On Thu, Dec 15, 2022 at 05:00:29PM +0800, Zqiang wrote:
> Currently, when CPUs going offline, the rcu boost kthreads CPU
> affinity has been reset in rcutree_offline_cpu(), therefore this
> commit remove duplicate settings in rcutree_dead_cpu().
>
> Signed-off-by: Zqiang <qiang1.zhang@xxxxxxxxx>
>
>One question...
>
>Given that rcutree_offline_cpu() causes rcu_boost_kthread_setaffinity()
>to be invoked with the number of the outgoing CPU, but rcutree_dead_cpu()
>instead passes in -1, are these two invocations really redundant?
>
>Although -1 is passed in, but at this time, the outgoing CPU has been removed from
>rcu_rnp_online_cpus(rnp), in other words, we will eliminate the same CPU, which is
>also we passed in cpu in the rcutree_offline_cpu() before.
>
I also used " qemu -smp 4 "for a simple test.
1) rcutree_offline_cpu()
(gdb) bt
#0 set_cpus_allowed_ptr (p=p@entry=0xffff888100bd9cc0, new_mask=new_mask@entry=0xffff888100ce7cd0)
at kernel/sched/core.c:2939
#1 0xffffffff811be169 in rcu_boost_kthread_setaffinity (rnp=0xffffffff837a4c00 <rcu_state>,
outgoingcpu=outgoingcpu@entry=3) at kernel/rcu/tree_plugin.h:1250
#2 0xffffffff811cfa9f in rcutree_affinity_setting (outgoing=3, cpu=3) at kernel/rcu/tree.c:4297
#3 rcutree_offline_cpu (cpu=3) at kernel/rcu/tree.c:4341
#4 0xffffffff810c4e6f in cpuhp_invoke_callback (cpu=cpu@entry=3, state=state@entry=CPUHP_AP_RCUTREE_ONLINE,
bringup=bringup@entry=false, node=<optimized out>, lastp=lastp@entry=0xffff88815b027568) at kernel/cpu.c:192
#5 0xffffffff810c6e24 in cpuhp_thread_fun (cpu=<optimized out>) at kernel/cpu.c:785
#6 0xffffffff8111784e in smpboot_thread_fn (data=0xffff88810014c3c0) at kernel/smpboot.c:164
#7 0xffffffff8110c88e in kthread (_create=0xffff8881009b8b00) at kernel/kthread.c:376
#8 0xffffffff81002902 in ret_from_fork () at arch/x86/entry/entry_64.S:306
#9 0x0000000000000000 in ?? ()
(gdb) p/x *0xffff888100ce7cd0
$1 = 0x7
2) rcutree_dead_cpu()
#0 set_cpus_allowed_ptr (p=p@entry=0xffff888100bd9cc0, new_mask=new_mask@entry=0xffff888109fc7948)
at kernel/sched/core.c:2939
#1 0xffffffff811be169 in rcu_boost_kthread_setaffinity (rnp=0xffffffff837a4c00 <rcu_state>,
outgoingcpu=outgoingcpu@entry=-1) at kernel/rcu/tree_plugin.h:1250
#2 0xffffffff811cf4a1 in rcutree_dead_cpu (cpu=3) at kernel/rcu/tree.c:4176
#3 0xffffffff810c4e6f in cpuhp_invoke_callback (cpu=cpu@entry=3, state=CPUHP_RCUTREE_PREP, bringup=bringup@entry=false,
node=node@entry=0x0 <fixed_percpu_data>, lastp=lastp@entry=0x0 <fixed_percpu_data>) at kernel/cpu.c:192
#4 0xffffffff810c58f5 in cpuhp_invoke_callback_range (bringup=bringup@entry=false, cpu=cpu@entry=3,
st=st@entry=0xffff88815b027540, target=target@entry=CPUHP_OFFLINE) at kernel/cpu.c:675
#5 0xffffffff827a5f6a in cpuhp_down_callbacks (target=CPUHP_OFFLINE, st=0xffff88815b027540, cpu=3) at kernel/cpu.c:1170
#6 _cpu_down (cpu=cpu@entry=3, tasks_frozen=tasks_frozen@entry=0, target=target@entry=CPUHP_OFFLINE) at kernel/cpu.c:1170
#7 0xffffffff810c6ff8 in cpu_down_maps_locked (target=CPUHP_OFFLINE, cpu=3) at kernel/cpu.c:1202
#8 cpu_down (cpu=3, target=target@entry=CPUHP_OFFLINE) at kernel/cpu.c:1210
#9 0xffffffff810c7906 in cpu_device_down (dev=dev@entry=0xffff88815b026988) at kernel/cpu.c:1227
(gdb) p/x *0xffff888109fc7948
$2 = 0x7
As can be seen from the above, we have set the same cpumask twice for the same boost kthreads.
Thanks
Zqiang
>Thanks
>Zqiang
>
> Thanx, paul
> ---
> kernel/rcu/tree.c | 5 -----
> 1 file changed, 5 deletions(-)
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 65f3dd2fd3ae..20de83ed0c7e 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -4122,15 +4122,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
> */
> int rcutree_dead_cpu(unsigned int cpu)
> {
> - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
> - struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
> -
> if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
> return 0;
>
> WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
> - /* Adjust any no-longer-needed kthreads. */
> - rcu_boost_kthread_setaffinity(rnp, -1);
> // Stop-machine done, so allow nohz_full to disable tick.
> tick_dep_clear(TICK_DEP_BIT_RCU);
> return 0;
> --
> 2.25.1
>
