[PATCH rcu 0/3] SRCU updates for v6.12

[PATCH rcu 0/3] SRCU updates for v6.12

[Neeraj Upadhyay]

Hello,

Following are the SRCU updates for v6.12:

1.      Faster gp seq wrap-around, courtesy of JP Kobryn.

2.      Check for concurrent updates of heuristics, courtesy of
        Paul E. McKenney.

3.      Mark callbacks not currently participating in barrier operation,
        courtesy of Paul E. McKenney.


Git tree: https://git.kernel.org/pub/scm/linux/kernel/git/neeraj.upadhyay/linux-rcu.git/log/?h=srcu.12.08.24a


- Neeraj

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

 include/linux/rcupdate.h |  3 +++
 include/linux/srcutree.h | 15 ++++++++++++++-
 kernel/rcu/rcu.h         |  3 ---
 kernel/rcu/srcutree.c    | 11 ++++++++---
 4 files changed, 25 insertions(+), 7 deletions(-)

[PATCH rcu 1/3] srcu: faster gp seq wrap-around

[neeraj.upadhyay]

From: JP Kobryn <inwardvessel@gmail.com>

Using a higher value for the initial gp sequence counters allows for
wrapping to occur faster. It can help with surfacing any issues that may
be happening as a result of the wrap around.

Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
---
 include/linux/rcupdate.h |  3 +++
 include/linux/srcutree.h | 15 ++++++++++++++-
 kernel/rcu/rcu.h         |  3 ---
 kernel/rcu/srcutree.c    |  7 ++++---
 4 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 13f6f00aecf9..8d56db70d417 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -34,6 +34,9 @@
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
 
+#define RCU_SEQ_CTR_SHIFT    2
+#define RCU_SEQ_STATE_MASK   ((1 << RCU_SEQ_CTR_SHIFT) - 1)
+
 /* Exported common interfaces */
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void rcu_barrier_tasks(void);
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 8f3f72480e78..ed57598394de 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -129,10 +129,23 @@ struct srcu_struct {
 #define SRCU_STATE_SCAN1	1
 #define SRCU_STATE_SCAN2	2
 
+/*
+ * Values for initializing gp sequence fields. Higher values allow wrap arounds to
+ * occur earlier.
+ * The second value with state is useful in the case of static initialization of
+ * srcu_usage where srcu_gp_seq_needed is expected to have some state value in its
+ * lower bits (or else it will appear to be already initialized within
+ * the call check_init_srcu_struct()).
+ */
+#define SRCU_GP_SEQ_INITIAL_VAL ((0UL - 100UL) << RCU_SEQ_CTR_SHIFT)
+#define SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE (SRCU_GP_SEQ_INITIAL_VAL - 1)
+
 #define __SRCU_USAGE_INIT(name)									\
 {												\
 	.lock = __SPIN_LOCK_UNLOCKED(name.lock),						\
-	.srcu_gp_seq_needed = -1UL,								\
+	.srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL,							\
+	.srcu_gp_seq_needed = SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE,				\
+	.srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL,					\
 	.work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0),					\
 }
 
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 38238e595a61..2bfed9855d67 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -54,9 +54,6 @@
  *					grace-period sequence number.
  */
 
-#define RCU_SEQ_CTR_SHIFT	2
-#define RCU_SEQ_STATE_MASK	((1 << RCU_SEQ_CTR_SHIFT) - 1)
-
 /* Low-order bit definition for polled grace-period APIs. */
 #define RCU_GET_STATE_COMPLETED	0x1
 
