summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/RCU/whatisRCU.txt2
-rw-r--r--drivers/nvme/host/core.c2
-rw-r--r--include/linux/rcupdate.h4
-rw-r--r--include/linux/rcutree.h1
-rw-r--r--include/linux/sched.h8
-rw-r--r--include/linux/srcu.h36
-rw-r--r--include/trace/events/rcu.h13
-rw-r--r--kernel/rcu/rcu.h12
-rw-r--r--kernel/rcu/rcu_segcblist.c18
-rw-r--r--kernel/rcu/rcu_segcblist.h2
-rw-r--r--kernel/rcu/rcuperf.c2
-rw-r--r--kernel/rcu/rcutorture.c15
-rw-r--r--kernel/rcu/srcutiny.c9
-rw-r--r--kernel/rcu/srcutree.c30
-rw-r--r--kernel/rcu/tree.c355
-rw-r--r--kernel/rcu/tree.h36
-rw-r--r--kernel/rcu/tree_exp.h235
-rw-r--r--kernel/rcu/tree_plugin.h98
-rw-r--r--kernel/rcu/update.c50
-rw-r--r--kernel/sched/core.c14
-rw-r--r--kernel/softirq.c3
-rw-r--r--kernel/torture.c2
-rw-r--r--kernel/trace/trace_benchmark.c4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh56
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh12
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh1
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh115
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-torture.sh105
29 files changed, 616 insertions, 628 deletions
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index a27fbfb0efb8..65eb856526b7 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -1,3 +1,5 @@
+What is RCU? -- "Read, Copy, Update"
+
Please note that the "What is RCU?" LWN series is an excellent place
to start learning about RCU:
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 99b857e5a7a9..00f5aad34fbc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -351,7 +351,7 @@ static void nvme_free_ns_head(struct kref *ref)
nvme_mpath_remove_disk(head);
ida_simple_remove(&head->subsys->ns_ida, head->instance);
list_del_init(&head->entry);
- cleanup_srcu_struct(&head->srcu);
+ cleanup_srcu_struct_quiesced(&head->srcu);
nvme_put_subsystem(head->subsys);
kfree(head);
}
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 36360d07f25b..19d235fefdb9 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -188,13 +188,13 @@ static inline void exit_tasks_rcu_finish(void) { }
#endif /* #else #ifdef CONFIG_TASKS_RCU */
/**
- * cond_resched_rcu_qs - Report potential quiescent states to RCU
+ * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU
*
* This macro resembles cond_resched(), except that it is defined to
* report potential quiescent states to RCU-tasks even if the cond_resched()
* machinery were to be shut off, as some advocate for PREEMPT kernels.
*/
-#define cond_resched_rcu_qs() \
+#define cond_resched_tasks_rcu_qs() \
do { \
if (!cond_resched()) \
rcu_note_voluntary_context_switch_lite(current); \
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index fd996cdf1833..448f20f27396 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -74,6 +74,7 @@ static inline void synchronize_rcu_bh_expedited(void)
void rcu_barrier(void);
void rcu_barrier_bh(void);
void rcu_barrier_sched(void);
+bool rcu_eqs_special_set(int cpu);
unsigned long get_state_synchronize_rcu(void);
void cond_synchronize_rcu(unsigned long oldstate);
unsigned long get_state_synchronize_sched(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c2413703f45d..8e2a84615bb6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1653,7 +1653,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
* explicit rescheduling in places that are safe. The return
* value indicates whether a reschedule was done in fact.
* cond_resched_lock() will drop the spinlock before scheduling,
- * cond_resched_softirq() will enable bhs before scheduling.
*/
#ifndef CONFIG_PREEMPT
extern int _cond_resched(void);
@@ -1673,13 +1672,6 @@ extern int __cond_resched_lock(spinlock_t *lock);
__cond_resched_lock(lock); \
})
-extern int __cond_resched_softirq(void);
-
-#define cond_resched_softirq() ({ \
- ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \
- __cond_resched_softirq(); \
-})
-
static inline void cond_resched_rcu(void)
{
#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 33c1c698df09..91494d7e8e41 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -69,11 +69,45 @@ struct srcu_struct { };
void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
void (*func)(struct rcu_head *head));
-void cleanup_srcu_struct(struct srcu_struct *sp);
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced);
int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
void synchronize_srcu(struct srcu_struct *sp);
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+static inline void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+ _cleanup_srcu_struct(sp, false);
+}
+
+/**
+ * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory. Also,
+ * all grace-period processing must have completed.
+ *
+ * "Completed" means that the last synchronize_srcu() and
+ * synchronize_srcu_expedited() calls must have returned before the call
+ * to cleanup_srcu_struct_quiesced(). It also means that the callback
+ * from the last call_srcu() must have been invoked before the call to
+ * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help
+ * with this last. Violating these rules will get you a WARN_ON() splat
+ * (with high probability, anyway), and will also cause the srcu_struct
+ * to be leaked.
+ */
+static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *sp)
+{
+ _cleanup_srcu_struct(sp, true);
+}
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d8c33298c153..5936aac357ab 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -84,20 +84,21 @@ TRACE_EVENT(rcu_grace_period,
);
/*
- * Tracepoint for future grace-period events, including those for no-callbacks
- * CPUs. The caller should pull the data from the rcu_node structure,
- * other than rcuname, which comes from the rcu_state structure, and event,
- * which is one of the following:
+ * Tracepoint for future grace-period events. The caller should pull
+ * the data from the rcu_node structure, other than rcuname, which comes
+ * from the rcu_state structure, and event, which is one of the following:
*
- * "Startleaf": Request a nocb grace period based on leaf-node data.
+ * "Startleaf": Request a grace period based on leaf-node data.
+ * "Prestarted": Someone beat us to the request
* "Startedleaf": Leaf-node start proved sufficient.
* "Startedleafroot": Leaf-node start proved sufficient after checking root.
* "Startedroot": Requested a nocb grace period based on root-node data.
+ * "NoGPkthread": The RCU grace-period kthread has not yet started.
* "StartWait": Start waiting for the requested grace period.
* "ResumeWait": Resume waiting after signal.
* "EndWait": Complete wait.
* "Cleanup": Clean up rcu_node structure after previous GP.
- * "CleanupMore": Clean up, and another no-CB GP is needed.
+ * "CleanupMore": Clean up, and another GP is needed.
*/
TRACE_EVENT(rcu_future_grace_period,
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7a693e31184a..40cea6735c2d 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -270,6 +270,12 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
}
}
+/* Returns first leaf rcu_node of the specified RCU flavor. */
+#define rcu_first_leaf_node(rsp) ((rsp)->level[rcu_num_lvls - 1])
+
+/* Is this rcu_node a leaf? */
+#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
+
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
@@ -284,8 +290,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
* rcu_node tree with but one rcu_node structure, this loop is a no-op.
*/
#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
- for ((rnp) = &(rsp)->node[0]; \
- (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
+ for ((rnp) = &(rsp)->node[0]; !rcu_is_leaf_node(rsp, rnp); (rnp)++)
/*
* Scan the leaves of the rcu_node hierarchy for the specified rcu_state
@@ -294,7 +299,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
* It is still a leaf node, even if it is also the root node.
