Merge tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Clean up SCHED_DEBUG: move the decades old mess of sysctl, procfs and
   debugfs interfaces to a unified debugfs interface.

 - Signals: Allow caching one sigqueue object per task, to improve
   performance & latencies.

 - Improve newidle_balance() irq-off latencies on systems with a large
   number of CPU cgroups.

 - Improve energy-aware scheduling

 - Improve the PELT metrics for certain workloads

 - Reintroduce select_idle_smt() to improve load-balancing locality -
   but without the previous regressions

 - Add 'scheduler latency debugging': warn after long periods of pending
   need_resched. This is an opt-in feature that requires the enabling of
   the LATENCY_WARN scheduler feature, or the use of the
   resched_latency_warn_ms=xx boot parameter.

 - CPU hotplug fixes for HP-rollback, and for the 'fail' interface. Fix
   remaining balance_push() vs. hotplug holes/races

 - PSI fixes, plus allow /proc/pressure/ files to be written by
   CAP_SYS_RESOURCE tasks as well

 - Fix/improve various load-balancing corner cases vs. capacity margins

 - Fix sched topology on systems with NUMA diameter of 3 or above

 - Fix PF_KTHREAD vs to_kthread() race

 - Minor rseq optimizations

 - Misc cleanups, optimizations, fixes and smaller updates

* tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  cpumask/hotplug: Fix cpu_dying() state tracking
  kthread: Fix PF_KTHREAD vs to_kthread() race
  sched/debug: Fix cgroup_path[] serialization
  sched,psi: Handle potential task count underflow bugs more gracefully
  sched: Warn on long periods of pending need_resched
  sched/fair: Move update_nohz_stats() to the CONFIG_NO_HZ_COMMON block to simplify the code & fix an unused function warning
  sched/debug: Rename the sched_debug parameter to sched_verbose
  sched,fair: Alternative sched_slice()
  sched: Move /proc/sched_debug to debugfs
  sched,debug: Convert sysctl sched_domains to debugfs
  debugfs: Implement debugfs_create_str()
  sched,preempt: Move preempt_dynamic to debug.c
  sched: Move SCHED_DEBUG sysctl to debugfs
  sched: Don't make LATENCYTOP select SCHED_DEBUG
  sched: Remove sched_schedstats sysctl out from under SCHED_DEBUG
  sched/numa: Allow runtime enabling/disabling of NUMA balance without SCHED_DEBUG
  sched: Use cpu_dying() to fix balance_push vs hotplug-rollback
  cpumask: Introduce DYING mask
  cpumask: Make cpu_{online,possible,present,active}() inline
  rseq: Optimise rseq_get_rseq_cs() and clear_rseq_cs()
  ...

1 files changed, 21 insertions, 8 deletions

diff --git a/kernel/rseq.c b/kernel/rseq.c
index a4f86a9d6937..35f7bd0fced0 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -84,13 +84,20 @@
 static int rseq_update_cpu_id(struct task_struct *t)
 {
 	u32 cpu_id = raw_smp_processor_id();
+	struct rseq __user *rseq = t->rseq;
 
-	if (put_user(cpu_id, &t->rseq->cpu_id_start))
-		return -EFAULT;
-	if (put_user(cpu_id, &t->rseq->cpu_id))
-		return -EFAULT;
+	if (!user_write_access_begin(rseq, sizeof(*rseq)))
+		goto efault;
+	unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end);
+	unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end);
+	user_write_access_end();
 	trace_rseq_update(t);
 	return 0;
+
+efault_end:
+	user_write_access_end();
+efault:
+	return -EFAULT;
 }
 
 static int rseq_reset_rseq_cpu_id(struct task_struct *t)
@@ -120,8 +127,13 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	u32 sig;
 	int ret;
 
+#ifdef CONFIG_64BIT
+	if (get_user(ptr, &t->rseq->rseq_cs.ptr64))
+		return -EFAULT;
+#else
 	if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
 		return -EFAULT;
+#endif
 	if (!ptr) {
 		memset(rseq_cs, 0, sizeof(*rseq_cs));
 		return 0;
@@ -204,9 +216,13 @@ static int clear_rseq_cs(struct task_struct *t)
 	 *
 	 * Set rseq_cs to NULL.
 	 */
+#ifdef CONFIG_64BIT
+	return put_user(0UL, &t->rseq->rseq_cs.ptr64);
+#else
 	if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
 		return -EFAULT;
 	return 0;
+#endif
 }
 
 /*
@@ -266,8 +282,6 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 
 	if (unlikely(t->flags & PF_EXITING))
 		return;
-	if (unlikely(!access_ok(t->rseq, sizeof(*t->rseq))))
-		goto error;
 	ret = rseq_ip_fixup(regs);
 	if (unlikely(ret < 0))
 		goto error;
@@ -294,8 +308,7 @@ void rseq_syscall(struct pt_regs *regs)
 
 	if (!t->rseq)
 		return;
-	if (!access_ok(t->rseq, sizeof(*t->rseq)) ||
-	    rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs))
+	if (rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs))
 		force_sig(SIGSEGV);
 }