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, 110 insertions, 0 deletions

diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
new file mode 100644
index 000000000..b3cd09beb
--- /dev/null
+++ b/tools/perf/util/thread-stack.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * thread-stack.h: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ */
+
+#ifndef __PERF_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+struct thread;
+struct comm;
+struct ip_callchain;
+struct symbol;
+struct dso;
+struct perf_sample;
+struct addr_location;
+struct call_path;
+
+/*
+ * Call/Return flags.
+ *
+ * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
+ * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ * CALL_RETURN_NON_CALL: a branch but not a 'call' to the start of a different
+ *                       symbol
+ */
+enum {
+	CALL_RETURN_NO_CALL	= 1 << 0,
+	CALL_RETURN_NO_RETURN	= 1 << 1,
+	CALL_RETURN_NON_CALL	= 1 << 2,
+};
+
+/**
+ * struct call_return - paired call/return information.
+ * @thread: thread in which call/return occurred
+ * @comm: comm in which call/return occurred
+ * @cp: call path
+ * @call_time: timestamp of call (if known)
+ * @return_time: timestamp of return (if known)
+ * @branch_count: number of branches seen between call and return
+ * @insn_count: approx. number of instructions between call and return
+ * @cyc_count: approx. number of cycles between call and return
+ * @call_ref: external reference to 'call' sample (e.g. db_id)
+ * @return_ref:  external reference to 'return' sample (e.g. db_id)
+ * @db_id: id used for db-export
+ * @parent_db_id: id of parent call used for db-export
+ * @flags: Call/Return flags
+ */
+struct call_return {
+	struct thread *thread;
+	struct comm *comm;
+	struct call_path *cp;
+	u64 call_time;
+	u64 return_time;
+	u64 branch_count;
+	u64 insn_count;
+	u64 cyc_count;
+	u64 call_ref;
+	u64 return_ref;
+	u64 db_id;
+	u64 parent_db_id;
+	u32 flags;
+};
+
+/**
+ * struct call_return_processor - provides a call-back to consume call-return
+ *                                information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
+ */
+struct call_return_processor {
+	struct call_path_root *cpr;
+	int (*process)(struct call_return *cr, u64 *parent_db_id, void *data);
+	void *data;
+};
+
+int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
+			u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+			unsigned int br_stack_sz, bool mispred_all);
+void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
+			  size_t sz, u64 ip, u64 kernel_start);
+void thread_stack__sample_late(struct thread *thread, int cpu,
+			       struct ip_callchain *chain, size_t sz, u64 ip,
+			       u64 kernel_start);
+void thread_stack__br_sample(struct thread *thread, int cpu,
+			     struct branch_stack *dst, unsigned int sz);
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+				  struct branch_stack *dst, unsigned int sz,
+				  u64 sample_ip, u64 kernel_start);
+int thread_stack__flush(struct thread *thread);
+void thread_stack__free(struct thread *thread);
+size_t thread_stack__depth(struct thread *thread, int cpu);
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
+			   void *data);
+void call_return_processor__free(struct call_return_processor *crp);
+int thread_stack__process(struct thread *thread, struct comm *comm,
+			  struct perf_sample *sample,
+			  struct addr_location *from_al,
+			  struct addr_location *to_al, u64 ref,
+			  struct call_return_processor *crp);
+
+#endif