number: 624 45 0
rcu: cputime: 69 1 2425 ==> 2500(ms)
This output shows that the number of hard and soft interrupts is small,
there are no context switches, and the system takes up a lot of time. This
indicates that the current task is looping with preemption disabled.
The impact on system performance is negligible because snapshot is
recorded only once for all continuous RCU stalls.
This added debugging information is suppressed by default and can be
enabled by building the kernel with CONFIG_RCU_CPU_STALL_CPUTIME=y or
by booting with rcupdate.rcu_cpu_stall_cputime=1.
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Reviewed-by: Mukesh Ojha <quic_mojha@quicinc.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
During rcutorture shutdown, the rcu_torture_cleanup() function calls
torture_cleanup_begin(), which sets the fullstop global variable to
FULLSTOP_RMMOD. This causes the rcutorture threads for readers and
fakewriters to exit all of their "while" loops and start shutting down.
They then call torture_kthread_stopping(), which in turn waits for
kthread_stop() to be called. However, rcu_torture_cleanup() has
not yet called kthread_stop() on those threads, and before it gets a
chance to do so, multiple instances of torture_kthread_stopping() invoke
schedule_timeout_interruptible(1) in a tight loop. Tracing confirms that
TIMER_SOFTIRQ can then continuously execute timer callbacks. If that
TIMER_SOFTIRQ preempts the task executing rcu_torture_cleanup(), that
task might never invoke kthread_stop().
This commit improves this situation by increasing the timeout passed to
schedule_timeout_interruptible() from one jiffy to 1/20th of a second.
This change prevents TIMER_SOFTIRQ from monopolizing its CPU, thus
allowing rcu_torture_cleanup() to carry out the needed kthread_stop()
invocations. Testing has shown 100 runs of TREE07 passing reliably,
as oppose to the tens-of-percent failure rates seen beforehand.
Cc: Paul McKenney <paulmck@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Zhouyi Zhou <zhouzhouyi@gmail.com>
Cc: <stable@vger.kernel.org> # 6.0.x
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Tested-by: Zhouyi Zhou <zhouzhouyi@gmail.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The sparse __acquires() and __releases() annotations provide very
little value. The argument is ignored, so sparse cannot tell the
differences between acquiring one lock and releasing another on the one
hand and acquiring and releasing a given lock on the other. In addition,
lockdep annotations provide much more precision, for but one example,
actually knowing which lock is held.
This commit therefore removes the __acquires() and __releases()
annotations from rcutorture.
Reported-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rt boosting in locktorture has a factor variable s currently large enough
that boosting only happens once every minute or so. Add a tunable to reduce the
factor so that boosting happens more often, to test paths and arrive at failure
modes earlier. With this change, I can set the factor to like 50 and have the
boosting happens every 10 seconds or so.
Tested with boot parameters:
locktorture.torture_type=mutex_lock
locktorture.onoff_interval=1
locktorture.nwriters_stress=8
locktorture.stutter=0
locktorture.rt_boost=1
locktorture.rt_boost_factor=50
locktorture.nlocks=3
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently RT boosting is only done for rtmutex_lock, however with proxy
execution, we also have the mutex_lock participating in priorities. To
exercise the testing better, add RT boosting to other lock testing types
as well, using a new knob (rt_boost).
Tested with boot parameters:
locktorture.torture_type=mutex_lock
locktorture.onoff_interval=1
locktorture.nwriters_stress=8
locktorture.stutter=0
locktorture.rt_boost=1
locktorture.rt_boost_factor=1
locktorture.nlocks=3
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit adds three read-side-only tests of three use cases featuring
SLAB_TYPESAFE_BY_RCU: One using per-object reference counting, one using
per-object locking, and one using per-object sequence locking.
[ paulmck: Apply feedback from kernel test robot. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
When we're pending, we only care about lock value. The xchg_tail
wouldn't affect the pending state. That means the hardware thread
could stay in a sleep state and leaves the rest execution units'
resources of pipeline to other hardware threads. This situation is
the SMT scenarios in the same core. Not an entering low-power state
situation. Of course, the granularity between cores is "cacheline",
but the granularity between SMT hw threads of the same core could
be "byte" which internal LSU handles. For example, when a hw-thread
yields the resources of the core to other hw-threads, this patch
could help the hw-thread stay in the sleep state and prevent it
from being woken up by other hw-threads xchg_tail.
