Resguardo inicial

linux-7.2.3/kernel/trace/Makefile

@@ -0,0 +1,166 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Do not instrument the tracer itself:
+
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
+
+ifdef CONFIG_FUNCTION_TRACER
+
+# Avoid recursion due to instrumentation.
+KCSAN_SANITIZE := n
+
+ifdef CONFIG_FTRACE_SELFTEST
+# selftest needs instrumentation
+CFLAGS_trace_selftest_dynamic.o = $(CC_FLAGS_FTRACE)
+obj-y += trace_selftest_dynamic.o
+endif
+endif
+
+# Allow some files to be function traced
+ifdef CONFIG_FUNCTION_SELF_TRACING
+CFLAGS_trace_output.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_seq.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_stat.o = $(CC_FLAGS_FTRACE)
+CFLAGS_tracing_map.o = $(CC_FLAGS_FTRACE)
+CFLAGS_synth_event_gen_test.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_events.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_syscalls.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_events_filter.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_events_trigger.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_events_synth.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_events_hist.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_events_user.o = $(CC_FLAGS_FTRACE)
+CFLAGS_trace_dynevent.o = $(CC_FLAGS_FTRACE)
+endif
+
+ifdef CONFIG_FTRACE_STARTUP_TEST
+CFLAGS_trace_kprobe_selftest.o = $(CC_FLAGS_FTRACE)
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe_selftest.o
+endif
+
+# If unlikely tracing is enabled, do not trace these files
+ifdef CONFIG_TRACING_BRANCHES
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+endif
+
+# for GCOV coverage profiling
+ifdef CONFIG_GCOV_PROFILE_FTRACE
+GCOV_PROFILE := y
+endif
+
+# Functions in these files can run from IRQ entry before hardirq context
+# is visible to KCOV, and produce coverage unrelated to syscall inputs.
+KCOV_INSTRUMENT_trace_preemptirq.o := n
+KCOV_INSTRUMENT_trace_irqsoff.o := n
+
+CFLAGS_bpf_trace.o := -I$(src)
+
+CFLAGS_trace_benchmark.o := -I$(src)
+CFLAGS_trace_events_filter.o := -I$(src)
+
+obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o
+
+obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
+obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
+obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
+
+obj-$(CONFIG_TRACING) += trace.o
+obj-$(CONFIG_TRACING) += trace_output.o
+obj-$(CONFIG_TRACING) += trace_seq.o
+obj-$(CONFIG_TRACING) += trace_stat.o
+obj-$(CONFIG_TRACING) += trace_printk.o
+obj-$(CONFIG_TRACING) += trace_pid.o
+obj-$(CONFIG_TRACER_SNAPSHOT) += trace_snapshot.o
+obj-$(CONFIG_TRACING) += 	pid_list.o
+obj-$(CONFIG_TRACING_MAP) += tracing_map.o
+obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o
+obj-$(CONFIG_SYNTH_EVENT_GEN_TEST) += synth_event_gen_test.o
+obj-$(CONFIG_KPROBE_EVENT_GEN_TEST) += kprobe_event_gen_test.o
+obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
+obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
+obj-$(CONFIG_PREEMPTIRQ_TRACEPOINTS) += trace_preemptirq.o
+obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
+obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
+obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_HWLAT_TRACER) += trace_hwlat.o
+obj-$(CONFIG_OSNOISE_TRACER) += trace_osnoise.o
+obj-$(CONFIG_NOP_TRACER) += trace_nop.o
+obj-$(CONFIG_STACK_TRACER) += trace_stack.o
+obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
+obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += fgraph.o
+ifeq ($(CONFIG_BLOCK),y)
+obj-$(CONFIG_EVENT_TRACING) += blktrace.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events.o
+obj-$(CONFIG_EVENT_TRACING) += trace_export.o
+obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
+ifeq ($(CONFIG_PERF_EVENTS),y)
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_EPROBE_EVENTS) += trace_eprobe.o
+obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o
+obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o
+obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
+obj-$(CONFIG_USER_EVENTS) += trace_events_user.o
+obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
+obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o
+obj-$(CONFIG_TRACEPOINTS) += power-traces.o
+ifeq ($(CONFIG_PM),y)
+obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
+endif
+ifeq ($(CONFIG_TRACING),y)
+obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
+endif
+obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o
+obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
+obj-$(CONFIG_PROBE_EVENTS_BTF_ARGS) += trace_btf.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
+obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o
+obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o
+obj-$(CONFIG_FPROBE) += fprobe.o
+obj-$(CONFIG_RETHOOK) += rethook.o
+obj-$(CONFIG_FPROBE_EVENTS) += trace_fprobe.o
+
+obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
+obj-$(CONFIG_RV) += rv/
+
+obj-$(CONFIG_TRACE_REMOTE) += trace_remote.o
+obj-$(CONFIG_SIMPLE_RING_BUFFER) += simple_ring_buffer.o
+obj-$(CONFIG_TRACE_REMOTE_TEST) += remote_test.o
+
+# simple_ring_buffer is used by the pKVM hypervisor which does not have access
+# to all kernel symbols. Fail the build if forbidden symbols are found.
+
+# Basic compiler and tooling-generated symbols that can safely be left
+# undefined. Ensure KASAN is enabled to avoid logic that may disable
+# FORTIFY_SOURCE when KASAN is not enabled. undefsyms_base.o does not
+# automatically get KASAN flags because it is not linked into vmlinux.
+targets += undefsyms_base.o
+KASAN_SANITIZE_undefsyms_base.o := y
+
+UNDEFINED_ALLOWLIST = __asan __gcov __kasan __kcsan __hwasan __sancov __sanitizer __tsan __ubsan __msan \
+		      __aeabi_unwind_cpp __s390_indirect_jump __x86_indirect_thunk simple_ring_buffer \
+		      $(shell $(NM) -u $(obj)/undefsyms_base.o 2>/dev/null | awk '{print $$2}')
+
+quiet_cmd_check_undefined = NM      $<
+      cmd_check_undefined = \
+          undefsyms=$$($(NM) -u $< | grep -v $(addprefix -e , $(UNDEFINED_ALLOWLIST)) || true); \
+          if [ -n "$$undefsyms" ]; then \
+              echo "Unexpected symbols in $<:" >&2; \
+              echo "$$undefsyms" >&2; \
+              false; \
+          fi; \
+          touch $@
+
+$(obj)/%.o.checked: $(obj)/%.o $(obj)/undefsyms_base.o FORCE
+	$(call if_changed,check_undefined)
+
+always-$(CONFIG_SIMPLE_RING_BUFFER) += simple_ring_buffer.o.checked
+
+libftrace-y := ftrace.o

linux-7.2.3/kernel/trace/bpf_trace.h

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_trace
+
+#if !defined(_TRACE_BPF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _TRACE_BPF_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(bpf_trace_printk,
+
+	TP_PROTO(const char *bpf_string),
+
+	TP_ARGS(bpf_string),
+
+	TP_STRUCT__entry(
+		__string(bpf_string, bpf_string)
+	),
+
+	TP_fast_assign(
+		__assign_str(bpf_string);
+	),
+
+	TP_printk("%s", __get_str(bpf_string))
+);
+
+#endif /* _TRACE_BPF_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE bpf_trace
+
+#include <trace/define_trace.h>

linux-7.2.3/kernel/trace/error_report-traces.c

@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Error reporting trace points.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/error_report.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(error_report_end);

