Merge branches 'doc.2022.06.21a', 'fixes.2022.07.19a', 'nocb.2022.07.19a',...

Merge branches 'doc.2022.06.21a', 'fixes.2022.07.19a', 'nocb.2022.07.19a', 'poll.2022.07.21a', 'rcu-tasks.2022.06.21a' and 'torture.2022.06.21a' into HEAD

doc.2022.06.21a: Documentation updates.
fixes.2022.07.19a: Miscellaneous fixes.
nocb.2022.07.19a: Callback-offload updates.
poll.2022.07.21a: Polled grace-period updates.
rcu-tasks.2022.06.21a: Tasks RCU updates.
torture.2022.06.21a: Torture-test updates.

Documentation/admin-guide/kernel-parameters.txt

@@ -3659,6 +3659,9 @@
 			just as if they had also been called out in the
 			rcu_nocbs= boot parameter.
 
+			Note that this argument takes precedence over
+			the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
+
 	noiotrap	[SH] Disables trapped I/O port accesses.
 
 	noirqdebug	[X86-32] Disables the code which attempts to detect and
@@ -4557,6 +4560,9 @@
 			no-callback mode from boot but the mode may be
 			toggled at runtime via cpusets.
 
+			Note that this argument takes precedence over
+			the CONFIG_RCU_NOCB_CPU_DEFAULT_ALL option.
+
 	rcu_nocb_poll	[KNL]
 			Rather than requiring that offloaded CPUs
 			(specified by rcu_nocbs= above) explicitly
@@ -5799,6 +5805,24 @@
 			expediting.  Set to zero to disable automatic
 			expediting.
 
+	srcutree.srcu_max_nodelay [KNL]
+			Specifies the number of no-delay instances
+			per jiffy for which the SRCU grace period
+			worker thread will be rescheduled with zero
+			delay. Beyond this limit, worker thread will
+			be rescheduled with a sleep delay of one jiffy.
+
+	srcutree.srcu_max_nodelay_phase [KNL]
+			Specifies the per-grace-period phase, number of
+			non-sleeping polls of readers. Beyond this limit,
+			grace period worker thread will be rescheduled
+			with a sleep delay of one jiffy, between each
+			rescan of the readers, for a grace period phase.
+
+	srcutree.srcu_retry_check_delay [KNL]
+			Specifies number of microseconds of non-sleeping
+			delay between each non-sleeping poll of readers.
+
 	srcutree.small_contention_lim [KNL]
 			Specifies the number of update-side contention
 			events per jiffy will be tolerated before

include/linux/rcupdate.h

@@ -41,6 +41,7 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void rcu_barrier_tasks(void);
 void rcu_barrier_tasks_rude(void);
 void synchronize_rcu(void);
+unsigned long get_completed_synchronize_rcu(void);
 
 #ifdef CONFIG_PREEMPT_RCU
 
@@ -169,13 +170,24 @@ void synchronize_rcu_tasks(void);
 # endif
 
 # ifdef CONFIG_TASKS_TRACE_RCU
-# define rcu_tasks_trace_qs(t)						\
-	do {								\
-		if (!likely(READ_ONCE((t)->trc_reader_checked)) &&	\
-		    !unlikely(READ_ONCE((t)->trc_reader_nesting))) {	\
-			smp_store_release(&(t)->trc_reader_checked, true); \
-			smp_mb(); /* Readers partitioned by store. */	\
-		}							\
+// Bits for ->trc_reader_special.b.need_qs field.
+#define TRC_NEED_QS		0x1  // Task needs a quiescent state.
+#define TRC_NEED_QS_CHECKED	0x2  // Task has been checked for needing quiescent state.
+
+u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new);
+void rcu_tasks_trace_qs_blkd(struct task_struct *t);
+
+# define rcu_tasks_trace_qs(t)							\
+	do {									\
+		int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting);	\
+										\
+		if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) &&	\
+		    likely(!___rttq_nesting)) {					\
+			rcu_trc_cmpxchg_need_qs((t), 0,	TRC_NEED_QS_CHECKED);	\
+		} else if (___rttq_nesting && ___rttq_nesting != INT_MIN &&	\
+			   !READ_ONCE((t)->trc_reader_special.b.blocked)) {	\
+			rcu_tasks_trace_qs_blkd(t);				\
+		}								\
 	} while (0)
 # else
 # define rcu_tasks_trace_qs(t) do { } while (0)
@@ -184,7 +196,7 @@ void synchronize_rcu_tasks(void);
 #define rcu_tasks_qs(t, preempt)					\
 do {									\
 	rcu_tasks_classic_qs((t), (preempt));				\
-	rcu_tasks_trace_qs((t));					\
+	rcu_tasks_trace_qs(t);						\
 } while (0)
 