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20230105021952.3090070-1-guoren@kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>
Daniel Borkmann says:
====================
bpf-next 2023-01-04
We've added 45 non-merge commits during the last 21 day(s) which contain
a total of 50 files changed, 1454 insertions(+), 375 deletions(-).
The main changes are:
1) Fixes, improvements and refactoring of parts of BPF verifier's
state equivalence checks, from Andrii Nakryiko.
2) Fix a few corner cases in libbpf's BTF-to-C converter in particular
around padding handling and enums, also from Andrii Nakryiko.
3) Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better
support decap on GRE tunnel devices not operating in collect metadata,
from Christian Ehrig.
4) Improve x86 JIT's codegen for PROBE_MEM runtime error checks,
from Dave Marchevsky.
5) Remove the need for trace_printk_lock for bpf_trace_printk
and bpf_trace_vprintk helpers, from Jiri Olsa.
6) Add proper documentation for BPF_MAP_TYPE_SOCK{MAP,HASH} maps,
from Maryam Tahhan.
7) Improvements in libbpf's btf_parse_elf error handling, from Changbin Du.
8) Bigger batch of improvements to BPF tracing code samples,
from Daniel T. Lee.
9) Add LoongArch support to libbpf's bpf_tracing helper header,
from Hengqi Chen.
10) Fix a libbpf compiler warning in perf_event_open_probe on arm32,
from Khem Raj.
11) Optimize bpf_local_storage_elem by removing 56 bytes of padding,
from Martin KaFai Lau.
12) Use pkg-config to locate libelf for resolve_btfids build,
from Shen Jiamin.
13) Various libbpf improvements around API documentation and errno
handling, from Xin Liu.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (45 commits)
libbpf: Return -ENODATA for missing btf section
libbpf: Add LoongArch support to bpf_tracing.h
libbpf: Restore errno after pr_warn.
libbpf: Added the description of some API functions
libbpf: Fix invalid return address register in s390
samples/bpf: Use BPF_KSYSCALL macro in syscall tracing programs
samples/bpf: Fix tracex2 by using BPF_KSYSCALL macro
samples/bpf: Change _kern suffix to .bpf with syscall tracing program
samples/bpf: Use vmlinux.h instead of implicit headers in syscall tracing program
samples/bpf: Use kyscall instead of kprobe in syscall tracing program
bpf: rename list_head -> graph_root in field info types
libbpf: fix errno is overwritten after being closed.
bpf: fix regs_exact() logic in regsafe() to remap IDs correctly
bpf: perform byte-by-byte comparison only when necessary in regsafe()
bpf: reject non-exact register type matches in regsafe()
bpf: generalize MAYBE_NULL vs non-MAYBE_NULL rule
bpf: reorganize struct bpf_reg_state fields
bpf: teach refsafe() to take into account ID remapping
bpf: Remove unused field initialization in bpf's ctl_table
selftests/bpf: Add jit probe_mem corner case tests to s390x denylist
...
====================
Link: https://lore.kernel.org/r/20230105000926.31350-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently if the user queues a new work item unintentionally
into a wq after the destroy_workqueue(wq), the work still can
be queued and scheduled without any noticeable kernel message
before the end of a RCU grace period.
As a debug-aid facility, this commit adds a new flag
__WQ_DESTROYING to spot that issue by triggering a kernel WARN
message.
Signed-off-by: Richard Clark <richard.xnu.clark@gmail.com>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
cpuset_rwsem is a static variable defined with DEFINE_STATIC_PERCPU_RWSEM().
It's initialized at build time and so there's no need for explicit runtime
init leaking one percpu int.