*/
#define rcu_for_each_leaf_node(rsp, rnp) \
- for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
+ for ((rnp) = rcu_first_leaf_node(rsp); \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
@@ -486,6 +491,7 @@ void rcu_force_quiescent_state(void);
void rcu_bh_force_quiescent_state(void);
void rcu_sched_force_quiescent_state(void);
extern struct workqueue_struct *rcu_gp_wq;
+extern struct workqueue_struct *rcu_par_gp_wq;
#endif /* #else #ifdef CONFIG_TINY_RCU */
#ifdef CONFIG_RCU_NOCB_CPU
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 88cba7c2956c..5aff271adf1e 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -404,24 +404,6 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
}
/*
- * Scan the specified rcu_segcblist structure for callbacks that need
- * a grace period later than the one specified by "seq". We don't look
- * at the RCU_DONE_TAIL or RCU_NEXT_TAIL segments because they don't
- * have a grace-period sequence number.
- */
-bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
- unsigned long seq)
-{
- int i;
-
- for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
- if (rsclp->tails[i - 1] != rsclp->tails[i] &&
- ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
- return true;
- return false;
-}
-
-/*
* Merge the source rcu_segcblist structure into the destination
* rcu_segcblist structure, then initialize the source. Any pending
* callbacks from the source get to start over. It is best to
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 581c12b63544..948470cef385 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -134,7 +134,5 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
-bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
- unsigned long seq);
void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
struct rcu_segcblist *src_rsclp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 777e7a6a0292..e232846516b3 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -369,7 +369,7 @@ static bool __maybe_unused torturing_tasks(void)
*/
static void rcu_perf_wait_shutdown(void)
{
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters)
return;
while (!torture_must_stop())
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 680c96d8c00f..e628fcfd1bde 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -593,7 +593,12 @@ static void srcu_torture_init(void)
static void srcu_torture_cleanup(void)
{
- cleanup_srcu_struct(&srcu_ctld);
+ static DEFINE_TORTURE_RANDOM(rand);
+
+ if (torture_random(&rand) & 0x800)
+ cleanup_srcu_struct(&srcu_ctld);
+ else
+ cleanup_srcu_struct_quiesced(&srcu_ctld);
srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
}
@@ -1609,6 +1614,9 @@ static enum cpuhp_state rcutor_hp;
static void
rcu_torture_cleanup(void)
{
+ int flags = 0;
+ unsigned long gpnum = 0;
+ unsigned long completed = 0;
int i;
rcutorture_record_test_transition();
@@ -1639,6 +1647,11 @@ rcu_torture_cleanup(void)
fakewriter_tasks = NULL;
}
+ rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
+ srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
+ &flags, &gpnum, &completed);
+ pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n",
+ cur_ops->name, gpnum, completed, flags);
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
for (i = 0; i < ncbflooders; i++)
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 76ac5f50b2c7..622792abe41a 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -86,16 +86,19 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
-void cleanup_srcu_struct(struct srcu_struct *sp)
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
{
WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
- flush_work(&sp->srcu_work);
+ if (quiesced)
+ WARN_ON(work_pending(&sp->srcu_work));
+ else
+ flush_work(&sp->srcu_work);
WARN_ON(sp->srcu_gp_running);
WARN_ON(sp->srcu_gp_waiting);
WARN_ON(sp->srcu_cb_head);
WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail);
}
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
/*
* Removes the count for the old reader from the appropriate element of
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index fb560fca9ef4..b4123d7a2cec 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -366,24 +366,28 @@ static unsigned long srcu_get_delay(struct srcu_struct *sp)
return SRCU_INTERVAL;
}
-/**
- * cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @sp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
- */
-void cleanup_srcu_struct(struct srcu_struct *sp)
+/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
{
int cpu;
if (WARN_ON(!srcu_get_delay(sp)))
- return; /* Leakage unless caller handles error. */
+ return; /* Just leak it! */
if (WARN_ON(srcu_readers_active(sp)))
- return; /* Leakage unless caller handles error. */
- flush_delayed_work(&sp->work);
+ return; /* Just leak it! */
+ if (quiesced) {
+ if (WARN_ON(delayed_work_pending(&sp->work)))
+ return; /* Just leak it! */
+ } else {
+ flush_delayed_work(&sp->work);
+ }
for_each_possible_cpu(cpu)
- flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ if (quiesced) {
+ if (WARN_ON(delayed_work_pending(&per_cpu_ptr(sp->sda, cpu)->work)))
+ return; /* Just leak it! */
+ } else {
+ flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ }
if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(sp))) {
pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
@@ -392,7 +396,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
free_percpu(sp->sda);
sp->sda = NULL;
}
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
/*
* Counts the new reader in the appropriate per-CPU element of the
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2a734692a581..4fccdfa25716 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -524,8 +524,6 @@ module_param(rcu_kick_kthreads, bool, 0644);
static ulong jiffies_till_sched_qs = HZ / 10;
module_param(jiffies_till_sched_qs, ulong, 0444);
-static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp);
static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp));
static void force_quiescent_state(struct rcu_state *rsp);
static int rcu_pending(void);
@@ -711,44 +709,6 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
}
/*
- * Is there any need for future grace periods?
- * Interrupts must be disabled. If the caller does not hold the root
- * rnp_node structure's ->lock, the results are advisory only.
- */
-static int rcu_future_needs_gp(struct rcu_state *rsp)
-{
- struct rcu_node *rnp = rcu_get_root(rsp);
- int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
- int *fp = &rnp->need_future_gp[idx];
-
- lockdep_assert_irqs_disabled();
- return READ_ONCE(*fp);
-}
-
-/*
- * Does the current CPU require a not-yet-started grace period?
- * The caller must have disabled interrupts to prevent races with
- * normal callback registry.
- */
-static bool
-cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- lockdep_assert_irqs_disabled();
- if (rcu_gp_in_progress(rsp))
- return false; /* No, a grace period is already in progress. */
- if (rcu_future_needs_gp(rsp))
- return true; /* Yes, a no-CBs CPU needs one. */
- if (!rcu_segcblist_is_enabled(&rdp->cblist))
- return false; /* No, this is a no-CBs (or offline) CPU. */
- if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
- return true; /* Yes, CPU has newly registered callbacks. */
- if (rcu_segcblist_future_gp_needed(&rdp->cblist,
- READ_ONCE(rsp->completed)))
- return true; /* Yes, CBs for future grace period. */
- return false; /* No grace period needed. */
-}
-
-/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*
@@ -1234,10 +1194,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
}
/*
- * Has this CPU encountered a cond_resched_rcu_qs() since the
- * beginning of the grace period? For this to be the case,
- * the CPU has to have noticed the current grace period. This
- * might not be the case for nohz_full CPUs looping in the kernel.
+ * Has this CPU encountered a cond_resched() since the beginning
+ * of the grace period? For this to be the case, the CPU has to
+ * have noticed the current grace period. This might not be the
+ * case for nohz_full CPUs looping in the kernel.
*/
jtsq = jiffies_till_sched_qs;
ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
@@ -1642,18 +1602,30 @@ static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
return rnp->completed + 1;
/*
+ * If the current rcu_node structure believes that RCU is
+ * idle, and if the rcu_state structure does not yet reflect
+ * the start of a new grace period, then the next grace period
+ * will suffice. The memory barrier is needed to accurately
+ * sample the rsp->gpnum, and pairs with the second lock
+ * acquisition in rcu_gp_init(), which is augmented with
+ * smp_mb__after_unlock_lock() for this purpose.
+ */
+ if (rnp->gpnum == rnp->completed) {
+ smp_mb(); /* See above block comment. */
+ if (READ_ONCE(rsp->gpnum) == rnp->completed)
+ return rnp->completed + 1;
+ }
+
+ /*
* Otherwise, wait for a possible partial grace period and
* then the subsequent full grace period.
*/
return rnp->completed + 2;
}
-/*
- * Trace-event helper function for rcu_start_future_gp() and
- * rcu_nocb_wait_gp().