linux-7.2.3/kernel/trace/ftrace_internal.h

@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KERNEL_FTRACE_INTERNAL_H
+#define  _LINUX_KERNEL_FTRACE_INTERNAL_H
+
+int __register_ftrace_function(struct ftrace_ops *ops);
+int __unregister_ftrace_function(struct ftrace_ops *ops);
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+extern struct mutex ftrace_lock;
+extern struct ftrace_ops global_ops;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+int ftrace_startup(struct ftrace_ops *ops, int command);
+int ftrace_shutdown(struct ftrace_ops *ops, int command);
+int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs);
+int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command);
+int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command);
+
+#else /* !CONFIG_DYNAMIC_FTRACE */
+
+/* Keep as macros so we do not need to define the commands */
+# define ftrace_startup(ops, command)					\
+	({								\
+		int ___ret = __register_ftrace_function(ops);		\
+		if (!___ret)						\
+			(ops)->flags |= FTRACE_OPS_FL_ENABLED;		\
+		___ret;							\
+	})
+# define ftrace_shutdown(ops, command)					\
+	({								\
+		int ___ret = __unregister_ftrace_function(ops);		\
+		if (!___ret)						\
+			(ops)->flags &= ~FTRACE_OPS_FL_ENABLED;		\
+		___ret;							\
+	})
+static inline int
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
+{
+	return 1;
+}
+static inline int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
+{
+	return -EINVAL;
+}
+static inline int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+extern int ftrace_graph_active;
+# ifdef CONFIG_DYNAMIC_FTRACE
+extern void fgraph_update_pid_func(void);
+# else
+static inline void fgraph_update_pid_func(void) {}
+# endif
+#else /* !CONFIG_FUNCTION_GRAPH_TRACER */
+# define ftrace_graph_active 0
+static inline void fgraph_update_pid_func(void) {}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#else /* !CONFIG_FUNCTION_TRACER */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#endif

linux-7.2.3/kernel/trace/kprobe_event_gen_test.c

@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test module for in-kernel kprobe event creation and generation.
+ *
+ * Copyright (C) 2019 Tom Zanussi <zanussi@kernel.org>
+ */
+
+#include <linux/module.h>
+#include <linux/trace_events.h>
+
+/*
+ * This module is a simple test of basic functionality for in-kernel
+ * kprobe/kretprobe event creation.  The first test uses
+ * kprobe_event_gen_cmd_start(), kprobe_event_add_fields() and
+ * kprobe_event_gen_cmd_end() to create a kprobe event, which is then
+ * enabled in order to generate trace output.  The second creates a
+ * kretprobe event using kretprobe_event_gen_cmd_start() and
+ * kretprobe_event_gen_cmd_end(), and is also then enabled.
+ *
+ * To test, select CONFIG_KPROBE_EVENT_GEN_TEST and build the module.
+ * Then:
+ *
+ * # insmod kernel/trace/kprobe_event_gen_test.ko
+ * # cat /sys/kernel/tracing/trace
+ *
+ * You should see many instances of the "gen_kprobe_test" and
+ * "gen_kretprobe_test" events in the trace buffer.
+ *
+ * To remove the events, remove the module:
+ *
+ * # rmmod kprobe_event_gen_test
+ *
+ */
+
+static struct trace_event_file *gen_kprobe_test;
+static struct trace_event_file *gen_kretprobe_test;
+
+#define KPROBE_GEN_TEST_FUNC	"do_sys_open"
+
+/* X86 */
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_32)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%ax"
+#define KPROBE_GEN_TEST_ARG1	"filename=%dx"
+#define KPROBE_GEN_TEST_ARG2	"flags=%cx"
+#define KPROBE_GEN_TEST_ARG3	"mode=+4($stack)"
+
+/* ARM64 */
+#elif defined(CONFIG_ARM64)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%x0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%x1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%x2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%x3"
+
+/* ARM */
+#elif defined(CONFIG_ARM)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%r0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%r1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%r2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%r3"
+
+/* RISCV */
+#elif defined(CONFIG_RISCV)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%a0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%a1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%a2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%a3"
+
+/* others */
+#else
+#define KPROBE_GEN_TEST_ARG0	NULL
+#define KPROBE_GEN_TEST_ARG1	NULL
+#define KPROBE_GEN_TEST_ARG2	NULL
+#define KPROBE_GEN_TEST_ARG3	NULL
+#endif
+
+static bool trace_event_file_is_valid(struct trace_event_file *input)
+{
+	return input && !IS_ERR(input);
+}
+
+/*
+ * Test to make sure we can create a kprobe event, then add more
+ * fields.
+ */
+static int __init test_gen_kprobe_cmd(void)
+{
+	struct dynevent_cmd cmd;
+	char *buf;
+	int ret;
+
+	/* Create a buffer to hold the generated command */
+	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Before generating the command, initialize the cmd object */
+	kprobe_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
+
+	/*
+	 * Define the gen_kprobe_test event with the first 2 kprobe
+	 * fields.
+	 */
+	ret = kprobe_event_gen_cmd_start(&cmd, "gen_kprobe_test",
+					 KPROBE_GEN_TEST_FUNC,
+					 KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1);
+	if (ret)
+		goto out;
+
+	/* Use kprobe_event_add_fields to add the rest of the fields */
+
+	ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3);
+	if (ret)
+		goto out;
+
+	/*
+	 * This actually creates the event.
+	 */
+	ret = kprobe_event_gen_cmd_end(&cmd);
+	if (ret)
+		goto out;
+
+	/*
+	 * Now get the gen_kprobe_test event file.  We need to prevent
+	 * the instance and event from disappearing from underneath
+	 * us, which trace_get_event_file() does (though in this case
+	 * we're using the top-level instance which never goes away).
+	 */
+	gen_kprobe_test = trace_get_event_file(NULL, "kprobes",
+					       "gen_kprobe_test");
+	if (IS_ERR(gen_kprobe_test)) {
+		ret = PTR_ERR(gen_kprobe_test);
+		goto delete;
+	}
+
+	/* Enable the event or you won't see anything */
+	ret = trace_array_set_clr_event(gen_kprobe_test->tr,
+					"kprobes", "gen_kprobe_test", true);
+	if (ret) {
+		trace_put_event_file(gen_kprobe_test);
+		goto delete;
+	}
+ out:
+	kfree(buf);
+	return ret;
+ delete:
+	if (trace_event_file_is_valid(gen_kprobe_test))
+		gen_kprobe_test = NULL;
+	/* We got an error after creating the event, delete it */
+	kprobe_event_delete("gen_kprobe_test");
+	goto out;
+}
+
+/*
+ * Test to make sure we can create a kretprobe event.
+ */
+static int __init test_gen_kretprobe_cmd(void)
+{
+	struct dynevent_cmd cmd;
+	char *buf;
+	int ret;
+
+	/* Create a buffer to hold the generated command */
+	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Before generating the command, initialize the cmd object */
+	kprobe_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
+
+	/*
+	 * Define the kretprobe event.
+	 */
+	ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test",
+					    KPROBE_GEN_TEST_FUNC,
+					    "$retval");
+	if (ret)
+		goto out;
+
+	/*
+	 * This actually creates the event.
+	 */
+	ret = kretprobe_event_gen_cmd_end(&cmd);
+	if (ret)
+		goto out;
+
+	/*
+	 * Now get the gen_kretprobe_test event file.  We need to
+	 * prevent the instance and event from disappearing from
+	 * underneath us, which trace_get_event_file() does (though in
+	 * this case we're using the top-level instance which never
+	 * goes away).
+	 */
+	gen_kretprobe_test = trace_get_event_file(NULL, "kprobes",
+						  "gen_kretprobe_test");
+	if (IS_ERR(gen_kretprobe_test)) {
+		ret = PTR_ERR(gen_kretprobe_test);
+		goto delete;
+	}
+
+	/* Enable the event or you won't see anything */
+	ret = trace_array_set_clr_event(gen_kretprobe_test->tr,
+					"kprobes", "gen_kretprobe_test", true);
+	if (ret) {
+		trace_put_event_file(gen_kretprobe_test);
+		goto delete;
+	}
+ out:
+	kfree(buf);
+	return ret;
+ delete:
+	if (trace_event_file_is_valid(gen_kretprobe_test))
+		gen_kretprobe_test = NULL;
+	/* We got an error after creating the event, delete it */
+	kprobe_event_delete("gen_kretprobe_test");
+	goto out;
+}
+
+static int __init kprobe_event_gen_test_init(void)
+{
+	int ret;
+
+	ret = test_gen_kprobe_cmd();
+	if (ret)
+		return ret;
+
+	ret = test_gen_kretprobe_cmd();
+	if (ret) {
+		if (trace_event_file_is_valid(gen_kretprobe_test)) {
+			WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
+							  "kprobes",
+							  "gen_kretprobe_test", false));
+			trace_put_event_file(gen_kretprobe_test);
+		}
+		WARN_ON(kprobe_event_delete("gen_kretprobe_test"));
+	}
+
+	return ret;
+}
+
+static void __exit kprobe_event_gen_test_exit(void)
+{
+	if (trace_event_file_is_valid(gen_kprobe_test)) {
+		/* Disable the event or you can't remove it */
+		WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
+						  "kprobes",
+						  "gen_kprobe_test", false));
+
+		/* Now give the file and instance back */
+		trace_put_event_file(gen_kprobe_test);
+	}
+
+
+	/* Now unregister and free the event */
+	WARN_ON(kprobe_event_delete("gen_kprobe_test"));
+
+	if (trace_event_file_is_valid(gen_kretprobe_test)) {
+		/* Disable the event or you can't remove it */
+		WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
+						  "kprobes",
+						  "gen_kretprobe_test", false));
+
+		/* Now give the file and instance back */
+		trace_put_event_file(gen_kretprobe_test);
+	}
+
+
+	/* Now unregister and free the event */
+	WARN_ON(kprobe_event_delete("gen_kretprobe_test"));
+}
+
+module_init(kprobe_event_gen_test_init)
+module_exit(kprobe_event_gen_test_exit)
+
+MODULE_AUTHOR("Tom Zanussi");
+MODULE_DESCRIPTION("kprobe event generation test");
+MODULE_LICENSE("GPL v2");

