diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2025-01-21 11:32:36 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2025-01-21 11:32:36 -0800 |
commit | 62de6e1685269e1637a6c6684c8be58cc8d4ff38 (patch) | |
tree | f868bf2f17466cfd50e016f32876b09af3c01fd0 /include/linux | |
parent | 858df1de2158bd7ab88d31b557592e990bacc0b5 (diff) | |
parent | 40724ecafccb1fb62b66264854e8c3ad394c8f3d (diff) |
Merge tag 'sched-core-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
"Fair scheduler (SCHED_FAIR) enhancements:
- Behavioral improvements:
- Untangle NEXT_BUDDY and pick_next_task() (Peter Zijlstra)
- Delayed-dequeue enhancements & fixes: (Vincent Guittot)
- Rename h_nr_running into h_nr_queued
- Add new cfs_rq.h_nr_runnable
- Use the new cfs_rq.h_nr_runnable
- Removed unsued cfs_rq.h_nr_delayed
- Rename cfs_rq.idle_h_nr_running into h_nr_idle
- Remove unused cfs_rq.idle_nr_running
- Rename cfs_rq.nr_running into nr_queued
- Do not try to migrate delayed dequeue task
- Fix variable declaration position
- Encapsulate set custom slice in a __setparam_fair() function
- Fixes:
- Fix race between yield_to() and try_to_wake_up() (Tianchen Ding)
- Fix CPU bandwidth limit bypass during CPU hotplug (Vishal
Chourasia)
- Cleanups:
- Clean up in migrate_degrades_locality() to improve readability
(Peter Zijlstra)
- Mark m*_vruntime() with __maybe_unused (Andy Shevchenko)
- Update comments after sched_tick() rename (Sebastian Andrzej
Siewior)
- Remove CONFIG_CFS_BANDWIDTH=n definition of cfs_bandwidth_used()
(Valentin Schneider)
Deadline scheduler (SCHED_DL) enhancements:
- Restore dl_server bandwidth on non-destructive root domain changes
(Juri Lelli)
- Correctly account for allocated bandwidth during hotplug (Juri
Lelli)
- Check bandwidth overflow earlier for hotplug (Juri Lelli)
- Clean up goto label in pick_earliest_pushable_dl_task() (John
Stultz)
- Consolidate timer cancellation (Wander Lairson Costa)
Load-balancer enhancements:
- Improve performance by prioritizing migrating eligible tasks in
sched_balance_rq() (Hao Jia)
- Do not compute NUMA Balancing stats unnecessarily during
load-balancing (K Prateek Nayak)
- Do not compute overloaded status unnecessarily during
load-balancing (K Prateek Nayak)
Generic scheduling code enhancements:
- Use READ_ONCE() in task_on_rq_queued(), to consistently use the
WRITE_ONCE() updated ->on_rq field (Harshit Agarwal)
Isolated CPUs support enhancements: (Waiman Long)
- Make "isolcpus=nohz" equivalent to "nohz_full"
- Consolidate housekeeping cpumasks that are always identical
- Remove HK_TYPE_SCHED
- Unify HK_TYPE_{TIMER|TICK|MISC} to HK_TYPE_KERNEL_NOISE
RSEQ enhancements:
- Validate read-only fields under DEBUG_RSEQ config (Mathieu
Desnoyers)
PSI enhancements:
- Fix race when task wakes up before psi_sched_switch() adjusts flags
(Chengming Zhou)
IRQ time accounting performance enhancements: (Yafang Shao)
- Define sched_clock_irqtime as static key
- Don't account irq time if sched_clock_irqtime is disabled
Virtual machine scheduling enhancements:
- Don't try to catch up excess steal time (Suleiman Souhlal)
Heterogenous x86 CPU scheduling enhancements: (K Prateek Nayak)
- Convert "sysctl_sched_itmt_enabled" to boolean
- Use guard() for itmt_update_mutex
- Move the "sched_itmt_enabled" sysctl to debugfs
- Remove x86_smt_flags and use cpu_smt_flags directly
- Use x86_sched_itmt_flags for PKG domain unconditionally
Debugging code & instrumentation enhancements:
- Change need_resched warnings to pr_err() (David Rientjes)
- Print domain name in /proc/schedstat (K Prateek Nayak)
- Fix value reported by hot tasks pulled in /proc/schedstat (Peter
Zijlstra)
- Report the different kinds of imbalances in /proc/schedstat
(Swapnil Sapkal)
- Move sched domain name out of CONFIG_SCHED_DEBUG (Swapnil Sapkal)
- Update Schedstat version to 17 (Swapnil Sapkal)"
* tag 'sched-core-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
rseq: Fix rseq unregistration regression
