From: Jakub Kicinski <kuba@kernel.org>
To: netdev@vger.kernel.org, davem@davemloft.net, edumazet@google.com,
pabeni@redhat.com
Cc: alexanderduyck@fb.com, roman.gushchin@linux.dev,
Jakub Kicinski <kuba@kernel.org>
Subject: [RFC net-next 1/3] net: provide macros for commonly copied lockless queue stop/wake code
Date: Fri, 10 Mar 2023 21:01:28 -0800 [thread overview]
Message-ID: <20230311050130.115138-1-kuba@kernel.org> (raw)
A lot of drivers follow the same scheme to stop / start queues
without introducing locks between xmit and NAPI tx completions.
I'm guessing they all copy'n'paste each other's code.
Smaller drivers shy away from the scheme and introduce a lock
which may cause deadlocks in netpoll.
Provide macros which encapsulate the necessary logic.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
include/net/netdev_queues.h | 166 ++++++++++++++++++++++++++++++++++++
1 file changed, 166 insertions(+)
create mode 100644 include/net/netdev_queues.h
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
new file mode 100644
index 000000000000..2a857faf28d8
--- /dev/null
+++ b/include/net/netdev_queues.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NET_QUEUES_H
+#define _LINUX_NET_QUEUES_H
+
+#include <linux/netdevice.h>
+
+/* Lockless queue stopping / waking helpers.
+ *
+ * These macroes are designed to safely implement stopping and waking
+ * netdev queues without any lock protection. We assume that there can
+ * be no concurrent stop attempts and no concurrent wake attempts.
+ * This is usually true as stop attempts happen from the xmit handler,
+ * while wake up is triggered from NAPI poll context. The two may run
+ * concurrently but are each protected by a lock (SPSC of sorts).
+ *
+ * All descriptor ring indexes (and other relevant shared state) must
+ * be updated before invoking the macros.
+ */
+
+#define netif_tx_queue_try_stop(txq, get_desc, start_thrs) \
+ ({ \
+ int _res; \
+ \
+ netif_tx_stop_queue(txq); \
+ \
+ smp_mb(); \
+ \
+ /* We need to check again in a case another \
+ * CPU has just made room available. \
+ */ \
+ if (likely(get_desc < start_thrs)) { \
+ _res = 0; \
+ } else { \
+ netif_tx_wake_queue(txq); \
+ _res = -1; \
+ } \
+ _res; \
+ }) \
+
+/**
+ * netif_tx_queue_maybe_stop() - locklessly stop a Tx queue, if needed
+ * @txq: struct netdev_queue to stop/start
+ * @get_desc: get current number of free descriptors (see requirements below!)
+ * @stop_thrs: minimal number of available descriptors for queue to be left
+ * enabled
+ * @start_thrs: minimal number of descriptors to re-enable the queue, can be
+ * equal to @stop_thrs or higher to avoid frequent waking
+ *
+ * All arguments may be evaluated multiple times, beware of side effects.
+ * @get_desc must be a formula or a function call, it must always
+ * return up-to-date information when evaluated!
+ *
+ * Returns:
+ * 0 if the queue was stopped
+ * 1 if the queue was left enabled
+ * -1 if the queue was re-enabled (raced with waking)
+ */
+#define netif_tx_queue_maybe_stop(txq, get_desc, stop_thrs, start_thrs) \
+ ({ \
+ int _res; \
+ \
+ if (likely(get_desc > stop_thrs)) \
+ _res = 1; \
+ else \
+ _res = netif_tx_queue_try_stop(txq, get_desc, \
+ start_thrs); \
+ _res; \
+ }) \
+
+#define __netif_tx_queue_try_wake(txq, get_desc, start_thrs, down_cond) \
+ ({ \
+ int _res; \
+ \
+ /* Make sure that anybody stopping the queue after \
+ * this sees the new next_to_clean. \
+ */ \
+ smp_mb(); \
+ if (netif_tx_queue_stopped(txq) && !(down_cond)) { \
+ netif_tx_wake_queue(txq); \
+ _res = 0; \
+ } else { \
+ _res = 1; \
+ } \
+ _res; \
+ })
+
+#define netif_tx_queue_try_wake(txq, get_desc, start_thrs) \
+ __netif_tx_queue_try_wake(txq, get_desc, start_thrs, false)
+
+/**
+ * __netif_tx_queue_maybe_wake() - locklessly wake a Tx queue, if needed
+ * @txq: struct netdev_queue to stop/start
+ * @get_desc: get current number of free descriptors (see requirements below!)