 # ifdef CONFIG_TASKS_RUDE_RCU

include/linux/rcupdate_trace.h

@@ -75,7 +75,7 @@ static inline void rcu_read_unlock_trace(void)
 	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
 	barrier(); // Critical section before disabling.
 	// Disable IPI-based setting of .need_qs.
-	WRITE_ONCE(t->trc_reader_nesting, INT_MIN);
+	WRITE_ONCE(t->trc_reader_nesting, INT_MIN + nesting);
 	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
 		WRITE_ONCE(t->trc_reader_nesting, nesting);
 		return;  // We assume shallow reader nesting.

include/linux/rcutiny.h

@@ -23,6 +23,16 @@ static inline void cond_synchronize_rcu(unsigned long oldstate)
 	might_sleep();
 }
 
+static inline unsigned long start_poll_synchronize_rcu_expedited(void)
+{
+	return start_poll_synchronize_rcu();
+}
+
+static inline void cond_synchronize_rcu_expedited(unsigned long oldstate)
+{
+	cond_synchronize_rcu(oldstate);
+}
+
 extern void rcu_barrier(void);
 
 static inline void synchronize_rcu_expedited(void)
@@ -38,7 +48,7 @@ static inline void synchronize_rcu_expedited(void)
  */
 extern void kvfree(const void *addr);
 
-static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+static inline void __kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	if (head) {
 		call_rcu(head, func);
@@ -51,6 +61,15 @@ static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	kvfree((void *) func);
 }
 
+#ifdef CONFIG_KASAN_GENERIC
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
+#else
+static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+	__kvfree_call_rcu(head, func);
+}
+#endif
+
 void rcu_qs(void);
 
 static inline void rcu_softirq_qs(void)

include/linux/rcutree.h

@@ -40,6 +40,8 @@ bool rcu_eqs_special_set(int cpu);
 void rcu_momentary_dyntick_idle(void);
 void kfree_rcu_scheduler_running(void);
 bool rcu_gp_might_be_stalled(void);
+unsigned long start_poll_synchronize_rcu_expedited(void);
+void cond_synchronize_rcu_expedited(unsigned long oldstate);
 unsigned long get_state_synchronize_rcu(void);
 unsigned long start_poll_synchronize_rcu(void);
 bool poll_state_synchronize_rcu(unsigned long oldstate);

include/linux/sched.h

@@ -843,8 +843,9 @@ struct task_struct {
 	int				trc_reader_nesting;
 	int				trc_ipi_to_cpu;
 	union rcu_special		trc_reader_special;
-	bool				trc_reader_checked;
 	struct list_head		trc_holdout_list;
+	struct list_head		trc_blkd_node;
+	int				trc_blkd_cpu;
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 
 	struct sched_info		sched_info;
@@ -2223,6 +2224,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
+extern struct task_struct *cpu_curr_snapshot(int cpu);
 
 /*
  * In order to reduce various lock holder preemption latencies provide an

init/init_task.c

@@ -157,6 +157,7 @@ struct task_struct init_task
 	.trc_reader_nesting = 0,
 	.trc_reader_special.s = 0,
 	.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
+	.trc_blkd_node = LIST_HEAD_INIT(init_task.trc_blkd_node),
 #endif
 #ifdef CONFIG_CPUSETS
 	.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,

kernel/fork.c

@@ -1814,6 +1814,7 @@ static inline void rcu_copy_process(struct task_struct *p)
 	p->trc_reader_nesting = 0;
 	p->trc_reader_special.s = 0;
 	INIT_LIST_HEAD(&p->trc_holdout_list);
+	INIT_LIST_HEAD(&p->trc_blkd_node);
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 

kernel/rcu/Kconfig

@@ -262,6 +262,35 @@ config RCU_NOCB_CPU
 	  Say Y here if you need reduced OS jitter, despite added overhead.
 	  Say N here if you are unsure.
 
+config RCU_NOCB_CPU_DEFAULT_ALL
+	bool "Offload RCU callback processing from all CPUs by default"
+	depends on RCU_NOCB_CPU
+	default n
+	help
+	  Use this option to offload callback processing from all CPUs
+	  by default, in the absence of the rcu_nocbs or nohz_full boot
+	  parameter. This also avoids the need to use any boot parameters
+	  to achieve the effect of offloading all CPUs on boot.
+
+	  Say Y here if you want offload all CPUs by default on boot.
+	  Say N here if you are unsure.
+
+config RCU_NOCB_CPU_CB_BOOST
+	bool "Offload RCU callback from real-time kthread"
+	depends on RCU_NOCB_CPU && RCU_BOOST
+	default y if PREEMPT_RT
+	help
+	  Use this option to invoke offloaded callbacks as SCHED_FIFO
+	  to avoid starvation by heavy SCHED_OTHER background load.
+	  Of course, running as SCHED_FIFO during callback floods will
+	  cause the rcuo[ps] kthreads to monopolize the CPU for hundreds
+	  of milliseconds or more.  Therefore, when enabling this option,
+	  it is your responsibility to ensure that latency-sensitive
+	  tasks either run with higher priority or run on some other CPU.
+
+	  Say Y here if you want to set RT priority for offloading kthreads.
+	  Say N here if you are building a !PREEMPT_RT kernel and are unsure.
+
 config TASKS_TRACE_RCU_READ_MB
 	bool "Tasks Trace RCU readers use memory barriers in user and idle"
 	depends on RCU_EXPERT && TASKS_TRACE_RCU

