[PATCH v6 0/2] sched/fair: Scan cluster before scanning LLC in wake-up path

[PATCH v6 0/2] sched/fair: Scan cluster before scanning LLC in wake-up path

[Yicong Yang]

From: Yicong Yang <yangyicong@hisilicon.com>

This is the follow-up work to support cluster scheduler. Previously
we have added cluster level in the scheduler for both ARM64[1] and
X86[2] to support load balance between clusters to bring more memory
bandwidth and decrease cache contention. This patchset, on the other
hand, takes care of wake-up path by giving CPUs within the same cluster
a try before scanning the whole LLC to benefit those tasks communicating
with each other.

[1] 778c558f49a2 ("sched: Add cluster scheduler level in core and related Kconfig for ARM64")
[2] 66558b730f25 ("sched: Add cluster scheduler level for x86")

Change since v5:
- Improve patch 2 according to Peter's suggestion:
  - use sched_cluster_active to indicate whether cluster is active
  - consider SMT case and use wrap iteration when scanning cluster
- Add Vincent's tag
Thanks.
Link: https://lore.kernel.org/lkml/20220720081150.22167-1-yangyicong@hisilicon.com/

Change since v4:
- rename cpus_share_resources to cpus_share_lowest_cache to be more informative, per Tim
- return -1 when nr==0 in scan_cluster(), per Abel
Thanks!
Link: https://lore.kernel.org/lkml/20220609120622.47724-1-yangyicong@hisilicon.com/

Change since v3:
- fix compile error when !CONFIG_SCHED_CLUSTER, reported by lkp test.
Link: https://lore.kernel.org/lkml/20220608095758.60504-1-yangyicong@hisilicon.com/

Change since v2:
- leverage SIS_PROP to suspend redundant scanning when LLC is overloaded
- remove the ping-pong suppression
- address the comment from Tim, thanks.
Link: https://lore.kernel.org/lkml/20220126080947.4529-1-yangyicong@hisilicon.com/

Change since v1:
- regain the performance data based on v5.17-rc1
- rename cpus_share_cluster to cpus_share_resources per Vincent and Gautham, thanks!
Link: https://lore.kernel.org/lkml/20211215041149.73171-1-yangyicong@hisilicon.com/

Barry Song (2):
  sched: Add per_cpu cluster domain info and cpus_share_lowest_cache API
  sched/fair: Scan cluster before scanning LLC in wake-up path

 include/linux/sched/sd_flags.h |  7 +++++++
 include/linux/sched/topology.h |  8 +++++++-
 kernel/sched/core.c            | 12 ++++++++++++
 kernel/sched/fair.c            | 31 ++++++++++++++++++++++++++++---
 kernel/sched/sched.h           |  4 ++++
 kernel/sched/topology.c        | 25 +++++++++++++++++++++++++
 6 files changed, 83 insertions(+), 4 deletions(-)

-- 
2.24.0

[PATCH v6 1/2] sched: Add per_cpu cluster domain info and cpus_share_lowest_cache API

[Yicong Yang]

From: Barry Song <song.bao.hua@hisilicon.com>

Add per-cpu cluster domain info and cpus_share_lowest_cache() API.
This is the preparation for the optimization of select_idle_cpu()
on platforms with cluster scheduler level.

Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/linux/sched/sd_flags.h |  7 +++++++
 include/linux/sched/topology.h |  8 +++++++-
 kernel/sched/core.c            | 12 ++++++++++++
 kernel/sched/sched.h           |  2 ++
 kernel/sched/topology.c        | 15 +++++++++++++++
 5 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 57bde66d95f7..42ed454e8b18 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -109,6 +109,13 @@ SD_FLAG(SD_ASYM_CPUCAPACITY_FULL, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
  */
 SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
+/*
+ * Domain members share CPU cluster (LLC tags or L2 cache)
+ *
+ * NEEDS_GROUPS: Clusters are shared between groups.
+ */
+SD_FLAG(SD_CLUSTER, SDF_NEEDS_GROUPS)
+
 /*
  * Domain members share CPU package resources (i.e. caches)
  *
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 816df6cc444e..c0d21667ddf3 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -45,7 +45,7 @@ static inline int cpu_smt_flags(void)
 #ifdef CONFIG_SCHED_CLUSTER
 static inline int cpu_cluster_flags(void)
 {
-	return SD_SHARE_PKG_RESOURCES;
+	return SD_CLUSTER | SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
@@ -179,6 +179,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
 bool cpus_share_cache(int this_cpu, int that_cpu);
+bool cpus_share_lowest_cache(int this_cpu, int that_cpu);
 
