From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- include/asm-generic/qspinlock.h | 184 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 184 insertions(+) create mode 100644 include/asm-generic/qspinlock.h (limited to 'include/asm-generic/qspinlock.h') diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h new file mode 100644 index 000000000..2ca94e418 --- /dev/null +++ b/include/asm-generic/qspinlock.h @@ -0,0 +1,184 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Queued spinlock + * + * A 'generic' spinlock implementation that is based on MCS locks. For an + * architecture that's looking for a 'generic' spinlock, please first consider + * ticket-lock.h and only come looking here when you've considered all the + * constraints below and can show your hardware does actually perform better + * with qspinlock. + * + * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no + * weaker than RCtso if you're power), where regular code only expects atomic_t + * to be RCpc. + * + * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set + * of atomic operations to behave well together, please audit them carefully to + * ensure they all have forward progress. Many atomic operations may default to + * cmpxchg() loops which will not have good forward progress properties on + * LL/SC architectures. + * + * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) + * do. Carefully read the patches that introduced + * queued_fetch_set_pending_acquire(). + * + * qspinlock also heavily relies on mixed size atomic operations, in specific + * it requires architectures to have xchg16; something which many LL/SC + * architectures need to implement as a 32bit and+or in order to satisfy the + * forward progress guarantees mentioned above. + * + * Further reading on mixed size atomics that might be relevant: + * + * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf + * + * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. + * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP + * + * Authors: Waiman Long + */ +#ifndef __ASM_GENERIC_QSPINLOCK_H +#define __ASM_GENERIC_QSPINLOCK_H + +#include +#include +#include + +#ifndef queued_spin_is_locked +/** + * queued_spin_is_locked - is the spinlock locked? + * @lock: Pointer to queued spinlock structure + * Return: 1 if it is locked, 0 otherwise + */ +static __always_inline int queued_spin_is_locked(struct qspinlock *lock) +{ + /* + * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL + * isn't immediately observable. + */ + return atomic_read(&lock->val); +} +#endif + +/** + * queued_spin_value_unlocked - is the spinlock structure unlocked? + * @lock: queued spinlock structure + * Return: 1 if it is unlocked, 0 otherwise + * + * N.B. Whenever there are tasks waiting for the lock, it is considered + * locked wrt the lockref code to avoid lock stealing by the lockref + * code and change things underneath the lock. This also allows some + * optimizations to be applied without conflict with lockref. + */ +static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) +{ + return !lock.val.counter; +} + +/** + * queued_spin_is_contended - check if the lock is contended + * @lock : Pointer to queued spinlock structure + * Return: 1 if lock contended, 0 otherwise + */ +static __always_inline int queued_spin_is_contended(struct qspinlock *lock) +{ + return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; +} +/** + * queued_spin_trylock - try to acquire the queued spinlock + * @lock : Pointer to queued spinlock structure + * Return: 1 if lock acquired, 0 if failed + */ +static __always_inline int queued_spin_trylock(struct qspinlock *lock) +{ + int val = atomic_read(&lock->val); + + if (unlikely(val)) + return 0; + + return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); +} + +extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); + +#ifndef queued_spin_lock +/** + * queued_spin_lock - acquire a queued spinlock + * @lock: Pointer to queued spinlock structure + */ +static __always_inline void queued_spin_lock(struct qspinlock *lock) +{ + int val = 0; + + if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) + return; + + queued_spin_lock_slowpath(lock, val); +} +#endif + +#ifndef queued_spin_release +/** + * queued_spin_release - release a queued spinlock + * @lock : Pointer to queued spinlock structure + */ +static __always_inline void queued_spin_release(struct qspinlock *lock) +{ + /* + * unlock() needs release semantics: + */ + smp_store_release(&lock->locked, 0); +} +#endif + +#ifndef queued_spin_unlock + +DECLARE_TRACEPOINT(contended_release); + +extern void queued_spin_release_traced(struct qspinlock *lock); + +/** + * queued_spin_unlock - unlock a queued spinlock + * @lock : Pointer to queued spinlock structure + * + * Generic tracing wrapper around the arch-overridable + * queued_spin_release(). + */ +static __always_inline void queued_spin_unlock(struct qspinlock *lock) +{ + /* + * Trace and release are combined in queued_spin_release_traced() so + * the compiler does not need to preserve the lock pointer across the + * function call, avoiding callee-saved register save/restore on the + * hot path. queued_spin_release() is therefore called both here and in + * queued_spin_release_traced(). Keep the two in sync. + */ + if (IS_ENABLED(CONFIG_QUEUED_SPINLOCKS_TRACE_CONTENDED_RELEASE) && + tracepoint_enabled(contended_release)) { + queued_spin_release_traced(lock); + return; + } + queued_spin_release(lock); +} +#endif + +#ifndef virt_spin_lock +static __always_inline bool virt_spin_lock(struct qspinlock *lock) +{ + return false; +} +#endif + +#ifndef __no_arch_spinlock_redefine +/* + * Remapping spinlock architecture specific functions to the corresponding + * queued spinlock functions. + */ +#define arch_spin_is_locked(l) queued_spin_is_locked(l) +#define arch_spin_is_contended(l) queued_spin_is_contended(l) +#define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) +#define arch_spin_lock(l) queued_spin_lock(l) +#define arch_spin_trylock(l) queued_spin_trylock(l) +#define arch_spin_unlock(l) queued_spin_unlock(l) +#endif + +#endif /* __ASM_GENERIC_QSPINLOCK_H */ -- cgit v1.3.1