kernel/rcu/Kconfig.debug

@@ -121,7 +121,7 @@ config RCU_EQS_DEBUG
 
 config RCU_STRICT_GRACE_PERIOD
 	bool "Provide debug RCU implementation with short grace periods"
-	depends on DEBUG_KERNEL && RCU_EXPERT && NR_CPUS <= 4
+	depends on DEBUG_KERNEL && RCU_EXPERT && NR_CPUS <= 4 && !TINY_RCU
 	default n
 	select PREEMPT_COUNT if PREEMPT=n
 	help

kernel/rcu/rcu.h

@@ -23,6 +23,9 @@
 #define RCU_SEQ_CTR_SHIFT	2
 #define RCU_SEQ_STATE_MASK	((1 << RCU_SEQ_CTR_SHIFT) - 1)
 
+/* Low-order bit definition for polled grace-period APIs. */
+#define RCU_GET_STATE_COMPLETED	0x1
+
 extern int sysctl_sched_rt_runtime;
 
 /*
@@ -119,6 +122,18 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
 	return ULONG_CMP_GE(READ_ONCE(*sp), s);
 }
 
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not a
+ * full update-side operation has occurred, but do not allow the
+ * (ULONG_MAX / 2) safety-factor/guard-band.
+ */
+static inline bool rcu_seq_done_exact(unsigned long *sp, unsigned long s)
+{
+	unsigned long cur_s = READ_ONCE(*sp);
+
+	return ULONG_CMP_GE(cur_s, s) || ULONG_CMP_LT(cur_s, s - (2 * RCU_SEQ_STATE_MASK + 1));
+}
+
 /*
  * Has a grace period completed since the time the old gp_seq was collected?
  */

kernel/rcu/rcuscale.c

@@ -419,6 +419,7 @@ rcu_scale_writer(void *arg)
 	VERBOSE_SCALEOUT_STRING("rcu_scale_writer task started");
 	WARN_ON(!wdpp);
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+	current->flags |= PF_NO_SETAFFINITY;
 	sched_set_fifo_low(current);
 
 	if (holdoff)

kernel/rcu/refscale.c

@@ -385,7 +385,7 @@ static struct ref_scale_ops rwsem_ops = {
 };
 
 // Definitions for global spinlock
-static DEFINE_SPINLOCK(test_lock);
+static DEFINE_RAW_SPINLOCK(test_lock);
 
 static void ref_lock_section(const int nloops)
 {
@@ -393,8 +393,8 @@ static void ref_lock_section(const int nloops)
 
 	preempt_disable();
 	for (i = nloops; i >= 0; i--) {
-		spin_lock(&test_lock);
-		spin_unlock(&test_lock);
+		raw_spin_lock(&test_lock);
+		raw_spin_unlock(&test_lock);
 	}
 	preempt_enable();
 }
@@ -405,9 +405,9 @@ static void ref_lock_delay_section(const int nloops, const int udl, const int nd
 
 	preempt_disable();
 	for (i = nloops; i >= 0; i--) {
-		spin_lock(&test_lock);
+		raw_spin_lock(&test_lock);
 		un_delay(udl, ndl);
-		spin_unlock(&test_lock);
+		raw_spin_unlock(&test_lock);
 	}
 	preempt_enable();
 }
@@ -427,8 +427,8 @@ static void ref_lock_irq_section(const int nloops)
 
 	preempt_disable();
 	for (i = nloops; i >= 0; i--) {
-		spin_lock_irqsave(&test_lock, flags);
-		spin_unlock_irqrestore(&test_lock, flags);
+		raw_spin_lock_irqsave(&test_lock, flags);
+		raw_spin_unlock_irqrestore(&test_lock, flags);
 	}
 	preempt_enable();
 }
@@ -440,9 +440,9 @@ static void ref_lock_irq_delay_section(const int nloops, const int udl, const in
 
 	preempt_disable();
 	for (i = nloops; i >= 0; i--) {
-		spin_lock_irqsave(&test_lock, flags);
+		raw_spin_lock_irqsave(&test_lock, flags);
 		un_delay(udl, ndl);
-		spin_unlock_irqrestore(&test_lock, flags);
+		raw_spin_unlock_irqrestore(&test_lock, flags);
 	}
 	preempt_enable();
 }

kernel/rcu/srcutree.c

@@ -511,10 +511,52 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
 	return sum;
 }
 
