[PATCH v2 0/2] sched: Enable preferred SMT siblings on NVIDIA Olympus

NVIDIA Olympus implements SMT with two symmetric processing elements (PEs).
When only one PE is active, the core operates in single-thread mode and
that PE can use the full core resources. When both PEs are active, the core
operates in two-thread mode and the PEs share those resources. This
behavior is common to SMT implementations, but Olympus is particularly
sensitive to brief sibling activations because returning from two-thread
mode to single-thread mode after a sibling becomes idle is not immediate.
As described by commit 293f9611ae735 ("sched/fair: Prefer fully idle cores
for NOHZ balancing"):

  Briefly activating an otherwise idle sibling can reduce the performance
  available to the other sibling and this effect does not necessarily end
  once the activated sibling becomes idle: after the ILB finishes and its
  CPU enters WFI, full single-thread performance is restored only after the
  sibling has remained idle for a qualification interval (10 Ki cycles on
  the tested Vera system).

That change prevents the NOHZ idle load balancer from unnecessarily waking
a sibling of a busy PE. However, ordinary task placement can still select
either sibling of an idle core and repeated changes of the active PE can
keep Olympus cores in two-thread mode despite little or no useful overlap
between the siblings.

This series makes PE0 the preferred sibling of an Olympus core using
SD_ASYM_PACKING and teaches the fair scheduler's idle-selection paths to
honor asymmetric SMT priority. The scheduler first selects an idle core
according to its existing placement and capacity rules, then chooses the
highest-priority available sibling within that core. The generic scheduler
behavior is enabled only when an architecture supplies an SD_ASYM_PACKING
SMT domain.

PE0 and PE1 have equal steady-state capacity, the preference does not
identify a faster PE. PE0 is used only as a canonical choice when both
siblings are available. Consistently selecting the same sibling avoids
alternating the active PE across wakeups, lets PE1 remain idle for longer,
and allows more cores to remain in, or return to, full-resource
single-thread mode.

The series was tested on a two-node Vera system using an 88-thread
single-precision GEMM on the 88 physical cores of NUMA node 0.

With the workload allowed to choose either sibling of every core, observed
throughput improved from approximately 9.4 TFLOP/s on the baseline kernel
to approximately 10.1 TFLOP/s with this series applied. Repeated runs also
became more predictable because the workload consistently settled on PE0
while PE1 remained quiet.

Changes in v2:
 - Clarify that the generic scheduler change also covers POWER7 (Dietmar
   Eggemann)
 - Simplify sched_smt_asym_prefer() by inspecting the lowest scheduling
   domain directly (Dietmar Eggemann)
 - Link to v1: https://lore.kernel.org/r/20260831181800.1668646-1-arighi@nvidia.com

Andrea Righi (2):
  arm64: topology: Prefer PE0 on NVIDIA Olympus SMT cores
  sched/fair: Honor asymmetric SMT priority in idle selection

 arch/arm64/include/asm/topology.h |  1 +
 arch/arm64/kernel/smp.c           |  1 +
 arch/arm64/kernel/topology.c      | 62 ++++++++++++++++++++++++++++++
 kernel/sched/fair.c               | 79 ++++++++++++++++++++++++++++++++++-----
 kernel/sched/sched.h              |  6 +++
 kernel/sched/topology.c           | 36 ++++++++++++++++++
 6 files changed, 176 insertions(+), 9 deletions(-)

NVIDIA Olympus implements spatial SMT with symmetric steady-state PE
capacity but two different resource modes. One-Thread Active mode gives
one PE the full core, while waking the other PE restores Two-Thread
Active mode and partitions decode, issue, cache, TLB, and vector
resources. Returning to full-resource mode requires the sibling to
remain in WFI for 10 Ki cycles.

Measurements show that pinned workloads perform equally on either PE,
but freely migratable workloads lose substantial throughput when they
alternate between PE identities. Consistently selecting PE0 keeps PE1
idle, avoids repeated SMT repartitioning, and restores one-thread-per-core
performance.

Describe this scheduling preference with SD_ASYM_PACKING and give PE0,
identified by MPIDR_EL1.Aff0, the higher arch_asym_cpu_priority(). This is
independent of SD_ASYM_CPUCAPACITY: SMT siblings retain equal capacity,
while physical cores with different maximum frequencies are handled by
a higher scheduling domain.

Firmware currently provides no interface for describing the preferred
SMT sibling. Detect Olympus by MIDR until such an interface is available.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 arch/arm64/include/asm/topology.h |  1 +
 arch/arm64/kernel/smp.c           |  1 +
 arch/arm64/kernel/topology.c      | 62 +++++++++++++++++++++++++++++++
 3 files changed, 64 insertions(+)

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index b9eaf4ad70850..edc1c59b3448d 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h

@@ -18,6 +18,7 @@ int pcibus_to_node(struct pci_bus *bus);
 #include <linux/arch_topology.h>
 
 void update_freq_counters_refs(void);
+void arm64_init_sched_topology(void);
 
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_tick topology_scale_freq_tick

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a61dc3016a117..0135ac4eea8bd 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c

@@ -443,6 +443,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	hyp_mode_check();
 	setup_system_features();
 	setup_user_features();
+	arm64_init_sched_topology();
 	mark_linear_text_alias_ro();
 }
 

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index d28438f8b83f1..0dd9eec1c4946 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c

@@ -19,6 +19,8 @@
 #include <linux/init.h>
 #include <linux/percpu.h>
 #include <linux/sched/isolation.h>
+#include <linux/sched/topology.h>
+#include <linux/smp.h>
 #include <linux/xarray.h>
 
