Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core fixes from Ingo Molnar:

 - workaround for gcc asm handling

 - futex race fixes

 - objtool build warning fix

 - two watchdog fixes: a crash fix (revert) and a bug fix for
   /proc/sys/kernel/watchdog_thresh handling.

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  objtool: Prevent GCC from merging annotate_unreachable(), take 2
  objtool: Resync objtool's instruction decoder source code copy with the kernel's latest version
  watchdog/hardlockup/perf: Use atomics to track in-use cpu counter
  watchdog/harclockup/perf: Revert a33d448 ("watchdog/hardlockup/perf: Simplify deferred event destroy")
  futex: Fix more put_pi_state() vs. exit_pi_state_list() races

Author: torvalds

include/linux/compiler.h

@@ -191,13 +191,13 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	asm("%c0:\n\t"							\
 	    ".pushsection .discard.reachable\n\t"			\
 	    ".long %c0b - .\n\t"					\
-	    ".popsection\n\t" : : "i" (__LINE__));			\
+	    ".popsection\n\t" : : "i" (__COUNTER__));			\
 })
 #define annotate_unreachable() ({					\
 	asm("%c0:\n\t"							\
 	    ".pushsection .discard.unreachable\n\t"			\
 	    ".long %c0b - .\n\t"					\
-	    ".popsection\n\t" : : "i" (__LINE__));			\
+	    ".popsection\n\t" : : "i" (__COUNTER__));			\
 })
 #define ASM_UNREACHABLE							\
 	"999:\n\t"							\

kernel/futex.c

@@ -903,11 +903,27 @@ void exit_pi_state_list(struct task_struct *curr)
 	 */
 	raw_spin_lock_irq(&curr->pi_lock);
 	while (!list_empty(head)) {
-
 		next = head->next;
 		pi_state = list_entry(next, struct futex_pi_state, list);
 		key = pi_state->key;
 		hb = hash_futex(&key);
+
+		/*
+		 * We can race against put_pi_state() removing itself from the
+		 * list (a waiter going away). put_pi_state() will first
+		 * decrement the reference count and then modify the list, so
+		 * its possible to see the list entry but fail this reference
+		 * acquire.
+		 *
+		 * In that case; drop the locks to let put_pi_state() make
+		 * progress and retry the loop.
+		 */
+		if (!atomic_inc_not_zero(&pi_state->refcount)) {
+			raw_spin_unlock_irq(&curr->pi_lock);
+			cpu_relax();
+			raw_spin_lock_irq(&curr->pi_lock);
+			continue;
+		}
 		raw_spin_unlock_irq(&curr->pi_lock);
 
 		spin_lock(&hb->lock);
@@ -918,18 +934,19 @@ void exit_pi_state_list(struct task_struct *curr)
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			/* retain curr->pi_lock for the loop invariant */
 			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
+			put_pi_state(pi_state);
 			continue;
 		}
 
 		WARN_ON(pi_state->owner != curr);
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		pi_state->owner = NULL;
-		raw_spin_unlock(&curr->pi_lock);
 
-		get_pi_state(pi_state);
+		raw_spin_unlock(&curr->pi_lock);
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 

kernel/watchdog_hld.c

@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) "NMI watchdog: " fmt
 
 #include <linux/nmi.h>
+#include <linux/atomic.h>
 #include <linux/module.h>
 #include <linux/sched/debug.h>
 
@@ -22,10 +23,11 @@
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+static DEFINE_PER_CPU(struct perf_event *, dead_event);
 static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
-static unsigned int watchdog_cpus;
+static atomic_t watchdog_cpus = ATOMIC_INIT(0);
 
 void arch_touch_nmi_watchdog(void)
 {
@@ -189,7 +191,8 @@ void hardlockup_detector_perf_enable(void)
 	if (hardlockup_detector_event_create())
 		return;
 
-	if (!watchdog_cpus++)
+	/* use original value for check */
+	if (!atomic_fetch_inc(&watchdog_cpus))
 		pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
 
 	perf_event_enable(this_cpu_read(watchdog_ev));
@@ -204,8 +207,10 @@ void hardlockup_detector_perf_disable(void)
 
 	if (event) {
 		perf_event_disable(event);
+		this_cpu_write(watchdog_ev, NULL);
+		this_cpu_write(dead_event, event);
 		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
-		watchdog_cpus--;
+		atomic_dec(&watchdog_cpus);
 	}
 }
 
@@ -219,15 +224,15 @@ void hardlockup_detector_perf_cleanup(void)
 	int cpu;
 
 	for_each_cpu(cpu, &dead_events_mask) {
-		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+		struct perf_event *event = per_cpu(dead_event, cpu);
 
 		/*
 		 * Required because for_each_cpu() reports  unconditionally
 		 * CPU0 as set on UP kernels. Sigh.
 		 */
 		if (event)
 			perf_event_release_kernel(event);
-		per_cpu(watchdog_ev, cpu) = NULL;
+		per_cpu(dead_event, cpu) = NULL;
 	}
 	cpumask_clear(&dead_events_mask);
 }

tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk

@@ -1,4 +1,5 @@
 #!/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0
 # gen-insn-attr-x86.awk: Instruction attribute table generator
 # Written by Masami Hiramatsu <[email protected]>
 #