@@ -712,6 +712,7 @@ TRACE_EVENT_RCU(rcu_torture_read,
* "Begin": rcu_barrier() started.
* "EarlyExit": rcu_barrier() piggybacked, thus early exit.
* "Inc1": rcu_barrier() piggyback check counter incremented.
+ * "OfflineNoCBQ": rcu_barrier() found offline no-CBs CPU with callbacks.
* "OnlineQ": rcu_barrier() found online CPU with callbacks.
* "OnlineNQ": rcu_barrier() found online CPU, no callbacks.
* "IRQ": An rcu_barrier_callback() callback posted on remote CPU.
@@ -3097,9 +3097,10 @@ static void rcu_barrier_callback(struct rcu_head *rhp)
/*
* Called with preemption disabled, and from cross-cpu IRQ context.
*/
-static void rcu_barrier_func(void *unused)
+static void rcu_barrier_func(void *cpu_in)
{
- struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
+ uintptr_t cpu = (uintptr_t)cpu_in;
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence);
rdp->barrier_head.func = rcu_barrier_callback;
@@ -3126,7 +3127,7 @@ static void rcu_barrier_func(void *unused)
*/
void rcu_barrier(void)
{
- int cpu;
+ uintptr_t cpu;
struct rcu_data *rdp;
unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
@@ -3149,13 +3150,14 @@ void rcu_barrier(void)
rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence);
/*
- * Initialize the count to one rather than to zero in order to
- * avoid a too-soon return to zero in case of a short grace period
- * (or preemption of this task). Exclude CPU-hotplug operations
- * to ensure that no offline CPU has callbacks queued.
+ * Initialize the count to two rather than to zero in order
+ * to avoid a too-soon return to zero in case of an immediate
+ * invocation of the just-enqueued callback (or preemption of
+ * this task). Exclude CPU-hotplug operations to ensure that no
+ * offline non-offloaded CPU has callbacks queued.
*/
init_completion(&rcu_state.barrier_completion);
- atomic_set(&rcu_state.barrier_cpu_count, 1);
+ atomic_set(&rcu_state.barrier_cpu_count, 2);
get_online_cpus();
/*
@@ -3165,13 +3167,23 @@ void rcu_barrier(void)
*/
for_each_possible_cpu(cpu) {
rdp = per_cpu_ptr(&rcu_data, cpu);
- if (!cpu_online(cpu) &&
+ if (cpu_is_offline(cpu) &&
!rcu_segcblist_is_offloaded(&rdp->cblist))
continue;
- if (rcu_segcblist_n_cbs(&rdp->cblist)) {
+ if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
rcu_barrier_trace(TPS("OnlineQ"), cpu,
rcu_state.barrier_sequence);
- smp_call_function_single(cpu, rcu_barrier_func, NULL, 1);
+ smp_call_function_single(cpu, rcu_barrier_func, (void *)cpu, 1);
+ } else if (rcu_segcblist_n_cbs(&rdp->cblist) &&
+ cpu_is_offline(cpu)) {
+ rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu,
+ rcu_state.barrier_sequence);
+ local_irq_disable();
+ rcu_barrier_func((void *)cpu);
+ local_irq_enable();
+ } else if (cpu_is_offline(cpu)) {
+ rcu_barrier_trace(TPS("OfflineNoCBNoQ"), cpu,
+ rcu_state.barrier_sequence);
} else {
rcu_barrier_trace(TPS("OnlineNQ"), cpu,
rcu_state.barrier_sequence);
@@ -3183,7 +3195,7 @@ void rcu_barrier(void)
* Now that we have an rcu_barrier_callback() callback on each
* CPU, and thus each counted, remove the initial count.
*/
- if (atomic_dec_and_test(&rcu_state.barrier_cpu_count))
+ if (atomic_sub_and_test(2, &rcu_state.barrier_cpu_count))
complete(&rcu_state.barrier_completion);
/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
The following commit has been merged into the core/rcu branch of tip: Commit-ID: 127e29815b4b2206c0a97ac1d83f92ffc0e25c34 Gitweb: https://git.kernel.org/tip/127e29815b4b2206c0a97ac1d83f92ffc0e25c34 Author: Paul E. McKenney <paulmck@kernel.org> AuthorDate: Tue, 11 Feb 2020 06:17:33 -08:00 Committer: Paul E. McKenney <paulmck@kernel.org> CommitterDate: Sat, 21 Mar 2020 16:14:25 -07:00 rcu: Make rcu_barrier() account for offline no-CBs CPUs Currently, rcu_barrier() ignores offline CPUs, However, it is possible for an offline no-CBs CPU to have callbacks queued, and rcu_barrier() must wait for those callbacks. This commit therefore makes rcu_barrier() directly invoke the rcu_barrier_func() with interrupts disabled for such CPUs. This requires passing the CPU number into this function so that it can entrain the rcu_barrier() callback onto the correct CPU's callback list, given that the code must instead execute on the current CPU. While in the area, this commit fixes a bug where the first CPU's callback might have been invoked before rcu_segcblist_entrain() returned, which would also result in an early wakeup. Fixes: 5d6742b37727 ("rcu/nocb: Use rcu_segcblist for no-CBs CPUs") Signed-off-by: Paul E. McKenney <paulmck@kernel.org> [ paulmck: Apply optimization feedback from Boqun Feng. ] Cc: <stable@vger.kernel.org> # 5.5.x --- include/trace/events/rcu.h | 1 + kernel/rcu/tree.c | 36 ++++++++++++++++++++++++------------ 2 files changed, 25 insertions(+), 12 deletions(-)