 #include <asm/cpu.h>

@@ -44,6 +46,66 @@
 static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
 static cpumask_var_t amu_fie_cpus;
 
+/*
+ * Switching the active PE on an NVIDIA Olympus SMT core can keep the core in
+ * two-thread active mode, with resources partitioned between the PEs.
+ *
+ * Prefer PE0 so PE1 can remain idle and the core can stay in full-resource
+ * mode. Firmware does not currently describe this preference, so detect
+ * Olympus by MIDR until a firmware interface is available.
+ */
+static bool olympus_prefer_pe0 __ro_after_init;
+
+#ifdef CONFIG_SCHED_SMT
+static int arm64_smt_flags(void)
+{
+	int flags = cpu_smt_flags();
+
+	if (olympus_prefer_pe0)
+		flags |= SD_ASYM_PACKING;
+
+	return flags;
+}
+#endif
+
+static struct sched_domain_topology_level arm64_asym_smt_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	SDTL_INIT(tl_smt_mask, arm64_smt_flags, SMT),
+#endif
+#ifdef CONFIG_SCHED_CLUSTER
+	SDTL_INIT(tl_cls_mask, cpu_cluster_flags, CLS),
+#endif
+#ifdef CONFIG_SCHED_MC
+	SDTL_INIT(tl_mc_mask, cpu_core_flags, MC),
+#endif
+	SDTL_INIT(tl_pkg_mask, NULL, PKG),
+	{ NULL, },
+};
+
+void __init arm64_init_sched_topology(void)
+{
+	if (!IS_ENABLED(CONFIG_SCHED_SMT))
+		return;
+
+	if ((read_cpuid_id() & MIDR_CPU_MODEL_MASK) != MIDR_NVIDIA_OLYMPUS)
+		return;
+
+	if (!topology_core_has_smt(smp_processor_id()))
+		return;
+
+	olympus_prefer_pe0 = true;
+	set_sched_topology(arm64_asym_smt_topology);
+	pr_info("Enabling PE0 SMT preference for NVIDIA Olympus\n");
+}
+
+int arch_asym_cpu_priority(int cpu)
+{
+	if (!olympus_prefer_pe0)
+		return 0;
+
+	return MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 0) == 0;
+}
+
 struct amu_cntr_sample {
 	u64		arch_const_cycles_prev;
 	u64		arch_core_cycles_prev;

-- 
2.55.0

POWER7 and NVIDIA Olympus use SD_ASYM_PACKING at the shared-capacity
SMT level to order hardware threads. Idle CPU selection does not consult
that order, so a task can wake on an arbitrary sibling and remain there
until load balancing corrects the placement. On these systems, that
initial choice can prevent the core from entering its preferred
lower-thread resource mode and cause a large and persistent performance
loss.

When idle selection finds an available CPU in an SMT core, choose the
highest-priority available sibling. On SMT2 Olympus this only changes
selection on fully idle cores. A partially idle core has only one
available CPU. On wider SMT systems such as POWER7, it also fills
available siblings in priority order while the core is partially busy.

Apply the preference to idle-core and idle-CPU scans,
asymmetric-capacity scans, and the target, previous, and recently-used
CPU fast paths. Inspect the lowest scheduling domain directly, but
require both CPUs to share its span because isolcpus can split hardware
siblings across scheduling domains.

Keep physical-core capacity selection independent from SMT sibling
ordering. SD_ASYM_CPUCAPACITY first selects among cores with different
maximum capacities, then SD_ASYM_PACKING selects the preferred available
sibling inside the chosen core, whose siblings continue to share equal
capacity.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/fair.c     | 79 ++++++++++++++++++++++++++++++++++++-----
 kernel/sched/sched.h    |  6 ++++
 kernel/sched/topology.c | 36 +++++++++++++++++++
 3 files changed, 112 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b8bd308c2d5b1..ff9a7b1fcbe7f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c

@@ -8587,6 +8587,63 @@ static inline bool test_idle_cores(int cpu)
 	return false;
 }
 
+/*
+ * Return true when @cpu has a higher asymmetric-packing priority than
+ * @other in their shared SMT scheduling domain.
+ */
+static bool sched_smt_asym_prefer(int cpu, int other)
+{
+	struct sched_domain *sd = rcu_dereference_all(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return false;
+
+	if (!(sd->flags & SD_SHARE_CPUCAPACITY) ||
+	    !(sd->flags & SD_ASYM_PACKING))
+		return false;
+
+	if (!cpumask_test_cpu(other, sched_domain_span(sd)))
+		return false;
+
+	return sched_asym_prefer(cpu, other);
+}
+
+/*
+ * Return the highest-priority available CPU in @cpu's SMT core that is also in @cpus.
+ */
+static int __select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	int best = cpu;
+	int sibling;
+
+	for_each_cpu_and(sibling, cpu_smt_mask(cpu), cpus) {
+		if (sibling == best || !choose_idle_cpu(sibling, p))
+			continue;
+
+		if (sched_smt_asym_prefer(sibling, best))
+			best = sibling;
+	}
+
+	return best;
+}
+
+static inline int
+select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	if (!sched_smt_asym_active())
+		return cpu;
+
+	return __select_idle_smt_cpu(p, cpu, cpus);
+}
+
+/*
+ * Redirect an available SMT CPU to a higher-priority available sibling allowed by task affinity.
+ */
+static inline int select_idle_smt_priority(struct task_struct *p, int cpu)
+{
+	return select_idle_smt_cpu(p, cpu, p->cpus_ptr);
+}
+
 /*
  * Scans the local SMT mask to see if the entire core is idle, and records this
  * information in sd_balance_shared->has_idle_cores.