- */
-static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long c, const char *s)
+/* Trace-event wrapper function for trace_rcu_future_grace_period. */
+static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+ unsigned long c, const char *s)
{
trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
rnp->completed, c, rnp->level,
@@ -1661,96 +1633,67 @@ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
}
/*
- * Start some future grace period, as needed to handle newly arrived
+ * Start the specified grace period, as needed to handle newly arrived
* callbacks. The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp field. Returns true if there
+ * rcu_node structure's ->need_future_gp[] field. Returns true if there
* is reason to awaken the grace-period kthread.
*
- * The caller must hold the specified rcu_node structure's ->lock.
+ * The caller must hold the specified rcu_node structure's ->lock, which
+ * is why the caller is responsible for waking the grace-period kthread.
*/
-static bool __maybe_unused
-rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long *c_out)
+static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+ unsigned long c)
{
- unsigned long c;
bool ret = false;
- struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
-
- raw_lockdep_assert_held_rcu_node(rnp);
-
- /*
- * Pick up grace-period number for new callbacks. If this
- * grace period is already marked as needed, return to the caller.
- */
- c = rcu_cbs_completed(rdp->rsp, rnp);
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf"));
- if (rnp->need_future_gp[c & 0x1]) {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf"));
- goto out;
- }
+ struct rcu_state *rsp = rdp->rsp;
+ struct rcu_node *rnp_root;
/*
- * If either this rcu_node structure or the root rcu_node structure
- * believe that a grace period is in progress, then we must wait
- * for the one following, which is in "c". Because our request
- * will be noticed at the end of the current grace period, we don't
- * need to explicitly start one. We only do the lockless check
- * of rnp_root's fields if the current rcu_node structure thinks
- * there is no grace period in flight, and because we hold rnp->lock,
- * the only possible change is when rnp_root's two fields are
- * equal, in which case rnp_root->gpnum might be concurrently
- * incremented. But that is OK, as it will just result in our
- * doing some extra useless work.
+ * Use funnel locking to either acquire the root rcu_node
+ * structure's lock or bail out if the need for this grace period
+ * has already been recorded -- or has already started. If there
+ * is already a grace period in progress in a non-leaf node, no
+ * recording is needed because the end of the grace period will
+ * scan the leaf rcu_node structures. Note that rnp->lock must
+ * not be released.
*/
- if (rnp->gpnum != rnp->completed ||
- READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
- rnp->need_future_gp[c & 0x1]++;
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
- goto out;
+ raw_lockdep_assert_held_rcu_node(rnp);
+ trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
+ for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
+ if (rnp_root != rnp)
+ raw_spin_lock_rcu_node(rnp_root);
+ WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
+ need_future_gp_mask(), c));
+ if (need_future_gp_element(rnp_root, c) ||
+ ULONG_CMP_GE(rnp_root->gpnum, c) ||
+ (rnp != rnp_root &&
+ rnp_root->gpnum != rnp_root->completed)) {
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+ goto unlock_out;
+ }
+ need_future_gp_element(rnp_root, c) = true;
+ if (rnp_root != rnp && rnp_root->parent != NULL)
+ raw_spin_unlock_rcu_node(rnp_root);
+ if (!rnp_root->parent)
+ break; /* At root, and perhaps also leaf. */
}
- /*
- * There might be no grace period in progress. If we don't already
- * hold it, acquire the root rcu_node structure's lock in order to
- * start one (if needed).
- */
- if (rnp != rnp_root)
- raw_spin_lock_rcu_node(rnp_root);
-
- /*
- * Get a new grace-period number. If there really is no grace
- * period in progress, it will be smaller than the one we obtained
- * earlier. Adjust callbacks as needed.
- */
- c = rcu_cbs_completed(rdp->rsp, rnp_root);
- if (!rcu_is_nocb_cpu(rdp->cpu))
- (void)rcu_segcblist_accelerate(&rdp->cblist, c);
-
- /*
- * If the needed for the required grace period is already
- * recorded, trace and leave.
- */
- if (rnp_root->need_future_gp[c & 0x1]) {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartedroot"));
+ /* If GP already in progress, just leave, otherwise start one. */
+ if (rnp_root->gpnum != rnp_root->completed) {
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
goto unlock_out;
}
-
- /* Record the need for the future grace period. */
- rnp_root->need_future_gp[c & 0x1]++;
-
- /* If a grace period is not already in progress, start one. */
- if (rnp_root->gpnum != rnp_root->completed) {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot"));
- } else {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot"));
- ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+ WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+ if (!rsp->gp_kthread) {
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+ goto unlock_out;
}
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+ ret = true; /* Caller must wake GP kthread. */
unlock_out:
if (rnp != rnp_root)
raw_spin_unlock_rcu_node(rnp_root);
-out:
- if (c_out != NULL)
- *c_out = c;
return ret;
}
@@ -1758,16 +1701,16 @@ out:
* Clean up any old requests for the just-ended grace period. Also return
* whether any additional grace periods have been requested.
*/
-static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
- int c = rnp->completed;
- int needmore;
+ unsigned long c = rnp->completed;
+ bool needmore;
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- rnp->need_future_gp[c & 0x1] = 0;
- needmore = rnp->need_future_gp[(c + 1) & 0x1];
- trace_rcu_future_gp(rnp, rdp, c,
- needmore ? TPS("CleanupMore") : TPS("Cleanup"));
+ need_future_gp_element(rnp, c) = false;
+ needmore = need_any_future_gp(rnp);
+ trace_rcu_this_gp(rnp, rdp, c,
+ needmore ? TPS("CleanupMore") : TPS("Cleanup"));
return needmore;
}
@@ -1802,6 +1745,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
+ unsigned long c;
bool ret = false;
raw_lockdep_assert_held_rcu_node(rnp);
@@ -1820,8 +1764,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
* accelerating callback invocation to an earlier grace-period
* number.
*/
- if (rcu_segcblist_accelerate(&rdp->cblist, rcu_cbs_completed(rsp, rnp)))
- ret = rcu_start_future_gp(rnp, rdp, NULL);
+ c = rcu_cbs_completed(rsp, rnp);
+ if (rcu_segcblist_accelerate(&rdp->cblist, c))
+ ret = rcu_start_this_gp(rnp, rdp, c);
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
@@ -2049,7 +1994,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
raw_spin_unlock_irq_rcu_node(rnp);
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
}
@@ -2108,7 +2053,6 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
{
unsigned long gp_duration;
bool needgp = false;
- int nocb = 0;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
struct swait_queue_head *sq;
@@ -2147,31 +2091,35 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
- nocb += rcu_future_gp_cleanup(rsp, rnp);
+ needgp = rcu_future_gp_cleanup(rsp, rnp) || needgp;
sq = rcu_nocb_gp_get(rnp);
raw_spin_unlock_irq_rcu_node(rnp);
rcu_nocb_gp_cleanup(sq);
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
- rcu_nocb_gp_set(rnp, nocb);
/* Declare grace period done. */
WRITE_ONCE(rsp->completed, rsp->gpnum);
trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
rsp->gp_state = RCU_GP_IDLE;
+ /* Check for GP requests since above loop. */
rdp = this_cpu_ptr(rsp->rda);
+ if (need_any_future_gp(rnp)) {
+ trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+ TPS("CleanupMore"));
+ needgp = true;
+ }
/* Advance CBs to reduce false positives below. */
- needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
- if (needgp || cpu_needs_another_gp(rsp, rdp)) {
+ if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
TPS("newreq"));
}
+ WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
raw_spin_unlock_irq_rcu_node(rnp);
}
@@ -2202,7 +2150,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
/* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
@@ -2247,7 +2195,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqsend"));
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
ret = 0; /* Force full wait till next FQS. */
j = jiffies_till_next_fqs;
@@ -2260,7 +2208,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
}
} else {
/* Deal with stray signal. */
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
@@ -2283,71 +2231,6 @@ static int __noreturn rcu_gp_kthread(void *arg)
}
/*
- * Start a new RCU grace period if warranted, re-initializing the hierarchy
- * in preparation for detecting the next grace period. The caller must hold
- * the root node's ->lock and hard irqs must be disabled.
