The following commit has been merged into the core/rcu branch of tip:
Commit-ID: 6bc335828056f3b301a3deadda782de4e8f0db08
Gitweb:
https://git.kernel.org/tip/6bc335828056f3b301a3deadda782de4e8f0db08
Author: Joel Fernandes (Google) <j...@joelfernandes.org>
AuthorDate: Tue, 03 Nov 2020 09:25:57 -05:00
Committer: Paul E. McKenney <paul...@kernel.org>
CommitterDate: Mon, 04 Jan 2021 13:22:12 -08:00
rcu/tree: Make rcu_do_batch count how many callbacks were executed
The rcu_do_batch() function extracts the ready-to-invoke callbacks
from the rcu_segcblist located in the ->cblist field of the current
CPU's rcu_data structure. These callbacks are first moved to a local
(unsegmented) rcu_cblist. The rcu_do_batch() function then uses this
rcu_cblist's ->len field to count how many CBs it has invoked, but it
does so by counting that field down from zero. Finally, this function
negates the value in this ->len field (resulting in a positive number)
and subtracts the result from the ->len field of the current CPU's
->cblist field.
Except that it is sometimes necessary for rcu_do_batch() to stop invoking
callbacks mid-stream, despite there being more ready to invoke, for
example, if a high-priority task wakes up. In this case the remaining
not-yet-invoked callbacks are requeued back onto the CPU's ->cblist,
but remain in the ready-to-invoke segment of that list. As above, the
negative of the local rcu_cblist's ->len field is still subtracted from
the ->len field of the current CPU's ->cblist field.
The design of counting down from 0 is confusing and error-prone, plus
use of a positive count will make it easier to provide a uniform and
consistent API to deal with the per-segment counts that are added
later in this series. For example, rcu_segcblist_extract_done_cbs()
can unconditionally populate the resulting unsegmented list's ->len
field during extraction.
This commit therefore explicitly counts how many callbacks were executed
in rcu_do_batch() itself, counting up from zero, and then uses that
to update the per-CPU segcb list's ->len field, without relying on the
downcounting of rcl->len from zero.
Reviewed-by: Frederic Weisbecker <frede...@kernel.org>
Reviewed-by: Neeraj Upadhyay <neer...@codeaurora.org>
Signed-off-by: Joel Fernandes (Google) <j...@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paul...@kernel.org>
---
kernel/rcu/rcu_segcblist.c | 2 +-
kernel/rcu/rcu_segcblist.h | 1 +
kernel/rcu/tree.c | 11 +++++------
3 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 2d2a6b6..bb246d8 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -95,7 +95,7 @@ static void rcu_segcblist_set_len(struct rcu_segcblist
*rsclp, long v)
* This increase is fully ordered with respect to the callers accesses
* both before and after.
*/
-static void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
+void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
{
#ifdef CONFIG_RCU_NOCB_CPU
smp_mb__before_atomic(); /* Up to the caller! */
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 492262b..1d2d614 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -76,6 +76,7 @@ static inline bool rcu_segcblist_restempty(struct
rcu_segcblist *rsclp, int seg)
}
void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp);
+void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v);
void rcu_segcblist_init(struct rcu_segcblist *rsclp);
void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
void rcu_segcblist_offload(struct rcu_segcblist *rsclp);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 40e5e3d..cc6f379 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2434,7 +2434,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
struct rcu_head *rhp;
struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
- long bl, count;
+ long bl, count = 0;
long pending, tlimit = 0;
/* If no callbacks are ready, just return. */
@@ -2479,6 +2479,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
rcu_callback_t f;
+ count++;
debug_rcu_head_unqueue(rhp);
rcu_lock_acquire(&rcu_callback_map);
@@ -2492,15 +2493,14 @@ static void rcu_do_batch(struct rcu_data *rdp)
/*
* Stop only if limit reached and CPU has something to do.
- * Note: The rcl structure counts down from zero.
*/
- if (-rcl.len >= bl && !offloaded &&
+ if (count >= bl && !offloaded &&
(need_resched() ||
(!is_idle_task(current) && !rcu_is_callbacks_kthread())))
break;
if (unlikely(tlimit)) {
/* only call local_clock() every 32 callbacks */
- if (likely((-rcl.len & 31) || local_clock() < tlimit))
+ if (likely((count & 31) || local_clock() < tlimit))
continue;
/* Exceeded the time limit, so leave. */
break;
@@ -2517,7 +2517,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
local_irq_save(flags);
rcu_nocb_lock(rdp);
- count = -rcl.len;
rdp->n_cbs_invoked += count;
trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
is_idle_task(current), rcu_is_callbacks_kthread());
@@ -2525,7 +2524,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
/* Update counts and requeue any remaining callbacks. */
rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
smp_mb(); /* List handling before counting for rcu_barrier(). */
- rcu_segcblist_insert_count(&rdp->cblist, &rcl);
+ rcu_segcblist_add_len(&rdp->cblist, -count);
/* Reinstate batch limit if we have worked down the excess. */
count = rcu_segcblist_n_cbs(&rdp->cblist);
