Merge tag 'core-rcu-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "These are the latest RCU updates for v5.12:

   - Documentation updates.

   - Miscellaneous fixes.

   - kfree_rcu() updates: Addition of mem_dump_obj() to provide
     allocator return addresses to more easily locate bugs. This has a
     couple of RCU-related commits, but is mostly MM. Was pulled in with
     akpm's agreement.

   - Per-callback-batch tracking of numbers of callbacks, which enables
     better debugging information and smarter reactions to large numbers
     of callbacks.

   - The first round of changes to allow CPUs to be runtime switched
     from and to callback-offloaded state.

   - CONFIG_PREEMPT_RT-related changes.

   - RCU CPU stall warning updates.

   - Addition of polling grace-period APIs for SRCU.

   - Torture-test and torture-test scripting updates, including a
     "torture everything" script that runs rcutorture, locktorture,
     scftorture, rcuscale, and refscale. Plus does an allmodconfig
     build.

   - nolibc fixes for the torture tests"

* tag 'core-rcu-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (130 commits)
  percpu_ref: Dump mem_dump_obj() info upon reference-count underflow
  rcu: Make call_rcu() print mem_dump_obj() info for double-freed callback
  mm: Make mem_obj_dump() vmalloc() dumps include start and length
  mm: Make mem_dump_obj() handle vmalloc() memory
  mm: Make mem_dump_obj() handle NULL and zero-sized pointers
  mm: Add mem_dump_obj() to print source of memory block
  tools/rcutorture: Fix position of -lgcc in mkinitrd.sh
  tools/nolibc: Fix position of -lgcc in the documented example
  tools/nolibc: Emit detailed error for missing alternate syscall number definitions
  tools/nolibc: Remove incorrect definitions of __ARCH_WANT_*
  tools/nolibc: Get timeval, timespec and timezone from linux/time.h
  tools/nolibc: Implement poll() based on ppoll()
  tools/nolibc: Implement fork() based on clone()
  tools/nolibc: Make getpgrp() fall back to getpgid(0)
  tools/nolibc: Make dup2() rely on dup3() when available
  tools/nolibc: Add the definition for dup()
  rcutorture: Add rcutree.use_softirq=0 to RUDE01 and TASKS01
  torture: Maintain torture-specific set of CPUs-online books
  torture: Clean up after torture-test CPU hotplugging
  rcutorture: Make object_debug also double call_rcu() heap object
  ...

1 files changed, 57 insertions, 3 deletions

diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 70d48c52fabc..475b26171b20 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -266,6 +266,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 	struct task_struct *t;
 	struct task_struct *ts[8];
 
+	lockdep_assert_irqs_disabled();
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
 	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
@@ -290,6 +291,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 				".q"[rscr.rs.b.need_qs],
 				".e"[rscr.rs.b.exp_hint],
 				".l"[rscr.on_blkd_list]);
+		lockdep_assert_irqs_disabled();
 		put_task_struct(t);
 		ndetected++;
 	}
@@ -333,9 +335,12 @@ static void rcu_dump_cpu_stacks(void)
 	rcu_for_each_leaf_node(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		for_each_leaf_node_possible_cpu(rnp, cpu)
-			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
-				if (!trigger_single_cpu_backtrace(cpu))
+			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
+				if (cpu_is_offline(cpu))
+					pr_err("Offline CPU %d blocking current GP.\n", cpu);
+				else if (!trigger_single_cpu_backtrace(cpu))
 					dump_cpu_task(cpu);
+			}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
@@ -449,25 +454,66 @@ static void print_cpu_stall_info(int cpu)
 /* Complain about starvation of grace-period kthread.  */
 static void rcu_check_gp_kthread_starvation(void)
 {
+	int cpu;
 	struct task_struct *gpk = rcu_state.gp_kthread;
 	unsigned long j;
 