- *
- * Note that it is legal for a dying CPU (which is marked as offline) to
- * invoke this function. This can happen when the dying CPU reports its
- * quiescent state.
- *
- * Returns true if the grace-period kthread must be awakened.
- */
-static bool
-rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp)
-{
- raw_lockdep_assert_held_rcu_node(rnp);
- if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
- /*
- * Either we have not yet spawned the grace-period
- * task, this CPU does not need another grace period,
- * or a grace period is already in progress.
- * Either way, don't start a new grace period.
- */
- return false;
- }
- WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
- TPS("newreq"));
-
- /*
- * We can't do wakeups while holding the rnp->lock, as that
- * could cause possible deadlocks with the rq->lock. Defer
- * the wakeup to our caller.
- */
- return true;
-}
-
-/*
- * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
- * callbacks. Note that rcu_start_gp_advanced() cannot do this because it
- * is invoked indirectly from rcu_advance_cbs(), which would result in
- * endless recursion -- or would do so if it wasn't for the self-deadlock
- * that is encountered beforehand.
- *
- * Returns true if the grace-period kthread needs to be awakened.
- */
-static bool rcu_start_gp(struct rcu_state *rsp)
-{
- struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- struct rcu_node *rnp = rcu_get_root(rsp);
- bool ret = false;
-
- /*
- * If there is no grace period in progress right now, any
- * callbacks we have up to this point will be satisfied by the
- * next grace period. Also, advancing the callbacks reduces the
- * probability of false positives from cpu_needs_another_gp()
- * resulting in pointless grace periods. So, advance callbacks
- * then start the grace period!
- */
- ret = rcu_advance_cbs(rsp, rnp, rdp) || ret;
- ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret;
- return ret;
-}
-
-/*
* Report a full set of quiescent states to the specified rcu_state data
* structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period
* kthread if another grace period is required. Whether we wake
@@ -2398,7 +2281,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
return;
}
WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
- WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1 &&
+ WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
rnp->qsmask &= ~mask;
trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
@@ -2782,7 +2665,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
struct rcu_node *rnp;
rcu_for_each_leaf_node(rsp, rnp) {
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->qsmask == 0) {
@@ -2874,22 +2757,27 @@ __rcu_process_callbacks(struct rcu_state *rsp)
unsigned long flags;
bool needwake;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
+ struct rcu_node *rnp;
WARN_ON_ONCE(!rdp->beenonline);
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rsp, rdp);
- /* Does this CPU require a not-yet-started grace period? */
- local_irq_save(flags);
- if (cpu_needs_another_gp(rsp, rdp)) {
- raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */
- needwake = rcu_start_gp(rsp);
- raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
- if (needwake)
- rcu_gp_kthread_wake(rsp);
- } else {
- local_irq_restore(flags);
+ /* No grace period and unregistered callbacks? */
+ if (!rcu_gp_in_progress(rsp) &&
+ rcu_segcblist_is_enabled(&rdp->cblist)) {
+ local_irq_save(flags);
+ if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
+ local_irq_restore(flags);
+ } else {
+ rnp = rdp->mynode;
+ raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
+ needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ if (needwake)
+ rcu_gp_kthread_wake(rsp);
+ }
}
/* If there are callbacks ready, invoke them. */
@@ -2973,11 +2861,11 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress(rsp)) {
- struct rcu_node *rnp_root = rcu_get_root(rsp);
+ struct rcu_node *rnp = rdp->mynode;
- raw_spin_lock_rcu_node(rnp_root);
- needwake = rcu_start_gp(rsp);
- raw_spin_unlock_rcu_node(rnp_root);
+ raw_spin_lock_rcu_node(rnp);
+ needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ raw_spin_unlock_rcu_node(rnp);
if (needwake)
rcu_gp_kthread_wake(rsp);
} else {
@@ -3368,7 +3256,9 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
return 1;
/* Has RCU gone idle with this CPU needing another grace period? */
- if (cpu_needs_another_gp(rsp, rdp))
+ if (!rcu_gp_in_progress(rsp) &&
+ rcu_segcblist_is_enabled(&rdp->cblist) &&
+ !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return 1;
/* Has another RCU grace period completed? */
@@ -3861,6 +3751,7 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
struct rcu_data *my_rdp;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+ bool needwake;
if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
return; /* No callbacks to migrate. */
@@ -3872,12 +3763,15 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
return;
}
raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
- rcu_advance_cbs(rsp, rnp_root, rdp); /* Leverage recent GPs. */
- rcu_advance_cbs(rsp, rnp_root, my_rdp); /* Assign GP to pending CBs. */
+ /* Leverage recent GPs and set GP for new callbacks. */
+ needwake = rcu_advance_cbs(rsp, rnp_root, rdp) ||
+ rcu_advance_cbs(rsp, rnp_root, my_rdp);
rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist);
WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
!rcu_segcblist_n_cbs(&my_rdp->cblist));
raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags);
+ if (needwake)
+ rcu_gp_kthread_wake(rsp);
WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
!rcu_segcblist_empty(&rdp->cblist),
"rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
@@ -4056,7 +3950,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
init_swait_queue_head(&rsp->gp_wq);
init_swait_queue_head(&rsp->expedited_wq);
- rnp = rsp->level[rcu_num_lvls - 1];
+ rnp = rcu_first_leaf_node(rsp);
for_each_possible_cpu(i) {
while (i > rnp->grphi)
rnp++;
@@ -4168,6 +4062,7 @@ static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
}
struct workqueue_struct *rcu_gp_wq;
+struct workqueue_struct *rcu_par_gp_wq;
void __init rcu_init(void)
{
@@ -4199,6 +4094,8 @@ void __init rcu_init(void)
/* Create workqueue for expedited GPs and for Tree SRCU. */
rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_gp_wq);
+ rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
+ WARN_ON(!rcu_par_gp_wq);
}
#include "tree_exp.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index f491ab4f2e8e..78e051dffc5b 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -58,6 +58,14 @@ struct rcu_dynticks {
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
};
+/* Communicate arguments to a workqueue handler. */
+struct rcu_exp_work {
+ smp_call_func_t rew_func;
+ struct rcu_state *rew_rsp;
+ unsigned long rew_s;
+ struct work_struct rew_work;
+};
+
/* RCU's kthread states for tracing. */
#define RCU_KTHREAD_STOPPED 0
#define RCU_KTHREAD_RUNNING 1
@@ -150,15 +158,32 @@ struct rcu_node {
struct swait_queue_head nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- int need_future_gp[2];
- /* Counts of upcoming no-CB GP requests. */
+ u8 need_future_gp[4]; /* Counts of upcoming GP requests. */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
unsigned long exp_seq_rq;
wait_queue_head_t exp_wq[4];
+ struct rcu_exp_work rew;
+ bool exp_need_flush; /* Need to flush workitem? */
} ____cacheline_internodealigned_in_smp;
+/* Accessors for ->need_future_gp[] array. */
+#define need_future_gp_mask() \
+ (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
+#define need_future_gp_element(rnp, c) \
+ ((rnp)->need_future_gp[(c) & need_future_gp_mask()])
+#define need_any_future_gp(rnp) \
+({ \
+ int __i; \
+ bool __nonzero = false; \
+ \
+ for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \
+ __nonzero = __nonzero || \
+ READ_ONCE((rnp)->need_future_gp[__i]); \
+ __nonzero; \
+})
+
/*
* Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
* are indexed relative to this interval rather than the global CPU ID space.
