summaryrefslogtreecommitdiff
path: root/kernel/rcu/tree.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/rcu/tree.c')
-rw-r--r--kernel/rcu/tree.c179
1 files changed, 116 insertions, 63 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f78ee759af9c..06895ef85d69 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -70,19 +70,6 @@
#endif
#define MODULE_PARAM_PREFIX "rcutree."
-#ifndef data_race
-#define data_race(expr) \
- ({ \
- expr; \
- })
-#endif
-#ifndef ASSERT_EXCLUSIVE_WRITER
-#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
-#endif
-#ifndef ASSERT_EXCLUSIVE_ACCESS
-#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
-#endif
-
/* Data structures. */
/*
@@ -178,6 +165,12 @@ module_param(gp_init_delay, int, 0444);
static int gp_cleanup_delay;
module_param(gp_cleanup_delay, int, 0444);
+// Add delay to rcu_read_unlock() for strict grace periods.
+static int rcu_unlock_delay;
+#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
+module_param(rcu_unlock_delay, int, 0444);
+#endif
+
/*
* This rcu parameter is runtime-read-only. It reflects
* a minimum allowed number of objects which can be cached
@@ -468,24 +461,25 @@ static int rcu_is_cpu_rrupt_from_idle(void)
return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
}
-#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch ... */
-#define DEFAULT_MAX_RCU_BLIMIT 10000 /* ... even during callback flood. */
+#define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10)
+ // Maximum callbacks per rcu_do_batch ...
+#define DEFAULT_MAX_RCU_BLIMIT 10000 // ... even during callback flood.
static long blimit = DEFAULT_RCU_BLIMIT;
-#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */
+#define DEFAULT_RCU_QHIMARK 10000 // If this many pending, ignore blimit.
static long qhimark = DEFAULT_RCU_QHIMARK;
-#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */
+#define DEFAULT_RCU_QLOMARK 100 // Once only this many pending, use blimit.
static long qlowmark = DEFAULT_RCU_QLOMARK;
#define DEFAULT_RCU_QOVLD_MULT 2
#define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK)
-static long qovld = DEFAULT_RCU_QOVLD; /* If this many pending, hammer QS. */
-static long qovld_calc = -1; /* No pre-initialization lock acquisitions! */
+static long qovld = DEFAULT_RCU_QOVLD; // If this many pending, hammer QS.
+static long qovld_calc = -1; // No pre-initialization lock acquisitions!
module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);
module_param(qovld, long, 0444);
-static ulong jiffies_till_first_fqs = ULONG_MAX;
+static ulong jiffies_till_first_fqs = IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 0 : ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
static bool rcu_kick_kthreads;
static int rcu_divisor = 7;
@@ -1092,11 +1086,6 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
}
}
-noinstr bool __rcu_is_watching(void)
-{
- return !rcu_dynticks_curr_cpu_in_eqs();
-}
-
/**
* rcu_is_watching - see if RCU thinks that the current CPU is not idle
*
@@ -1229,13 +1218,28 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
return 1;
}
- /* If waiting too long on an offline CPU, complain. */
- if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
- time_after(jiffies, rcu_state.gp_start + HZ)) {
+ /*
+ * Complain if a CPU that is considered to be offline from RCU's
+ * perspective has not yet reported a quiescent state. After all,
+ * the offline CPU should have reported a quiescent state during
+ * the CPU-offline process, or, failing that, by rcu_gp_init()
+ * if it ran concurrently with either the CPU going offline or the
+ * last task on a leaf rcu_node structure exiting its RCU read-side
+ * critical section while all CPUs corresponding to that structure
+ * are offline. This added warning detects bugs in any of these
+ * code paths.
+ *
+ * The rcu_node structure's ->lock is held here, which excludes
+ * the relevant portions the CPU-hotplug code, the grace-period
+ * initialization code, and the rcu_read_unlock() code paths.
+ *
+ * For more detail, please refer to the "Hotplug CPU" section
+ * of RCU's Requirements documentation.
+ */
+ if (WARN_ON_ONCE(!(rdp->grpmask & rcu_rnp_online_cpus(rnp)))) {
bool onl;
struct rcu_node *rnp1;
- WARN_ON(1); /* Offline CPUs are supposed to report QS! */
pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
__func__, rnp->grplo, rnp->grphi, rnp->level,
(long)rnp->gp_seq, (long)rnp->completedqs);
@@ -1498,9 +1502,10 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
- trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccWaitCB"));
+ trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccWaitCB"));
else
- trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccReadyCB"));
+ trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB"));
+
return ret;
}
@@ -1576,6 +1581,19 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
}
/*
+ * In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, attempt to generate a
+ * quiescent state. This is intended to be invoked when the CPU notices
+ * a new grace period.
