[PATCH 1/9] rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast

[PATCH 1/9] rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast

[Paul E. McKenney]

This commit saves more than 500 lines of RCU code by re-implementing
RCU Tasks Trace in terms of SRCU-fast.  Follow-up work will remove
more code that does not cause problems by its presence, but that is no
longer required.

This variant places smp_mb() in rcu_read_{,un}lock_trace(), and in the
same place that srcu_read_{,un}lock() would put them. These smp_mb()
calls will be removed on common-case architectures in a later commit.
In the meantime, it serves to enforce ordering between the underlying
srcu_read_{,un}lock_fast() markers and the intervening critical section,
even on architectures that permit attaching tracepoints on regions of
code not watched by RCU.  Such architectures defeat SRCU-fast's use of
implicit single-instruction, interrupts-disabled, and atomic-operation
RCU read-side critical sections, which have no effect when RCU is not
watching.  The aforementioned later commit will insert these smp_mb()
calls only on architectures that have not used noinstr to prevent
attaching tracepoints to code where RCU is not watching.

[ paulmck: Apply kernel test robot, Boqun Feng, and Zqiang feedback. ]
[ paulmck: Split out Tiny SRCU fixes per Andrii Nakryiko feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: kernel test robot <oliver.sang@intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 include/linux/rcupdate_trace.h | 107 ++++--
 include/linux/sched.h          |   1 +
 kernel/rcu/tasks.h             | 621 +--------------------------------
 3 files changed, 99 insertions(+), 630 deletions(-)

diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index e6c44eb428ab..3f46cbe67000 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -12,28 +12,28 @@
 #include <linux/rcupdate.h>
 #include <linux/cleanup.h>
 
-extern struct lockdep_map rcu_trace_lock_map;
+#ifdef CONFIG_TASKS_TRACE_RCU
+extern struct srcu_struct rcu_tasks_trace_srcu_struct;
+#endif // #ifdef CONFIG_TASKS_TRACE_RCU
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU)
 
 static inline int rcu_read_lock_trace_held(void)
 {
-	return lock_is_held(&rcu_trace_lock_map);
+	return srcu_read_lock_held(&rcu_tasks_trace_srcu_struct);
 }
 
-#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#else // #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU)
 
 static inline int rcu_read_lock_trace_held(void)
 {
 	return 1;
 }
 
-#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif // #else // #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU)
 
 #ifdef CONFIG_TASKS_TRACE_RCU
 
-void rcu_read_unlock_trace_special(struct task_struct *t);
-
 /**
  * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section
  *
@@ -50,12 +50,14 @@ static inline void rcu_read_lock_trace(void)
 {
 	struct task_struct *t = current;
 
-	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
-	barrier();
-	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
-	    t->trc_reader_special.b.need_mb)
-		smp_mb(); // Pairs with update-side barriers
-	rcu_lock_acquire(&rcu_trace_lock_map);
+	if (t->trc_reader_nesting++) {
+		// In case we interrupted a Tasks Trace RCU reader.
+		rcu_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map);
+		return;
+	}
+	barrier();  // nesting before scp to protect against interrupt handler.
+	t->trc_reader_scp = srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct);
+	smp_mb(); // Placeholder for more selective ordering
 }
 
 /**
@@ -69,26 +71,75 @@ static inline void rcu_read_lock_trace(void)
  */
 static inline void rcu_read_unlock_trace(void)
 {
-	int nesting;
+	struct srcu_ctr __percpu *scp;
 	struct task_struct *t = current;
 
-	rcu_lock_release(&rcu_trace_lock_map);
-	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 + nesting);
-	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
-		WRITE_ONCE(t->trc_reader_nesting, nesting);
-		return;  // We assume shallow reader nesting.
-	}
-	WARN_ON_ONCE(nesting != 0);
-	rcu_read_unlock_trace_special(t);
+	smp_mb(); // Placeholder for more selective ordering
+	scp = t->trc_reader_scp;
+	barrier();  // scp before nesting to protect against interrupt handler.
+	if (!--t->trc_reader_nesting)
+		srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp);
+	else
+		srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map);
+}
+
+/**
+ * call_rcu_tasks_trace() - Queue a callback trace task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a trace rcu-tasks
+ * grace period elapses, in other words after all currently executing
+ * trace rcu-tasks read-side critical sections have completed. These
+ * read-side critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func)
+{
+	call_srcu(&rcu_tasks_trace_srcu_struct, rhp, func);
+}
+
+/**
+ * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period
+ *
+ * Control will return to the caller some time after a trace rcu-tasks
+ * grace period has elapsed, in other words after all currently executing
+ * trace rcu-tasks read-side critical sections have elapsed. These read-side
+ * critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function preambles
+ * and profiling hooks.  The synchronize_rcu_tasks_trace() function is not
+ * (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+static inline void synchronize_rcu_tasks_trace(void)
+{
+	synchronize_srcu(&rcu_tasks_trace_srcu_struct);
 }
 
-void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
-void synchronize_rcu_tasks_trace(void);
-void rcu_barrier_tasks_trace(void);
+/**
+ * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks.
+ *
+ * Note that rcu_barrier_tasks_trace() is not obligated to actually wait,
+ * for example, if there are no pending callbacks.
+ */
+static inline void rcu_barrier_tasks_trace(void)
+{
+	srcu_barrier(&rcu_tasks_trace_srcu_struct);
+}
+
+// Placeholders to enable stepwise transition.
+void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq);
+void __init rcu_tasks_trace_suppress_unused(void);
 struct task_struct *get_rcu_tasks_trace_gp_kthread(void);
+
 #else
 /*
  * The BPF JIT forms these addresses even when it doesn't call these
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b272382673d..89d364615552 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -939,6 +939,7 @@ struct task_struct {
 
 #ifdef CONFIG_TASKS_TRACE_RCU
 	int				trc_reader_nesting;
+	struct srcu_ctr __percpu	*trc_reader_scp;
 	int				trc_ipi_to_cpu;
 	union rcu_special		trc_reader_special;
 	struct list_head		trc_holdout_list;
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 2dc044fd126e..1fe789c99f36 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -718,7 +718,6 @@ static void __init rcu_tasks_bootup_oddness(void)
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 
-
 /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */
 static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
 {
@@ -803,7 +802,7 @@ static void rcu_tasks_torture_stats_print_generic(struct rcu_tasks *rtp, char *t
 
 static void exit_tasks_rcu_finish_trace(struct task_struct *t);
 
-#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
+#if defined(CONFIG_TASKS_RCU)
 
 ////////////////////////////////////////////////////////////////////////
 //
@@ -898,7 +897,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 	rtp->postgp_func(rtp);
 }
 
-#endif /* #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) */
+#endif /* #if defined(CONFIG_TASKS_RCU) */
 
 #ifdef CONFIG_TASKS_RCU
 
@@ -1453,94 +1452,27 @@ EXPORT_SYMBOL_GPL(rcu_tasks_rude_get_gp_data);
 //
 // Tracing variant of Tasks RCU.  This variant is designed to be used
 // to protect tracing hooks, including those of BPF.  This variant
-// therefore:
-//
-// 1.	Has explicit read-side markers to allow finite grace periods
-//	in the face of in-kernel loops for PREEMPT=n builds.
-//
-// 2.	Protects code in the idle loop, exception entry/exit, and
-//	CPU-hotplug code paths, similar to the capabilities of SRCU.
-//
-// 3.	Avoids expensive read-side instructions, having overhead similar
-//	to that of Preemptible RCU.
-//
-// There are of course downsides.  For example, the grace-period code
-// can send IPIs to CPUs, even when those CPUs are in the idle loop or
-// in nohz_full userspace.  If needed, these downsides can be at least
-// partially remedied.
-//
-// Perhaps most important, this variant of RCU does not affect the vanilla
-// flavors, rcu_preempt and rcu_sched.  The fact that RCU Tasks Trace
-// readers can operate from idle, offline, and exception entry/exit in no
-// way allows rcu_preempt and rcu_sched readers to also do so.
-//
-// The implementation uses rcu_tasks_wait_gp(), which relies on function
-// pointers in the rcu_tasks structure.  The rcu_spawn_tasks_trace_kthread()
-// function sets these function pointers up so that rcu_tasks_wait_gp()
-// invokes these functions in this order:
-//
-// rcu_tasks_trace_pregp_step():
-//	Disables CPU hotplug, adds all currently executing tasks to the
-//	holdout list, then checks the state of all tasks that blocked
-//	or were preempted within their current RCU Tasks Trace read-side
-//	critical section, adding them to the holdout list if appropriate.
-//	Finally, this function re-enables CPU hotplug.
-// The ->pertask_func() pointer is NULL, so there is no per-task processing.
-// rcu_tasks_trace_postscan():
-//	Invokes synchronize_rcu() to wait for late-stage exiting tasks
-//	to finish exiting.
-// check_all_holdout_tasks_trace(), repeatedly until holdout list is empty:
-//	Scans the holdout list, attempting to identify a quiescent state
-//	for each task on the list.  If there is a quiescent state, the
-//	corresponding task is removed from the holdout list.  Once this
-//	list is empty, the grace period has completed.
-// rcu_tasks_trace_postgp():
-//	Provides the needed full memory barrier and does debug checks.
-//
-// The exit_tasks_rcu_finish_trace() synchronizes with exiting tasks.
-//
-// Pre-grace-period update-side code is ordered before the grace period
-// via the ->cbs_lock and barriers in rcu_tasks_kthread().  Pre-grace-period
-// read-side code is ordered before the grace period by atomic operations
-// on .b.need_qs flag of each task involved in this process, or by scheduler
-// context-switch ordering (for locked-down non-running readers).
-
-// The lockdep state must be outside of #ifdef to be useful.
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static struct lock_class_key rcu_lock_trace_key;
-struct lockdep_map rcu_trace_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_trace", &rcu_lock_trace_key);
-EXPORT_SYMBOL_GPL(rcu_trace_lock_map);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+// is implemented via a straightforward mapping onto SRCU-fast.
 
