From ecefbc09e8ee768ae85b7bb7a1de8c8287397d68 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 20 Jun 2024 15:21:58 +0200 Subject: net: softnet_data: Make xmit per task. 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. The `more' member is subject to similar problems if set by one thread for one driver and wrongly used by another driver within another thread. Instead of adding a lock to protect the per-CPU variable it is simpler to make xmit 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 softnet_data.xmit a task_struct member on PREEMPT_RT. Add needed wrapper. Cc: Ben Segall Cc: Daniel Bristot de Oliveira Cc: Dietmar Eggemann Cc: Juri Lelli Cc: Mel Gorman Cc: Steven Rostedt Cc: Valentin Schneider Cc: Vincent Guittot Signed-off-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20240620132727.660738-9-bigeasy@linutronix.de Signed-off-by: Jakub Kicinski --- net/core/dev.c | 14 ++++++++++++++ net/core/dev.h | 18 ++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 093d82bf0e28..95b9e4cc1767 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3940,6 +3940,7 @@ netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } +#ifndef CONFIG_PREEMPT_RT static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); @@ -3950,6 +3951,19 @@ void netdev_xmit_skip_txqueue(bool skip) __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); + +#else +static bool netdev_xmit_txqueue_skipped(void) +{ + return current->net_xmit.skip_txqueue; +} + +void netdev_xmit_skip_txqueue(bool skip) +{ + current->net_xmit.skip_txqueue = skip; +} +EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); +#endif #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_NET_XGRESS diff --git a/net/core/dev.h b/net/core/dev.h index 58f88d28bc99..5654325c5b71 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -150,6 +150,8 @@ struct napi_struct *napi_by_id(unsigned int napi_id); void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); #define XMIT_RECURSION_LIMIT 8 + +#ifndef CONFIG_PREEMPT_RT static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > @@ -165,6 +167,22 @@ static inline void dev_xmit_recursion_dec(void) { __this_cpu_dec(softnet_data.xmit.recursion); } +#else +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--; +} +#endif int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, -- cgit v1.2.3-70-g09d2