rcu: Don't use NMIs to dump other CPUs' stacks

Although NMI-based stack dumps are in principle more accurate, they are
also more likely to trigger deadlocks.  This commit therefore replaces
all uses of trigger_all_cpu_backtrace() with rcu_dump_cpu_stacks(), so
that the CPU detecting an RCU CPU stall does the stack dumping.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>

1 files changed, 3 insertions, 7 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3f93033d3c61..8f3e4d43d736 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1013,10 +1013,7 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 }
 
 /*
- * Dump stacks of all tasks running on stalled CPUs.  This is a fallback
- * for architectures that do not implement trigger_all_cpu_backtrace().
- * The NMI-triggered stack traces are more accurate because they are
- * printed by the target CPU.
+ * Dump stacks of all tasks running on stalled CPUs.
  */
 static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 {
@@ -1094,7 +1091,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
                (long)rsp->gpnum, (long)rsp->completed, totqlen);
         if (ndetected == 0)
                 pr_err("INFO: Stall ended before state dump start\n");
-        else if (!trigger_all_cpu_backtrace())
+        else
                 rcu_dump_cpu_stacks(rsp);
 
         /* Complain about tasks blocking the grace period. */
@@ -1125,8 +1122,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
         pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
                 jiffies - rsp->gp_start,
                 (long)rsp->gpnum, (long)rsp->completed, totqlen);
-        if (!trigger_all_cpu_backtrace())
-                dump_stack();
+        rcu_dump_cpu_stacks(rsp);
 
         raw_spin_lock_irqsave(&rnp->lock, flags);
         if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))