@@ -8645,7 +8702,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 	}
 
 	if (idle)
-		return core;
+		return select_idle_smt_cpu(p, core, cpus);
 
 	cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
 	return -1;

@@ -8668,7 +8725,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
 		if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
 			continue;
 		if (choose_idle_cpu(cpu, p))
-			return cpu;
+			return select_idle_smt_priority(p, cpu);
 	}
 
 	return -1;

@@ -8720,7 +8777,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 						return -1;
 					idle_cpu = __select_idle_cpu(cpu, p);
 					if ((unsigned int)idle_cpu < nr_cpumask_bits)
-						return idle_cpu;
+						return select_idle_smt_priority(p, idle_cpu);
 				}
 			}
 			cpumask_andnot(cpus, cpus, sched_group_span(sg));

@@ -8745,7 +8802,8 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 	if (has_idle_core)
 		set_idle_cores(target, false);
 
-	return idle_cpu;
+	return (unsigned int)idle_cpu < nr_cpumask_bits ?
+		select_idle_smt_priority(p, idle_cpu) : idle_cpu;
 }
 
 /*

@@ -8858,7 +8916,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 		 * immediately.
 		 */
 		if (fits > 0 && preferred_core)
-			return cpu;
+			return select_idle_smt_cpu(p, cpu, cpus);
 		/*
 		 * Only the min performance hint (i.e. uclamp_min) doesn't fit.
 		 * Look for the CPU with best capacity.

@@ -8915,6 +8973,9 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 	if (has_idle_core && best_fits > ASYM_IDLE_COMPLETE_MISFIT)
 		set_idle_cores(target, false);
 
+	if (best_cpu >= 0)
+		best_cpu = select_idle_smt_cpu(p, best_cpu, cpus);
+
 	return best_cpu;
 }
 

@@ -8971,7 +9032,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 	if (choose_idle_cpu(target, p) &&
 	    asym_fits_cpu(task_util, util_min, util_max, target))
-		return target;
+		return select_idle_smt_priority(p, target);
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:

@@ -8982,9 +9043,9 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
 		    cpus_share_resources(prev, target))
-			return prev;
+			return select_idle_smt_priority(p, prev);
 
-		prev_aff = prev;
+		prev_aff = select_idle_smt_priority(p, prev);
 	}
 
 	/*

@@ -9015,7 +9076,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
 		    cpus_share_resources(recent_used_cpu, target))
-			return recent_used_cpu;
+			return select_idle_smt_priority(p, recent_used_cpu);
 
 	} else {
 		recent_used_cpu = -1;

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6c3ad70e58b8e..568cb1ed2dd6b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h

@@ -2240,6 +2240,7 @@ 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_smt_asym_packing;
 extern struct static_key_false sched_cluster_active;
 
 static __always_inline bool sched_asym_cpucap_active(void)

@@ -2247,6 +2248,11 @@ static __always_inline bool sched_asym_cpucap_active(void)
 	return static_branch_unlikely(&sched_asym_cpucapacity);
 }
 
+static __always_inline bool sched_smt_asym_active(void)
+{
+	return static_branch_unlikely(&sched_smt_asym_packing);
+}
+
 struct sched_group_capacity {
 	atomic_t		ref;
 	/*

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 0248227d983a7..06c40eb5932af 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c

@@ -683,8 +683,24 @@ 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_smt_asym_packing);
 DEFINE_STATIC_KEY_FALSE(sched_cluster_active);
 
+static bool has_asym_smt_domain(int cpu)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd) {
+		if (!(sd->flags & SD_SHARE_CPUCAPACITY))
+			break;
+
+		if (sd->flags & SD_ASYM_PACKING)
+			return true;
+	}
+
+	return false;
+}
+
 static void update_top_cache_domain(int cpu)
 {
 	struct sched_domain_shared *sds = NULL;

@@ -3084,6 +3100,7 @@ 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_asym_smt = false;
 	bool has_cluster = false;
 
 	if (WARN_ON(cpumask_empty(cpu_map)))

@@ -3202,6 +3219,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 
 		cpu_attach_domain(sd, d.rd, i);
 
+		if (has_asym_smt_domain(i))
+			has_asym_smt = true;
+
 		if (lowest_flag_domain(i, SD_CLUSTER))
 			has_cluster = true;
 	}

@@ -3210,6 +3230,9 @@ 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_asym_smt)
+		static_branch_inc_cpuslocked(&sched_smt_asym_packing);
+
 	if (has_cluster)
 		static_branch_inc_cpuslocked(&sched_cluster_active);
 

@@ -3310,11 +3333,24 @@ int __init sched_init_domains(const struct cpumask *cpu_map)
 static void detach_destroy_domains(const struct cpumask *cpu_map)
 {
 	unsigned int cpu = cpumask_any(cpu_map);
+	bool has_asym_smt = false;
 	int i;
 
+	rcu_read_lock();
+	for_each_cpu(i, cpu_map) {
+		if (has_asym_smt_domain(i)) {
+			has_asym_smt = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
 	if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
 		static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
 
+	if (has_asym_smt)
+		static_branch_dec_cpuslocked(&sched_smt_asym_packing);
+
 	if (static_branch_unlikely(&sched_cluster_active))
 		static_branch_dec_cpuslocked(&sched_cluster_active);
 