 #ifdef CONFIG_TASKS_TRACE_RCU
 
-// Record outstanding IPIs to each CPU.  No point in sending two...
-static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
-
-// The number of detections of task quiescent state relying on
-// heavyweight readers executing explicit memory barriers.
-static unsigned long n_heavy_reader_attempts;
-static unsigned long n_heavy_reader_updates;
-static unsigned long n_heavy_reader_ofl_updates;
-static unsigned long n_trc_holdouts;
+DEFINE_SRCU_FAST(rcu_tasks_trace_srcu_struct);
+EXPORT_SYMBOL_GPL(rcu_tasks_trace_srcu_struct);
 
-void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
-DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
-		 "RCU Tasks Trace");
-
-/* Load from ->trc_reader_special.b.need_qs with proper ordering. */
-static u8 rcu_ld_need_qs(struct task_struct *t)
+// Placeholder to suppress build errors through transition period.
+void __init rcu_tasks_trace_suppress_unused(void)
 {
-	smp_mb(); // Enforce full grace-period ordering.
-	return smp_load_acquire(&t->trc_reader_special.b.need_qs);
-}
-
-/* Store to ->trc_reader_special.b.need_qs with proper ordering. */
-static void rcu_st_need_qs(struct task_struct *t, u8 v)
-{
-	smp_store_release(&t->trc_reader_special.b.need_qs, v);
-	smp_mb(); // Enforce full grace-period ordering.
+#ifndef CONFIG_TINY_RCU
+	show_rcu_tasks_generic_gp_kthread(NULL, NULL);
+#endif // #ifndef CONFIG_TINY_RCU
+	rcu_spawn_tasks_kthread_generic(NULL);
+	synchronize_rcu_tasks_generic(NULL);
+	call_rcu_tasks_generic(NULL, NULL, NULL);
+	call_rcu_tasks_iw_wakeup(NULL);
+	cblist_init_generic(NULL);
+#ifndef CONFIG_TINY_RCU
+	rcu_tasks_torture_stats_print_generic(NULL, NULL, NULL, NULL);
+#endif // #ifndef CONFIG_TINY_RCU
 }
 
 /*
@@ -1555,321 +1487,12 @@ u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new)
 }
 EXPORT_SYMBOL_GPL(rcu_trc_cmpxchg_need_qs);
 
-/*
- * If we are the last reader, signal the grace-period kthread.
- * Also remove from the per-CPU list of blocked tasks.
- */
-void rcu_read_unlock_trace_special(struct task_struct *t)
-{
-	unsigned long flags;
-	struct rcu_tasks_percpu *rtpcp;
-	union rcu_special trs;
-
-	// Open-coded full-word version of rcu_ld_need_qs().
-	smp_mb(); // Enforce full grace-period ordering.
-	trs = smp_load_acquire(&t->trc_reader_special);
-
-	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && t->trc_reader_special.b.need_mb)
-		smp_mb(); // Pairs with update-side barriers.
-	// Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
-	if (trs.b.need_qs == (TRC_NEED_QS_CHECKED | TRC_NEED_QS)) {
-		u8 result = rcu_trc_cmpxchg_need_qs(t, TRC_NEED_QS_CHECKED | TRC_NEED_QS,
-						       TRC_NEED_QS_CHECKED);
-
-		WARN_ONCE(result != trs.b.need_qs, "%s: result = %d", __func__, result);
-	}
-	if (trs.b.blocked) {
-		rtpcp = per_cpu_ptr(rcu_tasks_trace.rtpcpu, t->trc_blkd_cpu);
-		raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
-		list_del_init(&t->trc_blkd_node);
-		WRITE_ONCE(t->trc_reader_special.b.blocked, false);
-		raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
-	}
-	WRITE_ONCE(t->trc_reader_nesting, 0);
-}
-EXPORT_SYMBOL_GPL(rcu_read_unlock_trace_special);
-
 /* Add a newly blocked reader task to its CPU's list. */
 void rcu_tasks_trace_qs_blkd(struct task_struct *t)
 {
-	unsigned long flags;
-	struct rcu_tasks_percpu *rtpcp;
-
-	local_irq_save(flags);
-	rtpcp = this_cpu_ptr(rcu_tasks_trace.rtpcpu);
-	raw_spin_lock_rcu_node(rtpcp); // irqs already disabled
-	t->trc_blkd_cpu = smp_processor_id();
-	if (!rtpcp->rtp_blkd_tasks.next)
-		INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
-	list_add(&t->trc_blkd_node, &rtpcp->rtp_blkd_tasks);
-	WRITE_ONCE(t->trc_reader_special.b.blocked, true);
-	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
 }
 EXPORT_SYMBOL_GPL(rcu_tasks_trace_qs_blkd);
 
