summaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-06-28 12:14:19 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-06-28 12:14:19 -0700
commit54a728dc5e4feb0a9278ad62b19f34ad21ed0ee4 (patch)
tree2737c23d4dbc6426d6d9467626a7634cbbb40fcd /kernel/fork.c
parent28a27cbd86076c1a6be311c751b421c4c17a7dd9 (diff)
parentadf3c31e18b765ea24eba7b0c1efc076b8ee3d55 (diff)
Merge tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler udpates from Ingo Molnar: - Changes to core scheduling facilities: - Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables coordinated scheduling across SMT siblings. This is a much requested feature for cloud computing platforms, to allow the flexible utilization of SMT siblings, without exposing untrusted domains to information leaks & side channels, plus to ensure more deterministic computing performance on SMT systems used by heterogenous workloads. There are new prctls to set core scheduling groups, which allows more flexible management of workloads that can share siblings. - Fix task->state access anti-patterns that may result in missed wakeups and rename it to ->__state in the process to catch new abuses. - Load-balancing changes: - Tweak newidle_balance for fair-sched, to improve 'memcache'-like workloads. - "Age" (decay) average idle time, to better track & improve workloads such as 'tbench'. - Fix & improve energy-aware (EAS) balancing logic & metrics. - Fix & improve the uclamp metrics. - Fix task migration (taskset) corner case on !CONFIG_CPUSET. - Fix RT and deadline utilization tracking across policy changes - Introduce a "burstable" CFS controller via cgroups, which allows bursty CPU-bound workloads to borrow a bit against their future quota to improve overall latencies & batching. Can be tweaked via /sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us. - Rework assymetric topology/capacity detection & handling. - Scheduler statistics & tooling: - Disable delayacct by default, but add a sysctl to enable it at runtime if tooling needs it. Use static keys and other optimizations to make it more palatable. - Use sched_clock() in delayacct, instead of ktime_get_ns(). - Misc cleanups and fixes. * tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits) sched/doc: Update the CPU capacity asymmetry bits sched/topology: Rework CPU capacity asymmetry detection sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag psi: Fix race between psi_trigger_create/destroy sched/fair: Introduce the burstable CFS controller sched/uclamp: Fix uclamp_tg_restrict() sched/rt: Fix Deadline utilization tracking during policy change sched/rt: Fix RT utilization tracking during policy change sched: Change task_struct::state sched,arch: Remove unused TASK_STATE offsets sched,timer: Use __set_current_state() sched: Add get_current_state() sched,perf,kvm: Fix preemption condition sched: Introduce task_is_running() sched: Unbreak wakeups sched/fair: Age the average idle time sched/cpufreq: Consider reduced CPU capacity in energy calculation sched/fair: Take thermal pressure into account while estimating energy thermal/cpufreq_cooling: Update offline CPUs per-cpu thermal_pressure sched/fair: Return early from update_tg_cfs_load() if delta == 0 ...
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c12
1 files changed, 8 insertions, 4 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index a070caed5c8e..4820c2aaeb5a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -425,7 +425,7 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
static void release_task_stack(struct task_struct *tsk)
{
- if (WARN_ON(tsk->state != TASK_DEAD))
+ if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD))
return; /* Better to leak the stack than to free prematurely */
account_kernel_stack(tsk, -1);
@@ -742,6 +742,7 @@ void __put_task_struct(struct task_struct *tsk)
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
+ sched_core_free(tsk);
if (!profile_handoff_task(tsk))
free_task(tsk);
@@ -1999,7 +2000,7 @@ static __latent_entropy struct task_struct *copy_process(
goto bad_fork_cleanup_count;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
- p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE);
+ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY);
p->flags |= PF_FORKNOEXEC;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
@@ -2249,6 +2250,8 @@ static __latent_entropy struct task_struct *copy_process(
klp_copy_process(p);
+ sched_core_fork(p);
+
spin_lock(&current->sighand->siglock);
/*
@@ -2336,6 +2339,7 @@ static __latent_entropy struct task_struct *copy_process(
return p;
bad_fork_cancel_cgroup:
+ sched_core_free(p);
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p, args);
@@ -2387,7 +2391,7 @@ bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
exit_creds(p);
bad_fork_free:
- p->state = TASK_DEAD;
+ WRITE_ONCE(p->__state, TASK_DEAD);
put_task_stack(p);
delayed_free_task(p);
fork_out:
@@ -2407,7 +2411,7 @@ static inline void init_idle_pids(struct task_struct *idle)
}
}
-struct task_struct *fork_idle(int cpu)
+struct task_struct * __init fork_idle(int cpu)
{
struct task_struct *task;
struct kernel_clone_args args = {