-#define SRCU_INTERVAL		1	// Base delay if no expedited GPs pending.
-#define SRCU_MAX_INTERVAL	10	// Maximum incremental delay from slow readers.
-#define SRCU_MAX_NODELAY_PHASE	1	// Maximum per-GP-phase consecutive no-delay instances.
-#define SRCU_MAX_NODELAY	100	// Maximum consecutive no-delay instances.
+/*
+ * We use an adaptive strategy for synchronize_srcu() and especially for
+ * synchronize_srcu_expedited().  We spin for a fixed time period
+ * (defined below, boot time configurable) to allow SRCU readers to exit
+ * their read-side critical sections.  If there are still some readers
+ * after one jiffy, we repeatedly block for one jiffy time periods.
+ * The blocking time is increased as the grace-period age increases,
+ * with max blocking time capped at 10 jiffies.
+ */
+#define SRCU_DEFAULT_RETRY_CHECK_DELAY		5
+
+static ulong srcu_retry_check_delay = SRCU_DEFAULT_RETRY_CHECK_DELAY;
+module_param(srcu_retry_check_delay, ulong, 0444);
+
+#define SRCU_INTERVAL		1		// Base delay if no expedited GPs pending.
+#define SRCU_MAX_INTERVAL	10		// Maximum incremental delay from slow readers.
+
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE_LO	3UL	// Lowmark on default per-GP-phase
+							// no-delay instances.
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE_HI	1000UL	// Highmark on default per-GP-phase
+							// no-delay instances.
+
+#define SRCU_UL_CLAMP_LO(val, low)	((val) > (low) ? (val) : (low))
+#define SRCU_UL_CLAMP_HI(val, high)	((val) < (high) ? (val) : (high))
+#define SRCU_UL_CLAMP(val, low, high)	SRCU_UL_CLAMP_HI(SRCU_UL_CLAMP_LO((val), (low)), (high))
+// per-GP-phase no-delay instances adjusted to allow non-sleeping poll upto
+// one jiffies time duration. Mult by 2 is done to factor in the srcu_get_delay()
+// called from process_srcu().
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED	\
+	(2UL * USEC_PER_SEC / HZ / SRCU_DEFAULT_RETRY_CHECK_DELAY)
+
+// Maximum per-GP-phase consecutive no-delay instances.
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE	\
+	SRCU_UL_CLAMP(SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED,	\
+		      SRCU_DEFAULT_MAX_NODELAY_PHASE_LO,	\
+		      SRCU_DEFAULT_MAX_NODELAY_PHASE_HI)
+
+static ulong srcu_max_nodelay_phase = SRCU_DEFAULT_MAX_NODELAY_PHASE;
+module_param(srcu_max_nodelay_phase, ulong, 0444);
+
+// Maximum consecutive no-delay instances.
+#define SRCU_DEFAULT_MAX_NODELAY	(SRCU_DEFAULT_MAX_NODELAY_PHASE > 100 ?	\
+					 SRCU_DEFAULT_MAX_NODELAY_PHASE : 100)
+
+static ulong srcu_max_nodelay = SRCU_DEFAULT_MAX_NODELAY;
+module_param(srcu_max_nodelay, ulong, 0444);
 
 /*
  * Return grace-period delay, zero if there are expedited grace
@@ -522,16 +564,22 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
  */
 static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 {
+	unsigned long gpstart;
+	unsigned long j;
 	unsigned long jbase = SRCU_INTERVAL;
 
 	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
 		jbase = 0;
-	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)))
-		jbase += jiffies - READ_ONCE(ssp->srcu_gp_start);
-	if (!jbase) {
-		WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1);
-		if (READ_ONCE(ssp->srcu_n_exp_nodelay) > SRCU_MAX_NODELAY_PHASE)
-			jbase = 1;
+	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) {
+		j = jiffies - 1;
+		gpstart = READ_ONCE(ssp->srcu_gp_start);
+		if (time_after(j, gpstart))
+			jbase += j - gpstart;
+		if (!jbase) {
+			WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1);
+			if (READ_ONCE(ssp->srcu_n_exp_nodelay) > srcu_max_nodelay_phase)
+				jbase = 1;
+		}
 	}
 	return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase;
 }
@@ -606,15 +654,6 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
-/*
- * We use an adaptive strategy for synchronize_srcu() and especially for
- * synchronize_srcu_expedited().  We spin for a fixed time period
- * (defined below) to allow SRCU readers to exit their read-side critical
- * sections.  If there are still some readers after a few microseconds,
- * we repeatedly block for 1-millisecond time periods.
- */
-#define SRCU_RETRY_CHECK_DELAY		5
-
 /*
  * Start an SRCU grace period.
  */
@@ -700,7 +739,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp
  */
 static void srcu_gp_end(struct srcu_struct *ssp)
 {
-	unsigned long cbdelay;
+	unsigned long cbdelay = 1;
 	bool cbs;
 	bool last_lvl;
 	int cpu;
@@ -720,7 +759,9 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	spin_lock_irq_rcu_node(ssp);
 	idx = rcu_seq_state(ssp->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
-	cbdelay = !!srcu_get_delay(ssp);
+	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
+		cbdelay = 0;
+
 	WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns());
 	rcu_seq_end(&ssp->srcu_gp_seq);
 	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
@@ -921,12 +962,16 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
  */
 static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
 {
+	unsigned long curdelay;
+
+	curdelay = !srcu_get_delay(ssp);
+
 	for (;;) {
 		if (srcu_readers_active_idx_check(ssp, idx))
 			return true;
-		if (--trycount + !srcu_get_delay(ssp) <= 0)
+		if ((--trycount + curdelay) <= 0)
 			return false;
-		udelay(SRCU_RETRY_CHECK_DELAY);
+		udelay(srcu_retry_check_delay);
 	}
 }
 