-/* Add a task to the holdout list, if it is not already on the list. */
-static void trc_add_holdout(struct task_struct *t, struct list_head *bhp)
-{
-	if (list_empty(&t->trc_holdout_list)) {
-		get_task_struct(t);
-		list_add(&t->trc_holdout_list, bhp);
-		n_trc_holdouts++;
-	}
-}
-
-/* Remove a task from the holdout list, if it is in fact present. */
-static void trc_del_holdout(struct task_struct *t)
-{
-	if (!list_empty(&t->trc_holdout_list)) {
-		list_del_init(&t->trc_holdout_list);
-		put_task_struct(t);
-		n_trc_holdouts--;
-	}
-}
-
-/* IPI handler to check task state. */
-static void trc_read_check_handler(void *t_in)
-{
-	int nesting;
-	struct task_struct *t = current;
-	struct task_struct *texp = t_in;
-
-	// If the task is no longer running on this CPU, leave.
-	if (unlikely(texp != t))
-		goto reset_ipi; // Already on holdout list, so will check later.
-
-	// If the task is not in a read-side critical section, and
-	// if this is the last reader, awaken the grace-period kthread.
-	nesting = READ_ONCE(t->trc_reader_nesting);
-	if (likely(!nesting)) {
-		rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
-		goto reset_ipi;
-	}
-	// If we are racing with an rcu_read_unlock_trace(), try again later.
-	if (unlikely(nesting < 0))
-		goto reset_ipi;
-
-	// Get here if the task is in a read-side critical section.
-	// Set its state so that it will update state for the grace-period
-	// kthread upon exit from that critical section.
-	rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS | TRC_NEED_QS_CHECKED);
-
-reset_ipi:
-	// Allow future IPIs to be sent on CPU and for task.
-	// Also order this IPI handler against any later manipulations of
-	// the intended task.
-	smp_store_release(per_cpu_ptr(&trc_ipi_to_cpu, smp_processor_id()), false); // ^^^
-	smp_store_release(&texp->trc_ipi_to_cpu, -1); // ^^^
-}
-
-/* Callback function for scheduler to check locked-down task.  */
-static int trc_inspect_reader(struct task_struct *t, void *bhp_in)
-{
-	struct list_head *bhp = bhp_in;
-	int cpu = task_cpu(t);
-	int nesting;
-	bool ofl = cpu_is_offline(cpu);
-
-	if (task_curr(t) && !ofl) {
-		// If no chance of heavyweight readers, do it the hard way.
-		if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
-			return -EINVAL;
-
-		// If heavyweight readers are enabled on the remote task,
-		// we can inspect its state despite its currently running.
-		// However, we cannot safely change its state.
-		n_heavy_reader_attempts++;
-		// Check for "running" idle tasks on offline CPUs.
-		if (!rcu_watching_zero_in_eqs(cpu, &t->trc_reader_nesting))
-			return -EINVAL; // No quiescent state, do it the hard way.
-		n_heavy_reader_updates++;
-		nesting = 0;
-	} else {
-		// The task is not running, so C-language access is safe.
-		nesting = t->trc_reader_nesting;
-		WARN_ON_ONCE(ofl && task_curr(t) && (t != idle_task(task_cpu(t))));
-		if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && ofl)
-			n_heavy_reader_ofl_updates++;
-	}
-
-	// If not exiting a read-side critical section, mark as checked
-	// so that the grace-period kthread will remove it from the
-	// holdout list.
-	if (!nesting) {
-		rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
-		return 0;  // In QS, so done.
-	}
-	if (nesting < 0)
-		return -EINVAL; // Reader transitioning, try again later.
-
-	// The task is in a read-side critical section, so set up its
-	// state so that it will update state upon exit from that critical
-	// section.
-	if (!rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS | TRC_NEED_QS_CHECKED))
-		trc_add_holdout(t, bhp);
-	return 0;
-}
-
-/* Attempt to extract the state for the specified task. */
-static void trc_wait_for_one_reader(struct task_struct *t,
-				    struct list_head *bhp)
-{
-	int cpu;
-
-	// If a previous IPI is still in flight, let it complete.
-	if (smp_load_acquire(&t->trc_ipi_to_cpu) != -1) // Order IPI
-		return;
-
-	// The current task had better be in a quiescent state.
-	if (t == current) {
-		rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
-		WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
-		return;
-	}
-
-	// Attempt to nail down the task for inspection.
-	get_task_struct(t);
-	if (!task_call_func(t, trc_inspect_reader, bhp)) {
-		put_task_struct(t);
-		return;
-	}
-	put_task_struct(t);
-
-	// If this task is not yet on the holdout list, then we are in
-	// an RCU read-side critical section.  Otherwise, the invocation of
-	// trc_add_holdout() that added it to the list did the necessary
-	// get_task_struct().  Either way, the task cannot be freed out
-	// from under this code.
-
-	// If currently running, send an IPI, either way, add to list.
-	trc_add_holdout(t, bhp);
-	if (task_curr(t) &&
-	    time_after(jiffies + 1, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
-		// The task is currently running, so try IPIing it.
-		cpu = task_cpu(t);
-
-		// If there is already an IPI outstanding, let it happen.
-		if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0)
-			return;
-
-		per_cpu(trc_ipi_to_cpu, cpu) = true;
-		t->trc_ipi_to_cpu = cpu;
-		rcu_tasks_trace.n_ipis++;
-		if (smp_call_function_single(cpu, trc_read_check_handler, t, 0)) {
-			// Just in case there is some other reason for
-			// failure than the target CPU being offline.
-			WARN_ONCE(1, "%s():  smp_call_function_single() failed for CPU: %d\n",
-				  __func__, cpu);
-			rcu_tasks_trace.n_ipis_fails++;
-			per_cpu(trc_ipi_to_cpu, cpu) = false;
-			t->trc_ipi_to_cpu = -1;
-		}
-	}
-}
-
-/*
- * Initialize for first-round processing for the specified task.
- * Return false if task is NULL or already taken care of, true otherwise.
- */
-static bool rcu_tasks_trace_pertask_prep(struct task_struct *t, bool notself)
-{
-	// During early boot when there is only the one boot CPU, there
-	// is no idle task for the other CPUs.	Also, the grace-period
-	// kthread is always in a quiescent state.  In addition, just return
-	// if this task is already on the list.
-	if (unlikely(t == NULL) || (t == current && notself) || !list_empty(&t->trc_holdout_list))
-		return false;
-
-	rcu_st_need_qs(t, 0);
-	t->trc_ipi_to_cpu = -1;
-	return true;
-}
-
-/* Do first-round processing for the specified task. */
-static void rcu_tasks_trace_pertask(struct task_struct *t, struct list_head *hop)
-{
-	if (rcu_tasks_trace_pertask_prep(t, true))
-		trc_wait_for_one_reader(t, hop);
-}
-
-/* Initialize for a new RCU-tasks-trace grace period. */
-static void rcu_tasks_trace_pregp_step(struct list_head *hop)
-{
-	LIST_HEAD(blkd_tasks);
-	int cpu;
-	unsigned long flags;
-	struct rcu_tasks_percpu *rtpcp;
-	struct task_struct *t;
-
-	// There shouldn't be any old IPIs, but...
-	for_each_possible_cpu(cpu)
-		WARN_ON_ONCE(per_cpu(trc_ipi_to_cpu, cpu));
-
-	// Disable CPU hotplug across the CPU scan for the benefit of
-	// any IPIs that might be needed.  This also waits for all readers
-	// in CPU-hotplug code paths.
-	cpus_read_lock();
-
-	// These rcu_tasks_trace_pertask_prep() calls are serialized to
-	// allow safe access to the hop list.
-	for_each_online_cpu(cpu) {
-		rcu_read_lock();
-		// Note that cpu_curr_snapshot() picks up the target
-		// CPU's current task while its runqueue is locked with
-		// an smp_mb__after_spinlock().  This ensures that either
-		// the grace-period kthread will see that task's read-side
-		// critical section or the task will see the updater's pre-GP
-		// accesses.  The trailing smp_mb() in cpu_curr_snapshot()
-		// does not currently play a role other than simplify
-		// that function's ordering semantics.  If these simplified
-		// ordering semantics continue to be redundant, that smp_mb()
-		// might be removed.
-		t = cpu_curr_snapshot(cpu);
-		if (rcu_tasks_trace_pertask_prep(t, true))
-			trc_add_holdout(t, hop);
-		rcu_read_unlock();
-		cond_resched_tasks_rcu_qs();
-	}
-
-	// Only after all running tasks have been accounted for is it
-	// safe to take care of the tasks that have blocked within their
-	// current RCU tasks trace read-side critical section.
-	for_each_possible_cpu(cpu) {
-		rtpcp = per_cpu_ptr(rcu_tasks_trace.rtpcpu, cpu);
-		raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
-		list_splice_init(&rtpcp->rtp_blkd_tasks, &blkd_tasks);
-		while (!list_empty(&blkd_tasks)) {
-			rcu_read_lock();
-			t = list_first_entry(&blkd_tasks, struct task_struct, trc_blkd_node);
-			list_del_init(&t->trc_blkd_node);
-			list_add(&t->trc_blkd_node, &rtpcp->rtp_blkd_tasks);
-			raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
-			rcu_tasks_trace_pertask(t, hop);
-			rcu_read_unlock();
-			raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
-		}
-		raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
-		cond_resched_tasks_rcu_qs();
-	}
-
-	// Re-enable CPU hotplug now that the holdout list is populated.
-	cpus_read_unlock();
-}
-
-/*
- * Do intermediate processing between task and holdout scans.
- */
-static void rcu_tasks_trace_postscan(struct list_head *hop)
-{
-	// Wait for late-stage exiting tasks to finish exiting.
-	// These might have passed the call to exit_tasks_rcu_finish().
-
-	// If you remove the following line, update rcu_trace_implies_rcu_gp()!!!
-	synchronize_rcu();
-	// Any tasks that exit after this point will set
-	// TRC_NEED_QS_CHECKED in ->trc_reader_special.b.need_qs.
-}
-
 /* Communicate task state back to the RCU tasks trace stall warning request. */
 struct trc_stall_chk_rdr {
 	int nesting;
@@ -1877,241 +1500,39 @@ struct trc_stall_chk_rdr {
 	u8 needqs;
 };
 