linux-7.2.3/kernel/trace/pid_list.c

@@ -0,0 +1,504 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 VMware Inc, Steven Rostedt <rostedt@goodmis.org>
+ */
+#include <linux/spinlock.h>
+#include <linux/seqlock.h>
+#include <linux/irq_work.h>
+#include <linux/slab.h>
+#include "trace.h"
+
+/* See pid_list.h for details */
+
+static inline union lower_chunk *get_lower_chunk(struct trace_pid_list *pid_list)
+{
+	union lower_chunk *chunk;
+
+	lockdep_assert_held(&pid_list->lock);
+
+	if (!pid_list->lower_list)
+		return NULL;
+
+	chunk = pid_list->lower_list;
+	pid_list->lower_list = chunk->next;
+	pid_list->free_lower_chunks--;
+	WARN_ON_ONCE(pid_list->free_lower_chunks < 0);
+	chunk->next = NULL;
+	/*
+	 * If a refill needs to happen, it can not happen here
+	 * as the scheduler run queue locks are held.
+	 */
+	if (pid_list->free_lower_chunks <= CHUNK_REALLOC)
+		irq_work_queue(&pid_list->refill_irqwork);
+
+	return chunk;
+}
+
+static inline union upper_chunk *get_upper_chunk(struct trace_pid_list *pid_list)
+{
+	union upper_chunk *chunk;
+
+	lockdep_assert_held(&pid_list->lock);
+
+	if (!pid_list->upper_list)
+		return NULL;
+
+	chunk = pid_list->upper_list;
+	pid_list->upper_list = chunk->next;
+	pid_list->free_upper_chunks--;
+	WARN_ON_ONCE(pid_list->free_upper_chunks < 0);
+	chunk->next = NULL;
+	/*
+	 * If a refill needs to happen, it can not happen here
+	 * as the scheduler run queue locks are held.
+	 */
+	if (pid_list->free_upper_chunks <= CHUNK_REALLOC)
+		irq_work_queue(&pid_list->refill_irqwork);
+
+	return chunk;
+}
+
+static inline void put_lower_chunk(struct trace_pid_list *pid_list,
+				   union lower_chunk *chunk)
+{
+	lockdep_assert_held(&pid_list->lock);
+
+	chunk->next = pid_list->lower_list;
+	pid_list->lower_list = chunk;
+	pid_list->free_lower_chunks++;
+}
+
+static inline void put_upper_chunk(struct trace_pid_list *pid_list,
+				   union upper_chunk *chunk)
+{
+	lockdep_assert_held(&pid_list->lock);
+
+	chunk->next = pid_list->upper_list;
+	pid_list->upper_list = chunk;
+	pid_list->free_upper_chunks++;
+}
+
+static inline bool upper_empty(union upper_chunk *chunk)
+{
+	/*
+	 * If chunk->data has no lower chunks, it will be the same
+	 * as a zeroed bitmask.
+	 */
+	return bitmap_empty((unsigned long *)chunk->data, BITS_PER_TYPE(chunk->data));
+}
+
+static inline int pid_split(unsigned int pid, unsigned int *upper1,
+			     unsigned int *upper2, unsigned int *lower)
+{
+	/* MAX_PID should cover all pids */
+	BUILD_BUG_ON(MAX_PID < PID_MAX_LIMIT);
+
+	/* In case a bad pid is passed in, then fail */
+	if (unlikely(pid >= MAX_PID))
+		return -1;
+
+	*upper1 = (pid >> UPPER1_SHIFT) & UPPER_MASK;
+	*upper2 = (pid >> UPPER2_SHIFT) & UPPER_MASK;
+	*lower = pid & LOWER_MASK;
+
+	return 0;
+}
+
+static inline unsigned int pid_join(unsigned int upper1,
+				    unsigned int upper2, unsigned int lower)
+{
+	return ((upper1 & UPPER_MASK) << UPPER1_SHIFT) |
+		((upper2 & UPPER_MASK) << UPPER2_SHIFT) |
+		(lower & LOWER_MASK);
+}
+
+/**
+ * trace_pid_list_is_set - test if the pid is set in the list
+ * @pid_list: The pid list to test
+ * @pid: The pid to see if set in the list.
+ *
+ * Tests if @pid is set in the @pid_list. This is usually called
+ * from the scheduler when a task is scheduled. Its pid is checked
+ * if it should be traced or not.
+ *
+ * Return true if the pid is in the list, false otherwise.
+ */
+bool trace_pid_list_is_set(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned int seq;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+	bool ret = false;
+
+	if (!pid_list)
+		return false;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return false;
+
+	do {
+		seq = read_seqcount_begin(&pid_list->seqcount);
+		ret = false;
+		upper_chunk = pid_list->upper[upper1];
+		if (upper_chunk) {
+			lower_chunk = upper_chunk->data[upper2];
+			if (lower_chunk)
+				ret = test_bit(lower, lower_chunk->data);
+		}
+	} while (read_seqcount_retry(&pid_list->seqcount, seq));
+
+	return ret;
+}
+
+/**
+ * trace_pid_list_set - add a pid to the list
+ * @pid_list: The pid list to add the @pid to.
+ * @pid: The pid to add.
+ *
+ * Adds @pid to @pid_list. This is usually done explicitly by a user
+ * adding a task to be traced, or indirectly by the fork function
+ * when children should be traced and a task's pid is in the list.
+ *
+ * Return 0 on success, negative otherwise.
+ */
+int trace_pid_list_set(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned long flags;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+	int ret;
+
+	if (!pid_list)
+		return -ENODEV;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&pid_list->lock, flags);
+	write_seqcount_begin(&pid_list->seqcount);
+	upper_chunk = pid_list->upper[upper1];
+	if (!upper_chunk) {
+		upper_chunk = get_upper_chunk(pid_list);
+		if (!upper_chunk) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		pid_list->upper[upper1] = upper_chunk;
+	}
+	lower_chunk = upper_chunk->data[upper2];
+	if (!lower_chunk) {
+		lower_chunk = get_lower_chunk(pid_list);
+		if (!lower_chunk) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		upper_chunk->data[upper2] = lower_chunk;
+	}
+	set_bit(lower, lower_chunk->data);
+	ret = 0;
+ out:
+	write_seqcount_end(&pid_list->seqcount);
+	raw_spin_unlock_irqrestore(&pid_list->lock, flags);
+	return ret;
+}
+
+/**
+ * trace_pid_list_clear - remove a pid from the list
+ * @pid_list: The pid list to remove the @pid from.
+ * @pid: The pid to remove.
+ *
+ * Removes @pid from @pid_list. This is usually done explicitly by a user
+ * removing tasks from tracing, or indirectly by the exit function
+ * when a task that is set to be traced exits.
+ *
+ * Return 0 on success, negative otherwise.
+ */
+int trace_pid_list_clear(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned long flags;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+
+	if (!pid_list)
+		return -ENODEV;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&pid_list->lock, flags);
+	write_seqcount_begin(&pid_list->seqcount);
+	upper_chunk = pid_list->upper[upper1];
+	if (!upper_chunk)
+		goto out;
+
+	lower_chunk = upper_chunk->data[upper2];
+	if (!lower_chunk)
+		goto out;
+
+	clear_bit(lower, lower_chunk->data);
+
+	/* if there's no more bits set, add it to the free list */