@@ -1582,7 +1627,7 @@ static void process_srcu(struct work_struct *work)
 		j = jiffies;
 		if (READ_ONCE(ssp->reschedule_jiffies) == j) {
 			WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1);
-			if (READ_ONCE(ssp->reschedule_count) > SRCU_MAX_NODELAY)
+			if (READ_ONCE(ssp->reschedule_count) > srcu_max_nodelay)
 				curdelay = 1;
 		} else {
 			WRITE_ONCE(ssp->reschedule_count, 1);
@@ -1674,6 +1719,11 @@ static int __init srcu_bootup_announce(void)
 	pr_info("Hierarchical SRCU implementation.\n");
 	if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF)
 		pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff);
+	if (srcu_retry_check_delay != SRCU_DEFAULT_RETRY_CHECK_DELAY)
+		pr_info("\tNon-default retry check delay of %lu us.\n", srcu_retry_check_delay);
+	if (srcu_max_nodelay != SRCU_DEFAULT_MAX_NODELAY)
+		pr_info("\tNon-default max no-delay of %lu.\n", srcu_max_nodelay);
+	pr_info("\tMax phase no-delay instances is %lu.\n", srcu_max_nodelay_phase);
 	return 0;
 }
 early_initcall(srcu_bootup_announce);

kernel/rcu/tiny.c

@@ -58,7 +58,7 @@ void rcu_qs(void)
 		rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
 		raise_softirq_irqoff(RCU_SOFTIRQ);
 	}
-	WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 1);
+	WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
 	local_irq_restore(flags);
 }
 
@@ -139,8 +139,10 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
 /*
  * Wait for a grace period to elapse.  But it is illegal to invoke
  * synchronize_rcu() from within an RCU read-side critical section.
- * Therefore, any legal call to synchronize_rcu() is a quiescent
- * state, and so on a UP system, synchronize_rcu() need do nothing.
+ * Therefore, any legal call to synchronize_rcu() is a quiescent state,
+ * and so on a UP system, synchronize_rcu() need do nothing, other than
+ * let the polled APIs know that another grace period elapsed.
+ *
  * (But Lai Jiangshan points out the benefits of doing might_sleep()
  * to reduce latency.)
  *
@@ -152,6 +154,7 @@ void synchronize_rcu(void)
 			 lock_is_held(&rcu_lock_map) ||
 			 lock_is_held(&rcu_sched_lock_map),
 			 "Illegal synchronize_rcu() in RCU read-side critical section");
+	WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
@@ -213,10 +216,24 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
  */
 bool poll_state_synchronize_rcu(unsigned long oldstate)
 {
-	return READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
+	return oldstate == RCU_GET_STATE_COMPLETED || READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
 }
 EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
 
+#ifdef CONFIG_KASAN_GENERIC
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+	if (head) {
+		void *ptr = (void *) head - (unsigned long) func;
+
+		kasan_record_aux_stack_noalloc(ptr);
+	}
+
+	__kvfree_call_rcu(head, func);
+}
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
+#endif
+
 void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);

kernel/rcu/tree.h

@@ -133,6 +133,10 @@ struct rcu_node {
 	wait_queue_head_t exp_wq[4];
 	struct rcu_exp_work rew;
 	bool exp_need_flush;	/* Need to flush workitem? */
+	raw_spinlock_t exp_poll_lock;
+				/* Lock and data for polled expedited grace periods. */
+	unsigned long exp_seq_poll_rq;
+	struct work_struct exp_poll_wq;
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -235,6 +239,7 @@ struct rcu_data {
 					 * if rdp_gp.
 					 */
 	struct list_head nocb_entry_rdp; /* rcu_data node in wakeup chain. */
+	struct rcu_data *nocb_toggling_rdp; /* rdp queued for (de-)offloading */
 
 	/* The following fields are used by CB kthread, hence new cacheline. */
 	struct rcu_data *nocb_gp_rdp ____cacheline_internodealigned_in_smp;
@@ -323,6 +328,9 @@ struct rcu_state {
 	short gp_state;				/* GP kthread sleep state. */
 	unsigned long gp_wake_time;		/* Last GP kthread wake. */
 	unsigned long gp_wake_seq;		/* ->gp_seq at ^^^. */
+	unsigned long gp_seq_polled;		/* GP seq for polled API. */
+	unsigned long gp_seq_polled_snap;	/* ->gp_seq_polled at normal GP start. */
+	unsigned long gp_seq_polled_exp_snap;	/* ->gp_seq_polled at expedited GP start. */
 