-- 
2.55.0

Hello Andrea,

On 9/4/2026 2:48 PM, Andrea Righi wrote:

+/*
+ * Return true when @cpu has a higher asymmetric-packing priority than
+ * @other in their shared SMT scheduling domain.
+ */
+static bool sched_smt_asym_prefer(int cpu, int other)
+{
+	struct sched_domain *sd = rcu_dereference_all(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return false;
+
+	if (!(sd->flags & SD_SHARE_CPUCAPACITY) ||
+	    !(sd->flags & SD_ASYM_PACKING))
+		return false;
+
+	if (!cpumask_test_cpu(other, sched_domain_span(sd)))
+		return false;
+
+	return sched_asym_prefer(cpu, other);
+}
+
+/*
+ * Return the highest-priority available CPU in @cpu's SMT core that is also in @cpus.
+ */
+static int __select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	int best = cpu;
+	int sibling;
+
+	for_each_cpu_and(sibling, cpu_smt_mask(cpu), cpus) {
+		if (sibling == best || !choose_idle_cpu(sibling, p))
+			continue;
+
+		if (sched_smt_asym_prefer(sibling, best))
+			best = sibling;

nit. Since sched_smt_asym_prefer() is only used here, and we know rq->sd
is the one that can have SD_SHARE_CPUCAPACITY | SD_ASYM_PACKING, perhaps
you can inline the check here do a:

    sd = rcu_dereference_all(cpu_rq(cpu)->sd);

    if (!sd)
         return cpu;

   if (!(sd->flags & SD_SHARE_CPUCAPACITY) || !(sd->flags & SD_ASYM_PACKING))
       return cpu;

   for_each_cpu_and (sibling, sched_domain_span(sd), cpus) {
       ...
   }

  ...


That way, you don't need to dereference cpu_rq(cpu)->sd every time in
sched_smt_asym_prefer() and check cpumask_test_cpu(). Both, domain
span and task affinity will be covered at once.

Thoughts?

Question for Shrikanth: On larger SMT (SMT-4, SMT-8), does the ranking
make that big of a difference if the core is already busy?

Does the overehead of additional search get offset by the benefit of
being placed on a better ranked thread? If not, maybe the paths for
!has_idle_core can stay as is?

Since every path does a select_idle_smt_priority() - be it coming from
select_idle_core(), the early-return from the cluster scan, or just an
idle CPU from the LLc scan, can't we simply just do it once in
select_idle_sibling()?

Something like:

  (Only build tested)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f79fcba4afec..7c97585141dd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c

@@ -8964,7 +8964,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 	if (choose_idle_cpu(target, p) &&
 	    asym_fits_cpu(task_util, util_min, util_max, target))
-		return target;
+		goto out;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:

@@ -8974,8 +8974,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
-		    cpus_share_resources(prev, target))
-			return prev;
+		    cpus_share_resources(prev, target)) {
+			target = prev;
+			goto out;
+		}
 
 		prev_aff = prev;
 	}

@@ -8993,7 +8995,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    prev == smp_processor_id() &&
 	    this_rq()->nr_running <= 1 &&
 	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
-		return prev;
+		target = prev;
+		goto out;
 	}
 
 	/* Check a recently used CPU as a potential idle candidate: */

@@ -9007,8 +9010,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
-		    cpus_share_resources(recent_used_cpu, target))
-			return recent_used_cpu;
+		    cpus_share_resources(recent_used_cpu, target)) {
+			target = recent_used_cpu;
+			goto out;
+		}
 
 	} else {
 		recent_used_cpu = -1;

@@ -9030,7 +9035,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 		 */
 		if (sd) {
 			i = select_idle_capacity(p, sd, target);
-			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+			target = ((unsigned)i < nr_cpumask_bits) ? i : target;
+			goto out;
 		}
 	}
 

@@ -9043,27 +9049,31 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 		if (!has_idle_core && cpus_share_cache(prev, target)) {
 			i = select_idle_smt(p, sd, prev);
-			if ((unsigned int)i < nr_cpumask_bits)
-				return i;
+			if ((unsigned int)i < nr_cpumask_bits) {
+				target = i;
+				goto out;
+			}
 		}
 	}
 
 	i = select_idle_cpu(p, sd, has_idle_core, target);
 	if ((unsigned)i < nr_cpumask_bits)
-		return i;
-
+		target = i;
 	/*
 	 * For cluster machines which have lower sharing cache like L2 or
 	 * LLC Tag, we tend to find an idle CPU in the target's cluster
 	 * first. But prev_cpu or recent_used_cpu may also be a good candidate,
 	 * use them if possible when no idle CPU found in select_idle_cpu().
 	 */
-	if ((unsigned int)prev_aff < nr_cpumask_bits)
-		return prev_aff;
-	if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
-		return recent_used_cpu;
+	else if ((unsigned int)prev_aff < nr_cpumask_bits)
+		target = prev_aff;
+	else if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
+		target = recent_used_cpu;
+out:
+	if (!sched_smt_asym_active())
+		return target;
 
-	return target;
+	return select_idle_smt_priority(p, target);
 }
 
 /**
---

That way, it lives in a single place, and we don't have to pepper
select_idle_smt_priority() everywhere. Thoughts?