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
@@ -232,6 +233,11 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 	return true;
 }
 
+static inline bool cpus_share_lowest_cache(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 #endif	/* !CONFIG_SMP */
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a463dbc92fcd..96109ad82694 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3802,6 +3802,18 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
+/*
+ * Whether CPUs are share lowest cache, which means LLC on non-cluster
+ * machines and LLC tag or L2 on machines with clusters.
+ */
+bool cpus_share_lowest_cache(int this_cpu, int that_cpu)
+{
+	if (this_cpu == that_cpu)
+		return true;
+
+	return per_cpu(sd_lowest_cache_id, this_cpu) == per_cpu(sd_lowest_cache_id, that_cpu);
+}
+
 static inline bool ttwu_queue_cond(int cpu)
 {
 	/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 73ae32898f25..845cd029d572 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1802,7 +1802,9 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
+DECLARE_PER_CPU(int, sd_lowest_cache_id);
 DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_cluster);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8739c2a5a54e..8ab27c0d6d1f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -664,6 +664,8 @@ static void destroy_sched_domains(struct sched_domain *sd)
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(int, sd_lowest_cache_id);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_cluster);
 DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
@@ -689,6 +691,18 @@ static void update_top_cache_domain(int cpu)
 	per_cpu(sd_llc_id, cpu) = id;
 	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
 
+	sd = lowest_flag_domain(cpu, SD_CLUSTER);
+	if (sd)
+		id = cpumask_first(sched_domain_span(sd));
+	rcu_assign_pointer(per_cpu(sd_cluster, cpu), sd);
+
+	/*
+	 * This assignment should be placed after the sd_llc_id as
+	 * we want this id equals to cluster id on cluster machines
+	 * but equals to LLC id on non-Cluster machines.
+	 */
+	per_cpu(sd_lowest_cache_id, cpu) = id;
+
 	sd = lowest_flag_domain(cpu, SD_NUMA);
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
 
@@ -1532,6 +1546,7 @@ static struct cpumask		***sched_domains_numa_masks;
  */
 #define TOPOLOGY_SD_FLAGS		\
 	(SD_SHARE_CPUCAPACITY	|	\
+	 SD_CLUSTER		|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING)
-- 
2.24.0

[PATCH v6 2/2] sched/fair: Scan cluster before scanning LLC in wake-up path

[Yicong Yang]

From: Barry Song <song.bao.hua@hisilicon.com>

For platforms having clusters like Kunpeng920, CPUs within the same cluster
have lower latency when synchronizing and accessing shared resources like
cache. Thus, this patch tries to find an idle cpu within the cluster of the
target CPU before scanning the whole LLC to gain lower latency.

Testing has been done on Kunpeng920 by pinning tasks to one numa and two
numa. On Kunpeng920, Each numa has 8 clusters and each cluster has 4 CPUs.

With this patch, We noticed enhancement on tbench within one numa or cross
two numa.

On numa 0:
                     tip/sched/core                 patched
Hmean     1        345.89 (   0.00%)      398.43 *  15.19%*
Hmean     2        697.77 (   0.00%)      794.40 *  13.85%*
Hmean     4       1392.51 (   0.00%)     1577.60 *  13.29%*
Hmean     8       2800.61 (   0.00%)     3118.38 *  11.35%*
Hmean     16      5514.27 (   0.00%)     6124.51 *  11.07%*
Hmean     32     10869.81 (   0.00%)    10690.97 *  -1.65%*
Hmean     64      8315.22 (   0.00%)     8520.73 *   2.47%*
Hmean     128     6324.47 (   0.00%)     7253.65 *  14.69%*

On numa 0-1:
                     tip/sched/core                 patched
Hmean     1        348.68 (   0.00%)      397.74 *  14.07%*
Hmean     2        693.57 (   0.00%)      795.54 *  14.70%*
Hmean     4       1369.26 (   0.00%)     1548.72 *  13.11%*
Hmean     8       2772.99 (   0.00%)     3055.54 *  10.19%*
Hmean     16      4825.83 (   0.00%)     5936.64 *  23.02%*
Hmean     32     10250.32 (   0.00%)    11780.59 *  14.93%*
Hmean     64     16309.51 (   0.00%)    19864.38 *  21.80%*
Hmean     128    13022.32 (   0.00%)    16365.43 *  25.67%*
Hmean     256    11335.79 (   0.00%)    13991.33 *  23.43%*