@@ -224,10 +249,6 @@ struct rcu_data {
#ifdef CONFIG_RCU_FAST_NO_HZ
struct rcu_head oom_head;
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
- atomic_long_t exp_workdone0; /* # done by workqueue. */
- atomic_long_t exp_workdone1; /* # done by others #1. */
- atomic_long_t exp_workdone2; /* # done by others #2. */
- atomic_long_t exp_workdone3; /* # done by others #3. */
int exp_dynticks_snap; /* Double-check need for IPI. */
/* 6) Callback offloading. */
@@ -408,7 +429,6 @@ extern struct rcu_state rcu_preempt_state;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
-bool rcu_eqs_special_set(int cpu);
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -438,7 +458,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static void invoke_rcu_callbacks_kthread(void);
static bool rcu_is_callbacks_kthread(void);
#ifdef CONFIG_RCU_BOOST
-static void rcu_preempt_do_callbacks(void);
static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_BOOST */
@@ -454,7 +473,6 @@ static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static void increment_cpu_stall_ticks(void);
static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
static void rcu_init_one_nocb(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index f72eefab8543..d40708e8c5d6 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -20,6 +20,8 @@
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/lockdep.h>
+
/*
* Record the start of an expedited grace period.
*/
@@ -154,15 +156,35 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
* for the current expedited grace period. Works only for preemptible
* RCU -- other RCU implementation use other means.
*
- * Caller must hold the rcu_state's exp_mutex.
+ * Caller must hold the specificed rcu_node structure's ->lock
*/
static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
+ raw_lockdep_assert_held_rcu_node(rnp);
+
return rnp->exp_tasks == NULL &&
READ_ONCE(rnp->expmask) == 0;
}
/*
+ * Like sync_rcu_preempt_exp_done(), but this function assumes the caller
+ * doesn't hold the rcu_node's ->lock, and will acquire and release the lock
+ * itself
+ */
+static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
+{
+ unsigned long flags;
+ bool ret;
+
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ ret = sync_rcu_preempt_exp_done(rnp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+ return ret;
+}
+
+
+/*
* Report the exit from RCU read-side critical section for the last task
* that queued itself during or before the current expedited preemptible-RCU
* grace period. This event is reported either to the rcu_node structure on
@@ -170,8 +192,7 @@ static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
*
- * Caller must hold the rcu_state's exp_mutex and the specified rcu_node
- * structure's ->lock.
+ * Caller must hold the specified rcu_node structure's ->lock.
*/
static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake, unsigned long flags)
@@ -207,8 +228,6 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
/*
* Report expedited quiescent state for specified node. This is a
* lock-acquisition wrapper function for __rcu_report_exp_rnp().
- *
- * Caller must hold the rcu_state's exp_mutex.
*/
static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
struct rcu_node *rnp, bool wake)
@@ -221,8 +240,7 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
/*
* Report expedited quiescent state for multiple CPUs, all covered by the
- * specified leaf rcu_node structure. Caller must hold the rcu_state's
- * exp_mutex.
+ * specified leaf rcu_node structure.
*/
static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
unsigned long mask, bool wake)
@@ -248,14 +266,12 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
}
/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
-static bool sync_exp_work_done(struct rcu_state *rsp, atomic_long_t *stat,
- unsigned long s)
+static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s)
{
if (rcu_exp_gp_seq_done(rsp, s)) {
trace_rcu_exp_grace_period(rsp->name, s, TPS("done"));
/* Ensure test happens before caller kfree(). */
smp_mb__before_atomic(); /* ^^^ */
- atomic_long_inc(stat);
return true;
}
return false;
@@ -289,7 +305,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
* promoting locality and is not strictly needed for correctness.
*/
for (; rnp != NULL; rnp = rnp->parent) {
- if (sync_exp_work_done(rsp, &rdp->exp_workdone1, s))
+ if (sync_exp_work_done(rsp, s))
return true;
/* Work not done, either wait here or go up. */
@@ -302,8 +318,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
rnp->grplo, rnp->grphi,
TPS("wait"));
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
- sync_exp_work_done(rsp,
- &rdp->exp_workdone2, s));
+ sync_exp_work_done(rsp, s));
return true;
}
rnp->exp_seq_rq = s; /* Followers can wait on us. */
@@ -313,7 +328,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
}
mutex_lock(&rsp->exp_mutex);
fastpath:
- if (sync_exp_work_done(rsp, &rdp->exp_workdone3, s)) {
+ if (sync_exp_work_done(rsp, s)) {
mutex_unlock(&rsp->exp_mutex);
return true;
}
@@ -362,93 +377,129 @@ static void sync_sched_exp_online_cleanup(int cpu)
}
/*
- * Select the nodes that the upcoming expedited grace period needs
- * to wait for.
+ * Select the CPUs within the specified rcu_node that the upcoming
+ * expedited grace period needs to wait for.
*/
-static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
- smp_call_func_t func)
+static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
{
int cpu;
unsigned long flags;
+ smp_call_func_t func;
unsigned long mask_ofl_test;
unsigned long mask_ofl_ipi;
int ret;
- struct rcu_node *rnp;
-
- trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
- sync_exp_reset_tree(rsp);
- trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
- rcu_for_each_leaf_node(rsp, rnp) {
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ struct rcu_exp_work *rewp =
+ container_of(wp, struct rcu_exp_work, rew_work);
+ struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
+ struct rcu_state *rsp = rewp->rew_rsp;
- /* Each pass checks a CPU for identity, offline, and idle. */
- mask_ofl_test = 0;
- for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
- unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
- int snap;
+ func = rewp->rew_func;
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (raw_smp_processor_id() == cpu ||
- !(rnp->qsmaskinitnext & mask)) {
+ /* Each pass checks a CPU for identity, offline, and idle. */
+ mask_ofl_test = 0;
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+ unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+ struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+ struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
+ int snap;
+
+ if (raw_smp_processor_id() == cpu ||
+ !(rnp->qsmaskinitnext & mask)) {
+ mask_ofl_test |= mask;
+ } else {
+ snap = rcu_dynticks_snap(rdtp);
+ if (rcu_dynticks_in_eqs(snap))
mask_ofl_test |= mask;
- } else {
- snap = rcu_dynticks_snap(rdtp);
- if (rcu_dynticks_in_eqs(snap))
- mask_ofl_test |= mask;
- else
- rdp->exp_dynticks_snap = snap;
- }
+ else
+ rdp->exp_dynticks_snap = snap;
}
- mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
-
- /*
- * Need to wait for any blocked tasks as well. Note that
- * additional blocking tasks will also block the expedited
- * GP until such time as the ->expmask bits are cleared.
- */
- if (rcu_preempt_has_tasks(rnp))
- rnp->exp_tasks = rnp->blkd_tasks.next;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ }
+ mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
- /* IPI the remaining CPUs for expedited quiescent state. */
- for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
- unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+ /*
+ * Need to wait for any blocked tasks as well. Note that
+ * additional blocking tasks will also block the expedited GP
+ * until such time as the ->expmask bits are cleared.