-- 
Thanks and Regards,
Prateek

Hi Prateek,

On Mon, Sep 07, 2026 at 09:27:22AM +0530, K Prateek Nayak wrote:

Hello Andrea,

On 9/4/2026 2:48 PM, Andrea Righi wrote:

quoted

+/*
+ * Return true when @cpu has a higher asymmetric-packing priority than
+ * @other in their shared SMT scheduling domain.
+ */
+static bool sched_smt_asym_prefer(int cpu, int other)
+{
+	struct sched_domain *sd = rcu_dereference_all(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return false;
+
+	if (!(sd->flags & SD_SHARE_CPUCAPACITY) ||
+	    !(sd->flags & SD_ASYM_PACKING))
+		return false;
+
+	if (!cpumask_test_cpu(other, sched_domain_span(sd)))
+		return false;
+
+	return sched_asym_prefer(cpu, other);
+}
+
+/*
+ * Return the highest-priority available CPU in @cpu's SMT core that is also in @cpus.
+ */
+static int __select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	int best = cpu;
+	int sibling;
+
+	for_each_cpu_and(sibling, cpu_smt_mask(cpu), cpus) {
+		if (sibling == best || !choose_idle_cpu(sibling, p))
+			continue;
+
+		if (sched_smt_asym_prefer(sibling, best))
+			best = sibling;

nit. Since sched_smt_asym_prefer() is only used here, and we know rq->sd
is the one that can have SD_SHARE_CPUCAPACITY | SD_ASYM_PACKING, perhaps
you can inline the check here do a:

    sd = rcu_dereference_all(cpu_rq(cpu)->sd);

    if (!sd)
         return cpu;

   if (!(sd->flags & SD_SHARE_CPUCAPACITY) || !(sd->flags & SD_ASYM_PACKING))
       return cpu;

   for_each_cpu_and (sibling, sched_domain_span(sd), cpus) {
       ...
   }

  ...


That way, you don't need to dereference cpu_rq(cpu)->sd every time in
sched_smt_asym_prefer() and check cpumask_test_cpu(). Both, domain
span and task affinity will be covered at once.

Thoughts?

Yes, agreed. I like this way more.

quoted

+	}
+
+	return best;
+}
+
+static inline int
+select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	if (!sched_smt_asym_active())
+		return cpu;
+
+	return __select_idle_smt_cpu(p, cpu, cpus);
+}
+
+/*
+ * Redirect an available SMT CPU to a higher-priority available sibling allowed by task affinity.
+ */
+static inline int select_idle_smt_priority(struct task_struct *p, int cpu)
+{
+	return select_idle_smt_cpu(p, cpu, p->cpus_ptr);
+}
+
 /*
  * Scans the local SMT mask to see if the entire core is idle, and records this
  * information in sd_balance_shared->has_idle_cores.

@@ -8645,7 +8702,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 	}
 
 	if (idle)
-		return core;
+		return select_idle_smt_cpu(p, core, cpus);
 
 	cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
 	return -1;

@@ -8668,7 +8725,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
 		if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
 			continue;
 		if (choose_idle_cpu(cpu, p))
-			return cpu;
+			return select_idle_smt_priority(p, cpu);
 	}
 
 	return -1;

@@ -8720,7 +8777,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 						return -1;
 					idle_cpu = __select_idle_cpu(cpu, p);
 					if ((unsigned int)idle_cpu < nr_cpumask_bits)
-						return idle_cpu;
+						return select_idle_smt_priority(p, idle_cpu);

Question for Shrikanth: On larger SMT (SMT-4, SMT-8), does the ranking
make that big of a difference if the core is already busy?

Does the overehead of additional search get offset by the benefit of
being placed on a better ranked thread? If not, maybe the paths for
!has_idle_core can stay as is?

On Olympus it'd be fine either way, since it's an SMT2. For wider SMT systems I
also defer the question to Shrikanth, I don't have any of them to test. :)

quoted

 				}
 			}
 			cpumask_andnot(cpus, cpus, sched_group_span(sg));

@@ -8745,7 +8802,8 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 	if (has_idle_core)
 		set_idle_cores(target, false);
 
-	return idle_cpu;
+	return (unsigned int)idle_cpu < nr_cpumask_bits ?
+		select_idle_smt_priority(p, idle_cpu) : idle_cpu;

Since every path does a select_idle_smt_priority() - be it coming from
select_idle_core(), the early-return from the cluster scan, or just an
idle CPU from the LLc scan, can't we simply just do it once in
select_idle_sibling()?

Something like:

Yes, consolidating it in select_idle_sibling() looks cleaner. One comment below.

Not sure about this final fallback. Is it worth doing an additional
select_idle_smt_priority() after idle scan failed or stopped because the
SIS_UTIL scan budget was exhausted?

It seems better to jump to out only when one of these paths has actually
selected a candidate:

	i = select_idle_cpu(p, sd, has_idle_core, target);
	if ((unsigned int)i < nr_cpumask_bits) {
		target = i;
		goto out;
	}

The prev_aff and recent_used_cpu fallbacks can jump to "out" as well, since they
were already verified as suitable candidates. If none of those paths succeeds, I
think the existing final "return target" should remain unchanged.

Does that make sense?

