Rust-related/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2026-07-22 02:00:44 +09:00
Code Issues Packages Projects Releases Wiki Activity

sched: Simplify ifdeffery around cpu_smt_mask

Browse Source 
Now, that cpu_smt_mask is defined as cpumask_of(cpu) for
CONFIG_SCHED_SMT=n, it is possible to get rid of the ifdeffery.

Effectively,
 - This makes sched_smt_present is defined always

 - cpumask_weight(cpumask_of(cpu)) == 1. So sched_smt_present_inc/dec
   will never enable the sched_smt_present. Which is expected.

 - Paths that were compile-time eliminated become runtime guarded
   using static keys.

 - Defines set_idle_cores, test_idle_cores, etc which could likely benefit
   the CONFIG_SCHED_SMT=n systems to use the same optimizations within the
   LLC at wakeups.

 - This will expose sched_smt_present symbol for CONFIG_SCHED_SMT=n.
   Likely not a concern.

 - There is a bloat of code CONFIG_SCHED_SMT=n. (NR_CPUS=2048)
   add/remove: 24/18 grow/shrink: 26/28 up/down: 6396/-3188 (3208)
   Total: Before=30629880, After=30633088, chg +0.01%

 - No code bloat for CONFIG_SCHED_SMT=y, which is expected.

 - Add comments around stop_core_cpuslocked on why ifdefs are not
   removed.

 - This leaves the remaining uses of CONFIG_SCHED_SMT mainly for
   topology building bits which has a policy based decision.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://patch.msgid.link/20260515172456.542799-3-sshegde@linux.ibm.com
This commit is contained in:
Shrikanth Hegde
2026-05-15 22:54:54 +05:30
committed by Peter Zijlstra
parent 815c5cb76a
commit 5bc6ab2d42
8 changed files with 5 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/linux/sched/smt.h
View File

@@ -4,16 +4,12 @@
#include <linux/static_key.h>
#ifdef CONFIG_SCHED_SMT
extern struct static_key_false sched_smt_present;
static __always_inline bool sched_smt_active(void)
{
return static_branch_likely(&sched_smt_present);
}
#else
static __always_inline bool sched_smt_active(void) { return false; }
#endif
void arch_smt_update(void);

6
kernel/sched/core.c
View File

@@ -8612,18 +8612,14 @@ static void cpuset_cpu_inactive(unsigned int cpu)
static inline void sched_smt_present_inc(int cpu)
{
#ifdef CONFIG_SCHED_SMT
if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
static_branch_inc_cpuslocked(&sched_smt_present);
#endif
}
static inline void sched_smt_present_dec(int cpu)
{
#ifdef CONFIG_SCHED_SMT
if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
static_branch_dec_cpuslocked(&sched_smt_present);
#endif
}
int sched_cpu_activate(unsigned int cpu)
@@ -8711,9 +8707,7 @@ int sched_cpu_deactivate(unsigned int cpu)
*/
sched_smt_present_dec(cpu);
#ifdef CONFIG_SCHED_SMT
sched_core_cpu_deactivate(cpu);
#endif
if (!sched_smp_initialized)
return 0;

6
kernel/sched/ext_idle.c
View File

@@ -79,7 +79,6 @@ static bool scx_idle_test_and_clear_cpu(int cpu)
int node = scx_cpu_node_if_enabled(cpu);
struct cpumask *idle_cpus = idle_cpumask(node)->cpu;
#ifdef CONFIG_SCHED_SMT
/*
* SMT mask should be cleared whether we can claim @cpu or not. The SMT
* cluster is not wholly idle either way. This also prevents
@@ -104,7 +103,6 @@ static bool scx_idle_test_and_clear_cpu(int cpu)
else if (cpumask_test_cpu(cpu, idle_smts))
__cpumask_clear_cpu(cpu, idle_smts);
}
#endif
return cpumask_test_and_clear_cpu(cpu, idle_cpus);
}
@@ -622,7 +620,6 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
goto out_unlock;
}
#ifdef CONFIG_SCHED_SMT
/*
* Use @prev_cpu's sibling if it's idle.
*/
@@ -634,7 +631,6 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
goto out_unlock;
}
}
#endif
/*
* Search for any idle CPU in the same LLC domain.
@@ -714,7 +710,6 @@ static void update_builtin_idle(int cpu, bool idle)
assign_cpu(cpu, idle_cpus, idle);
#ifdef CONFIG_SCHED_SMT
if (sched_smt_active()) {
const struct cpumask *smt = cpu_smt_mask(cpu);
struct cpumask *idle_smts = idle_cpumask(node)->smt;
@@ -731,7 +726,6 @@ static void update_builtin_idle(int cpu, bool idle)
cpumask_andnot(idle_smts, idle_smts, smt);
}
}
#endif
}
/*

