From 2f7c68cb55ecb7331f2381deb497c27155f32faf Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 03 Jan 2024 09:43:39 +0000
Subject: [PATCH] update kernel to 5.10.198
---
kernel/kernel/rcu/tasks.h | 139 ++++++++++++++++++++++++++++------------------
1 files changed, 84 insertions(+), 55 deletions(-)
diff --git a/kernel/kernel/rcu/tasks.h b/kernel/kernel/rcu/tasks.h
index 8b51e6a..0b501c3 100644
--- a/kernel/kernel/rcu/tasks.h
+++ b/kernel/kernel/rcu/tasks.h
@@ -171,8 +171,9 @@
static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
{
/* Complain if the scheduler has not started. */
- WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
- "synchronize_rcu_tasks called too soon");
+ if (WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
+ "synchronize_%s() called too soon", rtp->name))
+ return;
/* Wait for the grace period. */
wait_rcu_gp(rtp->call_func);
@@ -416,11 +417,21 @@
static void rcu_tasks_postscan(struct list_head *hop)
{
/*
- * Wait for tasks that are in the process of exiting. This
- * does only part of the job, ensuring that all tasks that were
- * previously exiting reach the point where they have disabled
- * preemption, allowing the later synchronize_rcu() to finish
- * the job.
+ * Exiting tasks may escape the tasklist scan. Those are vulnerable
+ * until their final schedule() with TASK_DEAD state. To cope with
+ * this, divide the fragile exit path part in two intersecting
+ * read side critical sections:
+ *
+ * 1) An _SRCU_ read side starting before calling exit_notify(),
+ * which may remove the task from the tasklist, and ending after
+ * the final preempt_disable() call in do_exit().
+ *
+ * 2) An _RCU_ read side starting with the final preempt_disable()
+ * call in do_exit() and ending with the final call to schedule()
+ * with TASK_DEAD state.
+ *
+ * This handles the part 1). And postgp will handle part 2) with a
+ * call to synchronize_rcu().
*/
synchronize_srcu(&tasks_rcu_exit_srcu);
}
@@ -487,7 +498,10 @@
*
* In addition, this synchronize_rcu() waits for exiting tasks
* to complete their final preempt_disable() region of execution,
- * cleaning up after the synchronize_srcu() above.
+ * cleaning up after synchronize_srcu(&tasks_rcu_exit_srcu),
+ * enforcing the whole region before tasklist removal until
+ * the final schedule() with TASK_DEAD state to be an RCU TASKS
+ * read side critical section.
*/
synchronize_rcu();
}
@@ -576,28 +590,43 @@
}
#endif /* #ifndef CONFIG_TINY_RCU */
-/* Do the srcu_read_lock() for the above synchronize_srcu(). */
+/*
+ * Contribute to protect against tasklist scan blind spot while the
+ * task is exiting and may be removed from the tasklist. See
+ * corresponding synchronize_srcu() for further details.
+ */
void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
{
- preempt_disable();
current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
- preempt_enable();
}
-/* Do the srcu_read_unlock() for the above synchronize_srcu(). */
-void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
+/*
+ * Contribute to protect against tasklist scan blind spot while the
+ * task is exiting and may be removed from the tasklist. See
+ * corresponding synchronize_srcu() for further details.
+ */
+void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu)
{
struct task_struct *t = current;
- preempt_disable();
__srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx);
- preempt_enable();
- exit_tasks_rcu_finish_trace(t);
+}
+
+/*
+ * Contribute to protect against tasklist scan blind spot while the
+ * task is exiting and may be removed from the tasklist. See
+ * corresponding synchronize_srcu() for further details.
+ */
+void exit_tasks_rcu_finish(void)
+{
+ exit_tasks_rcu_stop();
+ exit_tasks_rcu_finish_trace(current);
}
#else /* #ifdef CONFIG_TASKS_RCU */
static inline void show_rcu_tasks_classic_gp_kthread(void) { }
void exit_tasks_rcu_start(void) { }
+void exit_tasks_rcu_stop(void) { }
void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
#endif /* #else #ifdef CONFIG_TASKS_RCU */
@@ -620,9 +649,6 @@
// Wait for one rude RCU-tasks grace period.
static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp)
{
- if (num_online_cpus() <= 1)
- return; // Fastpath for only one CPU.