 	/* End of fields guarded by root rcu_node's lock. */
 
@@ -425,7 +433,7 @@ static void rcu_flavor_sched_clock_irq(int user);
 static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
-static bool rcu_is_callbacks_kthread(void);
+static bool rcu_is_callbacks_kthread(struct rcu_data *rdp);
 static void rcu_cpu_kthread_setup(unsigned int cpu);
 static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
@@ -481,3 +489,6 @@ static void rcu_iw_handler(struct irq_work *iwp);
 static void check_cpu_stall(struct rcu_data *rdp);
 static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
 				     const unsigned long gpssdelay);
+
+/* Forward declarations for tree_exp.h. */
+static void sync_rcu_do_polled_gp(struct work_struct *wp);

kernel/rcu/tree_exp.h

@@ -18,6 +18,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 static void rcu_exp_gp_seq_start(void)
 {
 	rcu_seq_start(&rcu_state.expedited_sequence);
+	rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
 }
 
 /*
@@ -34,6 +35,7 @@ static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void)
  */
 static void rcu_exp_gp_seq_end(void)
 {
+	rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
 	rcu_seq_end(&rcu_state.expedited_sequence);
 	smp_mb(); /* Ensure that consecutive grace periods serialize. */
 }
@@ -621,7 +623,6 @@ static void synchronize_rcu_expedited_wait(void)
 			return;
 		if (rcu_stall_is_suppressed())
 			continue;
-		panic_on_rcu_stall();
 		trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
 		       rcu_state.name);
@@ -636,10 +637,11 @@ static void synchronize_rcu_expedited_wait(void)
 					continue;
 				ndetected++;
 				rdp = per_cpu_ptr(&rcu_data, cpu);
-				pr_cont(" %d-%c%c%c", cpu,
+				pr_cont(" %d-%c%c%c%c", cpu,
 					"O."[!!cpu_online(cpu)],
 					"o."[!!(rdp->grpmask & rnp->expmaskinit)],
-					"N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
+					"N."[!!(rdp->grpmask & rnp->expmaskinitnext)],
+					"D."[!!(rdp->cpu_no_qs.b.exp)]);
 			}
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
@@ -669,6 +671,7 @@ static void synchronize_rcu_expedited_wait(void)
 			}
 		}
 		jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3;
+		panic_on_rcu_stall();
 	}
 }
 
@@ -913,8 +916,18 @@ void synchronize_rcu_expedited(void)
 			 "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
 
 	/* Is the state is such that the call is a grace period? */
-	if (rcu_blocking_is_gp())
-		return;
+	if (rcu_blocking_is_gp()) {
+		// Note well that this code runs with !PREEMPT && !SMP.
+		// In addition, all code that advances grace periods runs
+		// at process level.  Therefore, this expedited GP overlaps
+		// with other expedited GPs only by being fully nested within
+		// them, which allows reuse of ->gp_seq_polled_exp_snap.
+		rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
+		rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
+		if (rcu_init_invoked())
+			cond_resched();
+		return;  // Context allows vacuous grace periods.
+	}
 
 	/* If expedited grace periods are prohibited, fall back to normal. */
 	if (rcu_gp_is_normal()) {
@@ -950,3 +963,93 @@ void synchronize_rcu_expedited(void)
 		synchronize_rcu_expedited_destroy_work(&rew);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
+ * Ensure that start_poll_synchronize_rcu_expedited() has the expedited
+ * RCU grace periods that it needs.
+ */
+static void sync_rcu_do_polled_gp(struct work_struct *wp)
+{
+	unsigned long flags;
+	int i = 0;
+	struct rcu_node *rnp = container_of(wp, struct rcu_node, exp_poll_wq);
+	unsigned long s;
+
+	raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
+	s = rnp->exp_seq_poll_rq;
+	rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
+	raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
+	if (s == RCU_GET_STATE_COMPLETED)
+		return;
+	while (!poll_state_synchronize_rcu(s)) {
+		synchronize_rcu_expedited();
+		if (i == 10 || i == 20)
+			pr_info("%s: i = %d s = %lx gp_seq_polled = %lx\n", __func__, i, s, READ_ONCE(rcu_state.gp_seq_polled));
+		i++;
+	}
+	raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
+	s = rnp->exp_seq_poll_rq;
+	if (poll_state_synchronize_rcu(s))
+		rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
+	raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
+}
+
+/**
+ * start_poll_synchronize_rcu_expedited - Snapshot current RCU state and start expedited grace period
+ *
+ * Returns a cookie to pass to a call to cond_synchronize_rcu(),
+ * cond_synchronize_rcu_expedited(), or poll_state_synchronize_rcu(),
+ * allowing them to determine whether or not any sort of grace period has
+ * elapsed in the meantime.  If the needed expedited grace period is not
+ * already slated to start, initiates that grace period.
+ */
+unsigned long start_poll_synchronize_rcu_expedited(void)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	unsigned long s;
+
+	s = get_state_synchronize_rcu();
+	rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
+	rnp = rdp->mynode;
+	if (rcu_init_invoked())
+		raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
+	if (!poll_state_synchronize_rcu(s)) {
+		rnp->exp_seq_poll_rq = s;
+		if (rcu_init_invoked())
+			queue_work(rcu_gp_wq, &rnp->exp_poll_wq);
+	}
+	if (rcu_init_invoked())
+		raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
+
+	return s;
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited);
+
+/**
+ * cond_synchronize_rcu_expedited - Conditionally wait for an expedited RCU grace period
+ *
+ * @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited()
+ *
+ * If any type of full RCU grace period has elapsed since the earlier
+ * call to get_state_synchronize_rcu(), start_poll_synchronize_rcu(),
+ * or start_poll_synchronize_rcu_expedited(), just return.  Otherwise,
+ * invoke synchronize_rcu_expedited() to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for a couple of additional grace periods should be just fine.
+ *
+ * This function provides the same memory-ordering guarantees that
+ * would be provided by a synchronize_rcu() that was invoked at the call
+ * to the function that provided @oldstate and that returned at the end
+ * of this function.
+ */
+void cond_synchronize_rcu_expedited(unsigned long oldstate)
+{
+	if (!poll_state_synchronize_rcu(oldstate))
+		synchronize_rcu_expedited();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited);