+ * @start_thrs: minimal number of descriptors to re-enable the queue
+ * @down_cond: down condition, perdicate indicating that the queue should
+ * not be woken up even if descriptors are available
+ *
+ * All arguments may be evaluated multiple times.
+ * @get_desc must be a formula or a function call, it must always
+ * return up-to-date information when evaluated!
+ *
+ * Returns:
+ * 0 if the queue was woken up
+ * 1 if the queue was already enabled (or disabled but @down_cond is true)
+ * -1 if the queue was left stopped
+ */
+#define __netif_tx_queue_maybe_wake(txq, get_desc, start_thrs, down_cond) \
+ ({ \
+ int _res; \
+ \
+ if (likely(get_desc < start_thrs)) \
+ _res = -1; \
+ else \
+ _res = __netif_tx_queue_try_wake(txq, get_desc, \
+ start_thrs, \
+ down_cond); \
+ _res; \
+ })
+
+#define netif_tx_queue_maybe_wake(txq, get_desc, start_thrs) \
+ __netif_tx_queue_maybe_wake(txq, get_desc, start_thrs, false)
+
+/* subqueue variants follow */
+
+#define netif_subqueue_try_stop(dev, idx, get_desc, start_thrs) \
+ ({ \
+ struct netdev_queue *txq; \
+ \
+ txq = netdev_get_tx_queue(dev, idx); \
+ netif_tx_queue_try_stop(txq, get_desc, start_thrs); \
+ })
+
+#define netif_subqueue_maybe_stop(dev, idx, get_desc, stop_thrs, start_thrs) \
+ ({ \
+ struct netdev_queue *txq; \
+ \
+ txq = netdev_get_tx_queue(dev, idx); \
+ netif_tx_queue_maybe_stop(txq, get_desc, \
+ stop_thrs, start_thrs); \
+ })
+
+#define __netif_subqueue_try_wake(dev, idx, get_desc, start_thrs, down_cond) \
+ ({ \
+ struct netdev_queue *txq; \
+ \
+ txq = netdev_get_tx_queue(dev, idx); \
+ __netif_tx_queue_try_wake(txq, get_desc, \
+ start_thrs, down_cond); \
+ })
+
+#define netif_subqueue_try_wake(dev, idx, get_desc, start_thrs) \
+ __netif_subqueue_try_wake(dev, idx, get_desc, start_thrs, false)
+
+#define __netif_subqueue_maybe_wake(dev, idx, get_desc, start_thrs, down_cond) \
+ ({ \
+ struct netdev_queue *txq; \
+ \
+ txq = netdev_get_tx_queue(dev, idx); \
+ __netif_tx_queue_maybe_wake(txq, get_desc, \
+ start_thrs, down_cond); \
+ })
+
+#define netif_subqueue_maybe_wake(dev, idx, get_desc, start_thrs) \
+ __netif_subqueue_maybe_wake(dev, idx, get_desc, start_thrs, false)
+
+#endif
--
2.39.2
next reply other threads:[~2023-03-11 5:01 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-11 5:01 Jakub Kicinski [this message]
2023-03-11 5:01 ` [RFC net-next 2/3] ixgbe: use new queue try_stop/try_wake macros Jakub Kicinski
2023-03-11 5:01 ` [RFC net-next 3/3] bnxt: " Jakub Kicinski
2023-03-11 16:28 ` [RFC net-next 1/3] net: provide macros for commonly copied lockless queue stop/wake code Stephen Hemminger
2023-03-13 1:37 ` Willem de Bruijn
2023-03-13 1:45 ` Stephen Hemminger
2023-03-13 20:56 ` Jakub Kicinski
2023-04-04 3:29 ` Herbert Xu
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=20230311050130.115138-1-kuba@kernel.org \
--to=kuba@kernel.org \
--cc=alexanderduyck@fb.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=roman.gushchin@linux.dev \
/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;
as well as URLs for NNTP newsgroup(s).