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b24db425f16d..6fd9c914ce64 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -247,7 +247,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	mutex_init(&ssp->srcu_sup->srcu_cb_mutex);
 	mutex_init(&ssp->srcu_sup->srcu_gp_mutex);
 	ssp->srcu_idx = 0;
-	ssp->srcu_sup->srcu_gp_seq = 0;
+	ssp->srcu_sup->srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL;
 	ssp->srcu_sup->srcu_barrier_seq = 0;
 	mutex_init(&ssp->srcu_sup->srcu_barrier_mutex);
 	atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0);
@@ -258,7 +258,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	if (!ssp->sda)
 		goto err_free_sup;
 	init_srcu_struct_data(ssp);
-	ssp->srcu_sup->srcu_gp_seq_needed_exp = 0;
+	ssp->srcu_sup->srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL;
 	ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
 		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC))
@@ -266,7 +266,8 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 		WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
 	}
 	ssp->srcu_sup->srcu_ssp = ssp;
-	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */
+	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed,
+			SRCU_GP_SEQ_INITIAL_VAL); /* Init done. */
 	return 0;
 
 err_free_sda:
-- 
2.40.1

[PATCH rcu 2/3] srcu: Check for concurrent updates of heuristics

[neeraj.upadhyay]

From: "Paul E. McKenney" <paulmck@kernel.org>

SRCU maintains the ->srcu_n_exp_nodelay and ->reschedule_count values
to guide heuristics governing auto-expediting of normal SRCU grace
periods and grace-period-state-machine delays.  This commit adds KCSAN
ASSERT_EXCLUSIVE_WRITER() calls to check for concurrent updates to
these fields.

Signed-off-by: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
---
 kernel/rcu/srcutree.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 6fd9c914ce64..aaee09a6748c 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -629,6 +629,7 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 		if (time_after(j, gpstart))
 			jbase += j - gpstart;
 		if (!jbase) {
+			ASSERT_EXCLUSIVE_WRITER(sup->srcu_n_exp_nodelay);
 			WRITE_ONCE(sup->srcu_n_exp_nodelay, READ_ONCE(sup->srcu_n_exp_nodelay) + 1);
 			if (READ_ONCE(sup->srcu_n_exp_nodelay) > srcu_max_nodelay_phase)
 				jbase = 1;
@@ -1819,6 +1820,7 @@ static void process_srcu(struct work_struct *work)
 	} else {
 		j = jiffies;
 		if (READ_ONCE(sup->reschedule_jiffies) == j) {
+			ASSERT_EXCLUSIVE_WRITER(sup->reschedule_count);
 			WRITE_ONCE(sup->reschedule_count, READ_ONCE(sup->reschedule_count) + 1);
 			if (READ_ONCE(sup->reschedule_count) > srcu_max_nodelay)
 				curdelay = 1;
-- 
2.40.1

[PATCH rcu 3/3] srcu: Mark callbacks not currently participating in barrier operation

[neeraj.upadhyay]

From: "Paul E. McKenney" <paulmck@kernel.org>

SRCU keeps a count of the number of callbacks that the current
srcu_barrier() is waiting on, but there is currently no easy way to
work out which callback is stuck.  One way to do this is to mark idle
SRCU-barrier callbacks by making the ->next pointer point to the callback
itself, and this commit does just that.

Later commits will use this for debug output.

Signed-off-by: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
---
 kernel/rcu/srcutree.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index aaee09a6748c..31706e3293bc 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -137,6 +137,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 		sdp->srcu_cblist_invoking = false;
 		sdp->srcu_gp_seq_needed = ssp->srcu_sup->srcu_gp_seq;
 		sdp->srcu_gp_seq_needed_exp = ssp->srcu_sup->srcu_gp_seq;
+		sdp->srcu_barrier_head.next = &sdp->srcu_barrier_head;
 		sdp->mynode = NULL;
 		sdp->cpu = cpu;
 		INIT_WORK(&sdp->work, srcu_invoke_callbacks);
@@ -1562,6 +1563,7 @@ static void srcu_barrier_cb(struct rcu_head *rhp)
 	struct srcu_data *sdp;
 	struct srcu_struct *ssp;
 
+	rhp->next = rhp; // Mark the callback as having been invoked.
 	sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
 	ssp = sdp->ssp;
 	if (atomic_dec_and_test(&ssp->srcu_sup->srcu_barrier_cpu_cnt))
-- 
2.40.1