Note neither Kunpeng920 nor x86 Jacobsville supports SMT, so the SMT branch
in the code has not been tested but it supposed to work.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
[https://lore.kernel.org/lkml/Ytfjs+m1kUs0ScSn@worktop.programming.kicks-ass.net]
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 kernel/sched/fair.c     | 31 ++++++++++++++++++++++++++++---
 kernel/sched/sched.h    |  2 ++
 kernel/sched/topology.c | 10 ++++++++++
 3 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2fc47257ae91..1100fbf7baaf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6437,6 +6437,31 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 		}
 	}
 
+	if (IS_ENABLED(CONFIG_SCHED_CLUSTER) &&
+	    static_branch_unlikely(&sched_cluster_active)) {
+		struct sched_domain *sdc = rcu_dereference(per_cpu(sd_cluster, target));
+
+		if (sdc) {
+			for_each_cpu_wrap(cpu, sched_domain_span(sdc), target + 1) {
+				if (!cpumask_test_cpu(cpu, cpus))
+					continue;
+
+				if (has_idle_core) {
+					i = select_idle_core(p, cpu, cpus, &idle_cpu);
+					if ((unsigned int)i < nr_cpumask_bits)
+						return i;
+				} else {
+					if (--nr <= 0)
+						return -1;
+					idle_cpu = __select_idle_cpu(cpu, p);
+					if ((unsigned int)idle_cpu < nr_cpumask_bits)
+						return idle_cpu;
+				}
+			}
+			cpumask_andnot(cpus, cpus, sched_domain_span(sdc));
+		}
+	}
+
 	for_each_cpu_wrap(cpu, cpus, target + 1) {
 		if (has_idle_core) {
 			i = select_idle_core(p, cpu, cpus, &idle_cpu);
@@ -6444,7 +6469,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 				return i;
 
 		} else {
-			if (!--nr)
+			if (--nr <= 0)
 				return -1;
 			idle_cpu = __select_idle_cpu(cpu, p);
 			if ((unsigned int)idle_cpu < nr_cpumask_bits)
@@ -6543,7 +6568,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
-	if (prev != target && cpus_share_cache(prev, target) &&
+	if (prev != target && cpus_share_lowest_cache(prev, target) &&
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
 	    asym_fits_capacity(task_util, prev))
 		return prev;
@@ -6569,7 +6594,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	p->recent_used_cpu = prev;
 	if (recent_used_cpu != prev &&
 	    recent_used_cpu != target &&
-	    cpus_share_cache(recent_used_cpu, target) &&
+	    cpus_share_lowest_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
 	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
 	    asym_fits_capacity(task_util, recent_used_cpu)) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 845cd029d572..4f0d3a74a532 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1808,7 +1808,9 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_cluster);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
+
 extern struct static_key_false sched_asym_cpucapacity;
+extern struct static_key_false sched_cluster_active;
 
 struct sched_group_capacity {
 	atomic_t		ref;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8ab27c0d6d1f..04ead3227201 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -670,7 +670,9 @@ DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
+
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
+DEFINE_STATIC_KEY_FALSE(sched_cluster_active);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -2268,6 +2270,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
 	bool has_asym = false;
+	bool has_cluster = false;
 
 	if (WARN_ON(cpumask_empty(cpu_map)))
 		goto error;
@@ -2289,6 +2292,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 
 			has_asym |= sd->flags & SD_ASYM_CPUCAPACITY;
+			has_cluster |= sd->flags & SD_CLUSTER;
 
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
@@ -2399,6 +2403,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	if (has_asym)
 		static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
 
+	if (has_cluster)
+		static_branch_inc_cpuslocked(&sched_cluster_active);
+
 	if (rq && sched_debug_verbose) {
 		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
 			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
@@ -2498,6 +2505,9 @@ static void detach_destroy_domains(const struct cpumask *cpu_map)
 	if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
 		static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
 
+	if (rcu_access_pointer(per_cpu(sd_cluster, cpu)))
+		static_branch_dec_cpuslocked(&sched_cluster_active);
+
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);
-- 
2.24.0