Re: [PATCH 2/3] nohz: Ensure full dynticks CPUs are RCU nocbs

From: Paul E. McKenney
Date: Wed Apr 17 2013 - 15:59:28 EST


On Wed, Apr 17, 2013 at 06:24:48PM +0200, Frederic Weisbecker wrote:
> We need full dynticks CPU to also be RCU nocb so
> that we don't have to keep the tick to handle RCU
> callbacks.
>
> Make sure the range passed to nohz_full= boot
> parameter is a subset of rcu_nocbs=
>
> The CPUs that fail to meet this requirement will be
> excluded from the nohz_full range. This is checked
> early in boot time, before any CPU has the opportunity
> to stop its tick.
>
> Suggested-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Chris Metcalf <cmetcalf@xxxxxxxxxx>
> Cc: Christoph Lameter <cl@xxxxxxxxx>
> Cc: Geoff Levand <geoff@xxxxxxxxxxxxx>
> Cc: Gilad Ben Yossef <gilad@xxxxxxxxxxxxx>
> Cc: Hakan Akkan <hakanakkan@xxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Cc: Kevin Hilman <khilman@xxxxxxxxxx>
> Cc: Li Zhong <zhong@xxxxxxxxxxxxxxxxxx>
> Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
> Cc: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

Reviewed-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>

(And again, also updated documentation.)