+ */
+ if (rcu_preempt_has_tasks(rnp))
+ rnp->exp_tasks = rnp->blkd_tasks.next;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- if (!(mask_ofl_ipi & mask))
- continue;
+ /* IPI the remaining CPUs for expedited quiescent state. */
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+ unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+ struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+
+ if (!(mask_ofl_ipi & mask))
+ continue;
retry_ipi:
- if (rcu_dynticks_in_eqs_since(rdp->dynticks,
- rdp->exp_dynticks_snap)) {
- mask_ofl_test |= mask;
- continue;
- }
- ret = smp_call_function_single(cpu, func, rsp, 0);
- if (!ret) {
- mask_ofl_ipi &= ~mask;
- continue;
- }
- /* Failed, raced with CPU hotplug operation. */
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if ((rnp->qsmaskinitnext & mask) &&
- (rnp->expmask & mask)) {
- /* Online, so delay for a bit and try again. */
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
- schedule_timeout_uninterruptible(1);
- goto retry_ipi;
- }
- /* CPU really is offline, so we can ignore it. */
- if (!(rnp->expmask & mask))
- mask_ofl_ipi &= ~mask;
+ if (rcu_dynticks_in_eqs_since(rdp->dynticks,
+ rdp->exp_dynticks_snap)) {
+ mask_ofl_test |= mask;
+ continue;
+ }
+ ret = smp_call_function_single(cpu, func, rsp, 0);
+ if (!ret) {
+ mask_ofl_ipi &= ~mask;
+ continue;
+ }
+ /* Failed, raced with CPU hotplug operation. */
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ if ((rnp->qsmaskinitnext & mask) &&
+ (rnp->expmask & mask)) {
+ /* Online, so delay for a bit and try again. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
+ schedule_timeout_uninterruptible(1);
+ goto retry_ipi;
+ }
+ /* CPU really is offline, so we can ignore it. */
+ if (!(rnp->expmask & mask))
+ mask_ofl_ipi &= ~mask;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ }
+ /* Report quiescent states for those that went offline. */
+ mask_ofl_test |= mask_ofl_ipi;
+ if (mask_ofl_test)
+ rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
+}
+
+/*
+ * Select the nodes that the upcoming expedited grace period needs
+ * to wait for.
+ */
+static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
+ smp_call_func_t func)
+{
+ struct rcu_node *rnp;
+
+ trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
+ sync_exp_reset_tree(rsp);
+ trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
+
+ /* Schedule work for each leaf rcu_node structure. */
+ rcu_for_each_leaf_node(rsp, rnp) {
+ rnp->exp_need_flush = false;
+ if (!READ_ONCE(rnp->expmask))
+ continue; /* Avoid early boot non-existent wq. */
+ rnp->rew.rew_func = func;
+ rnp->rew.rew_rsp = rsp;
+ if (!READ_ONCE(rcu_par_gp_wq) ||
+ rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
+ /* No workqueues yet. */
+ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
+ continue;
}
- /* Report quiescent states for those that went offline. */
- mask_ofl_test |= mask_ofl_ipi;
- if (mask_ofl_test)
- rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
+ INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
+ queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+ rnp->exp_need_flush = true;
}
+
+ /* Wait for workqueue jobs (if any) to complete. */
+ rcu_for_each_leaf_node(rsp, rnp)
+ if (rnp->exp_need_flush)
+ flush_work(&rnp->rew.rew_work);
}
static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
@@ -469,9 +520,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
for (;;) {
ret = swait_event_timeout(
rsp->expedited_wq,
- sync_rcu_preempt_exp_done(rnp_root),
+ sync_rcu_preempt_exp_done_unlocked(rnp_root),
jiffies_stall);
- if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root))
+ if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root))
return;
WARN_ON(ret < 0); /* workqueues should not be signaled. */
if (rcu_cpu_stall_suppress)
@@ -504,7 +555,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
rcu_for_each_node_breadth_first(rsp, rnp) {
if (rnp == rnp_root)
continue; /* printed unconditionally */
- if (sync_rcu_preempt_exp_done(rnp))
+ if (sync_rcu_preempt_exp_done_unlocked(rnp))
continue;
pr_cont(" l=%u:%d-%d:%#lx/%c",
rnp->level, rnp->grplo, rnp->grphi,
@@ -560,14 +611,6 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
mutex_unlock(&rsp->exp_wake_mutex);
}
-/* Let the workqueue handler know what it is supposed to do. */
-struct rcu_exp_work {
- smp_call_func_t rew_func;
- struct rcu_state *rew_rsp;
- unsigned long rew_s;
- struct work_struct rew_work;
-};
-
/*
* Common code to drive an expedited grace period forward, used by
* workqueues and mid-boot-time tasks.
@@ -633,7 +676,7 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
rnp = rcu_get_root(rsp);
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
- sync_exp_work_done(rsp, &rdp->exp_workdone0, s));
+ sync_exp_work_done(rsp, s));
smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 84fbee4686d3..7fd12039e512 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -182,7 +182,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
raw_lockdep_assert_held_rcu_node(rnp);
WARN_ON_ONCE(rdp->mynode != rnp);
- WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
+ WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
/*
* Decide where to queue the newly blocked task. In theory,
@@ -384,6 +384,50 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
}
/*
+ * Preemptible RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+ current->rcu_read_lock_nesting++;
+ barrier(); /* critical section after entry code. */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+/*
+ * Preemptible RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+ struct task_struct *t = current;
+
+ if (t->rcu_read_lock_nesting != 1) {
+ --t->rcu_read_lock_nesting;
+ } else {
+ barrier(); /* critical section before exit code. */
+ t->rcu_read_lock_nesting = INT_MIN;
+ barrier(); /* assign before ->rcu_read_unlock_special load */
+ if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
+ rcu_read_unlock_special(t);
+ barrier(); /* ->rcu_read_unlock_special load before assign */
+ t->rcu_read_lock_nesting = 0;
+ }
+#ifdef CONFIG_PROVE_LOCKING
+ {
+ int rrln = READ_ONCE(t->rcu_read_lock_nesting);
+
+ WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+ }
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+/*
* Advance a ->blkd_tasks-list pointer to the next entry, instead
* returning NULL if at the end of the list.
*/
@@ -489,7 +533,7 @@ void rcu_read_unlock_special(struct task_struct *t)
rnp = t->rcu_blocked_node;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
WARN_ON_ONCE(rnp != t->rcu_blocked_node);
- WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
+ WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
empty_exp = sync_rcu_preempt_exp_done(rnp);
smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -685,15 +729,6 @@ static void rcu_preempt_check_callbacks(void)
t->rcu_read_unlock_special.b.need_qs = true;
}
-#ifdef CONFIG_RCU_BOOST
-
-static void rcu_preempt_do_callbacks(void)
-{
- rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
-}
-
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
/**
* call_rcu() - Queue an RCU callback for invocation after a grace period.
* @head: structure to be used for queueing the RCU updates.
@@ -1140,7 +1175,7 @@ static void rcu_kthread_do_work(void)
{
rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
- rcu_preempt_do_callbacks();
+ rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
}
static void rcu_cpu_kthread_setup(unsigned int cpu)
@@ -1607,7 +1642,7 @@ static int rcu_oom_notify(struct notifier_block *self,
for_each_online_cpu(cpu) {
smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
}
/* Unconditionally decrement: no need to wake ourselves up. */
@@ -1780,19 +1815,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
swake_up_all(sq);
}
-/*
- * Set the root rcu_node structure's ->need_future_gp field
- * based on the sum of those of all rcu_node structures. This does
- * double-count the root rcu_node structure's requests, but this
- * is necessary to handle the possibility of a rcu_nocb_kthread()
- * having awakened during the time that the rcu_node structures
- * were being updated for the end of the previous grace period.