Signed-off-by: Daniel Vacek <neelx@redhat.com>
Reviewed-by: Aaron Tomlin <atomlin@atomlin.com>
Acked-by: Mukesh Ojha <quic_mojha@quicinc.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
When cs_watchdog_read() is unable to get a qualifying clocksource read
within the limit set by max_cswd_read_retries, it prints a message
and marks the clocksource under test as unstable. But that message is
unclear to anyone unfamiliar with the code:
clocksource: timekeeping watchdog on CPU13: wd-tsc-wd read-back delay 1000614ns, attempt 3, marking unstable
Therefore, add some context so that the message appears as follows:
clocksource: timekeeping watchdog on CPU13: wd-tsc-wd excessive read-back delay of 1000614ns vs. limit of 125000ns, wd-wd read-back delay only 27ns, attempt 3, marking tsc unstable
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: John Stultz <jstultz@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Feng Tang <feng.tang@intel.com>
Currently, MAX_SKEW_USEC is set to 100 microseconds, which has worked
reasonably well. However, NTP is willing to tolerate 500 microseconds
of skew per second, and a clocksource that is good enough for NTP should
be good enough for the clocksource watchdog. The watchdog's skew is
controlled by MAX_SKEW_USEC and the CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
Kconfig option. However, these values are doubled before being associated
with a clocksource's ->uncertainty_margin, and the ->uncertainty_margin
values of the pair of clocksource's being compared are summed before
checking against the skew.
Therefore, set both MAX_SKEW_USEC and the default for the
CLOCKSOURCE_WATCHDOG_MAX_SKEW_US Kconfig option to 125 microseconds of
skew per second, resulting in 500 microseconds of skew per second in
the clocksource watchdog's skew comparison.
Suggested-by Rik van Riel <riel@surriel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Some "TSC fall back to HPET" messages appear on systems having more than
2 NUMA nodes:
clocksource: timekeeping watchdog on CPU168: hpet read-back delay of 4296200ns, attempt 4, marking unstable
The "hpet" here is misleading the clocksource watchdog is really
doing repeated reads of "hpet" in order to check for unrelated delays.
Therefore, print the name of the clocksource under test, prefixed by
"wd-" and suffixed by "-wd", for example, "wd-tsc-wd".
Signed-off-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Current tests all have init() functions that are guaranteed to succeed.
But upcoming tests will need to allocate memory, thus possibly failing.
This commit therefore handles init() function failure.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The DEFINE_TORTURE_RANDOM_PERCPU() macro defines per-CPU random-number
generators for torture testing, but the seeds for each CPU's instance
will be identical if they are first used at the same time. This commit
therefore adds the CPU number to the mix when reseeding.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_tasks_need_gpcb() determines whether or not: (1) There are
callbacks needing another grace period, (2) There are callbacks ready
to be invoked, and (3) It would be a good time to shrink back down to a
single-CPU callback list. This third case is interesting because some
other CPU might be adding new callbacks, which might suddenly make this
a very bad time to be shrinking.
This is currently handled by requiring call_rcu_tasks_generic() to
enqueue callbacks under the protection of rcu_read_lock() and requiring
rcu_tasks_need_gpcb() to wait for an RCU grace period to elapse before
finalizing the transition. This works well in practice.
Unfortunately, the current code assumes that a grace period whose end is
detected by the poll_state_synchronize_rcu() in the second "if" condition
actually ended before the earlier code counted the callbacks queued on
CPUs other than CPU 0 (local variable "ncbsnz"). Given the current code,
it is possible that a long-delayed call_rcu_tasks_generic() invocation
will queue a callback on a non-zero CPU after these CPUs have had their
callbacks counted and zero has been stored to ncbsnz. Such a callback
would trigger the WARN_ON_ONCE() in the second "if" statement.
To see this, consider the following sequence of events:
o CPU 0 invokes rcu_tasks_one_gp(), and counts fewer than
rcu_task_collapse_lim callbacks. It sees at least one
callback queued on some other CPU, thus setting ncbsnz
to a non-zero value.
o CPU 1 invokes call_rcu_tasks_generic() and loads 42 from
->percpu_enqueue_lim. It therefore decides to enqueue its
callback onto CPU 1's callback list, but is delayed.
o CPU 0 sees the rcu_task_cb_adjust is non-zero and that the number
of callbacks does not exceed rcu_task_collapse_lim. It therefore
checks percpu_enqueue_lim, and sees that its value is greater
than the value one. CPU 0 therefore starts the shift back
to a single callback list. It sets ->percpu_enqueue_lim to 1,
but CPU 1 has already read the old value of 42. It also gets
a grace-period state value from get_state_synchronize_rcu().
