1 files changed, 36 insertions, 16 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index 385179dae360..f085ebcdf9e7 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -46,6 +46,8 @@ static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data);
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
 
+static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1);
+
 static void __flush_smp_call_function_queue(bool warn_cpu_offline);
 
 int smpcfd_prepare_cpu(unsigned int cpu)
@@ -125,7 +127,7 @@ send_call_function_ipi_mask(struct cpumask *mask)
 }
 
 static __always_inline void
-csd_do_func(smp_call_func_t func, void *info, struct __call_single_data *csd)
+csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd)
 {
 	trace_csd_function_entry(func, csd);
 	func(info);
@@ -168,11 +170,13 @@ static DEFINE_PER_CPU(void *, cur_csd_info);
 
 static ulong csd_lock_timeout = 5000;  /* CSD lock timeout in milliseconds. */
 module_param(csd_lock_timeout, ulong, 0444);
+static int panic_on_ipistall;  /* CSD panic timeout in milliseconds, 300000 for five minutes. */
+module_param(panic_on_ipistall, int, 0444);
 
 static atomic_t csd_bug_count = ATOMIC_INIT(0);
 
 /* Record current CSD work for current CPU, NULL to erase. */
-static void __csd_lock_record(struct __call_single_data *csd)
+static void __csd_lock_record(call_single_data_t *csd)
 {
 	if (!csd) {
 		smp_mb(); /* NULL cur_csd after unlock. */
@@ -187,13 +191,13 @@ static void __csd_lock_record(struct __call_single_data *csd)
 		  /* Or before unlock, as the case may be. */
 }
 
-static __always_inline void csd_lock_record(struct __call_single_data *csd)
+static __always_inline void csd_lock_record(call_single_data_t *csd)
 {
 	if (static_branch_unlikely(&csdlock_debug_enabled))
 		__csd_lock_record(csd);
 }
 
-static int csd_lock_wait_getcpu(struct __call_single_data *csd)
+static int csd_lock_wait_getcpu(call_single_data_t *csd)
 {
 	unsigned int csd_type;
 
@@ -208,7 +212,7 @@ static int csd_lock_wait_getcpu(struct __call_single_data *csd)
  * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU,
  * so waiting on other types gets much less information.
  */
-static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *ts1, int *bug_id)
+static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id)
 {
 	int cpu = -1;
 	int cpux;
@@ -228,6 +232,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
 	}
 
 	ts2 = sched_clock();
+	/* How long since we last checked for a stuck CSD lock.*/
 	ts_delta = ts2 - *ts1;
 	if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0))
 		return false;
@@ -241,9 +246,17 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
 	else
 		cpux = cpu;
 	cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */
+	/* How long since this CSD lock was stuck. */
+	ts_delta = ts2 - ts0;
 	pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n",
-		 firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts2 - ts0,
+		 firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta,
 		 cpu, csd->func, csd->info);
+	/*
+	 * If the CSD lock is still stuck after 5 minutes, it is unlikely
+	 * to become unstuck. Use a signed comparison to avoid triggering
+	 * on underflows when the TSC is out of sync between sockets.
+	 */
+	BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC));
 	if (cpu_cur_csd && csd != cpu_cur_csd) {
 		pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n",
 			 *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)),
@@ -253,13 +266,15 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
 			 *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request");
 	}
 	if (cpu >= 0) {
-		dump_cpu_task(cpu);
+		if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0))
+			dump_cpu_task(cpu);
 		if (!cpu_cur_csd) {
 			pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);
 			arch_send_call_function_single_ipi(cpu);
 		}
 	}
-	dump_stack();
+	if (firsttime)
+		dump_stack();
 	*ts1 = ts2;
 
 	return false;
@@ -272,7 +287,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
  * previous function call. For multi-cpu calls its even more interesting
  * as we'll have to ensure no other cpu is observing our csd.
  */
-static void __csd_lock_wait(struct __call_single_data *csd)
+static void __csd_lock_wait(call_single_data_t *csd)
 {
 	int bug_id = 0;
 	u64 ts0, ts1;
@@ -286,7 +301,7 @@ static void __csd_lock_wait(struct __call_single_data *csd)
 	smp_acquire__after_ctrl_dep();
 }
 
-static __always_inline void csd_lock_wait(struct __call_single_data *csd)
+static __always_inline void csd_lock_wait(call_single_data_t *csd)
 {
 	if (static_branch_unlikely(&csdlock_debug_enabled)) {
 		__csd_lock_wait(csd);
@@ -296,17 +311,17 @@ static __always_inline void csd_lock_wait(struct __call_single_data *csd)
 	smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
 }
 #else
-static void csd_lock_record(struct __call_single_data *csd)
+static void csd_lock_record(call_single_data_t *csd)
 {
 }
 
-static __always_inline void csd_lock_wait(struct __call_single_data *csd)
+static __always_inline void csd_lock_wait(call_single_data_t *csd)
 {
 	smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
 }
 #endif
 
-static __always_inline void csd_lock(struct __call_single_data *csd)
+static __always_inline void csd_lock(call_single_data_t *csd)
 {
 	csd_lock_wait(csd);
 	csd->node.u_flags |= CSD_FLAG_LOCK;
@@ -319,7 +334,7 @@ static __always_inline void csd_lock(struct __call_single_data *csd)
 	smp_wmb();
 }
 
-static __always_inline void csd_unlock(struct __call_single_data *csd)
+static __always_inline void csd_unlock(call_single_data_t *csd)
 {
 	WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK));
 
@@ -372,7 +387,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node)
  * for execution on the given CPU. data must already have
  * ->func, ->info, and ->flags set.
  */
-static int generic_exec_single(int cpu, struct __call_single_data *csd)
+static int generic_exec_single(int cpu, call_single_data_t *csd)
 {
 	if (cpu == smp_processor_id()) {
 		smp_call_func_t func = csd->func;
@@ -433,9 +448,14 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline)
 	struct llist_node *entry, *prev;
 	struct llist_head *head;
 	static bool warned;
+	atomic_t *tbt;
 
 	lockdep_assert_irqs_disabled();
 
+	/* Allow waiters to send backtrace NMI from here onwards */
+	tbt = this_cpu_ptr(&trigger_backtrace);
+	atomic_set_release(tbt, 1);
+
 	head = this_cpu_ptr(&call_single_queue);
 	entry = llist_del_all(head);
 	entry = llist_reverse_order(entry);
@@ -658,7 +678,7 @@ EXPORT_SYMBOL(smp_call_function_single);
  *
  * Return: %0 on success or negative errno value on error
  */
-int smp_call_function_single_async(int cpu, struct __call_single_data *csd)
+int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 {
 	int err = 0;