kernel/rcu/tree_plugin.h

@@ -460,7 +460,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
  * be quite short, for example, in the case of the call from
  * rcu_read_unlock_special().
  */
-static void
+static notrace void
 rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 {
 	bool empty_exp;
@@ -581,7 +581,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
  * is disabled.  This function cannot be expected to understand these
  * nuances, so the caller must handle them.
  */
-static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
+static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return (__this_cpu_read(rcu_data.cpu_no_qs.b.exp) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
@@ -595,7 +595,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
  * evaluate safety in terms of interrupt, softirq, and preemption
  * disabling.
  */
-static void rcu_preempt_deferred_qs(struct task_struct *t)
+static notrace void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	unsigned long flags;
 
@@ -899,8 +899,8 @@ void rcu_note_context_switch(bool preempt)
 	this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs)))
 		rcu_momentary_dyntick_idle();
-	rcu_tasks_qs(current, preempt);
 out:
+	rcu_tasks_qs(current, preempt);
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -926,7 +926,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
  * Because there is no preemptible RCU, there can be no deferred quiescent
  * states.
  */
-static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
+static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return false;
 }
@@ -935,7 +935,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 // period for a quiescent state from this CPU.  Note that requests from
 // tasks are handled when removing the task from the blocked-tasks list
 // below.
-static void rcu_preempt_deferred_qs(struct task_struct *t)
+static notrace void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
@@ -1012,6 +1012,25 @@ static void rcu_cpu_kthread_setup(unsigned int cpu)
 	WRITE_ONCE(rdp->rcuc_activity, jiffies);
 }
 
+static bool rcu_is_callbacks_nocb_kthread(struct rcu_data *rdp)
+{
+#ifdef CONFIG_RCU_NOCB_CPU
+	return rdp->nocb_cb_kthread == current;
+#else
+	return false;
+#endif
+}
+
+/*
+ * Is the current CPU running the RCU-callbacks kthread?
+ * Caller must have preemption disabled.
+ */
+static bool rcu_is_callbacks_kthread(struct rcu_data *rdp)
+{
+	return rdp->rcu_cpu_kthread_task == current ||
+			rcu_is_callbacks_nocb_kthread(rdp);
+}
+
 #ifdef CONFIG_RCU_BOOST
 
 /*
@@ -1140,7 +1159,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	    (rnp->gp_tasks != NULL &&
 	     rnp->boost_tasks == NULL &&
 	     rnp->qsmask == 0 &&
-	     (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld))) {
+	     (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld ||
+	      IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)))) {
 		if (rnp->exp_tasks == NULL)
 			WRITE_ONCE(rnp->boost_tasks, rnp->gp_tasks);
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -1151,15 +1171,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	}
 }
 
-/*
- * Is the current CPU running the RCU-callbacks kthread?
- * Caller must have preemption disabled.
- */
-static bool rcu_is_callbacks_kthread(void)
-{
-	return __this_cpu_read(rcu_data.rcu_cpu_kthread_task) == current;
-}
-
 #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
 
 /*
@@ -1242,11 +1253,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
-static bool rcu_is_callbacks_kthread(void)
-{
-	return false;
-}
-
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }

kernel/rcu/update.c

@@ -516,6 +516,19 @@ int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls.
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress_at_boot);
 module_param(rcu_cpu_stall_suppress_at_boot, int, 0444);
 