- */
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
-{
- rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq;
-}
-
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
{
return &rnp->nocb_gp_wq[rnp->completed & 0x1];
@@ -1966,7 +1988,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvf"));
} else {
- wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE,
+ wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE_FORCE,
TPS("WakeOvfIsDeferred"));
}
rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2048,7 +2070,8 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
struct rcu_node *rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- needwake = rcu_start_future_gp(rnp, rdp, &c);
+ c = rcu_cbs_completed(rdp->rsp, rnp);
+ needwake = rcu_start_this_gp(rnp, rdp, c);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (needwake)
rcu_gp_kthread_wake(rdp->rsp);
@@ -2057,7 +2080,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
* Wait for the grace period. Do so interruptibly to avoid messing
* up the load average.
*/
- trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait"));
+ trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
for (;;) {
swait_event_interruptible(
rnp->nocb_gp_wq[c & 0x1],
@@ -2065,9 +2088,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
if (likely(d))
break;
WARN_ON(signal_pending(current));
- trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait"));
+ trace_rcu_this_gp(rnp, rdp, c, TPS("ResumeWait"));
}
- trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait"));
+ trace_rcu_this_gp(rnp, rdp, c, TPS("EndWait"));
smp_mb(); /* Ensure that CB invocation happens after GP end. */
}
@@ -2236,7 +2259,7 @@ static int rcu_nocb_kthread(void *arg)
cl++;
c++;
local_bh_enable();
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
list = next;
}
trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
@@ -2292,7 +2315,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
void __init rcu_init_nohz(void)
{
int cpu;
- bool need_rcu_nocb_mask = true;
+ bool need_rcu_nocb_mask = false;
struct rcu_state *rsp;
#if defined(CONFIG_NO_HZ_FULL)
@@ -2315,7 +2338,7 @@ void __init rcu_init_nohz(void)
#endif /* #if defined(CONFIG_NO_HZ_FULL) */
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
- pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+ pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
cpumask_and(rcu_nocb_mask, cpu_possible_mask,
rcu_nocb_mask);
}
@@ -2495,10 +2518,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
{
}
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
-{
-}
-
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
{
return NULL;
@@ -2587,8 +2606,7 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
}
/*
- * Bind the grace-period kthread for the sysidle flavor of RCU to the
- * timekeeping CPU.
+ * Bind the RCU grace-period kthreads to the housekeeping CPU.
*/
static void rcu_bind_gp_kthread(void)
{
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 68fa19a5e7bd..4c230a60ece4 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -226,54 +226,6 @@ core_initcall(rcu_set_runtime_mode);
#endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */
-#ifdef CONFIG_PREEMPT_RCU
-
-/*
- * Preemptible RCU implementation for rcu_read_lock().
- * Just increment ->rcu_read_lock_nesting, shared state will be updated
- * if we block.
- */
-void __rcu_read_lock(void)
-{
- current->rcu_read_lock_nesting++;
- barrier(); /* critical section after entry code. */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_lock);
-
-/*
- * Preemptible RCU implementation for rcu_read_unlock().
- * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost
- * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
- * invoke rcu_read_unlock_special() to clean up after a context switch
- * in an RCU read-side critical section and other special cases.
- */
-void __rcu_read_unlock(void)
-{
- struct task_struct *t = current;
-
- if (t->rcu_read_lock_nesting != 1) {
- --t->rcu_read_lock_nesting;
- } else {
- barrier(); /* critical section before exit code. */
- t->rcu_read_lock_nesting = INT_MIN;
- barrier(); /* assign before ->rcu_read_unlock_special load */
- if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
- rcu_read_unlock_special(t);
- barrier(); /* ->rcu_read_unlock_special load before assign */
- t->rcu_read_lock_nesting = 0;
- }
-#ifdef CONFIG_PROVE_LOCKING
- {
- int rrln = READ_ONCE(t->rcu_read_lock_nesting);
-
- WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
- }
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_unlock);
-
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
struct lockdep_map rcu_lock_map =
@@ -624,7 +576,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks);
* grace period has elapsed, in other words after all currently
* executing rcu-tasks read-side critical sections have elapsed. These
* read-side critical sections are delimited by calls to schedule(),
- * cond_resched_rcu_qs(), idle execution, userspace execution, calls
+ * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
* to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
*
* This is a very specialized primitive, intended only for a few uses in
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 092f7c4de903..3e6737034175 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5008,20 +5008,6 @@ int __cond_resched_lock(spinlock_t *lock)
}
EXPORT_SYMBOL(__cond_resched_lock);
-int __sched __cond_resched_softirq(void)
-{
- BUG_ON(!in_softirq());
-
- if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
- local_bh_enable();
- preempt_schedule_common();
- local_bh_disable();
- return 1;
- }
- return 0;
-}
-EXPORT_SYMBOL(__cond_resched_softirq);
-
/**
* yield - yield the current processor to other threads.
*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 177de3640c78..03981f1c39ea 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -145,8 +145,7 @@ static void __local_bh_enable(unsigned int cnt)
}
/*
- * Special-case - softirqs can safely be enabled in
- * cond_resched_softirq(), or by __do_softirq(),
+ * Special-case - softirqs can safely be enabled by __do_softirq(),
* without processing still-pending softirqs:
*/
void _local_bh_enable(void)
diff --git a/kernel/torture.c b/kernel/torture.c
index 37b94012a3f8..3de1efbecd6a 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -574,7 +574,7 @@ void stutter_wait(const char *title)
{
int spt;
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
spt = READ_ONCE(stutter_pause_test);
for (; spt; spt = READ_ONCE(stutter_pause_test)) {
if (spt == 1) {
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 22fee766081b..80e0b2aca703 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -159,13 +159,13 @@ static int benchmark_event_kthread(void *arg)
* wants to run, schedule in, but if the CPU is idle,
* we'll keep burning cycles.
*
- * Note the _rcu_qs() version of cond_resched() will
+ * Note the tasks_rcu_qs() version of cond_resched() will
* notify synchronize_rcu_tasks() that this thread has
* passed a quiescent state for rcu_tasks. Otherwise
* this thread will never voluntarily schedule which would
* block synchronize_rcu_tasks() indefinitely.
*/
- cond_resched();
+ cond_resched_tasks_rcu_qs();
}
return 0;
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
new file mode 100755
index 000000000000..98f650c9bf54
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+#
+# Invoke a text editor on all console.log files for all runs with diagnostics,
+# that is, on all such files having a console.log.diags counterpart.
+# Note that both console.log.diags and console.log are passed to the
+# editor (currently defaulting to "vi"), allowing the user to get an
+# idea of what to search for in the console.log file.
+#
+# Usage: kvm-find-errors.sh directory
+#
+# The "directory" above should end with the date/time directory, for example,
+# "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27".
+
+rundir="${1}"
+if test -z "$rundir" -o ! -d "$rundir"
+then
+ echo Usage: $0 directory
+fi
+editor=${EDITOR-vi}
+
+# Find builds with errors
+files=
+for i in ${rundir}/*/Make.out
+do
+ if egrep -q "error:|warning:" < $i
+ then
+ egrep "error:|warning:" < $i > $i.diags
+ files="$files $i.diags $i"
+ fi
+done
+if test -n "$files"
+then
+ $editor $files
+else
+ echo No build errors.
+fi
+if grep -q -e "--buildonly" < ${rundir}/log
+then
+ echo Build-only run, no console logs to check.
+fi
+
+# Find console logs with errors
+files=
+for i in ${rundir}/*/console.log
+do
+ if test -r $i.diags
+ then
+ files="$files $i.diags $i"
+ fi
+done
+if test -n "$files"
+then
+ $editor $files
+else
+ echo No errors in console logs.