Thanks for looking at this!
-Andrea

 	/*
 	 * For cluster machines which have lower sharing cache like L2 or
 	 * LLC Tag, we tend to find an idle CPU in the target's cluster
 	 * first. But prev_cpu or recent_used_cpu may also be a good candidate,
 	 * use them if possible when no idle CPU found in select_idle_cpu().
 	 */
-	if ((unsigned int)prev_aff < nr_cpumask_bits)
-		return prev_aff;
-	if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
-		return recent_used_cpu;
+	else if ((unsigned int)prev_aff < nr_cpumask_bits)
+		target = prev_aff;
+	else if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
+		target = recent_used_cpu;
+out:
+	if (!sched_smt_asym_active())
+		return target;
 
-	return target;
+	return select_idle_smt_priority(p, target);
 }
 
 /**
---

That way, it lives in a single place, and we don't have to pepper
select_idle_smt_priority() everywhere. Thoughts?

-- 
Thanks and Regards,
Prateek

Hello Andrea,

On 9/7/2026 2:41 PM, Andrea Righi wrote:

quoted

quoted

@@ -8720,7 +8777,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 						return -1;
 					idle_cpu = __select_idle_cpu(cpu, p);
 					if ((unsigned int)idle_cpu < nr_cpumask_bits)
-						return idle_cpu;
+						return select_idle_smt_priority(p, idle_cpu);

Question for Shrikanth: On larger SMT (SMT-4, SMT-8), does the ranking
make that big of a difference if the core is already busy?

Does the overehead of additional search get offset by the benefit of
being placed on a better ranked thread? If not, maybe the paths for
!has_idle_core can stay as is?

On Olympus it'd be fine either way, since it's an SMT2. For wider SMT systems I
also defer the question to Shrikanth, I don't have any of them to test. :)

Same! Best I can do is a VM with -cpus ...,threads=8 but performance on
those are super flaky to make any meaningful deductions.

quoted

quoted

 				}
 			}
 			cpumask_andnot(cpus, cpus, sched_group_span(sg));

@@ -8745,7 +8802,8 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 	if (has_idle_core)
 		set_idle_cores(target, false);
 
-	return idle_cpu;
+	return (unsigned int)idle_cpu < nr_cpumask_bits ?
+		select_idle_smt_priority(p, idle_cpu) : idle_cpu;

Since every path does a select_idle_smt_priority() - be it coming from
select_idle_core(), the early-return from the cluster scan, or just an
idle CPU from the LLc scan, can't we simply just do it once in
select_idle_sibling()?

Something like:

Yes, consolidating it in select_idle_sibling() looks cleaner. One comment below.

quoted

  (Only build tested)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f79fcba4afec..7c97585141dd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c

@@ -8964,7 +8964,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 	if (choose_idle_cpu(target, p) &&
 	    asym_fits_cpu(task_util, util_min, util_max, target))
-		return target;
+		goto out;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:

@@ -8974,8 +8974,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
-		    cpus_share_resources(prev, target))
-			return prev;
+		    cpus_share_resources(prev, target)) {
+			target = prev;
+			goto out;
+		}
 
 		prev_aff = prev;
 	}

@@ -8993,7 +8995,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    prev == smp_processor_id() &&
 	    this_rq()->nr_running <= 1 &&
 	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
-		return prev;
+		target = prev;
+		goto out;
 	}
 
 	/* Check a recently used CPU as a potential idle candidate: */

@@ -9007,8 +9010,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
-		    cpus_share_resources(recent_used_cpu, target))
-			return recent_used_cpu;
+		    cpus_share_resources(recent_used_cpu, target)) {
+			target = recent_used_cpu;
+			goto out;
+		}
 
 	} else {
 		recent_used_cpu = -1;

@@ -9030,7 +9035,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 		 */
 		if (sd) {
 			i = select_idle_capacity(p, sd, target);
-			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+			target = ((unsigned)i < nr_cpumask_bits) ? i : target;
+			goto out;
 		}
 	}
 

@@ -9043,27 +9049,31 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 		if (!has_idle_core && cpus_share_cache(prev, target)) {
 			i = select_idle_smt(p, sd, prev);
-			if ((unsigned int)i < nr_cpumask_bits)
-				return i;
+			if ((unsigned int)i < nr_cpumask_bits) {
+				target = i;
+				goto out;
+			}
 		}
 	}
 
 	i = select_idle_cpu(p, sd, has_idle_core, target);
 	if ((unsigned)i < nr_cpumask_bits)
-		return i;
-
+		target = i;

Not sure about this final fallback. Is it worth doing an additional
select_idle_smt_priority() after idle scan failed or stopped because the
SIS_UTIL scan budget was exhausted?

I see what you mean! We'll end up doing a:

  select_idle_smt_priority(p, target)

at the end which might indeed be wasteful.

It seems better to jump to out only when one of these paths has actually
selected a candidate:

	i = select_idle_cpu(p, sd, has_idle_core, target);
	if ((unsigned int)i < nr_cpumask_bits) {
		target = i;
		goto out;
	}

The prev_aff and recent_used_cpu fallbacks can jump to "out" as well, since they
were already verified as suitable candidates. If none of those paths succeeds, I
think the existing final "return target" should remain unchanged.

Does that make sense?

Correct me if I'm wrong but you are suggesting to keep the current
return intact and put out label after it like:

    /* If no suitable target was found */
    return target;

out:
   if (!sched_smt_asym_active())
       return target;

   return select_idle_smt_priority(p, target);
---

That makes sense to me!