+	if (find_first_bit(lower_chunk->data, LOWER_MAX) >= LOWER_MAX) {
+		put_lower_chunk(pid_list, lower_chunk);
+		upper_chunk->data[upper2] = NULL;
+		if (upper_empty(upper_chunk)) {
+			put_upper_chunk(pid_list, upper_chunk);
+			pid_list->upper[upper1] = NULL;
+		}
+	}
+ out:
+	write_seqcount_end(&pid_list->seqcount);
+	raw_spin_unlock_irqrestore(&pid_list->lock, flags);
+	return 0;
+}
+
+/**
+ * trace_pid_list_next - return the next pid in the list
+ * @pid_list: The pid list to examine.
+ * @pid: The pid to start from
+ * @next: The pointer to place the pid that is set starting from @pid.
+ *
+ * Looks for the next consecutive pid that is in @pid_list starting
+ * at the pid specified by @pid. If one is set (including @pid), then
+ * that pid is placed into @next.
+ *
+ * Return 0 when a pid is found, -1 if there are no more pids included.
+ */
+int trace_pid_list_next(struct trace_pid_list *pid_list, unsigned int pid,
+			unsigned int *next)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned long flags;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+
+	if (!pid_list)
+		return -ENODEV;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&pid_list->lock, flags);
+	for (; upper1 <= UPPER_MASK; upper1++, upper2 = 0) {
+		upper_chunk = pid_list->upper[upper1];
+
+		if (!upper_chunk)
+			continue;
+
+		for (; upper2 <= UPPER_MASK; upper2++, lower = 0) {
+			lower_chunk = upper_chunk->data[upper2];
+			if (!lower_chunk)
+				continue;
+
+			lower = find_next_bit(lower_chunk->data, LOWER_MAX,
+					    lower);
+			if (lower < LOWER_MAX)
+				goto found;
+		}
+	}
+
+ found:
+	raw_spin_unlock_irqrestore(&pid_list->lock, flags);
+	if (upper1 > UPPER_MASK)
+		return -1;
+
+	*next = pid_join(upper1, upper2, lower);
+	return 0;
+}
+
+/**
+ * trace_pid_list_first - return the first pid in the list
+ * @pid_list: The pid list to examine.
+ * @pid: The pointer to place the pid first found pid that is set.
+ *
+ * Looks for the first pid that is set in @pid_list, and places it
+ * into @pid if found.
+ *
+ * Return 0 when a pid is found, -1 if there are no pids set.
+ */
+int trace_pid_list_first(struct trace_pid_list *pid_list, unsigned int *pid)
+{
+	return trace_pid_list_next(pid_list, 0, pid);
+}
+
+static void pid_list_refill_irq(struct irq_work *iwork)
+{
+	struct trace_pid_list *pid_list = container_of(iwork, struct trace_pid_list,
+						       refill_irqwork);
+	union upper_chunk *upper = NULL;
+	union lower_chunk *lower = NULL;
+	union upper_chunk **upper_next = &upper;
+	union lower_chunk **lower_next = &lower;
+	int upper_count;
+	int lower_count;
+	int ucnt = 0;
+	int lcnt = 0;
+
+ again:
+	raw_spin_lock(&pid_list->lock);
+	write_seqcount_begin(&pid_list->seqcount);
+	upper_count = CHUNK_ALLOC - pid_list->free_upper_chunks;
+	lower_count = CHUNK_ALLOC - pid_list->free_lower_chunks;
+	write_seqcount_end(&pid_list->seqcount);
+	raw_spin_unlock(&pid_list->lock);
+
+	if (upper_count <= 0 && lower_count <= 0)
+		return;
+
+	while (upper_count-- > 0) {
+		union upper_chunk *chunk;
+
+		chunk = kzalloc_obj(*chunk, GFP_NOWAIT);
+		if (!chunk)
+			break;
+		*upper_next = chunk;
+		upper_next = &chunk->next;
+		ucnt++;
+	}
+
+	while (lower_count-- > 0) {
+		union lower_chunk *chunk;
+
+		chunk = kzalloc_obj(*chunk, GFP_NOWAIT);
+		if (!chunk)
+			break;
+		*lower_next = chunk;
+		lower_next = &chunk->next;
+		lcnt++;
+	}
+
+	raw_spin_lock(&pid_list->lock);
+	write_seqcount_begin(&pid_list->seqcount);
+	if (upper) {
+		*upper_next = pid_list->upper_list;
+		pid_list->upper_list = upper;
+		pid_list->free_upper_chunks += ucnt;
+	}
+	if (lower) {
+		*lower_next = pid_list->lower_list;
+		pid_list->lower_list = lower;
+		pid_list->free_lower_chunks += lcnt;
+	}
+	write_seqcount_end(&pid_list->seqcount);
+	raw_spin_unlock(&pid_list->lock);
+
+	/*
+	 * On success of allocating all the chunks, both counters
+	 * will be less than zero. If they are not, then an allocation
+	 * failed, and we should not try again.
+	 */
+	if (upper_count >= 0 || lower_count >= 0)
+		return;
+	/*
+	 * When the locks were released, free chunks could have
+	 * been used and allocation needs to be done again. Might as
+	 * well allocate it now.
+	 */
+	goto again;
+}
+
+/**
+ * trace_pid_list_alloc - create a new pid_list
+ *
+ * Allocates a new pid_list to store pids into.
+ *
+ * Returns the pid_list on success, NULL otherwise.
+ */
+struct trace_pid_list *trace_pid_list_alloc(void)
+{
+	struct trace_pid_list *pid_list;
+	int i;
+
+	/* According to linux/thread.h, pids can be no bigger that 30 bits */
+	WARN_ON_ONCE(init_pid_ns.pid_max > (1 << 30));
+
+	pid_list = kzalloc_obj(*pid_list);
+	if (!pid_list)
+		return NULL;
+
+	init_irq_work(&pid_list->refill_irqwork, pid_list_refill_irq);
+
+	raw_spin_lock_init(&pid_list->lock);
+	seqcount_raw_spinlock_init(&pid_list->seqcount, &pid_list->lock);
+
+	for (i = 0; i < CHUNK_ALLOC; i++) {
+		union upper_chunk *chunk;
+
+		chunk = kzalloc_obj(*chunk);
+		if (!chunk)
+			break;
+		chunk->next = pid_list->upper_list;
+		pid_list->upper_list = chunk;
+		pid_list->free_upper_chunks++;
+	}
+
+	for (i = 0; i < CHUNK_ALLOC; i++) {
+		union lower_chunk *chunk;
+
+		chunk = kzalloc_obj(*chunk);
+		if (!chunk)
+			break;
+		chunk->next = pid_list->lower_list;
+		pid_list->lower_list = chunk;
+		pid_list->free_lower_chunks++;
+	}
+
+	return pid_list;
+}
+
+/**
+ * trace_pid_list_free - Frees an allocated pid_list.
+ * @pid_list: The pid list to free.
+ *
+ * Frees the memory for a pid_list that was allocated.
+ */
+void trace_pid_list_free(struct trace_pid_list *pid_list)
+{
+	union upper_chunk *upper;
+	union lower_chunk *lower;
+	int i, j;
+
+	if (!pid_list)
+		return;
+
+	irq_work_sync(&pid_list->refill_irqwork);
+
+	while (pid_list->lower_list) {
+		union lower_chunk *chunk;
+
+		chunk = pid_list->lower_list;
+		pid_list->lower_list = pid_list->lower_list->next;
+		kfree(chunk);
+	}
+
+	while (pid_list->upper_list) {
+		union upper_chunk *chunk;
+
+		chunk = pid_list->upper_list;
+		pid_list->upper_list = pid_list->upper_list->next;
+		kfree(chunk);
+	}
+
+	for (i = 0; i < UPPER1_SIZE; i++) {
+		upper = pid_list->upper[i];
+		if (upper) {
+			for (j = 0; j < UPPER2_SIZE; j++) {
+				lower = upper->data[j];
+				kfree(lower);
+			}
+			kfree(upper);
+		}
+	}
+	kfree(pid_list);
+}