-static int trc_check_slow_task(struct task_struct *t, void *arg)
-{
-	struct trc_stall_chk_rdr *trc_rdrp = arg;
-
-	if (task_curr(t) && cpu_online(task_cpu(t)))
-		return false; // It is running, so decline to inspect it.
-	trc_rdrp->nesting = READ_ONCE(t->trc_reader_nesting);
-	trc_rdrp->ipi_to_cpu = READ_ONCE(t->trc_ipi_to_cpu);
-	trc_rdrp->needqs = rcu_ld_need_qs(t);
-	return true;
-}
-
-/* Show the state of a task stalling the current RCU tasks trace GP. */
-static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
-{
-	int cpu;
-	struct trc_stall_chk_rdr trc_rdr;
-	bool is_idle_tsk = is_idle_task(t);
-
-	if (*firstreport) {
-		pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n");
-		*firstreport = false;
-	}
-	cpu = task_cpu(t);
-	if (!task_call_func(t, trc_check_slow_task, &trc_rdr))
-		pr_alert("P%d: %c%c\n",
-			 t->pid,
-			 ".I"[t->trc_ipi_to_cpu >= 0],
-			 ".i"[is_idle_tsk]);
-	else
-		pr_alert("P%d: %c%c%c%c nesting: %d%c%c cpu: %d%s\n",
-			 t->pid,
-			 ".I"[trc_rdr.ipi_to_cpu >= 0],
-			 ".i"[is_idle_tsk],
-			 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
-			 ".B"[!!data_race(t->trc_reader_special.b.blocked)],
-			 trc_rdr.nesting,
-			 " !CN"[trc_rdr.needqs & 0x3],
-			 " ?"[trc_rdr.needqs > 0x3],
-			 cpu, cpu_online(cpu) ? "" : "(offline)");
-	sched_show_task(t);
-}
-
-/* List stalled IPIs for RCU tasks trace. */
-static void show_stalled_ipi_trace(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		if (per_cpu(trc_ipi_to_cpu, cpu))
-			pr_alert("\tIPI outstanding to CPU %d\n", cpu);
-}
-
-/* Do one scan of the holdout list. */
-static void check_all_holdout_tasks_trace(struct list_head *hop,
-					  bool needreport, bool *firstreport)
-{
-	struct task_struct *g, *t;
-
-	// Disable CPU hotplug across the holdout list scan for IPIs.
-	cpus_read_lock();
-
-	list_for_each_entry_safe(t, g, hop, trc_holdout_list) {
-		// If safe and needed, try to check the current task.
-		if (READ_ONCE(t->trc_ipi_to_cpu) == -1 &&
-		    !(rcu_ld_need_qs(t) & TRC_NEED_QS_CHECKED))
-			trc_wait_for_one_reader(t, hop);
-
-		// If check succeeded, remove this task from the list.
-		if (smp_load_acquire(&t->trc_ipi_to_cpu) == -1 &&
-		    rcu_ld_need_qs(t) == TRC_NEED_QS_CHECKED)
-			trc_del_holdout(t);
-		else if (needreport)
-			show_stalled_task_trace(t, firstreport);
-		cond_resched_tasks_rcu_qs();
-	}
-
-	// Re-enable CPU hotplug now that the holdout list scan has completed.
-	cpus_read_unlock();
-
-	if (needreport) {
-		if (*firstreport)
-			pr_err("INFO: rcu_tasks_trace detected stalls? (Late IPI?)\n");
-		show_stalled_ipi_trace();
-	}
-}
-
-static void rcu_tasks_trace_empty_fn(void *unused)
-{
-}
-
-/* Wait for grace period to complete and provide ordering. */
-static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
-{
-	int cpu;
-
-	// Wait for any lingering IPI handlers to complete.  Note that
-	// if a CPU has gone offline or transitioned to userspace in the
-	// meantime, all IPI handlers should have been drained beforehand.
-	// Yes, this assumes that CPUs process IPIs in order.  If that ever
-	// changes, there will need to be a recheck and/or timed wait.
-	for_each_online_cpu(cpu)
-		if (WARN_ON_ONCE(smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu))))
-			smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1);
-
-	smp_mb(); // Caller's code must be ordered after wakeup.
-		  // Pairs with pretty much every ordering primitive.
-}
-
 /* Report any needed quiescent state for this exiting task. */
 static void exit_tasks_rcu_finish_trace(struct task_struct *t)
 {
-	union rcu_special trs = READ_ONCE(t->trc_reader_special);
-
-	rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED);
-	WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
-	if (WARN_ON_ONCE(rcu_ld_need_qs(t) & TRC_NEED_QS || trs.b.blocked))
-		rcu_read_unlock_trace_special(t);
-	else
-		WRITE_ONCE(t->trc_reader_nesting, 0);
-}
-
-/**
- * call_rcu_tasks_trace() - Queue a callback trace task-based grace period
- * @rhp: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a trace rcu-tasks
- * grace period elapses, in other words after all currently executing
- * trace rcu-tasks read-side critical sections have completed. These
- * read-side critical sections are delimited by calls to rcu_read_lock_trace()
- * and rcu_read_unlock_trace().
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func)
-{
-	call_rcu_tasks_generic(rhp, func, &rcu_tasks_trace);
 }
-EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
-
-/**
- * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period
- *
- * Control will return to the caller some time after a trace rcu-tasks
- * grace period has elapsed, in other words after all currently executing
- * trace rcu-tasks read-side critical sections have elapsed. These read-side
- * critical sections are delimited by calls to rcu_read_lock_trace()
- * and rcu_read_unlock_trace().
- *
- * This is a very specialized primitive, intended only for a few uses in
- * tracing and other situations requiring manipulation of function preambles
- * and profiling hooks.  The synchronize_rcu_tasks_trace() function is not
- * (yet) intended for heavy use from multiple CPUs.
- *
- * See the description of synchronize_rcu() for more detailed information
- * on memory ordering guarantees.
- */
-void synchronize_rcu_tasks_trace(void)
-{
-	RCU_LOCKDEP_WARN(lock_is_held(&rcu_trace_lock_map), "Illegal synchronize_rcu_tasks_trace() in RCU Tasks Trace read-side critical section");
-	synchronize_rcu_tasks_generic(&rcu_tasks_trace);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_trace);
-
-/**
- * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks.
- *
- * Although the current implementation is guaranteed to wait, it is not
- * obligated to, for example, if there are no pending callbacks.
- */
-void rcu_barrier_tasks_trace(void)
-{
-	rcu_barrier_tasks_generic(&rcu_tasks_trace);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
 
 int rcu_tasks_trace_lazy_ms = -1;
 module_param(rcu_tasks_trace_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_trace_kthread(void)
 {
-	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
-		rcu_tasks_trace.gp_sleep = HZ / 10;
-		rcu_tasks_trace.init_fract = HZ / 10;
-	} else {
-		rcu_tasks_trace.gp_sleep = HZ / 200;
-		if (rcu_tasks_trace.gp_sleep <= 0)
-			rcu_tasks_trace.gp_sleep = 1;
-		rcu_tasks_trace.init_fract = HZ / 200;
-		if (rcu_tasks_trace.init_fract <= 0)
-			rcu_tasks_trace.init_fract = 1;
-	}
-	if (rcu_tasks_trace_lazy_ms >= 0)
-		rcu_tasks_trace.lazy_jiffies = msecs_to_jiffies(rcu_tasks_trace_lazy_ms);
-	rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
-	rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
-	rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace;
-	rcu_tasks_trace.postgp_func = rcu_tasks_trace_postgp;
-	rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
 	return 0;
 }
 
 #if !defined(CONFIG_TINY_RCU)
 void show_rcu_tasks_trace_gp_kthread(void)
 {
-	char buf[64];
-
-	snprintf(buf, sizeof(buf), "N%lu h:%lu/%lu/%lu",
-		data_race(n_trc_holdouts),
-		data_race(n_heavy_reader_ofl_updates),
-		data_race(n_heavy_reader_updates),
-		data_race(n_heavy_reader_attempts));
-	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf);
 }
 EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread);
 
 void rcu_tasks_trace_torture_stats_print(char *tt, char *tf)
 {
-	rcu_tasks_torture_stats_print_generic(&rcu_tasks_trace, tt, tf, "");
 }
 EXPORT_SYMBOL_GPL(rcu_tasks_trace_torture_stats_print);
 #endif // !defined(CONFIG_TINY_RCU)
 
 struct task_struct *get_rcu_tasks_trace_gp_kthread(void)
 {
-	return rcu_tasks_trace.kthread_ptr;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(get_rcu_tasks_trace_gp_kthread);
 
 void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq)
 {
-	*flags = 0;
-	*gp_seq = rcu_seq_current(&rcu_tasks_trace.tasks_gp_seq);
 }
 EXPORT_SYMBOL_GPL(rcu_tasks_trace_get_gp_data);
 
@@ -2251,10 +1672,6 @@ void __init tasks_cblist_init_generic(void)
 #ifdef CONFIG_TASKS_RUDE_RCU
 	cblist_init_generic(&rcu_tasks_rude);
 #endif
-
-#ifdef CONFIG_TASKS_TRACE_RCU
-	cblist_init_generic(&rcu_tasks_trace);
-#endif
 }
 
 static int __init rcu_init_tasks_generic(void)
-- 
2.40.1

[PATCH 2/9] context_tracking: Remove rcu_task_trace_heavyweight_{enter,exit}()

[Paul E. McKenney]

Because SRCU-fast does not use IPIs for its grace periods, there is
no need for real-time workloads to switch to an IPI-free mode, and
there is in turn no need for either rcu_task_trace_heavyweight_enter()
or rcu_task_trace_heavyweight_exit().  This commit therefore removes them.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 kernel/context_tracking.c | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index fb5be6e9b423..a743e7ffa6c0 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -54,24 +54,6 @@ static __always_inline void rcu_task_enter(void)
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
 