psi: Fix race when task wakes up before psi_sched_switch() adjusts flags
sched, psi: Don't account irq time if sched_clock_irqtime is disabled
sched: Don't account irq time if sched_clock_irqtime is disabled
sched: Define sched_clock_irqtime as static key
sched/fair: Do not compute overloaded status unnecessarily during lb
sched/fair: Do not compute NUMA Balancing stats unnecessarily during lb
x86/topology: Use x86_sched_itmt_flags for PKG domain unconditionally
x86/topology: Remove x86_smt_flags and use cpu_smt_flags directly
x86/itmt: Move the "sched_itmt_enabled" sysctl to debugfs
x86/itmt: Use guard() for itmt_update_mutex
x86/itmt: Convert "sysctl_sched_itmt_enabled" to boolean
sched/core: Prioritize migrating eligible tasks in sched_balance_rq()
sched/debug: Change need_resched warnings to pr_err
sched/fair: Encapsulate set custom slice in a __setparam_fair() function
sched: Fix race between yield_to() and try_to_wake_up()
docs: Update Schedstat version to 17
sched/stats: Print domain name in /proc/schedstat
sched: Move sched domain name out of CONFIG_SCHED_DEBUG
sched: Report the different kinds of imbalances in /proc/schedstat
...
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/sched.h | 10 | ||||
-rw-r--r-- | include/linux/sched/isolation.h | 21 | ||||
-rw-r--r-- | include/linux/sched/topology.h | 13 |
3 files changed, 27 insertions, 17 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c7eb16ab1d5..ac08431e238f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -944,6 +944,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; @@ -1374,6 +1375,15 @@ struct task_struct { * with respect to preemption. */ unsigned long rseq_event_mask; +# ifdef CONFIG_DEBUG_RSEQ + /* + * This is a place holder to save a copy of the rseq fields for + * validation of read-only fields. The struct rseq has a + * variable-length array at the end, so it cannot be used + * directly. Reserve a size large enough for the known fields. + */ + char rseq_fields[sizeof(struct rseq)]; +# endif #endif #ifdef CONFIG_SCHED_MM_CID diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 2b461129d1fa..d8501f4709b5 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -7,16 +7,21 @@ #include <linux/tick.h> enum hk_type { - HK_TYPE_TIMER, - HK_TYPE_RCU, - HK_TYPE_MISC, - HK_TYPE_SCHED, - HK_TYPE_TICK, HK_TYPE_DOMAIN, - HK_TYPE_WQ, HK_TYPE_MANAGED_IRQ, - HK_TYPE_KTHREAD, - HK_TYPE_MAX + HK_TYPE_KERNEL_NOISE, + HK_TYPE_MAX, + + /* + * The following housekeeping types are only set by the nohz_full + * boot commandline option. So they can share the same value. + */ + HK_TYPE_TICK = HK_TYPE_KERNEL_NOISE, + HK_TYPE_TIMER = HK_TYPE_KERNEL_NOISE, + HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, + HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, + HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, + HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 4237daa5ac7a..7f3dbafe1817 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -114,7 +114,10 @@ struct sched_domain { unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; - unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_load[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_misfit[CPU_MAX_IDLE_TYPES]; unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; @@ -140,9 +143,7 @@ struct sched_domain { unsigned int ttwu_move_affine; unsigned int ttwu_move_balance; #endif -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif union { void *private; /* used during construction */ struct rcu_head rcu; /* used during destruction */ @@ -198,18 +199,12 @@ struct sched_domain_topology_level { int flags; int numa_level; struct sd_data data; -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif }; extern void __init set_sched_topology(struct sched_domain_topology_level *tl); -#ifdef CONFIG_SCHED_DEBUG # define SD_INIT_NAME(type) .name = #type -#else -# define SD_INIT_NAME(type) -#endif #else /* CONFIG_SMP */ |