+ */
+static void rcu_strict_gp_check_qs(void)
+{
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
+ rcu_read_lock();
+ rcu_read_unlock();
+ }
+}
+
+/*
* Update CPU-local rcu_data state to record the beginnings and ends of
* grace periods. The caller must hold the ->lock of the leaf rcu_node
* structure corresponding to the current CPU, and must have irqs disabled.
@@ -1645,6 +1663,7 @@ static void note_gp_changes(struct rcu_data *rdp)
}
needwake = __note_gp_changes(rnp, rdp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ rcu_strict_gp_check_qs();
if (needwake)
rcu_gp_kthread_wake();
}
@@ -1683,6 +1702,15 @@ static void rcu_gp_torture_wait(void)
}
/*
+ * Handler for on_each_cpu() to invoke the target CPU's RCU core
+ * processing.
+ */
+static void rcu_strict_gp_boundary(void *unused)
+{
+ invoke_rcu_core();
+}
+
+/*
* Initialize a new grace period. Return false if no grace period required.
*/
static bool rcu_gp_init(void)
@@ -1720,10 +1748,13 @@ static bool rcu_gp_init(void)
raw_spin_unlock_irq_rcu_node(rnp);
/*
- * Apply per-leaf buffered online and offline operations to the
- * rcu_node tree. Note that this new grace period need not wait
- * for subsequent online CPUs, and that quiescent-state forcing
- * will handle subsequent offline CPUs.
+ * Apply per-leaf buffered online and offline operations to
+ * the rcu_node tree. Note that this new grace period need not
+ * wait for subsequent online CPUs, and that RCU hooks in the CPU
+ * offlining path, when combined with checks in this function,
+ * will handle CPUs that are currently going offline or that will
+ * go offline later. Please also refer to "Hotplug CPU" section
+ * of RCU's Requirements documentation.
*/
rcu_state.gp_state = RCU_GP_ONOFF;
rcu_for_each_leaf_node(rnp) {
@@ -1810,6 +1841,10 @@ static bool rcu_gp_init(void)
WRITE_ONCE(rcu_state.gp_activity, jiffies);
}
+ // If strict, make all CPUs aware of new grace period.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
+
return true;
}
@@ -1898,7 +1933,7 @@ static void rcu_gp_fqs_loop(void)
break;
/* If time for quiescent-state forcing, do it. */
if (!time_after(rcu_state.jiffies_force_qs, jiffies) ||
- (gf & RCU_GP_FLAG_FQS)) {
+ (gf & (RCU_GP_FLAG_FQS | RCU_GP_FLAG_OVLD))) {
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqsstart"));
rcu_gp_fqs(first_gp_fqs);
@@ -2026,6 +2061,10 @@ static void rcu_gp_cleanup(void)
rcu_state.gp_flags & RCU_GP_FLAG_INIT);
}
raw_spin_unlock_irq_rcu_node(rnp);
+
+ // If strict, make all CPUs aware of the end of the old grace period.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
}
/*
@@ -2204,7 +2243,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
* structure. This must be called from the specified CPU.
*/
static void
-rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
+rcu_report_qs_rdp(struct rcu_data *rdp)
{
unsigned long flags;
unsigned long mask;
@@ -2213,6 +2252,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
rcu_segcblist_is_offloaded(&rdp->cblist);
struct rcu_node *rnp;
+ WARN_ON_ONCE(rdp->cpu != smp_processor_id());
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
@@ -2229,8 +2269,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
return;
}
mask = rdp->grpmask;
- if (rdp->cpu == smp_processor_id())
- rdp->core_needs_qs = false;
+ rdp->core_needs_qs = false;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
} else {
@@ -2279,7 +2318,7 @@ rcu_check_quiescent_state(struct rcu_data *rdp)
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
- rcu_report_qs_rdp(rdp->cpu, rdp);
+ rcu_report_qs_rdp(rdp);
}
/*
@@ -2376,6 +2415,7 @@ int rcutree_dead_cpu(unsigned int cpu)
*/
static void rcu_do_batch(struct rcu_data *rdp)
{
+ int div;
unsigned long flags;
const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
rcu_segcblist_is_offloaded(&rdp->cblist);
@@ -2404,9 +2444,15 @@ static void rcu_do_batch(struct rcu_data *rdp)
rcu_nocb_lock(rdp);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
pending = rcu_segcblist_n_cbs(&rdp->cblist);
- bl = max(rdp->blimit, pending >> rcu_divisor);
- if (unlikely(bl > 100))
- tlimit = local_clock() + rcu_resched_ns;
+ div = READ_ONCE(rcu_divisor);
+ div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
+ bl = max(rdp->blimit, pending >> div);
+ if (unlikely(bl > 100)) {
+ long rrn = READ_ONCE(rcu_resched_ns);
+
+ rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
+ tlimit = local_clock() + rrn;
+ }
trace_rcu_batch_start(rcu_state.name,
rcu_segcblist_n_cbs(&rdp->cblist), bl);
rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
@@ -2547,8 +2593,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rcu_state.cbovldnext |= !!rnp->cbovldmask;
if (rnp->qsmask == 0) {
- if (!IS_ENABLED(CONFIG_PREEMPT_RCU) ||
- rcu_preempt_blocked_readers_cgp(rnp)) {
+ if (rcu_preempt_blocked_readers_cgp(rnp)) {
/*
* No point in scanning bits because they
* are all zero. But we might need to
@@ -2616,6 +2661,14 @@ void rcu_force_quiescent_state(void)
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+// Workqueue handler for an RCU reader for kernels enforcing struct RCU
+// grace periods.
