Merge branches 'expcb.2026.07.24a', 'misc.2026.07.30a', 'rcu-tasks.2026.07.30a', 'srcu.2026.08.11a' and 'torture.2026.08.14a' into HEADgrafted

Changes:

Make expedited grace periods expedite normal RCU callbacks

Miscellaneous fixes:
 * Improve diagnostic output with character task states.
 * Mark accesses to inform KCSAN of concurrency design.
 * Move from kmalloc() to kmalloc_obj().
 * Documentation updates.
 * Improve handling of RCU deferred quiescent states.
 * Clean up unused function arguments and structure fields.
 * Reduce show_rcu_gp_kthreads() stack space.

Tasks RCU updates:
 * Clean up after SRCU re-implementation of Tasks Trace RCU.
 * Mark accesses to inform KCSAN of concurrency design.
 * Add ->lazy_timer status to diagnostic output.
 * Remove an unnecessary memory barrier.
 * Fix a data race, courtesy of KCSAN.
 * Documentation updates.
 * Convert cond_resched_tasks_rcu_qs() from macro to static inline
   function.

SRCU updates:
 * Add Rust helpers for SRCU.
 * Avoid losing queued work at cleanup_srcu_struct() time.

Torture-test updates:
 * Preparation work for immediate RCU priority deboosting.
 * Test RCU readers from real interrupt handlers (as opposed to softirq).
 * Simplify code through use of cpumask_next_wrap().
 * Improve diagnostic output with character task states.
 * Add rcutorture.nwriters parameter to allow lightweight stall testing,
   and rcutorture.stall_only to make doing so easier.
 * Test an RCU Tasks Trace grace period implying an RCU grace period.
 * Make RCU Tasks Trace torturing track reader batches.
 * Fix a data race, courtesy of KCSAN.
 * Plug a shuffle_tmp_mask memory leak on kthread spawn failure.

1 files changed, 152 insertions, 0 deletions

diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
new file mode 100644
index 000000000..bf47cca2c
--- /dev/null
+++ b/include/asm-generic/qspinlock.h
@@ -0,0 +1,152 @@
+/* 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 <waiman.long@hpe.com>
+ */
+#ifndef __ASM_GENERIC_QSPINLOCK_H
+#define __ASM_GENERIC_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+#include <linux/atomic.h>
+
+#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_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	/*
+	 * unlock() needs release semantics:
+	 */
+	smp_store_release(&lock->locked, 0);
+}
+#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 */