o CPU 0 sees that ncbsnz is non-zero in its second "if" statement,
so it declines to finalize the shrink operation.
o CPU 0 again invokes rcu_tasks_one_gp(), and counts fewer than
rcu_task_collapse_lim callbacks. It also sees that there are
no callback queued on any other CPU, and thus sets ncbsnz to zero.
o CPU 1 resumes execution and enqueues its callback onto its own
list. This invalidates the value of ncbsnz.
o CPU 0 sees the rcu_task_cb_adjust is non-zero and that the number
of callbacks does not exceed rcu_task_collapse_lim. It therefore
checks percpu_enqueue_lim, but sees that its value is already
unity. It therefore does not get a new grace-period state value.
o CPU 0 sees that rcu_task_cb_adjust is non-zero, ncbsnz is zero,
and that poll_state_synchronize_rcu() says that the grace period
has completed. it therefore finalizes the shrink operation,
setting ->percpu_dequeue_lim to the value one.
o CPU 0 does a debug check, scanning the other CPUs' callback lists.
It sees that CPU 1's list has a callback, so it (rightly)
triggers the WARN_ON_ONCE(). After all, the new value of
->percpu_dequeue_lim says to not bother looking at CPU 1's
callback list, which means that this callback will never be
invoked. This can result in hangs and maybe even OOMs.
Based on long experience with rcutorture, this is an extremely
low-probability race condition, but it really can happen, especially in
preemptible kernels or within guest OSes.
This commit therefore checks for completion of the grace period
before counting callbacks. With this change, in the above failure
scenario CPU 0 would know not to prematurely end the shrink operation
because the grace period would not have completed before the count
operation started.
[ paulmck: Adjust grace-period end rather than adding RCU reader. ]
[ paulmck: Avoid spurious WARN_ON_ONCE() with ->percpu_dequeue_lim check. ]
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The synchronize_rcu_tasks_rude() function invokes rcu_tasks_rude_wait_gp()
to wait one rude RCU-tasks grace period. The rcu_tasks_rude_wait_gp()
function in turn checks if there is only a single online CPU. If so, it
will immediately return, because a call to synchronize_rcu_tasks_rude()
is by definition a grace period on a single-CPU system. (We could
have blocked!)
Unfortunately, this check uses num_online_cpus() without synchronization,
which can result in too-short grace periods. To see this, consider the
following scenario:
CPU0 CPU1 (going offline)
migration/1 task:
cpu_stopper_thread
-> take_cpu_down
-> _cpu_disable
(dec __num_online_cpus)
->cpuhp_invoke_callback
preempt_disable
access old_data0
task1
del old_data0 .....
synchronize_rcu_tasks_rude()
task1 schedule out
....
task2 schedule in
rcu_tasks_rude_wait_gp()
->__num_online_cpus == 1
->return
....
task1 schedule in
->free old_data0
preempt_enable
When CPU1 decrements __num_online_cpus, its value becomes 1. However,
CPU1 has not finished going offline, and will take one last trip through
the scheduler and the idle loop before it actually stops executing
instructions. Because synchronize_rcu_tasks_rude() is mostly used for
tracing, and because both the scheduler and the idle loop can be traced,
this means that CPU0's prematurely ended grace period might disrupt the
tracing on CPU1. Given that this disruption might include CPU1 executing
instructions in memory that was just now freed (and maybe reallocated),
this is a matter of some concern.
This commit therefore removes that problematic single-CPU check from the
rcu_tasks_rude_wait_gp() function. This dispenses with the single-CPU
optimization, but there is no evidence indicating that this optimization
is important. In addition, synchronize_rcu_tasks_generic() contains a
similar optimization (albeit only for early boot), which also splats.
(As in exactly why are you invoking synchronize_rcu_tasks_rude() so
early in boot, anyway???)
It is OK for the synchronize_rcu_tasks_rude() function's check to be
unsynchronized because the only times that this check can evaluate to
true is when there is only a single CPU running with preemption
disabled.
While in the area, this commit also fixes a minor bug in which a
call to synchronize_rcu_tasks_rude() would instead be attributed to
synchronize_rcu_tasks().