+static void strict_work_handler(struct work_struct *work)
+{
+ rcu_read_lock();
+ rcu_read_unlock();
+}
+
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(void)
{
@@ -2660,6 +2713,10 @@ static __latent_entropy void rcu_core(void)
/* Do any needed deferred wakeups of rcuo kthreads. */
do_nocb_deferred_wakeup(rdp);
trace_rcu_utilization(TPS("End RCU core"));
+
+ // If strict GPs, schedule an RCU reader in a clean environment.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work);
}
static void rcu_core_si(struct softirq_action *h)
@@ -3022,6 +3079,12 @@ struct kfree_rcu_cpu_work {
* @monitor_todo: Tracks whether a @monitor_work delayed work is pending
* @initialized: The @rcu_work fields have been initialized
* @count: Number of objects for which GP not started
+ * @bkvcache:
+ * A simple cache list that contains objects for reuse purpose.
+ * In order to save some per-cpu space the list is singular.
+ * Even though it is lockless an access has to be protected by the
+ * per-cpu lock.
+ * @nr_bkv_objs: number of allocated objects at @bkvcache.
*
* This is a per-CPU structure. The reason that it is not included in
* the rcu_data structure is to permit this code to be extracted from
@@ -3037,14 +3100,6 @@ struct kfree_rcu_cpu {
bool monitor_todo;
bool initialized;
int count;
-
- /*
- * A simple cache list that contains objects for
- * reuse purpose. In order to save some per-cpu
- * space the list is singular. Even though it is
- * lockless an access has to be protected by the
- * per-cpu lock.
- */
struct llist_head bkvcache;
int nr_bkv_objs;
};
@@ -3445,7 +3500,7 @@ kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
unsigned long count = 0;
/* Snapshot count of all CPUs */
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
count += READ_ONCE(krcp->count);
@@ -3460,7 +3515,7 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
int cpu, freed = 0;
unsigned long flags;
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
int count;
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
@@ -3493,7 +3548,7 @@ void __init kfree_rcu_scheduler_running(void)
int cpu;
unsigned long flags;
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
raw_spin_lock_irqsave(&krcp->lock, flags);
@@ -3857,6 +3912,7 @@ rcu_boot_init_percpu_data(int cpu)
/* Set up local state, ensuring consistent view of global state. */
rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
+ INIT_WORK(&rdp->strict_work, strict_work_handler);
WARN_ON_ONCE(rdp->dynticks_nesting != 1);
WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;
@@ -3975,8 +4031,6 @@ int rcutree_offline_cpu(unsigned int cpu)
return 0;
}
-static DEFINE_PER_CPU(int, rcu_cpu_started);
-
/*
* Mark the specified CPU as being online so that subsequent grace periods
* (both expedited and normal) will wait on it. Note that this means that
@@ -3996,12 +4050,11 @@ void rcu_cpu_starting(unsigned int cpu)
struct rcu_node *rnp;
bool newcpu;
- if (per_cpu(rcu_cpu_started, cpu))
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (rdp->cpu_started)
return;
+ rdp->cpu_started = true;
- per_cpu(rcu_cpu_started, cpu) = 1;
-
- rdp = per_cpu_ptr(&rcu_data, cpu);
rnp = rdp->mynode;
mask = rdp->grpmask;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -4061,7 +4114,7 @@ void rcu_report_dead(unsigned int cpu)
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
raw_spin_unlock(&rcu_state.ofl_lock);
- per_cpu(rcu_cpu_started, cpu) = 0;
+ rdp->cpu_started = false;
}
/*
generated by cgit v1.2.3 (git 2.39.0) at 2024-10-22 23:37:50 +0300