Re: [PATCH v3 rcu 3/3] rcu: Finer-grained grace-period-end checks in rcu_dump_cpu_stacks()

On Wed, 2024-10-30 at 06:54 -0700, Paul E. McKenney wrote: > > > Alternatively, arm64 could continue using nmi_trigger_cpumask_backtrace() > > > with normal interrupts (for example, on SoCs not implementing true NMIs), > > > but have a short timeout (maybe a few jiffies?) after which its returns >

Re: [PATCH v3 rcu 3/3] rcu: Finer-grained grace-period-end checks in rcu_dump_cpu_stacks()

On Thu, 2024-10-31 at 14:27 -0700, Doug Anderson wrote: > Hi, > > On Wed, Oct 30, 2024 at 10:03 PM Paul E. McKenney wrote: > > > > > > > Note that: > > > > > > > > > > * Switching to real NMIs is impossible on many existing arm64 CPUs. > > > > > The hardware support simply isn't there. Pseudo-N

Re: [PATCH v3 rcu 3/3] rcu: Finer-grained grace-period-end checks in rcu_dump_cpu_stacks()

On Tue, 2024-10-29 at 09:29 -0700, Paul E. McKenney wrote: > External email : Please do not click links or open attachments until you have > verified the sender or the content. > > > On Tue, Oct 29, 2024 at 02:20:51AM +, Cheng-Jui Wang (王正睿) wrote: > > On Mon, 2024

Re: [PATCH v3 rcu 3/3] rcu: Finer-grained grace-period-end checks in rcu_dump_cpu_stacks()

On Mon, 2024-10-28 at 17:22 -0700, Paul E. McKenney wrote: > The result is that the current leaf rcu_node structure's ->lock is > acquired only if a stack backtrace might be needed from the current CPU, > and is held across only that CPU's backtrace. As a result, if there are After upgrading our d