linux-7.2.3/kernel/trace/pid_list.h

@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Do not include this file directly. */
+
+#ifndef _TRACE_INTERNAL_PID_LIST_H
+#define _TRACE_INTERNAL_PID_LIST_H
+
+/*
+ * In order to keep track of what pids to trace, a tree is created much
+ * like page tables are used. This creates a sparse bit map, where
+ * the tree is filled in when needed. A PID is at most 30 bits (see
+ * linux/thread.h), and is broken up into 3 sections based on the bit map
+ * of the bits. The 8 MSB is the "upper1" section. The next 8 MSB is the
+ * "upper2" section and the 14 LSB is the "lower" section.
+ *
+ * A trace_pid_list structure holds the "upper1" section, in an
+ * array of 256 pointers (1 or 2K in size) to "upper_chunk" unions, where
+ * each has an array of 256 pointers (1 or 2K in size) to the "lower_chunk"
+ * structures, where each has an array of size 2K bytes representing a bitmask
+ * of the 14 LSB of the PID (256 * 8 = 2048)
+ *
+ * When a trace_pid_list is allocated, it includes the 256 pointer array
+ * of the upper1 unions. Then a "cache" of upper and lower is allocated
+ * where these will be assigned as needed.
+ *
+ * When a bit is set in the pid_list bitmask, the pid to use has
+ * the 8 MSB masked, and this is used to index the array in the
+ * pid_list to find the next upper union. If the element is NULL,
+ * then one is retrieved from the upper_list cache. If none is
+ * available, then -ENOMEM is returned.
+ *
+ * The next 8 MSB is used to index into the "upper2" section. If this
+ * element is NULL, then it is retrieved from the lower_list cache.
+ * Again, if one is not available -ENOMEM is returned.
+ *
+ * Finally the 14 LSB of the PID is used to set the bit in the 16384
+ * bitmask (made up of 2K bytes).
+ *
+ * When the second upper section or the lower section has their last
+ * bit cleared, they are added back to the free list to be reused
+ * when needed.
+ */
+
+#define UPPER_BITS	8
+#define UPPER_MAX	(1 << UPPER_BITS)
+#define UPPER1_SIZE	(1 << UPPER_BITS)
+#define UPPER2_SIZE	(1 << UPPER_BITS)
+
+#define LOWER_BITS	14
+#define LOWER_MAX	(1 << LOWER_BITS)
+#define LOWER_SIZE	(LOWER_MAX / BITS_PER_LONG)
+
+#define UPPER1_SHIFT	(LOWER_BITS + UPPER_BITS)
+#define UPPER2_SHIFT	LOWER_BITS
+#define LOWER_MASK	(LOWER_MAX - 1)
+
+#define UPPER_MASK	(UPPER_MAX - 1)
+
+/* According to linux/thread.h pids can not be bigger than or equal to 1 << 30 */
+#define MAX_PID		(1 << 30)
+
+/* Just keep 6 chunks of both upper and lower in the cache on alloc */
+#define CHUNK_ALLOC 6
+
+/* Have 2 chunks free, trigger a refill of the cache */
+#define CHUNK_REALLOC 2
+
+union lower_chunk {
+	union lower_chunk		*next;
+	unsigned long			data[LOWER_SIZE]; // 2K in size
+};
+
+union upper_chunk {
+	union upper_chunk		*next;
+	union lower_chunk		*data[UPPER2_SIZE]; // 1 or 2K in size
+};
+
+struct trace_pid_list {
+	seqcount_raw_spinlock_t		seqcount;
+	raw_spinlock_t			lock;
+	struct irq_work			refill_irqwork;
+	union upper_chunk		*upper[UPPER1_SIZE]; // 1 or 2K in size
+	union upper_chunk		*upper_list;
+	union lower_chunk		*lower_list;
+	int				free_upper_chunks;
+	int				free_lower_chunks;
+};
+
+#endif /* _TRACE_INTERNAL_PID_LIST_H */