[ paulmck: Add "synchronize_" prefix and "()" suffix. ]
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
RCU Tasks and PID-namespace unshare can interact in do_exit() in a
complicated circular dependency:
1) TASK A calls unshare(CLONE_NEWPID), this creates a new PID namespace
that every subsequent child of TASK A will belong to. But TASK A
doesn't itself belong to that new PID namespace.
2) TASK A forks() and creates TASK B. TASK A stays attached to its PID
namespace (let's say PID_NS1) and TASK B is the first task belonging
to the new PID namespace created by unshare() (let's call it PID_NS2).
3) Since TASK B is the first task attached to PID_NS2, it becomes the
PID_NS2 child reaper.
4) TASK A forks() again and creates TASK C which get attached to PID_NS2.
Note how TASK C has TASK A as a parent (belonging to PID_NS1) but has
TASK B (belonging to PID_NS2) as a pid_namespace child_reaper.
5) TASK B exits and since it is the child reaper for PID_NS2, it has to
kill all other tasks attached to PID_NS2, and wait for all of them to
die before getting reaped itself (zap_pid_ns_process()).
6) TASK A calls synchronize_rcu_tasks() which leads to
synchronize_srcu(&tasks_rcu_exit_srcu).
7) TASK B is waiting for TASK C to get reaped. But TASK B is under a
tasks_rcu_exit_srcu SRCU critical section (exit_notify() is between
exit_tasks_rcu_start() and exit_tasks_rcu_finish()), blocking TASK A.
8) TASK C exits and since TASK A is its parent, it waits for it to reap
TASK C, but it can't because TASK A waits for TASK B that waits for
TASK C.
Pid_namespace semantics can hardly be changed at this point. But the
coverage of tasks_rcu_exit_srcu can be reduced instead.
The current task is assumed not to be concurrently reapable at this
stage of exit_notify() and therefore tasks_rcu_exit_srcu can be
temporarily relaxed without breaking its constraints, providing a way
out of the deadlock scenario.
[ paulmck: Fix build failure by adding additional declaration. ]
Fixes: 3f95aa81d2 ("rcu: Make TASKS_RCU handle tasks that are almost done exiting")
Reported-by: Pengfei Xu <pengfei.xu@intel.com>
Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Suggested-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Suggested-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Eric W . Biederman <ebiederm@xmission.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Ever since the following commit:
5a41344a3d ("srcu: Simplify __srcu_read_unlock() via this_cpu_dec()")
SRCU doesn't rely anymore on preemption to be disabled in order to
modify the per-CPU counter. And even then it used to be done from the API
itself.
Therefore and after checking further, it appears to be safe to remove
the preemption disablement around __srcu_read_[un]lock() in
exit_tasks_rcu_start() and exit_tasks_rcu_finish()
Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Suggested-by: Paul E. McKenney <paulmck@kernel.org>
Suggested-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, test_rcu_tasks_callback() reads from the jiffies counter only
once when this function is invoked. This introduces inaccuracies because
of the latencies induced by the synchronize_rcu_tasks*() invocations.
This commit therefore re-reads the jiffies counter at the beginning
of each test, thus avoiding penalizing later tests for the latencies
induced by earlier tests.
Therefore, this commit at the start of each RCU Tasks test, re-fetch the
jiffies time as the runstart time.
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Because there is not guaranteed to be a full memory barrier between
the ->srcu_unlock_count increment of an srcu_read_unlock() and the
->srcu_lock_count increment of the next srcu_read_lock(), this next
srcu_read_lock() is not guaranteed to see the effect of the index flip
just prior to this comment. However, this next srcu_read_lock() will
execute a full memory barrier, so the srcu_read_lock() after that is
guaranteed to see that index flip.
This guarantee is illustrated by the following diagram of events and
the litmus test following that.
------------------------------------------------------------------------
READER UPDATER
------------- ----------
// idx is initially 0.
srcu_flip() {
smp_mb();
// RSCS
srcu_read_unlock() {
smp_mb();
idx++; // P
smp_mb(); // QQ
}
srcu_readers_unlock_idx(0) {
,--counted------------ count all unlock[0]; // Q
|
unlock[0]++; // X
}
smp_mb();
srcu_read_lock() {
READ(idx) = 0; ,---- count all lock[0]; // contributes imbalance of 1.
lock[0]++; ----counted |
smp_mb(); // PP } |
} |
|
// RSCS not going to effect above scan
|
srcu_read_unlock() { |
smp_mb(); |
unlock[0]++; |
} |
/
/
srcu_read_lock() { |
READ(idx); // Y -----cannot be counted because of P (has to sample idx as 1)
lock[1]++;
...
