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
  ...

5 files changed, 13 insertions, 9 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 187b3f2b9202..3d73cbb439fa 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1537,7 +1537,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 {
 	const struct cred *cred;
 	unsigned int i, len;
-	
+	unsigned int state;
+
 	/* first copy the parameters from user space */
 	memset(psinfo, 0, sizeof(struct elf_prpsinfo));
 
@@ -1559,7 +1560,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 	psinfo->pr_pgrp = task_pgrp_vnr(p);
 	psinfo->pr_sid = task_session_vnr(p);
 
-	i = p->state ? ffz(~p->state) + 1 : 0;
+	state = READ_ONCE(p->__state);
+	i = state ? ffz(~state) + 1 : 0;
 	psinfo->pr_state = i;
 	psinfo->pr_sname = (i > 5) ? '.' : "RSDTZW"[i];
 	psinfo->pr_zomb = psinfo->pr_sname == 'Z';
@@ -1571,7 +1573,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 	SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid));
 	rcu_read_unlock();
 	strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
-	
+
 	return 0;
 }
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 2c99b102c860..ab9c31ddffda 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1331,6 +1331,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 {
 	const struct cred *cred;
 	unsigned int i, len;
+	unsigned int state;
 
 	/* first copy the parameters from user space */
 	memset(psinfo, 0, sizeof(struct elf_prpsinfo));
@@ -1353,7 +1354,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 	psinfo->pr_pgrp = task_pgrp_vnr(p);
 	psinfo->pr_sid = task_session_vnr(p);
 
-	i = p->state ? ffz(~p->state) + 1 : 0;
+	state = READ_ONCE(p->__state);
+	i = state ? ffz(~state) + 1 : 0;
 	psinfo->pr_state = i;
 	psinfo->pr_sname = (i > 5) ? '.' : "RSDTZW"[i];
 	psinfo->pr_zomb = psinfo->pr_sname == 'Z';
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index 8468baee951d..f32878d9a39f 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -16,7 +16,7 @@ static int loadavg_proc_show(struct seq_file *m, void *v)
 
 	get_avenrun(avnrun, FIXED_1/200, 0);
 
-	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n",
+	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %u/%d %d\n",
 		LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
 		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
 		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index f25e8531fd27..6561a06ef905 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -200,8 +200,8 @@ static int show_stat(struct seq_file *p, void *v)
 		"\nctxt %llu\n"
 		"btime %llu\n"
 		"processes %lu\n"
-		"procs_running %lu\n"
-		"procs_blocked %lu\n",
+		"procs_running %u\n"
+		"procs_blocked %u\n",
 		nr_context_switches(),
 		(unsigned long long)boottime.tv_sec,
 		total_forks,
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 14f92285d04f..dd7a6c62b56f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -337,7 +337,7 @@ out:
 	return ret;
 }
 
-static inline long userfaultfd_get_blocking_state(unsigned int flags)
+static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags)
 {
 	if (flags & FAULT_FLAG_INTERRUPTIBLE)
 		return TASK_INTERRUPTIBLE;
@@ -370,7 +370,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	struct userfaultfd_wait_queue uwq;
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 	bool must_wait;
-	long blocking_state;
+	unsigned int blocking_state;
 
 	/*
 	 * We don't do userfault handling for the final child pid update.