-
rtp->n_ipis += cpumask_weight(cpu_online_mask);
schedule_on_each_cpu(rcu_tasks_be_rude);
}
@@ -707,7 +733,7 @@
#endif /* #ifndef CONFIG_TINY_RCU */
#else /* #ifdef CONFIG_TASKS_RUDE_RCU */
-static void show_rcu_tasks_rude_gp_kthread(void) {}
+static inline void show_rcu_tasks_rude_gp_kthread(void) {}
#endif /* #else #ifdef CONFIG_TASKS_RUDE_RCU */
////////////////////////////////////////////////////////////////////////
@@ -775,7 +801,7 @@
/* If we are the last reader, wake up the grace-period kthread. */
void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
{
- int nq = t->trc_reader_special.b.need_qs;
+ int nq = READ_ONCE(t->trc_reader_special.b.need_qs);
if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
t->trc_reader_special.b.need_mb)
@@ -815,33 +841,25 @@
// If the task is no longer running on this CPU, leave.
if (unlikely(texp != t)) {
- if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
- wake_up(&trc_wait);
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.
- if (likely(!t->trc_reader_nesting)) {
- if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
- wake_up(&trc_wait);
- // Mark as checked after decrement to avoid false
- // positives on the above WARN_ON_ONCE().
+ if (likely(!READ_ONCE(t->trc_reader_nesting))) {
WRITE_ONCE(t->trc_reader_checked, true);
goto reset_ipi;
}
// If we are racing with an rcu_read_unlock_trace(), try again later.
- if (unlikely(t->trc_reader_nesting < 0)) {
- if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
- wake_up(&trc_wait);
+ if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0))
goto reset_ipi;
- }
WRITE_ONCE(t->trc_reader_checked, true);
// Get here if the task is in a read-side critical section. Set
// its state so that it will awaken the grace-period kthread upon
// exit from that critical section.
- WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+ atomic_inc(&trc_n_readers_need_end); // One more to wait on.
+ WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
reset_ipi:
@@ -856,7 +874,7 @@
static bool trc_inspect_reader(struct task_struct *t, void *arg)
{
int cpu = task_cpu(t);
- bool in_qs = false;
+ int nesting;
bool ofl = cpu_is_offline(cpu);
if (task_curr(t)) {
@@ -876,23 +894,24 @@
n_heavy_reader_updates++;
if (ofl)
n_heavy_reader_ofl_updates++;
- in_qs = true;
+ nesting = 0;
} else {
- in_qs = likely(!t->trc_reader_nesting);
+ // The task is not running, so C-language access is safe.
+ nesting = t->trc_reader_nesting;
}
- // Mark as checked so that the grace-period kthread will
- // remove it from the holdout list.
- t->trc_reader_checked = true;
-
- if (in_qs)
- return true; // Already in quiescent state, done!!!
+ // If not exiting a read-side critical section, mark as checked
+ // so that the grace-period kthread will remove it from the
+ // holdout list.
+ t->trc_reader_checked = nesting >= 0;
+ if (nesting <= 0)
+ return !nesting; // If in QS, done, otherwise try again later.
// The task is in a read-side critical section, so set up its
// state so that it will awaken the grace-period kthread upon exit
// from that critical section.
atomic_inc(&trc_n_readers_need_end); // One more to wait on.
- WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+ WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs));
WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
return true;
}
@@ -910,7 +929,7 @@
// The current task had better be in a quiescent state.
if (t == current) {
t->trc_reader_checked = true;
- WARN_ON_ONCE(t->trc_reader_nesting);
+ WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
return;
}
@@ -933,21 +952,17 @@
if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0)
return;
- atomic_inc(&trc_n_readers_need_end);
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)) {
+ 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 = cpu;
- if (atomic_dec_and_test(&trc_n_readers_need_end)) {
- WARN_ON_ONCE(1);
- wake_up(&trc_wait);
- }
+ t->trc_ipi_to_cpu = -1;
}
}
}
@@ -1020,8 +1035,8 @@
".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0],
".i"[is_idle_task(t)],
".N"[cpu > 0 && tick_nohz_full_cpu(cpu)],
- t->trc_reader_nesting,
- " N"[!!t->trc_reader_special.b.need_qs],
+ READ_ONCE(t->trc_reader_nesting),
+ " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)],
cpu);
sched_show_task(t);
}
@@ -1068,13 +1083,27 @@
}
}
+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;
bool firstreport;
struct task_struct *g, *t;
LIST_HEAD(holdouts);
long ret;
+
+ // 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 (smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu)))
+ smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1);
// Remove the safety count.
smp_mb__before_atomic(); // Order vs. earlier atomics
@@ -1115,7 +1144,7 @@
static void exit_tasks_rcu_finish_trace(struct task_struct *t)
{
WRITE_ONCE(t->trc_reader_checked, true);
- WARN_ON_ONCE(t->trc_reader_nesting);
+ WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting));
WRITE_ONCE(t->trc_reader_nesting, 0);
if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)))
rcu_read_unlock_trace_special(t, 0);
--
Gitblit v1.6.2