linux-7.2.3/kernel/trace/power-traces.c

@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Arjan van de Ven <arjan@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
+

linux-7.2.3/kernel/trace/preemptirq_delay_test.c

@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Preempt / IRQ disable delay thread to test latency tracers
+ *
+ * Copyright (C) 2018 Joel Fernandes (Google) <joel@joelfernandes.org>
+ */
+
+#include <linux/trace_clock.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/completion.h>
+
+static ulong delay = 100;
+static char test_mode[12] = "irq";
+static uint burst_size = 1;
+static int  cpu_affinity = -1;
+
+module_param_named(delay, delay, ulong, 0444);
+module_param_string(test_mode, test_mode, 12, 0444);
+module_param_named(burst_size, burst_size, uint, 0444);
+module_param_named(cpu_affinity, cpu_affinity, int, 0444);
+MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)");
+MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)");
+MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)");
+MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on");
+
+static struct completion done;
+
+static void busy_wait(ulong time)
+{
+	u64 start, end;
+
+	start = trace_clock_local();
+
+	do {
+		end = trace_clock_local();
+		if (kthread_should_stop())
+			break;
+	} while ((end - start) < (time * 1000));
+}
+
+static __always_inline void irqoff_test(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	busy_wait(delay);
+	local_irq_restore(flags);
+}
+
+static __always_inline void preemptoff_test(void)
+{
+	preempt_disable();
+	busy_wait(delay);
+	preempt_enable();
+}
+
+static void execute_preemptirqtest(int idx)
+{
+	if (!strcmp(test_mode, "irq"))
+		irqoff_test();
+	else if (!strcmp(test_mode, "preempt"))
+		preemptoff_test();
+	else if (!strcmp(test_mode, "alternate")) {
+		if (idx % 2 == 0)
+			irqoff_test();
+		else
+			preemptoff_test();
+	}
+}
+
+#define DECLARE_TESTFN(POSTFIX)				\
+	static void preemptirqtest_##POSTFIX(int idx)	\
+	{						\
+		execute_preemptirqtest(idx);		\
+	}						\
+
+/*
+ * We create 10 different functions, so that we can get 10 different
+ * backtraces.
+ */
+DECLARE_TESTFN(0)
+DECLARE_TESTFN(1)
+DECLARE_TESTFN(2)
+DECLARE_TESTFN(3)
+DECLARE_TESTFN(4)
+DECLARE_TESTFN(5)
+DECLARE_TESTFN(6)
+DECLARE_TESTFN(7)
+DECLARE_TESTFN(8)
+DECLARE_TESTFN(9)
+
+static void (*testfuncs[])(int)  = {
+	preemptirqtest_0,
+	preemptirqtest_1,
+	preemptirqtest_2,
+	preemptirqtest_3,
+	preemptirqtest_4,
+	preemptirqtest_5,
+	preemptirqtest_6,
+	preemptirqtest_7,
+	preemptirqtest_8,
+	preemptirqtest_9,
+};
+
+#define NR_TEST_FUNCS ARRAY_SIZE(testfuncs)
+
+static int preemptirq_delay_run(void *data)
+{
+	int i;
+	int s = MIN(burst_size, NR_TEST_FUNCS);
+	cpumask_var_t cpu_mask;
+
+	if (!alloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (cpu_affinity > -1) {
+		cpumask_clear(cpu_mask);
+		cpumask_set_cpu(cpu_affinity, cpu_mask);
+		if (set_cpus_allowed_ptr(current, cpu_mask))
+			pr_err("cpu_affinity:%d, failed\n", cpu_affinity);
+	}
+
+	for (i = 0; i < s; i++)
+		(testfuncs[i])(i);
+
+	complete(&done);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+
+	__set_current_state(TASK_RUNNING);
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+static int preemptirq_run_test(void)
+{
+	struct task_struct *task;
+	char task_name[50];
+
+	init_completion(&done);
+
+	snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
+	task =  kthread_run(preemptirq_delay_run, NULL, task_name);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	if (task) {
+		wait_for_completion(&done);
+		kthread_stop(task);
+	}
+	return 0;
+}
+
+
+static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr,
+			 const char *buf, size_t count)
+{
+	ssize_t ret;
+
+	ret = preemptirq_run_test();
+	if (ret)
+		return ret;
+	return count;
+}
+
+static struct kobj_attribute trigger_attribute =
+	__ATTR(trigger, 0200, NULL, trigger_store);
+
+static struct attribute *attrs[] = {
+	&trigger_attribute.attr,
+	NULL,
+};
+
+static struct attribute_group attr_group = {
+	.attrs = attrs,
+};
+
+static struct kobject *preemptirq_delay_kobj;
+
+static int __init preemptirq_delay_init(void)
+{
+	int retval;
+
+	retval = preemptirq_run_test();
+	if (retval != 0)
+		return retval;
+
+	preemptirq_delay_kobj = kobject_create_and_add("preemptirq_delay_test",
+						       kernel_kobj);
+	if (!preemptirq_delay_kobj)
+		return -ENOMEM;
+
+	retval = sysfs_create_group(preemptirq_delay_kobj, &attr_group);
+	if (retval)
+		kobject_put(preemptirq_delay_kobj);
+
+	return retval;
+}
+
+static void __exit preemptirq_delay_exit(void)
+{
+	kobject_put(preemptirq_delay_kobj);
+}
+
+module_init(preemptirq_delay_init)
+module_exit(preemptirq_delay_exit)
+MODULE_DESCRIPTION("Preempt / IRQ disable delay thread to test latency tracers");
+MODULE_LICENSE("GPL v2");