-- 
Thanks and Regards,
Prateek

On Mon, Sep 07, 2026 at 03:10:00PM +0530, K Prateek Nayak wrote:
...

quoted

quoted

@@ -9043,27 +9049,31 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 		if (!has_idle_core && cpus_share_cache(prev, target)) {
 			i = select_idle_smt(p, sd, prev);
-			if ((unsigned int)i < nr_cpumask_bits)
-				return i;
+			if ((unsigned int)i < nr_cpumask_bits) {
+				target = i;
+				goto out;
+			}
 		}
 	}
 
 	i = select_idle_cpu(p, sd, has_idle_core, target);
 	if ((unsigned)i < nr_cpumask_bits)
-		return i;
-
+		target = i;

Not sure about this final fallback. Is it worth doing an additional
select_idle_smt_priority() after idle scan failed or stopped because the
SIS_UTIL scan budget was exhausted?

I see what you mean! We'll end up doing a:

  select_idle_smt_priority(p, target)

at the end which might indeed be wasteful.

Exactly.

quoted

It seems better to jump to out only when one of these paths has actually
selected a candidate:

	i = select_idle_cpu(p, sd, has_idle_core, target);
	if ((unsigned int)i < nr_cpumask_bits) {
		target = i;
		goto out;
	}

The prev_aff and recent_used_cpu fallbacks can jump to "out" as well, since they
were already verified as suitable candidates. If none of those paths succeeds, I
think the existing final "return target" should remain unchanged.

Does that make sense?

Correct me if I'm wrong but you are suggesting to keep the current
return intact and put out label after it like:

    /* If no suitable target was found */
    return target;

out:
   if (!sched_smt_asym_active())
       return target;

   return select_idle_smt_priority(p, target);
---

That makes sense to me!

Correct, I'm going to run some tests with this and will send a v3 later.

Thanks!
-Andrea

On 9/7/26 9:27 AM, K Prateek Nayak wrote:

Hello Andrea,

On 9/4/2026 2:48 PM, Andrea Righi wrote:

quoted

+/*
+ * Return true when @cpu has a higher asymmetric-packing priority than
+ * @other in their shared SMT scheduling domain.
+ */
+static bool sched_smt_asym_prefer(int cpu, int other)
+{
+	struct sched_domain *sd = rcu_dereference_all(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return false;
+
+	if (!(sd->flags & SD_SHARE_CPUCAPACITY) ||
+	    !(sd->flags & SD_ASYM_PACKING))
+		return false;
+
+	if (!cpumask_test_cpu(other, sched_domain_span(sd)))
+		return false;
+
+	return sched_asym_prefer(cpu, other);
+}
+
+/*
+ * Return the highest-priority available CPU in @cpu's SMT core that is also in @cpus.
+ */
+static int __select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	int best = cpu;
+	int sibling;
+
+	for_each_cpu_and(sibling, cpu_smt_mask(cpu), cpus) {
+		if (sibling == best || !choose_idle_cpu(sibling, p))
+			continue;
+
+		if (sched_smt_asym_prefer(sibling, best))
+			best = sibling;

nit. Since sched_smt_asym_prefer() is only used here, and we know rq->sd
is the one that can have SD_SHARE_CPUCAPACITY | SD_ASYM_PACKING, perhaps
you can inline the check here do a:

     sd = rcu_dereference_all(cpu_rq(cpu)->sd);

     if (!sd)
          return cpu;

    if (!(sd->flags & SD_SHARE_CPUCAPACITY) || !(sd->flags & SD_ASYM_PACKING))
        return cpu;

    for_each_cpu_and (sibling, sched_domain_span(sd), cpus) {
        ...
    }

   ...


That way, you don't need to dereference cpu_rq(cpu)->sd every time in
sched_smt_asym_prefer() and check cpumask_test_cpu(). Both, domain
span and task affinity will be covered at once.

Thoughts?

quoted

+	}
+
+	return best;
+}
+
+static inline int
+select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	if (!sched_smt_asym_active())
+		return cpu;
+
+	return __select_idle_smt_cpu(p, cpu, cpus);
+}
+
+/*
+ * Redirect an available SMT CPU to a higher-priority available sibling allowed by task affinity.
+ */
+static inline int select_idle_smt_priority(struct task_struct *p, int cpu)
+{
+	return select_idle_smt_cpu(p, cpu, p->cpus_ptr);
+}
+
  /*
   * Scans the local SMT mask to see if the entire core is idle, and records this
   * information in sd_balance_shared->has_idle_cores.

@@ -8645,7 +8702,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
  	}
  
  	if (idle)
-		return core;
+		return select_idle_smt_cpu(p, core, cpus);
  
  	cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
  	return -1;

@@ -8668,7 +8725,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
  		if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
  			continue;
  		if (choose_idle_cpu(cpu, p))
-			return cpu;
+			return select_idle_smt_priority(p, cpu);
  	}
  
  	return -1;

@@ -8720,7 +8777,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
  						return -1;
  					idle_cpu = __select_idle_cpu(cpu, p);
  					if ((unsigned int)idle_cpu < nr_cpumask_bits)
-						return idle_cpu;
+						return select_idle_smt_priority(p, idle_cpu);

Question for Shrikanth: On larger SMT (SMT-4, SMT-8), does the ranking
make that big of a difference if the core is already busy?

Only on Power7 we had AYSM PACKING.
There IPC of CPU0 > CPU1 > CPU2 > CPU4 for the four siblings IIRC irrespective of busy
or idle.

PS: I haven't seen the patches in detail yet.

* Andrea Righi [off-list ref] [2026-09-04 11:18:05]:

Hi Andrea,

POWER7 and NVIDIA Olympus use SD_ASYM_PACKING at the shared-capacity
SMT level to order hardware threads. Idle CPU selection does not consult
that order, so a task can wake on an arbitrary sibling and remain there
until load balancing corrects the placement. On these systems, that
initial choice can prevent the core from entering its preferred
lower-thread resource mode and cause a large and persistent performance
loss.

When idle selection finds an available CPU in an SMT core, choose the
highest-priority available sibling. On SMT2 Olympus this only changes
selection on fully idle cores. A partially idle core has only one
available CPU. On wider SMT systems such as POWER7, it also fills
available siblings in priority order while the core is partially busy.

Don't we need changes in the slow path too?
Something like this?
https://lore.kernel.org/all/20251204175405.1511340-2-srikar@linux.ibm.com/T/#u

Nit: I see __select_idle_smt_cpu called only here.
Cant we fold __select_idle_smt_cpu() here itself.

+}
+
+/*
+ * Redirect an available SMT CPU to a higher-priority available sibling allowed by task affinity.
+ */
+static inline int select_idle_smt_priority(struct task_struct *p, int cpu)
+{
+	return select_idle_smt_cpu(p, cpu, p->cpus_ptr);
+}
+

nit: Can we also replace select_idle_smt_priority with select_idle_smt_cpu()
itself.

Otherwise looks good to me

Reviewed-by: Srikar Dronamraju <redacted>

-- 
Thanks and Regards
Srikar Dronamraju

Hi Srikar,

On Tue, Sep 08, 2026 at 11:07:20AM +0530, Srikar Dronamraju wrote:

* Andrea Righi [off-list ref] [2026-09-04 11:18:05]:

Hi Andrea,

quoted

POWER7 and NVIDIA Olympus use SD_ASYM_PACKING at the shared-capacity
SMT level to order hardware threads. Idle CPU selection does not consult
that order, so a task can wake on an arbitrary sibling and remain there
until load balancing corrects the placement. On these systems, that
initial choice can prevent the core from entering its preferred
lower-thread resource mode and cause a large and persistent performance
loss.

quoted

When idle selection finds an available CPU in an SMT core, choose the
highest-priority available sibling. On SMT2 Olympus this only changes
selection on fully idle cores. A partially idle core has only one
available CPU. On wider SMT systems such as POWER7, it also fills
available siblings in priority order while the core is partially busy.

Don't we need changes in the slow path too?
Something like this?
https://lore.kernel.org/all/20251204175405.1511340-2-srikar@linux.ibm.com/T/#u

Ah yes, good catch! I'll include the WF_FORK / WF_EXEC slow-path as well.

quoted

Apply the preference to idle-core and idle-CPU scans,
asymmetric-capacity scans, and the target, previous, and recently-used
CPU fast paths. Inspect the lowest scheduling domain directly, but
require both CPUs to share its span because isolcpus can split hardware
siblings across scheduling domains.

Keep physical-core capacity selection independent from SMT sibling
ordering. SD_ASYM_CPUCAPACITY first selects among cores with different
maximum capacities, then SD_ASYM_PACKING selects the preferred available
sibling inside the chosen core, whose siblings continue to share equal
capacity.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/fair.c     | 79 ++++++++++++++++++++++++++++++++++++-----
 kernel/sched/sched.h    |  6 ++++
 kernel/sched/topology.c | 36 +++++++++++++++++++
 3 files changed, 112 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b8bd308c2d5b1..ff9a7b1fcbe7f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c

@@ -8587,6 +8587,63 @@ static inline bool test_idle_cores(int cpu)
 	return false;
 }
 
+/*
+ * Return true when @cpu has a higher asymmetric-packing priority than
+ * @other in their shared SMT scheduling domain.
+ */
+static bool sched_smt_asym_prefer(int cpu, int other)
+{
+	struct sched_domain *sd = rcu_dereference_all(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return false;
+
+	if (!(sd->flags & SD_SHARE_CPUCAPACITY) ||
+	    !(sd->flags & SD_ASYM_PACKING))
+		return false;
+
+	if (!cpumask_test_cpu(other, sched_domain_span(sd)))
+		return false;
+
+	return sched_asym_prefer(cpu, other);
+}
+
+/*
+ * Return the highest-priority available CPU in @cpu's SMT core that is also in @cpus.
+ */
+static int __select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	int best = cpu;
+	int sibling;
+
+	for_each_cpu_and(sibling, cpu_smt_mask(cpu), cpus) {
+		if (sibling == best || !choose_idle_cpu(sibling, p))
+			continue;
+
+		if (sched_smt_asym_prefer(sibling, best))
+			best = sibling;
+	}
+
+	return best;
+}
+
+static inline int
+select_idle_smt_cpu(struct task_struct *p, int cpu, const struct cpumask *cpus)
+{
+	if (!sched_smt_asym_active())
+		return cpu;
+
+	return __select_idle_smt_cpu(p, cpu, cpus);

Nit: I see __select_idle_smt_cpu called only here.
Cant we fold __select_idle_smt_cpu() here itself.

Agreed, will fold in v4.

quoted

+}
+
+/*
+ * Redirect an available SMT CPU to a higher-priority available sibling allowed by task affinity.
+ */
+static inline int select_idle_smt_priority(struct task_struct *p, int cpu)
+{
+	return select_idle_smt_cpu(p, cpu, p->cpus_ptr);
+}
+

nit: Can we also replace select_idle_smt_priority with select_idle_smt_cpu()
itself.

Ack, we can use select_idle_smt_cpu() directly.

Otherwise looks good to me

Reviewed-by: Srikar Dronamraju <redacted>

Thanks for taking a look at this!
-Andrea

-- 
Thanks and Regards
Srikar Dronamraju