}
------------------------------------------------------------------------
This makes it similar to the store buffer pattern. Using X, Y, P and Q
annotated above, we get:
------------------------------------------------------------------------
READER UPDATER
X (write) P (write)
smp_mb(); //PP smp_mb(); //QQ
Y (read) Q (read)
------------------------------------------------------------------------
ASCII art courtesy of Joel Fernandes.
Reported-by: Joel Fernandes <joel@joelfernandes.org>
Reported-by: Boqun Feng <boqun.feng@gmail.com>
Reported-by: Frederic Weisbecker <frederic@kernel.org>
Reported-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The comment in srcu_readers_active_idx_check() following the smp_mb()
is out of date, hailing from a simpler time when preemption was disabled
across the bulk of __srcu_read_lock(). The fact that preemption was
disabled meant that the number of tasks that had fetched the old index
but not yet incremented counters was limited by the number of CPUs.
In our more complex modern times, the number of CPUs is no longer a limit.
This commit therefore updates this comment, additionally giving more
memory-ordering detail.
[ paulmck: Apply Nt->Nc feedback from Joel Fernandes. ]
Reported-by: Boqun Feng <boqun.feng@gmail.com>
Reported-by: Frederic Weisbecker <frederic@kernel.org>
Reported-by: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Reported-by: Neeraj Upadhyay <neeraj.iitr10@gmail.com>
Reported-by: Uladzislau Rezki <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The srcu_gp_start_if_needed() function now read-holds the srcu_struct
whose grace period is being started, which means that the corresponding
SRCU grace period cannot end. This in turn means that the SRCU
grace-period sequence number returned by rcu_seq_snap() cannot expire
during this time. And that means that the calls to rcu_seq_done() in
srcu_funnel_exp_start() and srcu_funnel_gp_start() can never return true.
This commit therefore removes these rcu_seq_done() checks, but adds checks
in kernels built with CONFIG_PROVE_RCU=y that splats if rcu_seq_done()
does somehow return true.
[ paulmck: Rearrange checks to handle kernels built with lockdep. ]
Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: rcu@vger.kernel.org
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
A grace-period sequence number contains two fields: counter and
state. SRCU_SNP_INIT_SEQ provides a guaranteed invalid value for
grace-period sequence numbers in newly allocated srcu_node structures'
->srcu_have_cbs[] and ->srcu_gp_seq_needed_exp fields. The point of the
comparison in srcu_invl_snp_seq() is not to detect invalid grace-period
sequence numbers in general, but rather to detect a newly allocated
srcu_node structure whose ->srcu_have_cbs[] and ->srcu_gp_seq_needed_exp
fields need to be brought into line with the srcu_struct structure's
->srcu_gp_seq field.
This commit therefore causes srcu_invl_snp_seq() to compare both fields
of the specified grace-period sequence number.
Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: <rcu@vger.kernel.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Kernels built with the CONFIG_TREE_SRCU Kconfig option set and then
booted with rcupdate.rcu_self_test=1 and srcutree.convert_to_big=1 will
test Tree SRCU during early boot. The early_srcu structure's srcu_node
array will be allocated when init_srcu_struct_fields() is invoked,
but after the test completes this early_srcu structure will not be used.
This commit therefore invokes cleanup_srcu_struct() to free that srcu_node
structure.
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This patch splits the lists of objects so as to avoid sending any
through RCU that have already been queued for more than one grace
period. These long-term-resident objects are immediately freed.
The remaining short-term-resident objects are queued for later freeing
using queue_rcu_work().
This change avoids delaying workqueue handlers with synchronize_rcu()
invocations. Yes, workqueue handlers are designed to handle blocking,
but avoiding blocking when unnecessary improves performance during
low-memory situations.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The schedule_delayed_monitor_work() function relies on the count of
objects queued into any given kfree_rcu_cpu structure. This count is
used to determine how quickly to schedule passing these objects to RCU.