linux-7.2.3/kernel/trace/remote_test.c

@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 - Google LLC
+ * Author: Vincent Donnefort <vdonnefort@google.com>
+ */
+
+#include <linux/module.h>
+#include <linux/simple_ring_buffer.h>
+#include <linux/trace_remote.h>
+#include <linux/tracefs.h>
+#include <linux/types.h>
+
+#define REMOTE_EVENT_INCLUDE_FILE kernel/trace/remote_test_events.h
+#include <trace/define_remote_events.h>
+
+static DEFINE_PER_CPU(struct simple_rb_per_cpu *, simple_rbs);
+static struct trace_buffer_desc *remote_test_buffer_desc;
+
+/*
+ * The trace_remote lock already serializes accesses from the trace_remote_callbacks.
+ * However write_event can still race with load/unload.
+ */
+static DEFINE_MUTEX(simple_rbs_lock);
+
+static int remote_test_load_simple_rb(int cpu, struct ring_buffer_desc *rb_desc)
+{
+	struct simple_rb_per_cpu *cpu_buffer;
+	struct simple_buffer_page *bpages;
+	int ret = -ENOMEM;
+
+	cpu_buffer = kmalloc_obj(*cpu_buffer);
+	if (!cpu_buffer)
+		return ret;
+
+	bpages = kmalloc_objs(*bpages, rb_desc->nr_page_va);
+	if (!bpages)
+		goto err_free_cpu_buffer;
+
+	ret = simple_ring_buffer_init(cpu_buffer, bpages, rb_desc);
+	if (ret)
+		goto err_free_bpages;
+
+	scoped_guard(mutex, &simple_rbs_lock) {
+		WARN_ON(*per_cpu_ptr(&simple_rbs, cpu));
+		*per_cpu_ptr(&simple_rbs, cpu) = cpu_buffer;
+	}
+
+	return 0;
+
+err_free_bpages:
+	kfree(bpages);
+
+err_free_cpu_buffer:
+	kfree(cpu_buffer);
+
+	return ret;
+}
+
+static void remote_test_unload_simple_rb(int cpu)
+{
+	struct simple_rb_per_cpu *cpu_buffer = *per_cpu_ptr(&simple_rbs, cpu);
+	struct simple_buffer_page *bpages;
+
+	if (!cpu_buffer)
+		return;
+
+	guard(mutex)(&simple_rbs_lock);
+
+	bpages = cpu_buffer->bpages;
+	simple_ring_buffer_unload(cpu_buffer);
+	kfree(bpages);
+	kfree(cpu_buffer);
+	*per_cpu_ptr(&simple_rbs, cpu) = NULL;
+}
+
+static struct trace_buffer_desc *remote_test_load(unsigned long size, void *unused)
+{
+	struct ring_buffer_desc *rb_desc;
+	struct trace_buffer_desc *desc;
+	size_t desc_size;
+	int cpu, ret;
+
+	if (WARN_ON(remote_test_buffer_desc))
+		return ERR_PTR(-EINVAL);
+
+	desc_size = trace_buffer_desc_size(size, num_possible_cpus());
+	if (desc_size == SIZE_MAX) {
+		ret = -E2BIG;
+		goto err;
+	}
+
+	desc = kmalloc(desc_size, GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = trace_remote_alloc_buffer(desc, desc_size, size, cpu_possible_mask);
+	if (ret)
+		goto err_free_desc;
+
+	for_each_ring_buffer_desc(rb_desc, cpu, desc) {
+		ret = remote_test_load_simple_rb(rb_desc->cpu, rb_desc);
+		if (ret)
+			goto err_unload;
+	}
+
+	remote_test_buffer_desc = desc;
+
+	return remote_test_buffer_desc;
+
+err_unload:
+	for_each_ring_buffer_desc(rb_desc, cpu, desc)
+		remote_test_unload_simple_rb(rb_desc->cpu);
+	trace_remote_free_buffer(desc);
+
+err_free_desc:
+	kfree(desc);
+
+err:
+	return ERR_PTR(ret);
+}
+
+static void remote_test_unload(struct trace_buffer_desc *desc, void *unused)
+{
+	struct ring_buffer_desc *rb_desc;
+	int cpu;
+
+	if (WARN_ON(desc != remote_test_buffer_desc))
+		return;
+
+	for_each_ring_buffer_desc(rb_desc, cpu, desc)
+		remote_test_unload_simple_rb(rb_desc->cpu);
+
+	remote_test_buffer_desc = NULL;
+	trace_remote_free_buffer(desc);
+	kfree(desc);
+}
+
+static int remote_test_enable_tracing(bool enable, void *unused)
+{
+	struct ring_buffer_desc *rb_desc;
+	int cpu;
+
+	if (!remote_test_buffer_desc)
+		return -ENODEV;
+
+	for_each_ring_buffer_desc(rb_desc, cpu, remote_test_buffer_desc)
+		WARN_ON(simple_ring_buffer_enable_tracing(*per_cpu_ptr(&simple_rbs, rb_desc->cpu),
+							  enable));
+	return 0;
+}
+
+static int remote_test_swap_reader_page(unsigned int cpu, void *unused)
+{
+	struct simple_rb_per_cpu *cpu_buffer;
+
+	if (cpu >= NR_CPUS)
+		return -EINVAL;
+
+	cpu_buffer = *per_cpu_ptr(&simple_rbs, cpu);
+	if (!cpu_buffer)
+		return -EINVAL;
+
+	return simple_ring_buffer_swap_reader_page(cpu_buffer);
+}
+
+static int remote_test_reset(unsigned int cpu, void *unused)
+{
+	struct simple_rb_per_cpu *cpu_buffer;
+
+	if (cpu >= NR_CPUS)
+		return -EINVAL;
+
+	cpu_buffer = *per_cpu_ptr(&simple_rbs, cpu);
+	if (!cpu_buffer)
+		return -EINVAL;
+
+	return simple_ring_buffer_reset(cpu_buffer);
+}
+
+static int remote_test_enable_event(unsigned short id, bool enable, void *unused)
+{
+	if (id != REMOTE_TEST_EVENT_ID)
+		return -EINVAL;
+
+	/*
+	 * Let's just use the struct remote_event enabled field that is turned on and off by
+	 * trace_remote. This is a bit racy but good enough for a simple test module.
+	 */
+	return 0;
+}
+
+static ssize_t
+write_event_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *pos)
+{
+	struct remote_event_format_selftest *evt_test;
+	struct simple_rb_per_cpu *cpu_buffer;
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	guard(mutex)(&simple_rbs_lock);
+
+	if (!remote_event_selftest.enabled)
+		return -ENODEV;
+
+	guard(preempt)();
+
+	cpu_buffer = *this_cpu_ptr(&simple_rbs);
+	if (!cpu_buffer)
+		return -ENODEV;
+
+	evt_test = simple_ring_buffer_reserve(cpu_buffer,
+					      sizeof(struct remote_event_format_selftest),
+					      trace_clock_global());
+	if (!evt_test)
+		return -ENODEV;
+
+	evt_test->hdr.id = REMOTE_TEST_EVENT_ID;
+	evt_test->id = val;
+
+	simple_ring_buffer_commit(cpu_buffer);
+
+	return cnt;
+}
+
+static const struct file_operations write_event_fops = {
+	.write	= write_event_write,
+};
+
+static int remote_test_init_tracefs(struct dentry *d, void *unused)
+{
+	return tracefs_create_file("write_event", 0200, d, NULL, &write_event_fops) ?
+		0 : -ENOMEM;
+}
+
+static struct trace_remote_callbacks trace_remote_callbacks = {
+	.init			= remote_test_init_tracefs,
+	.load_trace_buffer	= remote_test_load,
+	.unload_trace_buffer	= remote_test_unload,
+	.enable_tracing		= remote_test_enable_tracing,
+	.swap_reader_page	= remote_test_swap_reader_page,
+	.reset			= remote_test_reset,
+	.enable_event		= remote_test_enable_event,
+};
+
+static int __init remote_test_init(void)
+{
+	return trace_remote_register("test", &trace_remote_callbacks, NULL,
+				     &remote_event_selftest, 1);
+}
+
+module_init(remote_test_init);
+
+MODULE_DESCRIPTION("Test module for the trace remote interface");
+MODULE_AUTHOR("Vincent Donnefort");
+MODULE_LICENSE("GPL");

linux-7.2.3/kernel/trace/remote_test_events.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define REMOTE_TEST_EVENT_ID 1
+
+REMOTE_EVENT(selftest, REMOTE_TEST_EVENT_ID,
+	RE_STRUCT(
+		re_field(u64, id)
+	),
+	RE_PRINTK("id=%llu", __entry->id)
+);