 	if (rcu_is_gp_kthread_starving(&j)) {
+		cpu = gpk ? task_cpu(gpk) : -1;
 		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rcu_state.name, j,
 		       (long)rcu_seq_current(&rcu_state.gp_seq),
 		       data_race(rcu_state.gp_flags),
 		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
-		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
+		       gpk ? gpk->state : ~0, cpu);
 		if (gpk) {
 			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(gpk);
+			if (cpu >= 0) {
+				if (cpu_is_offline(cpu)) {
+					pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
+				} else  {
+					pr_err("Stack dump where RCU GP kthread last ran:\n");
+					if (!trigger_single_cpu_backtrace(cpu))
+						dump_cpu_task(cpu);
+				}
+			}
 			wake_up_process(gpk);
 		}
 	}
 }
 
+/* Complain about missing wakeups from expired fqs wait timer */
+static void rcu_check_gp_kthread_expired_fqs_timer(void)
+{
+	struct task_struct *gpk = rcu_state.gp_kthread;
+	short gp_state;
+	unsigned long jiffies_fqs;
+	int cpu;
+
+	/*
+	 * Order reads of .gp_state and .jiffies_force_qs.
+	 * Matching smp_wmb() is present in rcu_gp_fqs_loop().
+	 */
+	gp_state = smp_load_acquire(&rcu_state.gp_state);
+	jiffies_fqs = READ_ONCE(rcu_state.jiffies_force_qs);
+
+	if (gp_state == RCU_GP_WAIT_FQS &&
+	    time_after(jiffies, jiffies_fqs + RCU_STALL_MIGHT_MIN) &&
+	    gpk && !READ_ONCE(gpk->on_rq)) {
+		cpu = task_cpu(gpk);
+		pr_err("%s kthread timer wakeup didn't happen for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx\n",
+		       rcu_state.name, (jiffies - jiffies_fqs),
+		       (long)rcu_seq_current(&rcu_state.gp_seq),
+		       data_race(rcu_state.gp_flags),
+		       gp_state_getname(RCU_GP_WAIT_FQS), RCU_GP_WAIT_FQS,
+		       gpk->state);
+		pr_err("\tPossible timer handling issue on cpu=%d timer-softirq=%u\n",
+		       cpu, kstat_softirqs_cpu(TIMER_SOFTIRQ, cpu));
+	}
+}
+
 static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 {
 	int cpu;
@@ -478,6 +524,8 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	struct rcu_node *rnp;
 	long totqlen = 0;
 
+	lockdep_assert_irqs_disabled();
+
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads();
 	if (rcu_stall_is_suppressed())
@@ -499,6 +547,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 				}
 		}
 		ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock.
+		lockdep_assert_irqs_disabled();
 	}
 
 	for_each_possible_cpu(cpu)
@@ -529,6 +578,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 		WRITE_ONCE(rcu_state.jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 
+	rcu_check_gp_kthread_expired_fqs_timer();
 	rcu_check_gp_kthread_starvation();
 
 	panic_on_rcu_stall();
@@ -544,6 +594,8 @@ static void print_cpu_stall(unsigned long gps)
 	struct rcu_node *rnp = rcu_get_root();
 	long totqlen = 0;
 
+	lockdep_assert_irqs_disabled();
+
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads();
 	if (rcu_stall_is_suppressed())
@@ -564,6 +616,7 @@ static void print_cpu_stall(unsigned long gps)
 		jiffies - gps,
 		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
 
+	rcu_check_gp_kthread_expired_fqs_timer();
 	rcu_check_gp_kthread_starvation();
 
 	rcu_dump_cpu_stacks();
@@ -598,6 +651,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	unsigned long js;
 	struct rcu_node *rnp;
 
+	lockdep_assert_irqs_disabled();
 	if ((rcu_stall_is_suppressed() && !READ_ONCE(rcu_kick_kthreads)) ||
 	    !rcu_gp_in_progress())
 		return;