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, 67 insertions, 0 deletions

diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
new file mode 100644
index 000000000..33b08ca1c
--- /dev/null
+++ b/arch/arm/lib/delay-loop.S
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/arch/arm/lib/delay.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ */
+#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <asm/assembler.h>
+#include <asm/delay.h>
+
+#ifdef CONFIG_ARCH_RPC
+		.arch	armv4
+#endif
+
+		.text
+
+.LC0:		.word	loops_per_jiffy
+.LC1:		.word	UDELAY_MULT
+
+/*
+ * loops = r0 * HZ * loops_per_jiffy / 1000000
+ *
+ * r0  <= 2000
+ * HZ  <= 1000
+ */
+
+SYM_TYPED_FUNC_START(__loop_udelay)
+		ldr	r2, .LC1
+		mul	r0, r2, r0		@ r0 = delay_us * UDELAY_MULT
+		b	__loop_const_udelay
+SYM_FUNC_END(__loop_udelay)
+
+SYM_TYPED_FUNC_START(__loop_const_udelay)	@ 0 <= r0 <= 0xfffffaf0
+		ldr	r2, .LC0
+		ldr	r2, [r2]
+		umull	r1, r0, r2, r0		@ r0-r1 = r0 * loops_per_jiffy
+		adds	r1, r1, #0xffffffff	@ rounding up ...
+		adcs	r0, r0, r0		@ and right shift by 31
+		reteq	lr
+		b	__loop_delay
+SYM_FUNC_END(__loop_const_udelay)
+
+		.align 3
+
+@ Delay routine
+SYM_TYPED_FUNC_START(__loop_delay)
+		subs	r0, r0, #1
+#if 0
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+		retls	lr
+		subs	r0, r0, #1
+#endif
+		bhi	__loop_delay
+		ret	lr
+SYM_FUNC_END(__loop_delay)