> ---
> Documentation/kernel-parameters.txt | 2 ++
> include/linux/rcupdate.h | 7 +++++++
> include/linux/tick.h | 2 ++
> init/main.c | 1 +
> kernel/rcutree.c | 6 +++---
> kernel/rcutree.h | 1 -
> kernel/rcutree_plugin.h | 13 ++++---------
> kernel/time/tick-sched.c | 22 ++++++++++++++++------
> 8 files changed, 35 insertions(+), 19 deletions(-)
>
> diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
> index 887b297..4865e9b 100644
> --- a/Documentation/kernel-parameters.txt
> +++ b/Documentation/kernel-parameters.txt
> @@ -1918,6 +1918,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
> the specified list of CPUs whose tick will be stopped
> whenever possible. The boot CPU will be forced outside
> the range to maintain the timekeeping.
> + The CPUs in this range must also be included in the
> + rcu_nocbs= set.
>
> noiotrap [SH] Disables trapped I/O port accesses.
>
> diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
> index b758ce1..8e0948c 100644
> --- a/include/linux/rcupdate.h
> +++ b/include/linux/rcupdate.h
> @@ -999,4 +999,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
> #define kfree_rcu(ptr, rcu_head) \
> __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
>
> +#ifdef CONFIG_RCU_NOCB_CPU
> +extern bool rcu_is_nocb_cpu(int cpu);
> +#else
> +static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
> +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
> +
> +
> #endif /* __LINUX_RCUPDATE_H */
> diff --git a/include/linux/tick.h b/include/linux/tick.h
> index b4e3b0c..0b6873c 100644
> --- a/include/linux/tick.h
> +++ b/include/linux/tick.h
> @@ -158,8 +158,10 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
> # endif /* !CONFIG_NO_HZ_COMMON */
>
> #ifdef CONFIG_NO_HZ_FULL
> +extern void tick_nohz_init(void);
> extern int tick_nohz_full_cpu(int cpu);
> #else
> +static inline void tick_nohz_init(void) { }
> static inline int tick_nohz_full_cpu(int cpu) { return 0; }
> #endif
>
> diff --git a/init/main.c b/init/main.c
> index 63534a1..2acb5bb 100644
> --- a/init/main.c
> +++ b/init/main.c
> @@ -547,6 +547,7 @@ asmlinkage void __init start_kernel(void)
> idr_init_cache();
> perf_event_init();
> rcu_init();
> + tick_nohz_init();
> radix_tree_init();
> /* init some links before init_ISA_irqs() */
> early_irq_init();
> diff --git a/kernel/rcutree.c b/kernel/rcutree.c
> index f5ab502..1d4ceff 100644
> --- a/kernel/rcutree.c
> +++ b/kernel/rcutree.c
> @@ -1695,7 +1695,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
> struct rcu_node *rnp, struct rcu_data *rdp)
> {
> /* No-CBs CPUs do not have orphanable callbacks. */
> - if (is_nocb_cpu(rdp->cpu))
> + if (rcu_is_nocb_cpu(rdp->cpu))
> return;
>
> /*
> @@ -2757,10 +2757,10 @@ static void _rcu_barrier(struct rcu_state *rsp)
> * corresponding CPU's preceding callbacks have been invoked.
> */
> for_each_possible_cpu(cpu) {
> - if (!cpu_online(cpu) && !is_nocb_cpu(cpu))
> + if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu))
> continue;
> rdp = per_cpu_ptr(rsp->rda, cpu);
> - if (is_nocb_cpu(cpu)) {
> + if (rcu_is_nocb_cpu(cpu)) {
> _rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
> rsp->n_barrier_done);
> atomic_inc(&rsp->barrier_cpu_count);
> diff --git a/kernel/rcutree.h b/kernel/rcutree.h
> index f993c0a..38acc49 100644
> --- a/kernel/rcutree.h
> +++ b/kernel/rcutree.h
> @@ -529,7 +529,6 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
> static void print_cpu_stall_info_end(void);
> static void zero_cpu_stall_ticks(struct rcu_data *rdp);
> static void increment_cpu_stall_ticks(void);
> -static bool is_nocb_cpu(int cpu);
> static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
> bool lazy);
> static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
> diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
> index a5745e9..0cd91cc 100644
> --- a/kernel/rcutree_plugin.h
> +++ b/kernel/rcutree_plugin.h
> @@ -2167,7 +2167,7 @@ static int __init parse_rcu_nocb_poll(char *arg)
> early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
>
> /* Is the specified CPU a no-CPUs CPU? */
> -static bool is_nocb_cpu(int cpu)
> +bool rcu_is_nocb_cpu(int cpu)
> {
> if (have_rcu_nocb_mask)
> return cpumask_test_cpu(cpu, rcu_nocb_mask);
> @@ -2225,7 +2225,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
> bool lazy)
> {
>
> - if (!is_nocb_cpu(rdp->cpu))
> + if (!rcu_is_nocb_cpu(rdp->cpu))
> return 0;
> __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
> return 1;
> @@ -2242,7 +2242,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
> long qll = rsp->qlen_lazy;
>
> /* If this is not a no-CBs CPU, tell the caller to do it the old way. */
> - if (!is_nocb_cpu(smp_processor_id()))
> + if (!rcu_is_nocb_cpu(smp_processor_id()))
> return 0;
> rsp->qlen = 0;
> rsp->qlen_lazy = 0;
> @@ -2282,7 +2282,7 @@ static bool nocb_cpu_expendable(int cpu)
> * If there are no no-CB CPUs or if this CPU is not a no-CB CPU,
> * then offlining this CPU is harmless. Let it happen.
> */
> - if (!have_rcu_nocb_mask || is_nocb_cpu(cpu))
> + if (!have_rcu_nocb_mask || rcu_is_nocb_cpu(cpu))
> return 1;
>
> /* If no memory, play it safe and keep the CPU around. */
> @@ -2464,11 +2464,6 @@ static void __init rcu_init_nocb(void)
>
> #else /* #ifdef CONFIG_RCU_NOCB_CPU */
>
> -static bool is_nocb_cpu(int cpu)
> -{
> - return false;
> -}
> -
> static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
> bool lazy)
> {
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index 2bac5ea..d71a5f2 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -203,17 +203,27 @@ static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb,
> */
> static char __initdata nohz_full_buf[NR_CPUS + 1];
>
> -static int __init init_tick_nohz_full(void)
> +void __init tick_nohz_init(void)
> {
> - if (have_nohz_full_mask)
> - cpu_notifier(tick_nohz_cpu_down_callback, 0);
> + int cpu;
> +
> + if (!have_nohz_full_mask)
> + return;
> +
> + cpu_notifier(tick_nohz_cpu_down_callback, 0);
> +
> + /* Make sure full dynticks CPU are also RCU nocbs */
> + for_each_cpu(cpu, nohz_full_mask) {
> + if (!rcu_is_nocb_cpu(cpu)) {
> + pr_warning("NO_HZ: CPU %d is not RCU nocb: "
> + "cleared from nohz_full range", cpu);
> + cpumask_clear_cpu(cpu, nohz_full_mask);
> + }
> + }
>
> cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask);
> pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf);
> -
> - return 0;
> }
> -core_initcall(init_tick_nohz_full);
> #else
> #define have_nohz_full_mask (0)
> #endif
> --
> 1.7.5.4
>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/