-/* Turn on heavyweight RCU tasks trace readers on kernel exit. */
-static __always_inline void rcu_task_trace_heavyweight_enter(void)
-{
-#ifdef CONFIG_TASKS_TRACE_RCU
-	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
-		current->trc_reader_special.b.need_mb = true;
-#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
-}
-
-/* Turn off heavyweight RCU tasks trace readers on kernel entry. */
-static __always_inline void rcu_task_trace_heavyweight_exit(void)
-{
-#ifdef CONFIG_TASKS_TRACE_RCU
-	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
-		current->trc_reader_special.b.need_mb = false;
-#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
-}
-
 /*
  * Record entry into an extended quiescent state.  This is only to be
  * called when not already in an extended quiescent state, that is,
@@ -85,7 +67,6 @@ static noinstr void ct_kernel_exit_state(int offset)
 	 * critical sections, and we also must force ordering with the
 	 * next idle sojourn.
 	 */
-	rcu_task_trace_heavyweight_enter();  // Before CT state update!
 	// RCU is still watching.  Better not be in extended quiescent state!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !rcu_is_watching_curr_cpu());
 	(void)ct_state_inc(offset);
@@ -108,7 +89,6 @@ static noinstr void ct_kernel_enter_state(int offset)
 	 */
 	seq = ct_state_inc(offset);
 	// RCU is now watching.  Better not be in an extended quiescent state!
-	rcu_task_trace_heavyweight_exit();  // After CT state update!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & CT_RCU_WATCHING));
 }
 
-- 
2.40.1

[PATCH v3 RFC 0/9] Implement RCU Tasks Trace in terms of SRCU

[Paul E. McKenney]

Hello!

This v3 patch series re-implements RCU Tasks Trace in terms of SRCU-fast,
reducing the size of the Linux-kernel RCU implementation by several
hundred lines of code.  It is deferred from the v6.19 merge window
due to performance issues on arm64, which are in the process of being
addressed:

	https://lore.kernel.org/all/aQU7l-qMKJTx4znJ@arm.com/

This series depends on the SRCU series:

https://lore.kernel.org/all/6eb0d40f-9776-412a-9ab4-2d3298ead766@paulmck-laptop

Unlike for SRCU-fast-updown, there are no straightforward workarounds,
hence the deferral.  The patches are as follows:

1.	Re-implement RCU Tasks Trace in terms of SRCU-fast.

2.	context_tracking: Remove
	rcu_task_trace_heavyweight_{enter,exit}().

3.	Clean up after the SRCU-fastification of RCU Tasks Trace.

4.	Move rcu_tasks_trace_srcu_struct out of #ifdef
	CONFIG_TASKS_RCU_GENERIC.

5.	Add noinstr-fast rcu_read_{,un}lock_tasks_trace() APIs.

6.	Update Requirements.rst for RCU Tasks Trace.

7.	Deprecate rcu_read_{,un}lock_trace().

8.	Create an rcu_tasks_trace_expedite_current() function.

9.	Test rcu_tasks_trace_expedite_current().

Changes since v2:

o	SRCU improvments not strictly related to RCU tasks trace have
	been moved out to a separate series.

o	Use the new DEFINE_SRCU_FAST().

https://lore.kernel.org/all/7fa58961-2dce-4e08-8174-1d1cc592210f@paulmck-laptop/

Changes since v1:

o	Consolidate RCU Tasks Trace cleanup patches per Alexei Starovoitov
	feedback.  This explains the decrease from 34 patches in v1 to
	only 21 in this v2 series.

o	While consolidating, consolidate the noinstr-fast patches and the
	DEFINE_SRCU_FAST()/init_srcu_struct_fast() patches.

o	Upgrade comments per Peter Zijlstra feedback.

o	Extract Tiny SRCU bug fix into its own commit per Andrii Nakryiko
	feedback.

o	Switch srcu_expedite_current() from preempt_disable() to
	migrate_disable() for PREEMPT_RT kernels per Zqiang feedback.

o	Apply tags.

https://lore.kernel.org/all/580ea2de-799a-4ddc-bde9-c16f3fb1e6e7@paulmck-laptop/

						Thanx, Paul

------------------------------------------------------------------------

 b/Documentation/RCU/Design/Requirements/Requirements.rst |   12 
 b/Documentation/admin-guide/kernel-parameters.txt        |   15 
 b/include/linux/rcupdate.h                               |   31 
 b/include/linux/rcupdate_trace.h                         |  107 +-
 b/include/linux/sched.h                                  |    1 
 b/init/init_task.c                                       |    3 
 b/kernel/context_tracking.c                              |   20 
 b/kernel/fork.c                                          |    3 
 b/kernel/rcu/Kconfig                                     |   18 
 b/kernel/rcu/rcu.h                                       |    9 
 b/kernel/rcu/rcuscale.c                                  |    7 
 b/kernel/rcu/rcutorture.c                                |    2 
 b/kernel/rcu/tasks.h                                     |  621 ---------------
 b/scripts/checkpatch.pl                                  |    2 
 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 |    1 
 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 |    1 
 include/linux/rcupdate_trace.h                           |   81 +
 include/linux/sched.h                                    |    5 
 kernel/rcu/Kconfig                                       |   25 
 kernel/rcu/rcutorture.c                                  |    1 
 kernel/rcu/tasks.h                                       |  121 --
 21 files changed, 218 insertions(+), 868 deletions(-)

[PATCH 3/9] rcu: Clean up after the SRCU-fastification of RCU Tasks Trace

[Paul E. McKenney]

Now that RCU Tasks Trace has been re-implemented in terms of SRCU-fast,
the ->trc_ipi_to_cpu, ->trc_blkd_cpu, ->trc_blkd_node, ->trc_holdout_list,
and ->trc_reader_special task_struct fields are no longer used.

In addition, the rcu_tasks_trace_qs(), rcu_tasks_trace_qs_blkd(),
exit_tasks_rcu_finish_trace(), and rcu_spawn_tasks_trace_kthread(),
show_rcu_tasks_trace_gp_kthread(), rcu_tasks_trace_get_gp_data(),
rcu_tasks_trace_torture_stats_print(), and get_rcu_tasks_trace_gp_kthread()
functions and all the other functions that they invoke are no longer used.

Also, the TRC_NEED_QS and TRC_NEED_QS_CHECKED CPP macros are no longer used.
Neither are the rcu_tasks_trace_lazy_ms and rcu_task_ipi_delay rcupdate
module parameters and the TASKS_TRACE_RCU_READ_MB Kconfig option.

This commit therefore removes all of them.

[ paulmck: Apply Alexei Starovoitov feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 .../admin-guide/kernel-parameters.txt         | 15 ----
 include/linux/rcupdate.h                      | 31 +-------
 include/linux/rcupdate_trace.h                |  2 -
 include/linux/sched.h                         |  5 --
 init/init_task.c                              |  3 -
 kernel/fork.c                                 |  3 -
 kernel/rcu/Kconfig                            | 18 -----
 kernel/rcu/rcu.h                              |  9 ---
 kernel/rcu/rcuscale.c                         |  7 --
 kernel/rcu/rcutorture.c                       |  2 -
 kernel/rcu/tasks.h                            | 79 +------------------
 .../selftests/rcutorture/configs/rcu/TRACE01  |  1 -
 .../selftests/rcutorture/configs/rcu/TRACE02  |  1 -
 13 files changed, 2 insertions(+), 174 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 747a55abf494..40fc198bed4d 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6078,13 +6078,6 @@
 			dynamically) adjusted.	This parameter is intended
 			for use in testing.
 
-	rcupdate.rcu_task_ipi_delay= [KNL]
-			Set time in jiffies during which RCU tasks will
-			avoid sending IPIs, starting with the beginning
-			of a given grace period.  Setting a large
-			number avoids disturbing real-time workloads,
-			but lengthens grace periods.
-
 	rcupdate.rcu_task_lazy_lim= [KNL]
 			Number of callbacks on a given CPU that will
 			cancel laziness on that CPU.  Use -1 to disable
@@ -6128,14 +6121,6 @@
 			of zero will disable batching.	Batching is
 			always disabled for synchronize_rcu_tasks().
 
