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, 95 insertions, 0 deletions

diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
new file mode 100644
index 000000000..bdd8836dc
--- /dev/null
+++ b/arch/arm/lib/putuser.S
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/arch/arm/lib/putuser.S
+ *
+ *  Copyright (C) 2001 Russell King
+ *
+ *  Idea from x86 version, (C) Copyright 1998 Linus Torvalds
+ *
+ * These functions have a non-standard call interface to make
+ * them more efficient, especially as they return an error
+ * value in addition to the "real" return value.
+ *
+ * __put_user_X
+ *
+ * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
+ *		r2, r3 contains the value
+ * Outputs:	r0 is the error code
+ *		lr corrupted
+ *
+ * No other registers must be altered.  (see <asm/uaccess.h>
+ * for specific ASM register usage).
+ *
+ * Note that ADDR_LIMIT is either 0 or 0xc0000000
+ * Note also that it is intended that __put_user_bad is not global.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+#include <asm/domain.h>
+
+ENTRY(__put_user_1)
+	check_uaccess r0, 1, r1, ip, __put_user_bad
+1: TUSER(strb)	r2, [r0]
+	mov	r0, #0
+	ret	lr
+ENDPROC(__put_user_1)
+
+ENTRY(__put_user_2)
+	check_uaccess r0, 2, r1, ip, __put_user_bad
+#if __LINUX_ARM_ARCH__ >= 6
+
+2: TUSER(strh)	r2, [r0]
+
+#else
+
+	mov	ip, r2, lsr #8
+#ifndef __ARMEB__
+2: TUSER(strb)	r2, [r0], #1
+3: TUSER(strb)	ip, [r0]
+#else
+2: TUSER(strb)	ip, [r0], #1
+3: TUSER(strb)	r2, [r0]
+#endif
+
+#endif /* __LINUX_ARM_ARCH__ >= 6 */
+	mov	r0, #0
+	ret	lr
+ENDPROC(__put_user_2)
+
+ENTRY(__put_user_4)
+	check_uaccess r0, 4, r1, ip, __put_user_bad
+4: TUSER(str)	r2, [r0]
+	mov	r0, #0
+	ret	lr
+ENDPROC(__put_user_4)
+
+ENTRY(__put_user_8)
+	check_uaccess r0, 8, r1, ip, __put_user_bad
+#ifdef CONFIG_THUMB2_KERNEL
+5: TUSER(str)	r2, [r0]
+6: TUSER(str)	r3, [r0, #4]
+#else
+5: TUSER(str)	r2, [r0], #4
+6: TUSER(str)	r3, [r0]
+#endif
+	mov	r0, #0
+	ret	lr
+ENDPROC(__put_user_8)
+
+__put_user_bad:
+	mov	r0, #-EFAULT
+	ret	lr
+ENDPROC(__put_user_bad)
+
+.pushsection __ex_table, "a"
+	.long	1b, __put_user_bad
+	.long	2b, __put_user_bad
+#if __LINUX_ARM_ARCH__ < 6
+	.long	3b, __put_user_bad
+#endif
+	.long	4b, __put_user_bad
+	.long	5b, __put_user_bad
+	.long	6b, __put_user_bad
+.popsection