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, 107 insertions, 0 deletions

diff --git a/include/asm-generic/local64.h b/include/asm-generic/local64.h
new file mode 100644
index 000000000..14963a7a6
--- /dev/null
+++ b/include/asm-generic/local64.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_LOCAL64_H
+#define _ASM_GENERIC_LOCAL64_H
+
+#include <linux/percpu.h>
+#include <asm/types.h>
+
+/*
+ * A signed long type for operations which are atomic for a single CPU.
+ * Usually used in combination with per-cpu variables.
+ *
+ * This is the default implementation, which uses atomic64_t.  Which is
+ * rather pointless.  The whole point behind local64_t is that some processors
+ * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs
+ * running on this CPU.  local64_t allows exploitation of such capabilities.
+ */
+
+/* Implement in terms of atomics. */
+
+#if BITS_PER_LONG == 64
+
+#include <asm/local.h>
+
+typedef struct {
+	local_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i)	{ LOCAL_INIT(i) }
+
+#define local64_read(l)		local_read(&(l)->a)
+#define local64_set(l,i)	local_set((&(l)->a),(i))
+#define local64_inc(l)		local_inc(&(l)->a)
+#define local64_dec(l)		local_dec(&(l)->a)
+#define local64_add(i,l)	local_add((i),(&(l)->a))
+#define local64_sub(i,l)	local_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) local_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) local_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) local_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) local_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) local_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)	local_inc_return(&(l)->a)
+
+static inline s64 local64_cmpxchg(local64_t *l, s64 old, s64 new)
+{
+	return local_cmpxchg(&l->a, old, new);
+}
+
+static inline bool local64_try_cmpxchg(local64_t *l, s64 *old, s64 new)
+{
+	return local_try_cmpxchg(&l->a, (long *)old, new);
+}
+
+#define local64_xchg(l, n)	local_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l)	local_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)	local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)	local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)	local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)	local64_set((l), local64_read(l) - (i))
+
+#else /* BITS_PER_LONG != 64 */
+
+#include <linux/atomic.h>
+
+/* Don't use typedef: don't want them to be mixed with atomic_t's. */
+typedef struct {
+	atomic64_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local64_read(l)		atomic64_read(&(l)->a)
+#define local64_set(l,i)	atomic64_set((&(l)->a),(i))
+#define local64_inc(l)		atomic64_inc(&(l)->a)
+#define local64_dec(l)		atomic64_dec(&(l)->a)
+#define local64_add(i,l)	atomic64_add((i),(&(l)->a))
+#define local64_sub(i,l)	atomic64_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)	atomic64_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n))
+#define local64_try_cmpxchg(l, po, n) atomic64_try_cmpxchg((&(l)->a), (po), (n))
+#define local64_xchg(l, n)	atomic64_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l)	atomic64_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)	local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)	local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)	local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)	local64_set((l), local64_read(l) - (i))
+
+#endif /* BITS_PER_LONG != 64 */
+
+#endif /* _ASM_GENERIC_LOCAL64_H */