-	rcupdate.rcu_tasks_trace_lazy_ms= [KNL]
-			Set timeout in milliseconds RCU Tasks
-			Trace asynchronous callback batching for
-			call_rcu_tasks_trace().  A negative value
-			will take the default.	A value of zero will
-			disable batching.  Batching is always disabled
-			for synchronize_rcu_tasks_trace().
-
 	rcupdate.rcu_self_test= [KNL]
 			Run the RCU early boot self tests
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 120536f4c6eb..2237c56d3241 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -175,36 +175,7 @@ void rcu_tasks_torture_stats_print(char *tt, char *tf);
 # define synchronize_rcu_tasks synchronize_rcu
 # endif
 
-# ifdef CONFIG_TASKS_TRACE_RCU
-// 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 (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) &&	\
-		    likely(!___rttq_nesting)) {					\
-			rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, 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)
-void rcu_tasks_trace_torture_stats_print(char *tt, char *tf);
-# else
-# define rcu_tasks_trace_qs(t) do { } while (0)
-# endif
-
-#define rcu_tasks_qs(t, preempt)					\
-do {									\
-	rcu_tasks_classic_qs((t), (preempt));				\
-	rcu_tasks_trace_qs(t);						\
-} while (0)
+#define rcu_tasks_qs(t, preempt) rcu_tasks_classic_qs((t), (preempt))
 
 # ifdef CONFIG_TASKS_RUDE_RCU
 void synchronize_rcu_tasks_rude(void);
diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index 3f46cbe67000..0bd47f12ecd1 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -136,9 +136,7 @@ static inline void rcu_barrier_tasks_trace(void)
 }
 
 // Placeholders to enable stepwise transition.
-void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq);
 void __init rcu_tasks_trace_suppress_unused(void);
-struct task_struct *get_rcu_tasks_trace_gp_kthread(void);
 
 #else
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 89d364615552..577fafd22a0e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -940,11 +940,6 @@ struct task_struct {
 #ifdef CONFIG_TASKS_TRACE_RCU
 	int				trc_reader_nesting;
 	struct srcu_ctr __percpu	*trc_reader_scp;
-	int				trc_ipi_to_cpu;
-	union rcu_special		trc_reader_special;
-	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;
diff --git a/init/init_task.c b/init/init_task.c
index e557f622bd90..0c075f3cc8fc 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -165,9 +165,6 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 #endif
 #ifdef CONFIG_TASKS_TRACE_RCU
 	.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,
diff --git a/kernel/fork.c b/kernel/fork.c
index af673856499d..5686d50b62cf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1780,9 +1780,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_RCU */
 #ifdef CONFIG_TASKS_TRACE_RCU
 	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 */
 }
 
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index ceaf6594f634..54b4c4aa553a 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -313,24 +313,6 @@ config RCU_NOCB_CPU_CB_BOOST
 	  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
-	default PREEMPT_RT || NR_CPUS < 8
-	help
-	  Use this option to further reduce the number of IPIs sent
-	  to CPUs executing in userspace or idle during tasks trace
-	  RCU grace periods.  Given that a reasonable setting of
-	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
-	  eliminates such IPIs for many workloads, proper setting
-	  of this Kconfig option is important mostly for aggressive
-	  real-time installations and for battery-powered devices,
-	  hence the default chosen above.
-
-	  Say Y here if you hate IPIs.
-	  Say N here if you hate read-side memory barriers.
-	  Take the default if you are unsure.
-
 config RCU_LAZY
 	bool "RCU callback lazy invocation functionality"
 	depends on RCU_NOCB_CPU
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 9cf01832a6c3..dc5d614b372c 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -544,10 +544,6 @@ struct task_struct *get_rcu_tasks_rude_gp_kthread(void);
 void rcu_tasks_rude_get_gp_data(int *flags, unsigned long *gp_seq);
 #endif // # ifdef CONFIG_TASKS_RUDE_RCU
 
-#ifdef CONFIG_TASKS_TRACE_RCU
-void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq);
-#endif
-
 #ifdef CONFIG_TASKS_RCU_GENERIC
 void tasks_cblist_init_generic(void);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
@@ -673,11 +669,6 @@ void show_rcu_tasks_rude_gp_kthread(void);
 #else
 static inline void show_rcu_tasks_rude_gp_kthread(void) {}
 #endif
-#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_TRACE_RCU)
-void show_rcu_tasks_trace_gp_kthread(void);
-#else
-static inline void show_rcu_tasks_trace_gp_kthread(void) {}
-#endif
 
 #ifdef CONFIG_TINY_RCU
 static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index b521d0455992..17d038e26b65 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -400,11 +400,6 @@ static void tasks_trace_scale_read_unlock(int idx)
 	rcu_read_unlock_trace();
 }
 
-static void rcu_tasks_trace_scale_stats(void)
-{
-	rcu_tasks_trace_torture_stats_print(scale_type, SCALE_FLAG);
-}
-
 static struct rcu_scale_ops tasks_tracing_ops = {
 	.ptype		= RCU_TASKS_FLAVOR,
 	.init		= rcu_sync_scale_init,
@@ -416,8 +411,6 @@ static struct rcu_scale_ops tasks_tracing_ops = {
 	.gp_barrier	= rcu_barrier_tasks_trace,
 	.sync		= synchronize_rcu_tasks_trace,
 	.exp_sync	= synchronize_rcu_tasks_trace,
-	.rso_gp_kthread	= get_rcu_tasks_trace_gp_kthread,
-	.stats		= IS_ENABLED(CONFIG_TINY_RCU) ? NULL : rcu_tasks_trace_scale_stats,
 	.name		= "tasks-tracing"
 };
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 423c4bddd17c..647af81e0b21 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1182,8 +1182,6 @@ static struct rcu_torture_ops tasks_tracing_ops = {
 	.exp_sync	= synchronize_rcu_tasks_trace,
 	.call		= call_rcu_tasks_trace,
 	.cb_barrier	= rcu_barrier_tasks_trace,
-	.gp_kthread_dbg	= show_rcu_tasks_trace_gp_kthread,
-	.get_gp_data    = rcu_tasks_trace_get_gp_data,
 	.cbflood_max	= 50000,
 	.irq_capable	= 1,
 	.slow_gps	= 1,
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 1fe789c99f36..1249b47f0a8d 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -161,11 +161,6 @@ static void tasks_rcu_exit_srcu_stall(struct timer_list *unused);
 static DEFINE_TIMER(tasks_rcu_exit_srcu_stall_timer, tasks_rcu_exit_srcu_stall);
 #endif
 
-/* Avoid IPIing CPUs early in the grace period. */
-#define RCU_TASK_IPI_DELAY (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) ? HZ / 2 : 0)
-static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
-module_param(rcu_task_ipi_delay, int, 0644);
-
 /* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
 #define RCU_TASK_BOOT_STALL_TIMEOUT (HZ * 30)
 #define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
@@ -800,8 +795,6 @@ static void rcu_tasks_torture_stats_print_generic(struct rcu_tasks *rtp, char *t
 
 #endif // #ifndef CONFIG_TINY_RCU
 
-static void exit_tasks_rcu_finish_trace(struct task_struct *t);
-
 #if defined(CONFIG_TASKS_RCU)
 
 ////////////////////////////////////////////////////////////////////////
@@ -1321,13 +1314,11 @@ void exit_tasks_rcu_finish(void)
 	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
 	list_del_init(&t->rcu_tasks_exit_list);
 	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
-
-	exit_tasks_rcu_finish_trace(t);
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
 void exit_tasks_rcu_start(void) { }
-void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
+void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 #ifdef CONFIG_TASKS_RUDE_RCU
@@ -1475,69 +1466,6 @@ void __init rcu_tasks_trace_suppress_unused(void)
 #endif // #ifndef CONFIG_TINY_RCU
 }
 
-/*
- * Do a cmpxchg() on ->trc_reader_special.b.need_qs, allowing for
- * the four-byte operand-size restriction of some platforms.
- *
- * Returns the old value, which is often ignored.
- */
-u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new)
-{
-	return cmpxchg(&t->trc_reader_special.b.need_qs, old, new);
-}
-EXPORT_SYMBOL_GPL(rcu_trc_cmpxchg_need_qs);
-
-/* Add a newly blocked reader task to its CPU's list. */
-void rcu_tasks_trace_qs_blkd(struct task_struct *t)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_tasks_trace_qs_blkd);
-
-/* Communicate task state back to the RCU tasks trace stall warning request. */
-struct trc_stall_chk_rdr {
-	int nesting;
-	int ipi_to_cpu;
-	u8 needqs;
-};
-
-/* Report any needed quiescent state for this exiting task. */
-static void exit_tasks_rcu_finish_trace(struct task_struct *t)
-{
-}
-
-int rcu_tasks_trace_lazy_ms = -1;
-module_param(rcu_tasks_trace_lazy_ms, int, 0444);
-
-static int __init rcu_spawn_tasks_trace_kthread(void)
-{
-	return 0;
-}
-
-#if !defined(CONFIG_TINY_RCU)
-void show_rcu_tasks_trace_gp_kthread(void)
-{
-}
-EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread);
-
-void rcu_tasks_trace_torture_stats_print(char *tt, char *tf)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_tasks_trace_torture_stats_print);
-#endif // !defined(CONFIG_TINY_RCU)
-
-struct task_struct *get_rcu_tasks_trace_gp_kthread(void)
-{
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(get_rcu_tasks_trace_gp_kthread);
-
-void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_tasks_trace_get_gp_data);
-
-#else /* #ifdef CONFIG_TASKS_TRACE_RCU */
-static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
 #endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
 
