Merge tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Fair scheduler (SCHED_OTHER) improvements:
   - Remove the old and now unused SIS_PROP code & option
   - Scan cluster before LLC in the wake-up path
   - Use candidate prev/recent_used CPU if scanning failed for cluster
     wakeup

  NUMA scheduling improvements:
   - Improve the VMA access-PID code to better skip/scan VMAs
   - Extend tracing to cover VMA-skipping decisions
   - Improve/fix the recently introduced sched_numa_find_nth_cpu() code
   - Generalize numa_map_to_online_node()

  Energy scheduling improvements:
   - Remove the EM_MAX_COMPLEXITY limit
   - Add tracepoints to track energy computation
   - Make the behavior of the 'sched_energy_aware' sysctl more
     consistent
   - Consolidate and clean up access to a CPU's max compute capacity
   - Fix uclamp code corner cases

  RT scheduling improvements:
   - Drive dl_rq->overloaded with dl_rq->pushable_dl_tasks updates
   - Drive the ->rto_mask with rt_rq->pushable_tasks updates

  Scheduler scalability improvements:
   - Rate-limit updates to tg->load_avg
   - On x86 disable IBRS when CPU is offline to improve single-threaded
     performance
   - Micro-optimize in_task() and in_interrupt()
   - Micro-optimize the PSI code
   - Avoid updating PSI triggers and ->rtpoll_total when there are no
     state changes

  Core scheduler infrastructure improvements:
   - Use saved_state to reduce some spurious freezer wakeups
   - Bring in a handful of fast-headers improvements to scheduler
     headers
   - Make the scheduler UAPI headers more widely usable by user-space
   - Simplify the control flow of scheduler syscalls by using lock
     guards
   - Fix sched_setaffinity() vs. CPU hotplug race

  Scheduler debuggability improvements:
   - Disallow writing invalid values to sched_rt_period_us
   - Fix a race in the rq-clock debugging code triggering warnings
   - Fix a warning in the bandwidth distribution code
   - Micro-optimize in_atomic_preempt_off() checks
   - Enforce that the tasklist_lock is held in for_each_thread()
   - Print the TGID in sched_show_task()
   - Remove the /proc/sys/kernel/sched_child_runs_first sysctl

  ... and misc cleanups & fixes"

* tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
  sched/fair: Remove SIS_PROP
  sched/fair: Use candidate prev/recent_used CPU if scanning failed for cluster wakeup
  sched/fair: Scan cluster before scanning LLC in wake-up path
  sched: Add cpus_share_resources API
  sched/core: Fix RQCF_ACT_SKIP leak
  sched/fair: Remove unused 'curr' argument from pick_next_entity()
  sched/nohz: Update comments about NEWILB_KICK
  sched/fair: Remove duplicate #include
  sched/psi: Update poll => rtpoll in relevant comments
  sched: Make PELT acronym definition searchable
  sched: Fix stop_one_cpu_nowait() vs hotplug
  sched/psi: Bail out early from irq time accounting
  sched/topology: Rename 'DIE' domain to 'PKG'
  sched/psi: Delete the 'update_total' function parameter from update_triggers()
  sched/psi: Avoid updating PSI triggers and ->rtpoll_total when there are no state changes
  sched/headers: Remove comment referring to rq::cpu_load, since this has been removed
  sched/numa: Complete scanning of inactive VMAs when there is no alternative
  sched/numa: Complete scanning of partial VMAs regardless of PID activity
  sched/numa: Move up the access pid reset logic
  sched/numa: Trace decisions related to skipping VMAs
  ...

4 files changed, 24 insertions, 5 deletions

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5826f5108a12..4e4870031265 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1051,7 +1051,7 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 #endif
 	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
 	{ cpu_mc_mask, SD_INIT_NAME(MC) },
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
 	{ NULL, },
 };
 
@@ -1595,7 +1595,7 @@ static void add_cpu_to_masks(int cpu)
 	/* Skip all CPUs already part of current CPU core mask */
 	cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
 
-	/* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+	/* If chip_id is -1; limit the cpu_core_mask to within PKG */
 	if (chip_id == -1)
 		cpumask_and(mask, mask, cpu_cpu_mask(cpu));
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 68adf1de8888..66bda6a8f918 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -522,7 +522,7 @@ static struct sched_domain_topology_level s390_topology[] = {
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
 	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
 	{ cpu_drawer_mask, SD_INIT_NAME(DRAWER) },
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
 	{ NULL, },
 };
 
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index cb0386fc4dc3..c648502e4535 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -4,6 +4,7 @@
 
 #include <linux/thread_info.h>
 #include <asm/nospec-branch.h>
+#include <asm/msr.h>
 
 /*
  * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
@@ -76,6 +77,16 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
 	return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
 }
 
+/*
+ * This can be used in noinstr functions & should only be called in bare
+ * metal context.
+ */
+static __always_inline void __update_spec_ctrl(u64 val)
+{
+	__this_cpu_write(x86_spec_ctrl_current, val);
+	native_wrmsrl(MSR_IA32_SPEC_CTRL, val);
+}
+
 #ifdef CONFIG_SMP
 extern void speculative_store_bypass_ht_init(void);
 #else
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2a187c0cbd5b..f7bcd42edaeb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -87,6 +87,7 @@
 #include <asm/hw_irq.h>
 #include <asm/stackprotector.h>
 #include <asm/sev.h>
+#include <asm/spec-ctrl.h>
 
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -640,13 +641,13 @@ static void __init build_sched_topology(void)
 	};
 #endif
 	/*
-	 * When there is NUMA topology inside the package skip the DIE domain
+	 * When there is NUMA topology inside the package skip the PKG domain
 	 * since the NUMA domains will auto-magically create the right spanning
 	 * domains based on the SLIT.
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE)
+			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(PKG)
 		};
 	}
 
@@ -1596,8 +1597,15 @@ void __noreturn hlt_play_dead(void)
 		native_halt();
 }
 
+/*
+ * native_play_dead() is essentially a __noreturn function, but it can't
+ * be marked as such as the compiler may complain about it.
+ */
 void native_play_dead(void)
 {
+	if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS))
+		__update_spec_ctrl(0);
+
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);