+/**
+ * get_completed_synchronize_rcu - Return a pre-completed polled state cookie
+ *
+ * Returns a value that will always be treated by functions like
+ * poll_state_synchronize_rcu() as a cookie whose grace period has already
+ * completed.
+ */
+unsigned long get_completed_synchronize_rcu(void)
+{
+	return RCU_GET_STATE_COMPLETED;
+}
+EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu);
+
 #ifdef CONFIG_PROVE_RCU
 
 /*

kernel/sched/core.c

@@ -4263,6 +4263,38 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
 	return ret;
 }
 
+/**
+ * cpu_curr_snapshot - Return a snapshot of the currently running task
+ * @cpu: The CPU on which to snapshot the task.
+ *
+ * Returns the task_struct pointer of the task "currently" running on
+ * the specified CPU.  If the same task is running on that CPU throughout,
+ * the return value will be a pointer to that task's task_struct structure.
+ * If the CPU did any context switches even vaguely concurrently with the
+ * execution of this function, the return value will be a pointer to the
+ * task_struct structure of a randomly chosen task that was running on
+ * that CPU somewhere around the time that this function was executing.
+ *
+ * If the specified CPU was offline, the return value is whatever it
+ * is, perhaps a pointer to the task_struct structure of that CPU's idle
+ * task, but there is no guarantee.  Callers wishing a useful return
+ * value must take some action to ensure that the specified CPU remains
+ * online throughout.
+ *
+ * This function executes full memory barriers before and after fetching
+ * the pointer, which permits the caller to confine this function's fetch
+ * with respect to the caller's accesses to other shared variables.
+ */
+struct task_struct *cpu_curr_snapshot(int cpu)
+{
+	struct task_struct *t;
+
+	smp_mb(); /* Pairing determined by caller's synchronization design. */
+	t = rcu_dereference(cpu_curr(cpu));
+	smp_mb(); /* Pairing determined by caller's synchronization design. */
+	return t;
+}
+
 /**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.

kernel/smp.c

@@ -174,9 +174,9 @@ static int __init csdlock_debug(char *str)
 	if (val)
 		static_branch_enable(&csdlock_debug_enabled);
 
-	return 0;
+	return 1;
 }
-early_param("csdlock_debug", csdlock_debug);
+__setup("csdlock_debug=", csdlock_debug);
 
 static DEFINE_PER_CPU(call_single_data_t *, cur_csd);
 static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func);

tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh

@@ -35,7 +35,7 @@ then
 	exit 1
 fi
 
-# Remember where we started so that we can get back and the end.
+# Remember where we started so that we can get back at the end.
 curcommit="`git status | head -1 | awk '{ print $NF }'`"
 
 nfail=0
@@ -73,15 +73,10 @@ do
 		# Test the specified commit.
 		git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1
 		echo git checkout return code: $? "(Commit $ntry: $i)"
-		kvm.sh --allcpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1
+		kvm.sh --allcpus --duration 3 --trust-make --datestamp "$ds/$idir" > $resdir/$ds/$idir/kvm.sh.out 2>&1
 		ret=$?
 		echo kvm.sh return code $ret for commit $i from branch $gitbr
-
-		# Move the build products to their resting place.
-		runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`"
-		mv $runresdir $resdir/$ds/$idir
-		rrd="`echo $runresdir | sed -e 's,^.*/,,'`"
-		echo Run results: $resdir/$ds/$idir/$rrd
+		echo Run results: $resdir/$ds/$idir
 		if test "$ret" -ne 0
 		then
 			# Failure, so leave all evidence intact.

tools/testing/selftests/rcutorture/bin/kvm-remote.sh

@@ -262,6 +262,7 @@ echo All batches started. `date` | tee -a "$oldrun/remote-log"
 # Wait for all remaining scenarios to complete and collect results.
 for i in $systems
 do
+	echo " ---" Waiting for $i `date` | tee -a "$oldrun/remote-log"
 	while checkremotefile "$i" "$resdir/$ds/remote.run"
 	do
 		sleep 30

tools/testing/selftests/rcutorture/bin/kvm.sh

@@ -164,7 +164,7 @@ do
 		shift
 		;;
 	--gdb)
-		TORTURE_KCONFIG_GDB_ARG="CONFIG_DEBUG_INFO=y"; export TORTURE_KCONFIG_GDB_ARG
+		TORTURE_KCONFIG_GDB_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y"; export TORTURE_KCONFIG_GDB_ARG
 		TORTURE_BOOT_GDB_ARG="nokaslr"; export TORTURE_BOOT_GDB_ARG
 		TORTURE_QEMU_GDB_ARG="-s -S"; export TORTURE_QEMU_GDB_ARG
 		;;
@@ -180,7 +180,7 @@ do
 		shift
 		;;
 	--kasan)
-		TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+		TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
 		if test -n "$torture_qemu_mem_default"
 		then
 			TORTURE_QEMU_MEM=2G
@@ -192,7 +192,7 @@ do
 		shift
 		;;
 	--kcsan)
-		TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
+		TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
 		;;
 	--kmake-arg|--kmake-args)
 		checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'