 #ifndef CONFIG_TINY_RCU
@@ -1545,7 +1473,6 @@ void show_rcu_tasks_gp_kthreads(void)
 {
 	show_rcu_tasks_classic_gp_kthread();
 	show_rcu_tasks_rude_gp_kthread();
-	show_rcu_tasks_trace_gp_kthread();
 }
 #endif /* #ifndef CONFIG_TINY_RCU */
 
@@ -1684,10 +1611,6 @@ static int __init rcu_init_tasks_generic(void)
 	rcu_spawn_tasks_rude_kthread();
 #endif
 
-#ifdef CONFIG_TASKS_TRACE_RCU
-	rcu_spawn_tasks_trace_kthread();
-#endif
-
 	// Run the self-tests.
 	rcu_tasks_initiate_self_tests();
 
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
index 85b407467454..18efab346381 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -10,5 +10,4 @@ CONFIG_PROVE_LOCKING=n
 #CHECK#CONFIG_PROVE_RCU=n
 CONFIG_FORCE_TASKS_TRACE_RCU=y
 #CHECK#CONFIG_TASKS_TRACE_RCU=y
-CONFIG_TASKS_TRACE_RCU_READ_MB=y
 CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
index 9003c56cd764..8da390e82829 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
@@ -9,6 +9,5 @@ CONFIG_PROVE_LOCKING=y
 #CHECK#CONFIG_PROVE_RCU=y
 CONFIG_FORCE_TASKS_TRACE_RCU=y
 #CHECK#CONFIG_TASKS_TRACE_RCU=y
-CONFIG_TASKS_TRACE_RCU_READ_MB=n
 CONFIG_RCU_EXPERT=y
 CONFIG_DEBUG_OBJECTS=y
-- 
2.40.1

[PATCH 4/9] rcu: Move rcu_tasks_trace_srcu_struct out of #ifdef CONFIG_TASKS_RCU_GENERIC

[Paul E. McKenney]

Moving the rcu_tasks_trace_srcu_struct structure instance out
from under the CONFIG_TASKS_RCU_GENERIC Kconfig option permits
the CONFIG_TASKS_TRACE_RCU Kconfig option to stop enabling this
CONFIG_TASKS_RCU_GENERIC Kconfig option.  This commit also therefore
makes it so.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 kernel/rcu/Kconfig |  2 +-
 kernel/rcu/tasks.h | 42 +++++++++++++-----------------------------
 2 files changed, 14 insertions(+), 30 deletions(-)

diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 54b4c4aa553a..73a6cc364628 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -82,7 +82,7 @@ config NEED_SRCU_NMI_SAFE
 	def_bool HAVE_NMI && !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !TINY_SRCU
 
 config TASKS_RCU_GENERIC
-	def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
+	def_bool TASKS_RCU || TASKS_RUDE_RCU
 	help
 	  This option enables generic infrastructure code supporting
 	  task-based RCU implementations.  Not for manual selection.
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 1249b47f0a8d..76f952196a29 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -1439,35 +1439,6 @@ EXPORT_SYMBOL_GPL(rcu_tasks_rude_get_gp_data);
 
 #endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
 
-////////////////////////////////////////////////////////////////////////
-//
-// Tracing variant of Tasks RCU.  This variant is designed to be used
-// to protect tracing hooks, including those of BPF.  This variant
-// is implemented via a straightforward mapping onto SRCU-fast.
-
-#ifdef CONFIG_TASKS_TRACE_RCU
-
-DEFINE_SRCU_FAST(rcu_tasks_trace_srcu_struct);
-EXPORT_SYMBOL_GPL(rcu_tasks_trace_srcu_struct);
-
-// Placeholder to suppress build errors through transition period.
-void __init rcu_tasks_trace_suppress_unused(void)
-{
-#ifndef CONFIG_TINY_RCU
-	show_rcu_tasks_generic_gp_kthread(NULL, NULL);
-#endif // #ifndef CONFIG_TINY_RCU
-	rcu_spawn_tasks_kthread_generic(NULL);
-	synchronize_rcu_tasks_generic(NULL);
-	call_rcu_tasks_generic(NULL, NULL, NULL);
-	call_rcu_tasks_iw_wakeup(NULL);
-	cblist_init_generic(NULL);
-#ifndef CONFIG_TINY_RCU
-	rcu_tasks_torture_stats_print_generic(NULL, NULL, NULL, NULL);
-#endif // #ifndef CONFIG_TINY_RCU
-}
-
-#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
-
 #ifndef CONFIG_TINY_RCU
 void show_rcu_tasks_gp_kthreads(void)
 {
@@ -1621,3 +1592,16 @@ core_initcall(rcu_init_tasks_generic);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 static inline void rcu_tasks_bootup_oddness(void) {}
 #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+
+////////////////////////////////////////////////////////////////////////
+//
+// Tracing variant of Tasks RCU.  This variant is designed to be used
+// to protect tracing hooks, including those of BPF.  This variant
+// is implemented via a straightforward mapping onto SRCU-fast.
+
+DEFINE_SRCU_FAST(rcu_tasks_trace_srcu_struct);
+EXPORT_SYMBOL_GPL(rcu_tasks_trace_srcu_struct);
+
+#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
-- 
2.40.1

[PATCH 5/9] rcu: Add noinstr-fast rcu_read_{,un}lock_tasks_trace() APIs

[Paul E. McKenney]

When expressing RCU Tasks Trace in terms of SRCU-fast, it was
necessary to keep a nesting count and per-CPU srcu_ctr structure
pointer in the task_struct structure, which is slow to access.
But an alternative is to instead make rcu_read_lock_tasks_trace() and
rcu_read_unlock_tasks_trace(), which match the underlying SRCU-fast
semantics, avoiding the task_struct accesses.

When all callers have switched to the new API, the previous
rcu_read_lock_trace() and rcu_read_unlock_trace() APIs will be removed.

The rcu_read_{,un}lock_{,tasks_}trace() functions need to use smp_mb()
only if invoked where RCU is not watching, that is, from locations where
a call to rcu_is_watching() would return false.  In architectures that
define the ARCH_WANTS_NO_INSTR Kconfig option, use of noinstr and friends
ensures that tracing happens only where RCU is watching, so those
architectures can dispense entirely with the read-side calls to smp_mb().

Other architectures include these read-side calls by default, but in many
installations there might be either larger than average tolerance for
risk, prohibition of removing tracing on a running system, or careful
review and approval of removing of tracing.  Such installations can
build their kernels with CONFIG_TASKS_TRACE_RCU_NO_MB=y to avoid those
read-side calls to smp_mb(), thus accepting responsibility for run-time
removal of tracing from code regions that RCU is not watching.

Those wishing to disable read-side memory barriers for an entire
architecture can select this TASKS_TRACE_RCU_NO_MB Kconfig option,
hence the polarity.

[ paulmck: Apply Peter Zijlstra feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 include/linux/rcupdate_trace.h | 65 +++++++++++++++++++++++++++++-----
 kernel/rcu/Kconfig             | 23 ++++++++++++
 2 files changed, 80 insertions(+), 8 deletions(-)

diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index 0bd47f12ecd1..f47ba9c07460 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -34,6 +34,53 @@ static inline int rcu_read_lock_trace_held(void)
 