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index c2e1bb6d0cba..477ecb1293ab 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -34,11 +34,15 @@ fi
configfile=`echo $i | sed -e 's/^.*\///'`
ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
+stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null |
+ tail -1 | sed -e 's/^\[[ 0-9.]*] //' |
+ awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' |
+ tr -d '\012\015'`"
if test -z "$ngps"
then
- echo "$configfile -------"
+ echo "$configfile ------- " $stopstate
else
- title="$configfile ------- $ngps grace periods"
+ title="$configfile ------- $ngps GPs"
dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
if test -z "$dur"
then
@@ -46,9 +50,9 @@ else
else
ngpsps=`awk -v ngps=$ngps -v dur=$dur '
BEGIN { print ngps / dur }' < /dev/null`
- title="$title ($ngpsps per second)"
+ title="$title ($ngpsps/s)"
fi
- echo $title
+ echo $title $stopstate
nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
if test -z "$nclosecalls"
then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index f7e988f369dd..c27e97824163 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -48,10 +48,6 @@ do
cat $i/Make.oldconfig.err
fi
parse-build.sh $i/Make.out $configfile
- if test "$TORTURE_SUITE" != rcuperf
- then
- parse-torture.sh $i/console.log $configfile
- fi
parse-console.sh $i/console.log $configfile
if test -r $i/Warnings
then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 5f8fbb0d7c17..c5b0f94341d9 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -267,5 +267,4 @@ then
echo Unknown PID, cannot kill qemu command
fi
-parse-torture.sh $resdir/console.log $title
parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 08aa7d50ae0e..17293436f551 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -24,57 +24,146 @@
#
# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+T=${TMPDIR-/tmp}/parse-console.sh.$$
file="$1"
title="$2"
+trap 'rm -f $T.seq $T.diags' 0
+
. functions.sh
+# Check for presence and readability of console output file
+if test -f "$file" -a -r "$file"
+then
+ :
+else
+ echo $title unreadable console output file: $file
+ exit 1
+fi
if grep -Pq '\x00' < $file
then
print_warning Console output contains nul bytes, old qemu still running?
fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
-if test -s $1.diags
+cat /dev/null > $file.diags
+
+# Check for proper termination, except that rcuperf runs don't indicate this.
+if test "$TORTURE_SUITE" != rcuperf
then
- print_warning Assertion failure in $file $title
- # cat $1.diags
+ # check for abject failure
+
+ if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
+ then
+ nerrs=`grep --binary-files=text '!!!' $file |
+ tail -1 |
+ awk '
+ {
+ for (i=NF-8;i<=NF;i++)
+ sum+=$i;
+ }
+ END { print sum }'`
+ print_bug $title FAILURE, $nerrs instances
+ exit
+ fi
+
+ grep --binary-files=text 'torture:.*ver:' $file |
+ egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' |
+ sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
+ awk '
+ BEGIN {
+ ver = 0;
+ badseq = 0;
+ }
+
+ {
+ if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
+ badseqno1 = ver;
+ badseqno2 = $5;
+ badseqnr = NR;
+ badseq = 1;
+ }
+ ver = $5
+ }
+
+ END {
+ if (badseq) {
+ if (badseqno1 == badseqno2 && badseqno2 == ver)
+ print "GP HANG at " ver " torture stat " badseqnr;
+ else
+ print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
+ }
+ }' > $T.seq
+
+ if grep -q SUCCESS $file
+ then
+ if test -s $T.seq
+ then
+ print_warning $title `cat $T.seq`
+ echo " " $file
+ exit 2
+ fi
+ else
+ if grep -q "_HOTPLUG:" $file
+ then
+ print_warning HOTPLUG FAILURES $title `cat $T.seq`
+ echo " " $file
+ exit 3
+ fi
+ echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
+ if test -s $T.seq
+ then
+ print_warning $title `cat $T.seq`
+ fi
+ exit 2
+ fi
+fi | tee -a $file.diags
+
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file |
+grep -v 'ODEBUG: ' |
+grep -v 'Warning: unable to open an initial console' > $T.diags
+if test -s $T.diags
+then
+ print_warning "Assertion failure in $file $title"
+ # cat $T.diags
summary=""
- n_badness=`grep -c Badness $1`
+ n_badness=`grep -c Badness $file`
if test "$n_badness" -ne 0
then
summary="$summary Badness: $n_badness"
fi
- n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'`
+ n_warn=`grep -v 'Warning: unable to open an initial console' $file | egrep -c 'WARNING:|Warn'`
if test "$n_warn" -ne 0
then
summary="$summary Warnings: $n_warn"
fi
- n_bugs=`egrep -c 'BUG|Oops:' $1`
+ n_bugs=`egrep -c 'BUG|Oops:' $file`
if test "$n_bugs" -ne 0
then
summary="$summary Bugs: $n_bugs"
fi
- n_calltrace=`grep -c 'Call Trace:' $1`
+ n_calltrace=`grep -c 'Call Trace:' $file`
if test "$n_calltrace" -ne 0
then
summary="$summary Call Traces: $n_calltrace"
fi
- n_lockdep=`grep -c =========== $1`
+ n_lockdep=`grep -c =========== $file`
if test "$n_badness" -ne 0
then
summary="$summary lockdep: $n_badness"
fi
- n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1`
+ n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $file`
if test "$n_stalls" -ne 0
then
summary="$summary Stalls: $n_stalls"
fi
- n_starves=`grep -c 'rcu_.*kthread starved for' $1`
+ n_starves=`grep -c 'rcu_.*kthread starved for' $file`
if test "$n_starves" -ne 0
then
summary="$summary Starves: $n_starves"
fi
print_warning Summary: $summary
-else
- rm $1.diags
+ cat $T.diags >> $file.diags
+fi
+if ! test -s $file.diags
+then
+ rm -f $file.diags
fi
diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
deleted file mode 100755
index 5987e50cfeb4..000000000000
--- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh
+++ /dev/null
@@ -1,105 +0,0 @@
-#!/bin/bash
-#
-# Check the console output from a torture run for goodness.
-# The "file" is a pathname on the local system, and "title" is
-# a text string for error-message purposes.
-#
-# The file must contain torture output, but can be interspersed
-# with other dmesg text, as in console-log output.
-#
-# Usage: parse-torture.sh file title
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2011
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-T=${TMPDIR-/tmp}/parse-torture.sh.$$
-file="$1"
-title="$2"
-
-trap 'rm -f $T.seq' 0
-
-. functions.sh
-
-# check for presence of torture output file.
-
-if test -f "$file" -a -r "$file"
-then
- :
-else
- echo $title unreadable torture output file: $file
- exit 1
-fi
-
-# check for abject failure
-
-if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
-then
- nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
- print_bug $title FAILURE, $nerrs instances
- echo " " $url
- exit
-fi
-
-grep --binary-files=text 'torture:.*ver:' $file | egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
-awk '
-BEGIN {
- ver = 0;
- badseq = 0;
- }
-
- {
- if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
- badseqno1 = ver;
- badseqno2 = $5;
- badseqnr = NR;
- badseq = 1;
- }
- ver = $5
- }
-
-END {
- if (badseq) {
- if (badseqno1 == badseqno2 && badseqno2 == ver)
- print "GP HANG at " ver " torture stat " badseqnr;
- else
- print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
- }
- }' > $T.seq
-
-if grep -q SUCCESS $file
-then
- if test -s $T.seq
- then
- print_warning $title $title `cat $T.seq`
- echo " " $file
- exit 2
- fi
-else
- if grep -q "_HOTPLUG:" $file
- then
- print_warning HOTPLUG FAILURES $title `cat $T.seq`
- echo " " $file
- exit 3
- fi
- echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
- if test -s $T.seq
- then
- print_warning $title `cat $T.seq`
- fi
- exit 2
-fi