diff mbox series

[2/8] sched/topology: introduce sched_numa_find_next_cpu()

Message ID 20230325185514.425745-3-yury.norov@gmail.com
State New
Headers
Series sched/topology: add for_each_numa_cpu() macro |

Commit Message

Yury Norov March 25, 2023, 6:55 p.m. UTC 
  The function searches for the next CPU in a given cpumask according to
NUMA topology, so that it traverses cpus per-hop.

If the CPU is the last cpu in a given hop, sched_numa_find_next_cpu()
switches to the next hop, and picks the first CPU from there, excluding
those already traversed.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/topology.h |  7 +++++++
 kernel/sched/topology.c  | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

Comments

Andy Shevchenko March 27, 2023, 10:28 a.m. UTC | #1 
On Sat, Mar 25, 2023 at 11:55:08AM -0700, Yury Norov wrote:
> The function searches for the next CPU in a given cpumask according to
> NUMA topology, so that it traverses cpus per-hop.
> 
> If the CPU is the last cpu in a given hop, sched_numa_find_next_cpu()
> switches to the next hop, and picks the first CPU from there, excluding
> those already traversed.

...

> +/*

Hmm... Is it deliberately not a kernel doc?

> + * sched_numa_find_next_cpu() - given the NUMA topology, find the next cpu
> + * cpumask: cpumask to find a cpu from
> + * cpu: current cpu
> + * node: local node
> + * hop: (in/out) indicates distance order of current CPU to a local node
> + *
> + * The function searches for next cpu at a given NUMA distance, indicated
> + * by hop, and if nothing found, tries to find CPUs at a greater distance,
> + * starting from the beginning.
> + *
> + * returns: cpu, or >= nr_cpu_ids when nothing found.
> + */
Yury Norov April 10, 2023, 6 p.m. UTC | #2 
On Mon, Mar 27, 2023 at 01:28:12PM +0300, Andy Shevchenko wrote:
> On Sat, Mar 25, 2023 at 11:55:08AM -0700, Yury Norov wrote:
> > The function searches for the next CPU in a given cpumask according to
> > NUMA topology, so that it traverses cpus per-hop.
> > 
> > If the CPU is the last cpu in a given hop, sched_numa_find_next_cpu()
> > switches to the next hop, and picks the first CPU from there, excluding
> > those already traversed.
> 
> ...
> 
> > +/*
> 
> Hmm... Is it deliberately not a kernel doc?

Yes, I'd prefer to encourage people to use for_each() approach instead
of calling it directly.

If there will be a good reason to make it a more self-consistent thing,
we'll have to add a wrapper, just like sched_numa_find_nth_cpu() is
wrapped with cpumask_local_spread(). Particularly, use RCU lock/unlock
and properly handle NUMA_NO_NODE.
 
> > + * sched_numa_find_next_cpu() - given the NUMA topology, find the next cpu
> > + * cpumask: cpumask to find a cpu from
> > + * cpu: current cpu
> > + * node: local node
> > + * hop: (in/out) indicates distance order of current CPU to a local node
> > + *
> > + * The function searches for next cpu at a given NUMA distance, indicated
> > + * by hop, and if nothing found, tries to find CPUs at a greater distance,
> > + * starting from the beginning.
> > + *
> > + * returns: cpu, or >= nr_cpu_ids when nothing found.
> > + */
> 
> -- 
> With Best Regards,
> Andy Shevchenko
>
diff mbox series

Patch

diff --git a/include/linux/topology.h b/include/linux/topology.h
index fea32377f7c7..4a63154fa036 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -247,6 +247,7 @@  static inline const struct cpumask *cpu_cpu_mask(int cpu)
 
 #ifdef CONFIG_NUMA
 int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node);
+int sched_numa_find_next_cpu(const struct cpumask *cpus, int cpu, int node, unsigned int *hop);
 extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops);
 #else
 static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
@@ -254,6 +255,12 @@  static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, i
 	return cpumask_nth(cpu, cpus);
 }
 
+static __always_inline
+int sched_numa_find_next_cpu(const struct cpumask *cpus, int cpu, int node, unsigned int *hop)
+{
+	return find_next_bit(cpumask_bits(cpus), small_cpumask_bits, cpu);
+}
+
 static inline const struct cpumask *
 sched_numa_hop_mask(unsigned int node, unsigned int hops)
 {
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 051aaf65c749..1860d9487fe1 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2130,6 +2130,45 @@  int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
 }
 EXPORT_SYMBOL_GPL(sched_numa_find_nth_cpu);
 
+/*
+ * sched_numa_find_next_cpu() - given the NUMA topology, find the next cpu
+ * cpumask: cpumask to find a cpu from
+ * cpu: current cpu
+ * node: local node
+ * hop: (in/out) indicates distance order of current CPU to a local node
+ *
+ * The function searches for next cpu at a given NUMA distance, indicated
+ * by hop, and if nothing found, tries to find CPUs at a greater distance,
+ * starting from the beginning.
+ *
+ * returns: cpu, or >= nr_cpu_ids when nothing found.
+ */
+int sched_numa_find_next_cpu(const struct cpumask *cpus, int cpu, int node, unsigned int *hop)
+{
+	unsigned long *cur, *prev;
+	struct cpumask ***masks;
+	unsigned int ret;
+
+	if (*hop >= sched_domains_numa_levels)
+		return nr_cpu_ids;
+
+	masks = rcu_dereference(sched_domains_numa_masks);
+	cur = cpumask_bits(masks[*hop][node]);
+	if (*hop == 0)
+		ret = find_next_and_bit(cpumask_bits(cpus), cur, nr_cpu_ids, cpu);
+	else {
+		prev = cpumask_bits(masks[*hop - 1][node]);
+		ret = find_next_and_andnot_bit(cpumask_bits(cpus), cur, prev, nr_cpu_ids, cpu);
+	}
+
+	if (ret < nr_cpu_ids)
+		return ret;
+
+	*hop += 1;
+	return sched_numa_find_next_cpu(cpus, 0, node, hop);
+}
+EXPORT_SYMBOL_GPL(sched_numa_find_next_cpu);
+
 /**
  * sched_numa_hop_mask() - Get the cpumask of CPUs at most @hops hops away from
  *                         @node