 #ifdef CONFIG_TASKS_TRACE_RCU
 
+/**
+ * rcu_read_lock_tasks_trace - mark beginning of RCU-trace read-side critical section
+ *
+ * When synchronize_rcu_tasks_trace() is invoked by one task, then that
+ * task is guaranteed to block until all other tasks exit their read-side
+ * critical sections.  Similarly, if call_rcu_trace() is invoked on one
+ * task while other tasks are within RCU read-side critical sections,
+ * invocation of the corresponding RCU callback is deferred until after
+ * the all the other tasks exit their critical sections.
+ *
+ * For more details, please see the documentation for
+ * srcu_read_lock_fast().  For a description of how implicit RCU
+ * readers provide the needed ordering for architectures defining the
+ * ARCH_WANTS_NO_INSTR Kconfig option (and thus promising never to trace
+ * code where RCU is not watching), please see the __srcu_read_lock_fast()
+ * (non-kerneldoc) header comment.  Otherwise, the smp_mb() below provided
+ * the needed ordering.
+ */
+static inline struct srcu_ctr __percpu *rcu_read_lock_tasks_trace(void)
+{
+	struct srcu_ctr __percpu *ret = __srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct);
+
+	rcu_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map);
+	if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB))
+		smp_mb(); // Provide ordering on noinstr-incomplete architectures.
+	return ret;
+}
+
+/**
+ * rcu_read_unlock_tasks_trace - mark end of RCU-trace read-side critical section
+ * @scp: return value from corresponding rcu_read_lock_tasks_trace().
+ *
+ * Pairs with the preceding call to rcu_read_lock_tasks_trace() that
+ * returned the value passed in via scp.
+ *
+ * For more details, please see the documentation for rcu_read_unlock().
+ * For memory-ordering information, please see the header comment for the
+ * rcu_read_lock_tasks_trace() function.
+ */
+static inline void rcu_read_unlock_tasks_trace(struct srcu_ctr __percpu *scp)
+{
+	if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB))
+		smp_mb(); // Provide ordering on noinstr-incomplete architectures.
+	__srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp);
+	srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map);
+}
+
 /**
  * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section
  *
@@ -50,14 +97,15 @@ static inline void rcu_read_lock_trace(void)
 {
 	struct task_struct *t = current;
 
+	rcu_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map);
 	if (t->trc_reader_nesting++) {
 		// In case we interrupted a Tasks Trace RCU reader.
-		rcu_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map);
 		return;
 	}
 	barrier();  // nesting before scp to protect against interrupt handler.
-	t->trc_reader_scp = srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct);
-	smp_mb(); // Placeholder for more selective ordering
+	t->trc_reader_scp = __srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct);
+	if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB))
+		smp_mb(); // Placeholder for more selective ordering
 }
 
 /**
@@ -74,13 +122,14 @@ static inline void rcu_read_unlock_trace(void)
 	struct srcu_ctr __percpu *scp;
 	struct task_struct *t = current;
 
-	smp_mb(); // Placeholder for more selective ordering
 	scp = t->trc_reader_scp;
 	barrier();  // scp before nesting to protect against interrupt handler.
-	if (!--t->trc_reader_nesting)
-		srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp);
-	else
-		srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map);
+	if (!--t->trc_reader_nesting) {
+		if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB))
+			smp_mb(); // Placeholder for more selective ordering
+		__srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp);
+	}
+	srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map);
 }
 
 /**
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 73a6cc364628..6a319e292658 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -142,6 +142,29 @@ config TASKS_TRACE_RCU
 	default n
 	select IRQ_WORK
 
+config TASKS_TRACE_RCU_NO_MB
+	bool "Override RCU Tasks Trace inclusion of read-side memory barriers"
+	depends on RCU_EXPERT && TASKS_TRACE_RCU
+	default ARCH_WANTS_NO_INSTR
+	help
+	  This option prevents the use of read-side memory barriers in
+	  rcu_read_lock_tasks_trace() and rcu_read_unlock_tasks_trace()
+	  even in kernels built with CONFIG_ARCH_WANTS_NO_INSTR=n, that is,
+	  in kernels that do not have noinstr set up in entry/exit code.
+	  By setting this option, you are promising to carefully review
+	  use of ftrace, BPF, and friends to ensure that no tracing
+	  operation is attached to a function that runs in that portion
+	  of the entry/exit code that RCU does not watch, that is,
+	  where rcu_is_watching() returns false.  Alternatively, you
+	  might choose to never remove traces except by rebooting.
+
+	  Those wishing to disable read-side memory barriers for an entire
+	  architecture can select this Kconfig option, hence the polarity.
+
+	  Say Y here if you need speed and will review use of tracing.
+	  Say N here for certain esoteric testing of RCU itself.
+	  Take the default if you are unsure.
+
 config RCU_STALL_COMMON
 	def_bool TREE_RCU
 	help
-- 
2.40.1

[PATCH 6/9] rcu: Update Requirements.rst for RCU Tasks Trace

[Paul E. McKenney]

This commit updates the documentation to declare that RCU Tasks Trace
is implemented as a thin wrapper around SRCU-fast.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 .../RCU/Design/Requirements/Requirements.rst         | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst
index ba417a08b93d..b5cdbba3ec2e 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.rst
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -2780,12 +2780,12 @@ Tasks Trace RCU
 ~~~~~~~~~~~~~~~
 
 Some forms of tracing need to sleep in readers, but cannot tolerate
-SRCU's read-side overhead, which includes a full memory barrier in both
-srcu_read_lock() and srcu_read_unlock().  This need is handled by a
-Tasks Trace RCU that uses scheduler locking and IPIs to synchronize with
-readers.  Real-time systems that cannot tolerate IPIs may build their
-kernels with ``CONFIG_TASKS_TRACE_RCU_READ_MB=y``, which avoids the IPIs at
-the expense of adding full memory barriers to the read-side primitives.
+SRCU's read-side overhead, which includes a full memory barrier in
+both srcu_read_lock() and srcu_read_unlock().  This need is handled by
+a Tasks Trace RCU API implemented as thin wrappers around SRCU-fast,
+which avoids the read-side memory barriers, at least for architectures
+that apply noinstr to kernel entry/exit code (or that build with
+``CONFIG_TASKS_TRACE_RCU_NO_MB=y``.
 
 The tasks-trace-RCU API is also reasonably compact,
 consisting of rcu_read_lock_trace(), rcu_read_unlock_trace(),
-- 
2.40.1

[PATCH 7/9] checkpatch: Deprecate rcu_read_{,un}lock_trace()

[Paul E. McKenney]

Uses of rcu_read_lock_trace() and rcu_read_unlock_trace()
are better served by the new rcu_read_lock_tasks_trace() and
rcu_read_unlock_tasks_trace() APIs.  Therefore, mark the old APIs as
deprecated.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Joe Perches <joe@perches.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Dwaipayan Ray <dwaipayanray1@gmail.com>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 scripts/checkpatch.pl | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e722dd6fa8ef..3bb7d35a5cfc 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -860,6 +860,8 @@ our %deprecated_apis = (
 	"kunmap"				=> "kunmap_local",
 	"kmap_atomic"				=> "kmap_local_page",
 	"kunmap_atomic"				=> "kunmap_local",
+	"rcu_read_lock_trace"			=> "rcu_read_lock_tasks_trace",
+	"rcu_read_unlock_trace"			=> "rcu_read_unlock_tasks_trace",
 );
 
 #Create a search pattern for all these strings to speed up a loop below
-- 
2.40.1

[PATCH 8/9] srcu: Create an rcu_tasks_trace_expedite_current() function

[Paul E. McKenney]

This commit creates an rcu_tasks_trace_expedite_current() function
that expedites the current (and possibly the next) RCU Tasks Trace
grace period.

If the current RCU Tasks Trace grace period is already waiting, that wait
will complete before the expediting takes effect.  If there is no RCU
Tasks Trace  grace period in flight, this function might well create one.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 include/linux/rcupdate_trace.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index f47ba9c07460..cee89e51e45c 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -184,6 +184,20 @@ static inline void rcu_barrier_tasks_trace(void)
 	srcu_barrier(&rcu_tasks_trace_srcu_struct);
 }
 
+/**
+ * rcu_tasks_trace_expedite_current - Expedite the current Tasks Trace RCU grace period
+ *
+ * Cause the current Tasks Trace RCU grace period to become expedited.
+ * The grace period following the current one might also be expedited.
+ * If there is no current grace period, one might be created.  If the
+ * current grace period is currently sleeping, that sleep will complete
+ * before expediting will take effect.
+ */
+static inline void rcu_tasks_trace_expedite_current(void)
+{
+	srcu_expedite_current(&rcu_tasks_trace_srcu_struct);
+}
+
 // Placeholders to enable stepwise transition.
 void __init rcu_tasks_trace_suppress_unused(void);
 
-- 
2.40.1

[PATCH 9/9] rcutorture: Test rcu_tasks_trace_expedite_current()

[Paul E. McKenney]

This commit adds a ->exp_current member to the tasks_tracing_ops structure
to test the rcu_tasks_trace_expedite_current() function.

[ paulmck: Apply kernel test robot feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <bpf@vger.kernel.org>
---
 kernel/rcu/rcutorture.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 647af81e0b21..f651b1dc2c97 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1180,6 +1180,7 @@ static struct rcu_torture_ops tasks_tracing_ops = {
 	.deferred_free	= rcu_tasks_tracing_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks_trace,
 	.exp_sync	= synchronize_rcu_tasks_trace,
+	.exp_current	= rcu_tasks_trace_expedite_current,
 	.call		= call_rcu_tasks_trace,
 	.cb_barrier	= rcu_barrier_tasks_trace,
 	.cbflood_max	= 50000,
-- 
2.40.1