[PATCH v2 4/5] nohz: add cpu_isolated_debug boot flag

[Chris Metcalf]

This flag simplifies debugging of NO_HZ_FULL kernels when processes
are running in PR_CPU_ISOLATED_ENABLE mode.  Such processes should
get no interrupts from the kernel, and if they do, when this boot
flag is specified a kernel stack dump on the console is generated.

It's possible to use ftrace to simply detect whether a cpu_isolated core
has unexpectedly entered the kernel.  But what this boot flag does
is allow the kernel to provide better diagnostics, e.g. by reporting
in the IPI-generating code what remote core and context is preparing
to deliver an interrupt to a cpu_isolated core.

It may be worth considering other ways to generate useful debugging
output rather than console spew, but for now that is simple and direct.

Signed-off-by: Chris Metcalf <cmetcalf@xxxxxxxxxx>
---
 Documentation/kernel-parameters.txt |  6 ++++++
 arch/tile/mm/homecache.c            |  5 ++++-
 include/linux/tick.h                |  2 ++
 kernel/irq_work.c                   |  4 +++-
 kernel/sched/core.c                 | 18 ++++++++++++++++++
 kernel/signal.c                     |  5 +++++
 kernel/smp.c                        |  4 ++++
 kernel/softirq.c                    |  6 ++++++
 8 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f6befa9855c1..2b4c89225d25 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -743,6 +743,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			/proc/<pid>/coredump_filter.
 			See also Documentation/filesystems/proc.txt.
 
+	cpu_isolated_debug	[KNL]
+			In kernels built with CONFIG_NO_HZ_FULL and booted
+			in nohz_full= mode, this setting will generate console
+			backtraces when the kernel is about to interrupt a
+			task that has requested PR_CPU_ISOLATED_ENABLE.
+
 	cpuidle.off=1	[CPU_IDLE]
 			disable the cpuidle sub-system
 
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index 40ca30a9fee3..f336880e1b01 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -31,6 +31,7 @@
 #include <linux/smp.h>
 #include <linux/module.h>
 #include <linux/hugetlb.h>
+#include <linux/tick.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -83,8 +84,10 @@ static void hv_flush_update(const struct cpumask *cache_cpumask,
 	 * Don't bother to update atomically; losing a count
 	 * here is not that critical.
 	 */
-	for_each_cpu(cpu, &mask)
+	for_each_cpu(cpu, &mask) {
 		++per_cpu(irq_stat, cpu).irq_hv_flush_count;
+		tick_nohz_cpu_isolated_debug(cpu);
+	}
 }
 
 /*
diff --git a/include/linux/tick.h b/include/linux/tick.h
index b7ffb10337ba..0b0d76106b8c 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -149,6 +149,7 @@ extern void __tick_nohz_task_switch(struct task_struct *tsk);
 extern void tick_nohz_cpu_isolated_enter(void);
 extern void tick_nohz_cpu_isolated_syscall(int nr);
 extern void tick_nohz_cpu_isolated_exception(void);
+extern void tick_nohz_cpu_isolated_debug(int cpu);
 #else
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
@@ -161,6 +162,7 @@ static inline bool tick_nohz_is_cpu_isolated(void) { return false; }
 static inline void tick_nohz_cpu_isolated_enter(void) { }
 static inline void tick_nohz_cpu_isolated_syscall(int nr) { }
 static inline void tick_nohz_cpu_isolated_exception(void) { }
+static inline void tick_nohz_cpu_isolated_debug(int cpu) { }
 #endif
 
 static inline bool is_housekeeping_cpu(int cpu)
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index cbf9fb899d92..7f35c90346de 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -75,8 +75,10 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	if (!irq_work_claim(work))
 		return false;
 
-	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) {
+		tick_nohz_cpu_isolated_debug(cpu);
 		arch_send_call_function_single_ipi(cpu);
+	}
 
 	return true;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9123a82cbb6..7315e7272e94 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -719,6 +719,24 @@ bool sched_can_stop_tick(void)
 
 	return true;
 }
+
+/* Enable debugging of any interrupts of cpu_isolated cores. */
+static int cpu_isolated_debug;
+static int __init cpu_isolated_debug_func(char *str)
+{
+	cpu_isolated_debug = true;
+	return 1;
+}
+__setup("cpu_isolated_debug", cpu_isolated_debug_func);
+
+void tick_nohz_cpu_isolated_debug(int cpu)
+{
+	if (cpu_isolated_debug && tick_nohz_full_cpu(cpu) &&
+	    (cpu_curr(cpu)->cpu_isolated_flags & PR_CPU_ISOLATED_ENABLE)) {
+		pr_err("Interrupt detected for cpu_isolated cpu %d\n", cpu);
+		dump_stack();
+	}
+}
 #endif /* CONFIG_NO_HZ_FULL */
 
 void sched_avg_update(struct rq *rq)
diff --git a/kernel/signal.c b/kernel/signal.c
index d51c5ddd855c..1a810ac2656e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -689,6 +689,11 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
  */
 void signal_wake_up_state(struct task_struct *t, unsigned int state)
 {
+#ifdef CONFIG_NO_HZ_FULL
+	/* If the task is being killed, don't complain about cpu_isolated. */
+	if (state & TASK_WAKEKILL)
+		t->cpu_isolated_flags = 0;
+#endif
 	set_tsk_thread_flag(t, TIF_SIGPENDING);
 	/*
 	 * TASK_WAKEKILL also means wake it up in the stopped/traced/killable
diff --git a/kernel/smp.c b/kernel/smp.c
index 07854477c164..6b7d8e2c8af4 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -14,6 +14,7 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/tick.h>
 
 #include "smpboot.h"
 
@@ -178,6 +179,7 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 	 * locking and barrier primitives. Generic code isn't really
 	 * equipped to do the right thing...
 	 */
+	tick_nohz_cpu_isolated_debug(cpu);
 	if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
 		arch_send_call_function_single_ipi(cpu);
 
@@ -457,6 +459,8 @@ void smp_call_function_many(const struct cpumask *mask,
 	}
 
 	/* Send a message to all CPUs in the map */
+	for_each_cpu(cpu, cfd->cpumask)
+		tick_nohz_cpu_isolated_debug(cpu);
 	arch_send_call_function_ipi_mask(cfd->cpumask);
 
 	if (wait) {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 479e4436f787..333872925ff6 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -24,6 +24,7 @@
 #include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/smpboot.h>
+#include <linux/context_tracking.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
 
@@ -335,6 +336,11 @@ void irq_enter(void)
 		_local_bh_enable();
 	}
 
+	if (context_tracking_cpu_is_enabled() &&
+	    context_tracking_in_user() &&
+	    !in_interrupt())
+		tick_nohz_cpu_isolated_debug(smp_processor_id());
+
 	__irq_enter();
 }
 
-- 
2.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/