[PATCH RFC tip/core/rcu 7/9] locking/percpu-rwsem: Fix the comments outdated by rcu_sync
From: Oleg Nesterov
Update the comments broken by the previous change.
Signed-off-by: Oleg Nesterov
Signed-off-by: Paul E. McKenney
---
kernel/locking/percpu-rwsem.c | 50 ++-
1 file changed, 11 insertions(+), 39 deletions(-)
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 7abc0e150a22..25b73448929c 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -38,27 +38,12 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
}
/*
- * This is the fast-path for down_read/up_read, it only needs to ensure
- * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the
- * fast per-cpu counter. The writer uses synchronize_sched_expedited() to
- * serialize with the preempt-disabled section below.
- *
- * The nontrivial part is that we should guarantee acquire/release semantics
- * in case when
- *
- * R_W: down_write() comes after up_read(), the writer should see all
- * changes done by the reader
- * or
- * W_R: down_read() comes after up_write(), the reader should see all
- * changes done by the writer
+ * This is the fast-path for down_read/up_read. If it succeeds we rely
+ * on the barriers provided by rcu_sync_enter/exit; see the comments in
+ * percpu_down_write() and percpu_up_write().
*
* If this helper fails the callers rely on the normal rw_semaphore and
* atomic_dec_and_test(), so in this case we have the necessary barriers.
- *
- * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or
- * __this_cpu_add() below can be reordered with any LOAD/STORE done by the
- * reader inside the critical section. See the comments in down_write and
- * up_write below.
*/
static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
{
@@ -120,29 +105,15 @@ static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
return sum;
}
-/*
- * A writer increments ->write_ctr to force the readers to switch to the
- * slow mode, note the atomic_read() check in update_fast_ctr().
- *
- * After that the readers can only inc/dec the slow ->slow_read_ctr counter,
- * ->fast_read_ctr is stable. Once the writer moves its sum into the slow
- * counter it represents the number of active readers.
- *
- * Finally the writer takes ->rw_sem for writing and blocks the new readers,
- * then waits until the slow counter becomes zero.
- */
void percpu_down_write(struct percpu_rw_semaphore *brw)
{
/*
-* 1. Ensures that write_ctr != 0 is visible to any down_read/up_read
-*so that update_fast_ctr() can't succeed.
-*
-* 2. Ensures we see the result of every previous this_cpu_add() in
-*update_fast_ctr().
+* Make rcu_sync_is_idle() == F and thus disable the fast-path in
+* percpu_down_read() and percpu_up_read(), and wait for gp pass.
*
-* 3. Ensures that if any reader has exited its critical section via
-*fast-path, it executes a full memory barrier before we return.
-*See R_W case in the comment above update_fast_ctr().
+* The latter synchronises us with the preceding readers which used
+* the fast-past, so we can not miss the result of __this_cpu_add()
+* or anything else inside their criticial sections.
*/
rcu_sync_enter(>rss);
@@ -161,8 +132,9 @@ void percpu_up_write(struct percpu_rw_semaphore *brw)
/* release the lock, but the readers can't use the fast-path */
up_write(>rw_sem);
/*
-* Insert the barrier before the next fast-path in down_read,
-* see W_R case in the comment above update_fast_ctr().
+* Enable the fast-path in percpu_down_read() and percpu_up_read()
+* but only after another gp pass; this adds the necessary barrier
+* to ensure the reader can't miss the changes done by us.
*/
rcu_sync_exit(>rss);
}
--
1.8.1.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[PATCH RFC tip/core/rcu 7/9] locking/percpu-rwsem: Fix the comments outdated by rcu_sync
From: Oleg Nesterov o...@redhat.com
Update the comments broken by the previous change.
Signed-off-by: Oleg Nesterov o...@redhat.com
Signed-off-by: Paul E. McKenney paul...@linux.vnet.ibm.com
---
kernel/locking/percpu-rwsem.c | 50 ++-
1 file changed, 11 insertions(+), 39 deletions(-)
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 7abc0e150a22..25b73448929c 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -38,27 +38,12 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
}
/*
- * This is the fast-path for down_read/up_read, it only needs to ensure
- * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the
- * fast per-cpu counter. The writer uses synchronize_sched_expedited() to
- * serialize with the preempt-disabled section below.
- *
- * The nontrivial part is that we should guarantee acquire/release semantics
- * in case when
- *
- * R_W: down_write() comes after up_read(), the writer should see all
- * changes done by the reader
- * or
- * W_R: down_read() comes after up_write(), the reader should see all
- * changes done by the writer
+ * This is the fast-path for down_read/up_read. If it succeeds we rely
+ * on the barriers provided by rcu_sync_enter/exit; see the comments in
+ * percpu_down_write() and percpu_up_write().
*
* If this helper fails the callers rely on the normal rw_semaphore and
* atomic_dec_and_test(), so in this case we have the necessary barriers.
- *
- * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or
- * __this_cpu_add() below can be reordered with any LOAD/STORE done by the
- * reader inside the critical section. See the comments in down_write and
- * up_write below.
*/
static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
{
@@ -120,29 +105,15 @@ static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
return sum;
}
-/*
- * A writer increments -write_ctr to force the readers to switch to the
- * slow mode, note the atomic_read() check in update_fast_ctr().
- *
- * After that the readers can only inc/dec the slow -slow_read_ctr counter,
- * -fast_read_ctr is stable. Once the writer moves its sum into the slow
- * counter it represents the number of active readers.
- *
- * Finally the writer takes -rw_sem for writing and blocks the new readers,
- * then waits until the slow counter becomes zero.
- */
void percpu_down_write(struct percpu_rw_semaphore *brw)
{
/*
-* 1. Ensures that write_ctr != 0 is visible to any down_read/up_read
-*so that update_fast_ctr() can't succeed.
-*
-* 2. Ensures we see the result of every previous this_cpu_add() in
-*update_fast_ctr().
+* Make rcu_sync_is_idle() == F and thus disable the fast-path in
+* percpu_down_read() and percpu_up_read(), and wait for gp pass.
*
-* 3. Ensures that if any reader has exited its critical section via
-*fast-path, it executes a full memory barrier before we return.
-*See R_W case in the comment above update_fast_ctr().
+* The latter synchronises us with the preceding readers which used
+* the fast-past, so we can not miss the result of __this_cpu_add()
+* or anything else inside their criticial sections.
*/
rcu_sync_enter(brw-rss);
@@ -161,8 +132,9 @@ void percpu_up_write(struct percpu_rw_semaphore *brw)
/* release the lock, but the readers can't use the fast-path */
up_write(brw-rw_sem);
/*
-* Insert the barrier before the next fast-path in down_read,
-* see W_R case in the comment above update_fast_ctr().
+* Enable the fast-path in percpu_down_read() and percpu_up_read()
+* but only after another gp pass; this adds the necessary barrier
+* to ensure the reader can't miss the changes done by us.
*/
rcu_sync_exit(brw-rss);
}
--
1.8.1.5
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
