From 7c527c15cdda2e0a26a05ac15a44d3e14738fc55 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 3 Aug 2025 21:20:12 +0900 Subject: firewire: core: use reference counting to invoke address handlers safely The lifetime of address handler has been managed by linked list and RCU. This approach was introduced in commit 35202f7d8420 ("firewire: remove global lock around address handlers, convert to RCU"). The invocations of address handler are performed within RCU read-side critical sections. In commit 57e6d9f85fff ("firewire: ohci: use workqueue to handle events of AR request/response contexts"), the invocations are in a workqueue context. The approach still imposes limitation that sleeping is not allowed within RCU read-side critical sections. However, since sleeping is not permitted within RCU read-side critical sections, this approach still has a limitation. This commit adds reference counting to decouple handler invocation from handler discovery. The linked list and RCU is used to discover the handlers, while the reference counting is used to invoke them safely. Link: https://lore.kernel.org/r/20250803122015.236493-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- include/linux/firewire.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index cceb70415ed2..d38c6e538e5c 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -341,7 +341,11 @@ struct fw_address_handler { u64 length; fw_address_callback_t address_callback; void *callback_data; + + // Only for core functions. struct list_head link; + struct kref kref; + struct completion done; }; struct fw_address_region { -- cgit v1.2.3 From ccba9f6baa900e31ad1a4c36e6f3c176694f9eac Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Aug 2025 17:12:04 -0700 Subject: net: update NAPI threaded config even for disabled NAPIs We have to make sure that all future NAPIs will have the right threaded state when the state is configured on the device level. We chose not to have an "unset" state for threaded, and not to wipe the NAPI config clean when channels are explicitly disabled. This means the persistent config structs "exist" even when their NAPIs are not instantiated. Differently put - the NAPI persistent state lives in the net_device (ncfg == struct napi_config): ,--- [napi 0] - [napi 1] [dev] | | `--- [ncfg 0] - [ncfg 1] so say we a device with 2 queues but only 1 enabled: ,--- [napi 0] [dev] | `--- [ncfg 0] - [ncfg 1] now we set the device to threaded=1: ,---------- [napi 0 (thr:1)] [dev(thr:1)] | `---------- [ncfg 0 (thr:1)] - [ncfg 1 (thr:?)] Since [ncfg 1] was not attached to a NAPI during configuration we skipped it. If we create a NAPI for it later it will have the old setting (presumably disabled). One could argue if this is right or not "in principle", but it's definitely not how things worked before per-NAPI config.. Fixes: 2677010e7793 ("Add support to set NAPI threaded for individual NAPI") Signed-off-by: Jakub Kicinski Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250809001205.1147153-3-kuba@kernel.org Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e5de4b0a433..f3a3b761abfb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2071,6 +2071,8 @@ enum netdev_reg_state { * @max_pacing_offload_horizon: max EDT offload horizon in nsec. * @napi_config: An array of napi_config structures containing per-NAPI * settings. + * @num_napi_configs: number of allocated NAPI config structs, + * always >= max(num_rx_queues, num_tx_queues). * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. @@ -2482,8 +2484,9 @@ struct net_device { u64 max_pacing_offload_horizon; struct napi_config *napi_config; - unsigned long gro_flush_timeout; + u32 num_napi_configs; u32 napi_defer_hard_irqs; + unsigned long gro_flush_timeout; /** * @up: copy of @state's IFF_UP, but safe to read with just @lock. -- cgit v1.2.3 From 21924af67d69d7c9fdaf845be69043cfe75196a1 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 5 Aug 2025 00:10:02 +0000 Subject: locking: Fix __clear_task_blocked_on() warning from __ww_mutex_wound() path The __clear_task_blocked_on() helper added a number of sanity checks ensuring we hold the mutex wait lock and that the task we are clearing blocked_on pointer (if set) matches the mutex. However, there is an edge case in the _ww_mutex_wound() logic where we need to clear the blocked_on pointer for the task that owns the mutex, not the task that is waiting on the mutex. For this case the sanity checks aren't valid, so handle this by allowing a NULL lock to skip the additional checks. K Prateek Nayak and Maarten Lankhorst also pointed out that in this case where we don't hold the owner's mutex wait_lock, we need to be a bit more careful using READ_ONCE/WRITE_ONCE in both the __clear_task_blocked_on() and __set_task_blocked_on() implementations to avoid accidentally tripping WARN_ONs if two instances race. So do that here as well. This issue was easier to miss, I realized, as the test-ww_mutex driver only exercises the wait-die class of ww_mutexes. I've sent a patch[1] to address this so the logic will be easier to test. [1]: https://lore.kernel.org/lkml/20250801023358.562525-2-jstultz@google.com/ Fixes: a4f0b6fef4b0 ("locking/mutex: Add p->blocked_on wrappers for correctness checks") Closes: https://lore.kernel.org/lkml/68894443.a00a0220.26d0e1.0015.GAE@google.com/ Reported-by: syzbot+602c4720aed62576cd79@syzkaller.appspotmail.com Reported-by: Maarten Lankhorst Signed-off-by: John Stultz Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: K Prateek Nayak Acked-by: Maarten Lankhorst Tested-by: K Prateek Nayak Link: https://lore.kernel.org/r/20250805001026.2247040-1-jstultz@google.com --- include/linux/sched.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 40d2fa90df42..62103dd6a48e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2144,6 +2144,8 @@ static inline struct mutex *__get_task_blocked_on(struct task_struct *p) static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + WARN_ON_ONCE(!m); /* The task should only be setting itself as blocked */ WARN_ON_ONCE(p != current); @@ -2154,8 +2156,8 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) * with a different mutex. Note, setting it to the same * lock repeatedly is ok. */ - WARN_ON_ONCE(p->blocked_on && p->blocked_on != m); - p->blocked_on = m; + WARN_ON_ONCE(blocked_on && blocked_on != m); + WRITE_ONCE(p->blocked_on, m); } static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) @@ -2166,16 +2168,19 @@ static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m) { - WARN_ON_ONCE(!m); - /* Currently we serialize blocked_on under the mutex::wait_lock */ - lockdep_assert_held_once(&m->wait_lock); - /* - * There may be cases where we re-clear already cleared - * blocked_on relationships, but make sure we are not - * clearing the relationship with a different lock. - */ - WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m); - p->blocked_on = NULL; + if (m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + + /* Currently we serialize blocked_on under the mutex::wait_lock */ + lockdep_assert_held_once(&m->wait_lock); + /* + * There may be cases where we re-clear already cleared + * blocked_on relationships, but make sure we are not + * clearing the relationship with a different lock. + */ + WARN_ON_ONCE(blocked_on && blocked_on != m); + } + WRITE_ONCE(p->blocked_on, NULL); } static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m) -- cgit v1.2.3