From: Bart Van Assche <bart.vanassche@wdc.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
Bart Van Assche <bart.vanassche@wdc.com>,
Tejun Heo <tj@kernel.org>, Ming Lei <ming.lei@redhat.com>,
Jianchao Wang <jianchao.w.wang@oracle.com>,
Hannes Reinecke <hare@suse.com>,
Johannes Thumshirn <jthumshirn@suse.de>,
Alan Stern <stern@rowland.harvard.edu>
Subject: [PATCH v5 4/9] percpu-refcount: Introduce percpu_ref_is_in_use()
Date: Tue, 7 Aug 2018 15:51:28 -0700 [thread overview]
Message-ID: <20180807225133.27221-5-bart.vanassche@wdc.com> (raw)
In-Reply-To: <20180807225133.27221-1-bart.vanassche@wdc.com>
Introduce a function that allows to determine whether a per-cpu refcount
is in use. This function will be used in a later patch to determine
whether or not any block layer requests are being executed.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Jianchao Wang <jianchao.w.wang@oracle.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Alan Stern <stern@rowland.harvard.edu>
---
include/linux/percpu-refcount.h | 2 ++
lib/percpu-refcount.c | 40 +++++++++++++++++++++++++++++++++
2 files changed, 42 insertions(+)
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 009cdf3d65b6..dd247756d634 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -331,4 +331,6 @@ static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
return !atomic_long_read(&ref->count);
}
+bool percpu_ref_is_in_use(struct percpu_ref *ref);
+
#endif
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 9f96fa7bc000..1dcb47e2c561 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -369,3 +369,43 @@ void percpu_ref_reinit(struct percpu_ref *ref)
spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
}
EXPORT_SYMBOL_GPL(percpu_ref_reinit);
+
+/**
+ * percpu_ref_is_in_use - verify whether or not a percpu refcount is in use
+ * @ref: percpu_ref to test
+ *
+ * For a percpu refcount that is in percpu-mode, verify whether the reference
+ * count is above one. For a percpu refcount that is in atomic mode, verify
+ * whether the reference count is above zero. This function allows to verify
+ * whether any references are held on a percpu refcount that is switched
+ * between atomic and percpu mode with percpu_ref_reinit() /
+ * percpu_ref_kill().
+ *
+ * This function is safe to call as long as @ref is between init and exit. It
+ * is the responsibility of the caller to handle percpu_ref_get() and
+ * percpu_ref_put() calls that occur concurrently with this function.
+ */
+bool percpu_ref_is_in_use(struct percpu_ref *ref)
+{
+ unsigned long __percpu *percpu_count;
+ unsigned long sum = 0;
+ int cpu;
+ unsigned long flags;
+
+ /* Obtain percpu_ref_switch_lock to serialize against mode switches. */
+ spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+ rcu_read_lock_sched();
+ if (__ref_is_percpu(ref, &percpu_count)) {
+ for_each_possible_cpu(cpu)
+ sum += *per_cpu_ptr(percpu_count, cpu);
+ }
+ rcu_read_unlock_sched();
+ sum += atomic_long_read(&ref->count);
+ sum &= ~PERCPU_COUNT_BIAS;
+ sum += (ref->percpu_count_ptr & __PERCPU_REF_DEAD);
+ spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+
+ WARN_ON_ONCE(sum == 0);
+ return sum > 1;
+}
+EXPORT_SYMBOL_GPL(percpu_ref_is_in_use);
--
2.18.0
next prev parent reply other threads:[~2018-08-07 22:51 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-07 22:51 [PATCH v5 0/9] blk-mq: Implement runtime power management Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 1/9] block: Change the preempt-only flag into a counter Bart Van Assche
2018-08-08 8:21 ` Ming Lei
2018-08-08 15:27 ` Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 2/9] block: Move power management code into a new source file Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 3/9] block, scsi: Introduce blk_pm_runtime_exit() Bart Van Assche
2018-08-07 22:51 ` Bart Van Assche [this message]
2018-08-08 15:23 ` [PATCH v5 4/9] percpu-refcount: Introduce percpu_ref_is_in_use() Tejun Heo
2018-08-09 14:32 ` Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 5/9] block: Change the runtime power management approach (1/2) Bart Van Assche
2018-08-08 6:11 ` jianchao.wang
2018-08-08 6:43 ` jianchao.wang
2018-08-08 17:28 ` Bart Van Assche
2018-08-09 2:52 ` Ming Lei
2018-08-09 17:12 ` Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 6/9] block: Change the runtime power management approach (2/2) Bart Van Assche
2018-08-08 8:50 ` Ming Lei
2018-08-08 17:32 ` Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 7/9] block: Remove blk_pm_requeue_request() Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 8/9] blk-mq: Insert a blk_pm_put_request() call Bart Van Assche
2018-08-07 22:51 ` [PATCH v5 9/9] blk-mq: Enable support for runtime power management Bart Van Assche
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180807225133.27221-5-bart.vanassche@wdc.com \
--to=bart.vanassche@wdc.com \
--cc=axboe@kernel.dk \
--cc=hare@suse.com \
--cc=hch@lst.de \
--cc=jianchao.w.wang@oracle.com \
--cc=jthumshirn@suse.de \
--cc=linux-block@vger.kernel.org \
--cc=ming.lei@redhat.com \
--cc=stern@rowland.harvard.edu \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox