[PATCH tip/core/rcu 03/10] rcu: Fix data-race due to atomic_t copy-by-value

[paulmck]

From: Marco Elver <elver@xxxxxxxxxx>

This fixes a data-race where `atomic_t dynticks` is copied by value. The
copy is performed non-atomically, resulting in a data-race if `dynticks`
is updated concurrently.

This data-race was found with KCSAN:
==================================================================
BUG: KCSAN: data-race in dyntick_save_progress_counter / rcu_irq_enter

write to 0xffff989dbdbe98e0 of 4 bytes by task 10 on cpu 3:
 atomic_add_return include/asm-generic/atomic-instrumented.h:78 [inline]
 rcu_dynticks_snap kernel/rcu/tree.c:310 [inline]
 dyntick_save_progress_counter+0x43/0x1b0 kernel/rcu/tree.c:984
 force_qs_rnp+0x183/0x200 kernel/rcu/tree.c:2286
 rcu_gp_fqs kernel/rcu/tree.c:1601 [inline]
 rcu_gp_fqs_loop+0x71/0x880 kernel/rcu/tree.c:1653
 rcu_gp_kthread+0x22c/0x3b0 kernel/rcu/tree.c:1799
 kthread+0x1b5/0x200 kernel/kthread.c:255
 <snip>

read to 0xffff989dbdbe98e0 of 4 bytes by task 154 on cpu 7:
 rcu_nmi_enter_common kernel/rcu/tree.c:828 [inline]
 rcu_irq_enter+0xda/0x240 kernel/rcu/tree.c:870
 irq_enter+0x5/0x50 kernel/softirq.c:347
 <snip>

Reported by Kernel Concurrency Sanitizer on:
CPU: 7 PID: 154 Comm: kworker/7:1H Not tainted 5.3.0+ #5
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
Workqueue: kblockd blk_mq_run_work_fn
==================================================================

Signed-off-by: Marco Elver <elver@xxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
Cc: rcu@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Reviewed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
---
 include/trace/events/rcu.h |  4 ++--
 kernel/rcu/tree.c          | 11 ++++++-----
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 6612260..697e2c0 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -449,7 +449,7 @@ TRACE_EVENT_RCU(rcu_fqs,
  */
 TRACE_EVENT_RCU(rcu_dyntick,
 
-	TP_PROTO(const char *polarity, long oldnesting, long newnesting, atomic_t dynticks),
+	TP_PROTO(const char *polarity, long oldnesting, long newnesting, int dynticks),
 
 	TP_ARGS(polarity, oldnesting, newnesting, dynticks),
 
@@ -464,7 +464,7 @@ TRACE_EVENT_RCU(rcu_dyntick,
 		__entry->polarity = polarity;
 		__entry->oldnesting = oldnesting;
 		__entry->newnesting = newnesting;
-		__entry->dynticks = atomic_read(&dynticks);
+		__entry->dynticks = dynticks;
 	),
 
 	TP_printk("%s %lx %lx %#3x", __entry->polarity,
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1694a6b..6145e08 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -577,7 +577,7 @@ static void rcu_eqs_enter(bool user)
 	}
 
 	lockdep_assert_irqs_disabled();
-	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, rdp->dynticks);
+	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	rdp = this_cpu_ptr(&rcu_data);
 	do_nocb_deferred_wakeup(rdp);
@@ -650,14 +650,15 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 	 * leave it in non-RCU-idle state.
 	 */
 	if (rdp->dynticks_nmi_nesting != 1) {
-		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks);
+		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
+				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
 			   rdp->dynticks_nmi_nesting - 2);
 		return;
 	}
 
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
-	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, rdp->dynticks);
+	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
 	if (irq)
@@ -744,7 +745,7 @@ static void rcu_eqs_exit(bool user)
 	rcu_dynticks_task_exit();
 	rcu_dynticks_eqs_exit();
 	rcu_cleanup_after_idle();
-	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, rdp->dynticks);
+	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
 	WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
@@ -833,7 +834,7 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 	}
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
-			  rdp->dynticks_nmi_nesting + incby, rdp->dynticks);
+			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
 		   rdp->dynticks_nmi_nesting + incby);
 	barrier();
-- 
2.9.5