[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Yl36+skjQn26Mg43@google.com>
Date: Mon, 18 Apr 2022 16:57:46 -0700
From: Kalesh Singh <kaleshsingh@...gle.com>
To: "Joel Fernandes (Google)" <joel@...lfernandes.org>
Cc: linux-kernel@...r.kernel.org,
Josh Triplett <josh@...htriplett.org>,
Lai Jiangshan <jiangshanlai@...il.com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
"Paul E. McKenney" <paulmck@...nel.org>, rcu@...r.kernel.org,
Steven Rostedt <rostedt@...dmis.org>,
rushikesh.s.kadam@...el.com, vineethrp@...il.com, urezki@...il.com
Subject: Re: [PATCH v4] rcu/nocb: Add an option to offload all CPUs on boot
On Mon, Apr 18, 2022 at 05:54:03PM +0000, Joel Fernandes (Google) wrote:
> From: Joel Fernandes <joel@...lfernandes.org>
>
> On systems with CONFIG_RCU_NOCB_CPU=y, there is no default mask provided
> which ends up not offloading any CPU. This patch removes a dependency
> from the bootloader having to know about RCU and about how to provide
> the mask.
>
> With the new option enabled, all CPUs will be offloaded on boot unless
> rcu_nocbs= or rcu_nohz_full= kernel parameters provide a CPU list.
>
> Signed-off-by: Joel Fernandes <joel@...lfernandes.org>
Hi Joel,
You can add Reviewed-by: Kalesh Singh <kaleshsingh@...gle.com>
Thanks,
Kalesh
> ---
> v4: mostly style related fixes.
> v3 is back to v1 but with a config option defaulting to 'n'.
> v2 was forcing the option to override no_cbs=
>
> Documentation/admin-guide/kernel-parameters.txt | 6 ++++++
> kernel/rcu/Kconfig | 13 +++++++++++++
> kernel/rcu/tree_nocb.h | 15 ++++++++++++++-
> 3 files changed, 33 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index f5a27f067db9..4beb15ccac1a 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -3506,6 +3506,9 @@
> just as if they had also been called out in the
> rcu_nocbs= boot parameter.
>
> + Note that this argument takes precedence over
> + the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
> +
> noiotrap [SH] Disables trapped I/O port accesses.
>
> noirqdebug [X86-32] Disables the code which attempts to detect and
> @@ -4398,6 +4401,9 @@
> no-callback mode from boot but the mode may be
> toggled at runtime via cpusets.
>
> + Note that this argument takes precedence over
> + the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
> +
> rcu_nocb_poll [KNL]
> Rather than requiring that offloaded CPUs
> (specified by rcu_nocbs= above) explicitly
> diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
> index bf8e341e75b4..746a668bf81d 100644
> --- a/kernel/rcu/Kconfig
> +++ b/kernel/rcu/Kconfig
> @@ -223,6 +223,19 @@ config RCU_NOCB_CPU
> Say Y here if you need reduced OS jitter, despite added overhead.
> Say N here if you are unsure.
>
> +config RCU_NOCB_CPU_DEFAULT_ALL
> + bool "Offload RCU callback processing from all CPUs by default"
> + depends on RCU_NOCB_CPU
> + default n
> + help
> + Use this option to offload callback processing from all CPUs
> + by default, in the absence of the rcu_nocbs or nohz_full boot
> + parameter. This also avoids the need to use any boot parameters
> + to achieve the effect of offloading all CPUs on boot.
> +
> + Say Y here if you want offload all CPUs by default on boot.
> + Say N here if you are unsure.
> +
> config TASKS_TRACE_RCU_READ_MB
> bool "Tasks Trace RCU readers use memory barriers in user and idle"
> depends on RCU_EXPERT
> diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
> index eeafb546a7a0..f648f773600a 100644
> --- a/kernel/rcu/tree_nocb.h
> +++ b/kernel/rcu/tree_nocb.h
> @@ -1166,11 +1166,21 @@ void __init rcu_init_nohz(void)
> {
> int cpu;
> bool need_rcu_nocb_mask = false;
> + bool offload_all = false;
> struct rcu_data *rdp;
>
> +#if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL)
> + if (!rcu_nocb_is_setup) {
> + need_rcu_nocb_mask = true;
> + offload_all = true;
> + }
> +#endif
> +
> #if defined(CONFIG_NO_HZ_FULL)
> - if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask))
> + if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) {
> need_rcu_nocb_mask = true;
> + offload_all = false; /* NO_HZ_FULL has its own mask. */
> + }
> #endif /* #if defined(CONFIG_NO_HZ_FULL) */
>
> if (need_rcu_nocb_mask) {
> @@ -1191,6 +1201,9 @@ void __init rcu_init_nohz(void)
> cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
> #endif /* #if defined(CONFIG_NO_HZ_FULL) */
>
> + if (offload_all)
> + cpumask_setall(rcu_nocb_mask);
> +
> if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
> pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
> cpumask_and(rcu_nocb_mask, cpu_possible_mask,
> --
> 2.36.0.rc0.470.gd361397f0d-goog
>
>
Powered by blists - more mailing lists