There are three pipes where pointers can be placed. When any pipe is
offloaded, the kfree_rcu_cpu structure's ->count counter is set to zero,
which is wrong because the other pipes might still be non-empty.
This commit therefore maintains per-pipe counters, and introduces a
krc_count() helper to access the aggregate value of those counters.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The need_offload_krc() function is now lock-free, which gives the
compiler freedom to load old values from plain C-language loads from
the kfree_rcu_cpu struture's ->head pointer. This commit therefore
applied READ_ONCE() to these loads.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently all objects placed into a batch wait for a full grace period
to elapse after that batch is ready to send to RCU. However, this
can unnecessarily delay freeing of the first objects that were added
to the batch. After all, several RCU grace periods might have elapsed
since those objects were added, and if so, there is no point in further
deferring their freeing.
This commit therefore adds per-page grace-period snapshots which are
obtained from get_state_synchronize_rcu(). When the batch is ready
to be passed to call_rcu(), each page's snapshot is checked by passing
it to poll_state_synchronize_rcu(). If a given page's RCU grace period
has already elapsed, its objects are freed immediately by kvfree_rcu_bulk().
Otherwise, these objects are freed after a call to synchronize_rcu().
This approach requires that the pages be traversed in reverse order,
that is, the oldest ones first.
Test example:
kvm.sh --memory 10G --torture rcuscale --allcpus --duration 1 \
--kconfig CONFIG_NR_CPUS=64 \
--kconfig CONFIG_RCU_NOCB_CPU=y \
--kconfig CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y \
--kconfig CONFIG_RCU_LAZY=n \
--bootargs "rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 \
rcuscale.holdoff=20 rcuscale.kfree_loops=10000 \
torture.disable_onoff_at_boot" --trust-make
Before this commit:
Total time taken by all kfree'ers: 8535693700 ns, loops: 10000, batches: 1188, memory footprint: 2248MB
Total time taken by all kfree'ers: 8466933582 ns, loops: 10000, batches: 1157, memory footprint: 2820MB
Total time taken by all kfree'ers: 5375602446 ns, loops: 10000, batches: 1130, memory footprint: 6502MB
Total time taken by all kfree'ers: 7523283832 ns, loops: 10000, batches: 1006, memory footprint: 3343MB
Total time taken by all kfree'ers: 6459171956 ns, loops: 10000, batches: 1150, memory footprint: 6549MB
After this commit:
Total time taken by all kfree'ers: 8560060176 ns, loops: 10000, batches: 1787, memory footprint: 61MB
Total time taken by all kfree'ers: 8573885501 ns, loops: 10000, batches: 1777, memory footprint: 93MB
Total time taken by all kfree'ers: 8320000202 ns, loops: 10000, batches: 1727, memory footprint: 66MB
Total time taken by all kfree'ers: 8552718794 ns, loops: 10000, batches: 1790, memory footprint: 75MB
Total time taken by all kfree'ers: 8601368792 ns, loops: 10000, batches: 1724, memory footprint: 62MB
The reduction in memory footprint is well in excess of an order of
magnitude.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The need_offload_krc() function currently holds the krcp->lock in order
to safely check krcp->head. This commit removes the need for this lock
in that function by updating the krcp->head pointer using WRITE_ONCE()
macro so that readers can carry out lockless loads of that pointer.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The kvfree_rcu() code maintains lists of pages of pointers, but also a
singly linked list, with the latter being used when memory allocation
fails. Traversal of these two types of lists is currently open coded.
This commit simplifies the code by providing kvfree_rcu_bulk() and
kvfree_rcu_list() functions, respectively, to traverse these two types
of lists. This patch does not introduce any functional change.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit improves the readability and maintainability of the
kvfree_rcu() code by switching from an open-coded linked list to
the standard Linux-kernel circular doubly linked list. This patch
does not introduce any functional change.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently a kvfree_call_rcu() takes an offset within a structure as
a second parameter, so a helper such as a kvfree_rcu_arg_2() has to
convert rcu_head and a freed ptr to an offset in order to pass it. That
leads to an extra conversion on macro entry.
Instead of converting, refactor the code in way that a pointer that has
to be freed is passed directly to the kvfree_call_rcu().
This patch does not make any functional change and is transparent to
all kvfree_rcu() users.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
