Merge tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Improve the scalability of the CFS bandwidth unthrottling logic with
   large number of CPUs.

 - Fix & rework various cpuidle routines, simplify interaction with the
   generic scheduler code. Add __cpuidle methods as noinstr to objtool's
   noinstr detection and fix boatloads of cpuidle bugs & quirks.

 - Add new ABI: introduce MEMBARRIER_CMD_GET_REGISTRATIONS, to query
   previously issued registrations.

 - Limit scheduler slice duration to the sysctl_sched_latency period, to
   improve scheduling granularity with a large number of SCHED_IDLE
   tasks.

 - Debuggability enhancement on sys_exit(): warn about disabled IRQs,
   but also enable them to prevent a cascade of followup problems and
   repeat warnings.

 - Fix the rescheduling logic in prio_changed_dl().

 - Micro-optimize cpufreq and sched-util methods.

 - Micro-optimize ttwu_runnable()

 - Micro-optimize the idle-scanning in update_numa_stats(),
   select_idle_capacity() and steal_cookie_task().

 - Update the RSEQ code & self-tests

 - Constify various scheduler methods

 - Remove unused methods

 - Refine __init tags

 - Documentation updates

 - Misc other cleanups, fixes

* tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
  sched/rt: pick_next_rt_entity(): check list_entry
  sched/deadline: Add more reschedule cases to prio_changed_dl()
  sched/fair: sanitize vruntime of entity being placed
  sched/fair: Remove capacity inversion detection
  sched/fair: unlink misfit task from cpu overutilized
  objtool: mem*() are not uaccess safe
  cpuidle: Fix poll_idle() noinstr annotation
  sched/clock: Make local_clock() noinstr
  sched/clock/x86: Mark sched_clock() noinstr
  x86/pvclock: Improve atomic update of last_value in pvclock_clocksource_read()
  x86/atomics: Always inline arch_atomic64*()
  cpuidle: tracing, preempt: Squash _rcuidle tracing
  cpuidle: tracing: Warn about !rcu_is_watching()
  cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG
  cpuidle: drivers: firmware: psci: Dont instrument suspend code
  KVM: selftests: Fix build of rseq test
  exit: Detect and fix irq disabled state in oops
  cpuidle, arm64: Fix the ARM64 cpuidle logic
  cpuidle: mvebu: Fix duplicate flags assignment
  sched/fair: Limit sched slice duration
  ...

2 files changed, 9 insertions, 0 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 9a780fafc539..8a884e795f6a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -46,6 +46,7 @@
 #include <linux/cred.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
+#include <linux/rseq.h>
 #include <asm/param.h>
 #include <asm/page.h>
 
@@ -288,6 +289,10 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	if (bprm->have_execfd) {
 		NEW_AUX_ENT(AT_EXECFD, bprm->execfd);
 	}
+#ifdef CONFIG_RSEQ
+	NEW_AUX_ENT(AT_RSEQ_FEATURE_SIZE, offsetof(struct rseq, end));
+	NEW_AUX_ENT(AT_RSEQ_ALIGN, __alignof__(struct rseq));
+#endif
 #undef NEW_AUX_ENT
 	/* AT_NULL is zero; clear the rest too */
 	memset(elf_info, 0, (char *)mm->saved_auxv +
diff --git a/fs/exec.c b/fs/exec.c
index 3d2b80d8d58e..5c00670d25f3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1010,6 +1010,7 @@ static int exec_mmap(struct mm_struct *mm)
 	active_mm = tsk->active_mm;
 	tsk->active_mm = mm;
 	tsk->mm = mm;
+	mm_init_cid(mm);
 	/*
 	 * This prevents preemption while active_mm is being loaded and
 	 * it and mm are being updated, which could cause problems for
@@ -1822,6 +1823,7 @@ static int bprm_execve(struct linux_binprm *bprm,
 	 */
 	check_unsafe_exec(bprm);
 	current->in_execve = 1;
+	sched_mm_cid_before_execve(current);
 
 	file = do_open_execat(fd, filename, flags);
 	retval = PTR_ERR(file);
@@ -1852,6 +1854,7 @@ static int bprm_execve(struct linux_binprm *bprm,
 	if (retval < 0)
 		goto out;
 
+	sched_mm_cid_after_execve(current);
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
@@ -1871,6 +1874,7 @@ out:
 		force_fatal_sig(SIGSEGV);
 
 out_unmark:
+	sched_mm_cid_after_execve(current);
 	current->fs->in_exec = 0;
 	current->in_execve = 0;