35
kernel/sched/fair.c
View File

@@ -1555,7 +1555,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
static inline bool is_core_idle(int cpu)
{
#ifdef CONFIG_SCHED_SMT
int sibling;
for_each_cpu(sibling, cpu_smt_mask(cpu)) {
@@ -1565,7 +1564,6 @@ static inline bool is_core_idle(int cpu)
if (!idle_cpu(sibling))
return false;
}
#endif
return true;
}
@@ -2248,7 +2246,6 @@ numa_type numa_classify(unsigned int imbalance_pct,
return node_fully_busy;
}
#ifdef CONFIG_SCHED_SMT
/* Forward declarations of select_idle_sibling helpers */
static inline bool test_idle_cores(int cpu);
static inline int numa_idle_core(int idle_core, int cpu)
@@ -2266,12 +2263,6 @@ static inline int numa_idle_core(int idle_core, int cpu)
return idle_core;
}
#else /* !CONFIG_SCHED_SMT: */
static inline int numa_idle_core(int idle_core, int cpu)
{
return idle_core;
}
#endif /* !CONFIG_SCHED_SMT */
/*
* Gather all necessary information to make NUMA balancing placement
@@ -7778,7 +7769,6 @@ static inline int __select_idle_cpu(int cpu, struct task_struct *p)
return -1;
}
#ifdef CONFIG_SCHED_SMT
DEFINE_STATIC_KEY_FALSE(sched_smt_present);
EXPORT_SYMBOL_GPL(sched_smt_present);
@@ -7888,29 +7878,6 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
return -1;
}
#else /* !CONFIG_SCHED_SMT: */
static inline void set_idle_cores(int cpu, int val)
{
}
static inline bool test_idle_cores(int cpu)
{
return false;
}
static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu)
{
return __select_idle_cpu(core, p);
}
static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
{
return -1;
}
#endif /* !CONFIG_SCHED_SMT */
/*
* Scan the LLC domain for idle CPUs; this is dynamically regulated by
* comparing the average scan cost (tracked in sd->avg_scan_cost) against the
@@ -12002,9 +11969,7 @@ static int should_we_balance(struct lb_env *env)
* idle has been found, then its not needed to check other
* SMT siblings for idleness:
*/
#ifdef CONFIG_SCHED_SMT
cpumask_andnot(swb_cpus, swb_cpus, cpu_smt_mask(cpu));
#endif
continue;
}

6
kernel/sched/sched.h
View File

@@ -1667,7 +1667,6 @@ do { \
flags = _raw_spin_rq_lock_irqsave(rq); \
} while (0)
#ifdef CONFIG_SCHED_SMT
extern void __update_idle_core(struct rq *rq);
static inline void update_idle_core(struct rq *rq)
@@ -1676,12 +1675,7 @@ static inline void update_idle_core(struct rq *rq)
__update_idle_core(rq);
}
#else /* !CONFIG_SCHED_SMT: */
static inline void update_idle_core(struct rq *rq) { }
#endif /* !CONFIG_SCHED_SMT */
#ifdef CONFIG_FAIR_GROUP_SCHED
static inline struct task_struct *task_of(struct sched_entity *se)
{
WARN_ON_ONCE(!entity_is_task(se));

2
kernel/sched/topology.c
View File

@@ -1310,9 +1310,7 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
cpumask_copy(mask, sched_group_span(sg));
for_each_cpu(cpu, mask) {
cores++;
#ifdef CONFIG_SCHED_SMT
cpumask_andnot(mask, mask, cpu_smt_mask(cpu));
#endif
}
sg->cores = cores;

5
kernel/stop_machine.c
View File

@@ -633,6 +633,11 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
EXPORT_SYMBOL_GPL(stop_machine);
#ifdef CONFIG_SCHED_SMT
/*
* INTEL_IFS is the only user of this API. That selftest can
* only be compiled if SMP=y. On x86 it selects SCHED_SMT.
* Keep the ifdefs for now.
*/
int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data)
{
const struct cpumask *smt_mask = cpu_smt_mask(cpu);

4
kernel/workqueue.c
View File

@@ -8187,11 +8187,7 @@ static bool __init cpus_dont_share(int cpu0, int cpu1)
static bool __init cpus_share_smt(int cpu0, int cpu1)
{
#ifdef CONFIG_SCHED_SMT
return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1));
#else
return false;
#endif
}
static bool __init cpus_share_numa(int cpu0, int cpu1)