[PATCH net-next 08/24] net: softnet_data: Make xmit.recursion per task.

[Sebastian Andrzej Siewior]

Softirq is preemptible on PREEMPT_RT. Without a per-CPU lock in
local_bh_disable() there is no guarantee that only one device is
transmitting at a time.
With preemption and multiple senders it is possible that the per-CPU
recursion counter gets incremented by different threads and exceeds
XMIT_RECURSION_LIMIT leading to a false positive recursion alert.

Instead of adding a lock to protect the per-CPU variable it is simpler
to make the counter per-task. Sending and receiving skbs happens always
in thread context anyway.

Having a lock to protected the per-CPU counter would block/ serialize two
sending threads needlessly. It would also require a recursive lock to
ensure that the owner can increment the counter further.

Make the recursion counter a task_struct member on PREEMPT_RT.

Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
 include/linux/netdevice.h | 30 +++++++++++++++++++++++++++++-
 include/linux/sched.h     |  4 +++-
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2564e209465ea..06436695c3679 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3260,7 +3260,9 @@ struct softnet_data {
 #endif
 	/* written and read only by owning cpu: */
 	struct {
+#ifndef CONFIG_PREEMPT_RT
 		u16 recursion;
+#endif
 		u8  more;
 #ifdef CONFIG_NET_EGRESS
 		u8  skip_txqueue;
@@ -3308,12 +3310,36 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd,
 
 DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
+#define XMIT_RECURSION_LIMIT	8
+#ifdef CONFIG_PREEMPT_RT
+
+static inline int dev_recursion_level(void)
+{
+	return current->net_xmit_recursion;
+}
+
+static inline bool dev_xmit_recursion(void)
+{
+	return unlikely(current->net_xmit_recursion > XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+	current->net_xmit_recursion++;
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+	current->net_xmit_recursion--;
+}
+
+#else
+
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
 
-#define XMIT_RECURSION_LIMIT	8
 static inline bool dev_xmit_recursion(void)
 {
 	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
@@ -3330,6 +3356,8 @@ static inline void dev_xmit_recursion_dec(void)
 	__this_cpu_dec(softnet_data.xmit.recursion);
 }
 
+#endif
+
 void __netif_schedule(struct Qdisc *q);
 void netif_schedule_queue(struct netdev_queue *txq);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c316972485..26b1b7d674b5d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -964,7 +964,9 @@ struct task_struct {
 	/* delay due to memory thrashing */
 	unsigned                        in_thrashing:1;
 #endif
-
+#ifdef CONFIG_PREEMPT_RT
+	u8				net_xmit_recursion;
+#endif
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
 	struct restart_block		restart_block;
-- 
2.43.0