linux-7.2.3/kernel/trace/rethook.c

@@ -0,0 +1,337 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt) "rethook: " fmt
+
+#include <linux/bug.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/preempt.h>
+#include <linux/rethook.h>
+#include <linux/slab.h>
+
+/* Return hook list (shadow stack by list) */
+
+/*
+ * This function is called from delayed_put_task_struct() when a task is
+ * dead and cleaned up to recycle any kretprobe instances associated with
+ * this task. These left over instances represent probed functions that
+ * have been called but will never return.
+ */
+void rethook_flush_task(struct task_struct *tk)
+{
+	struct rethook_node *rhn;
+	struct llist_node *node;
+
+	node = __llist_del_all(&tk->rethooks);
+	while (node) {
+		rhn = container_of(node, struct rethook_node, llist);
+		node = node->next;
+		preempt_disable();
+		rethook_recycle(rhn);
+		preempt_enable();
+	}
+}
+
+static void rethook_free_rcu(struct rcu_head *head)
+{
+	struct rethook *rh = container_of(head, struct rethook, rcu);
+	objpool_fini(&rh->pool);
+}
+
+/**
+ * rethook_stop() - Stop using a rethook.
+ * @rh: the struct rethook to stop.
+ *
+ * Stop using a rethook to prepare for freeing it. If you want to wait for
+ * all running rethook handler before calling rethook_free(), you need to
+ * call this first and wait RCU, and call rethook_free().
+ */
+void rethook_stop(struct rethook *rh)
+{
+	rcu_assign_pointer(rh->handler, NULL);
+}
+
+/**
+ * rethook_free() - Free struct rethook.
+ * @rh: the struct rethook to be freed.
+ *
+ * Free the rethook. Before calling this function, user must ensure the
+ * @rh::data is cleaned if needed (or, the handler can access it after
+ * calling this function.) This function will set the @rh to be freed
+ * after all rethook_node are freed (not soon). And the caller must
+ * not touch @rh after calling this.
+ */
+void rethook_free(struct rethook *rh)
+{
+	rethook_stop(rh);
+
+	call_rcu(&rh->rcu, rethook_free_rcu);
+}
+
+static int rethook_init_node(void *nod, void *context)
+{
+	struct rethook_node *node = nod;
+
+	node->rethook = context;
+	return 0;
+}
+
+static int rethook_fini_pool(struct objpool_head *head, void *context)
+{
+	kfree(context);
+	return 0;
+}
+
+static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
+{
+	return (rethook_handler_t)rcu_dereference_check(rh->handler,
+							rcu_read_lock_any_held());
+}
+
+/**
+ * rethook_alloc() - Allocate struct rethook.
+ * @data: a data to pass the @handler when hooking the return.
+ * @handler: the return hook callback function, must NOT be NULL
+ * @size: node size: rethook node and additional data
+ * @num: number of rethook nodes to be preallocated
+ *
+ * Allocate and initialize a new rethook with @data and @handler.
+ * Return pointer of new rethook, or error codes for failures.
+ *
+ * Note that @handler == NULL means this rethook is going to be freed.
+ */
+struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
+			      int size, int num)
+{
+	struct rethook *rh;
+
+	if (!handler || num <= 0 || size < sizeof(struct rethook_node))
+		return ERR_PTR(-EINVAL);
+
+	rh = kzalloc_obj(struct rethook);
+	if (!rh)
+		return ERR_PTR(-ENOMEM);
+
+	rh->data = data;
+	rcu_assign_pointer(rh->handler, handler);
+
+	/* initialize the objpool for rethook nodes */
+	if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
+			 rethook_init_node, rethook_fini_pool)) {
+		kfree(rh);
+		return ERR_PTR(-ENOMEM);
+	}
+	return rh;
+}
+
+static void free_rethook_node_rcu(struct rcu_head *head)
+{
+	struct rethook_node *node = container_of(head, struct rethook_node, rcu);
+	struct rethook *rh = node->rethook;
+
+	objpool_drop(node, &rh->pool);
+}
+
+/**
+ * rethook_recycle() - return the node to rethook.
+ * @node: The struct rethook_node to be returned.
+ *
+ * Return back the @node to @node::rethook. If the @node::rethook is already
+ * marked as freed, this will free the @node.
+ */
+void rethook_recycle(struct rethook_node *node)
+{
+	rethook_handler_t handler;
+
+	handler = rethook_get_handler(node->rethook);
+	if (likely(handler))
+		objpool_push(node, &node->rethook->pool);
+	else
+		call_rcu(&node->rcu, free_rethook_node_rcu);
+}
+NOKPROBE_SYMBOL(rethook_recycle);
+
+/**
+ * rethook_try_get() - get an unused rethook node.
+ * @rh: The struct rethook which pools the nodes.
+ *
+ * Get an unused rethook node from @rh. If the node pool is empty, this
+ * will return NULL. Caller must disable preemption.
+ */
+struct rethook_node *rethook_try_get(struct rethook *rh)
+{
+	rethook_handler_t handler = rethook_get_handler(rh);
+
+	/* Check whether @rh is going to be freed. */
+	if (unlikely(!handler))
+		return NULL;
+
+#if defined(CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING) || defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
+	/*
+	 * This expects the caller will set up a rethook on a function entry.
+	 * When the function returns, the rethook will eventually be reclaimed
+	 * or released in the rethook_recycle() with call_rcu().
+	 * This means the caller must be run in the RCU-availabe context.
+	 */
+	if (unlikely(!rcu_is_watching()))
+		return NULL;
+#endif
+
+	return (struct rethook_node *)objpool_pop(&rh->pool);
+}
+NOKPROBE_SYMBOL(rethook_try_get);
+
+/**
+ * rethook_hook() - Hook the current function return.
+ * @node: The struct rethook node to hook the function return.
+ * @regs: The struct pt_regs for the function entry.
+ * @mcount: True if this is called from mcount(ftrace) context.
+ *
+ * Hook the current running function return. This must be called when the
+ * function entry (or at least @regs must be the registers of the function
+ * entry.) @mcount is used for identifying the context. If this is called
+ * from ftrace (mcount) callback, @mcount must be set true. If this is called
+ * from the real function entry (e.g. kprobes) @mcount must be set false.
+ * This is because the way to hook the function return depends on the context.
+ */
+void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount)
+{
+	arch_rethook_prepare(node, regs, mcount);
+	__llist_add(&node->llist, &current->rethooks);
+}
+NOKPROBE_SYMBOL(rethook_hook);
+
+/* This assumes the 'tsk' is the current task or is not running. */
+static unsigned long __rethook_find_ret_addr(struct task_struct *tsk,
+					     struct llist_node **cur)
+{
+	struct rethook_node *rh = NULL;
+	struct llist_node *node = *cur;
+
+	if (!node)
+		node = tsk->rethooks.first;
+	else
+		node = node->next;
+
+	while (node) {
+		rh = container_of(node, struct rethook_node, llist);
+		if (rh->ret_addr != (unsigned long)arch_rethook_trampoline) {
+			*cur = node;
+			return rh->ret_addr;
+		}
+		node = node->next;
+	}
+	return 0;
+}
+NOKPROBE_SYMBOL(__rethook_find_ret_addr);
+
+/**
+ * rethook_find_ret_addr -- Find correct return address modified by rethook
+ * @tsk: Target task
+ * @frame: A frame pointer
+ * @cur: a storage of the loop cursor llist_node pointer for next call
+ *
+ * Find the correct return address modified by a rethook on @tsk in unsigned
+ * long type.
+ * The @tsk must be 'current' or a task which is not running. @frame is a hint
+ * to get the currect return address - which is compared with the
+ * rethook::frame field. The @cur is a loop cursor for searching the
+ * kretprobe return addresses on the @tsk. The '*@cur' should be NULL at the
+ * first call, but '@cur' itself must NOT NULL.
+ *
+ * Returns found address value or zero if not found.
+ */
+unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame,
+				    struct llist_node **cur)
+{
+	struct rethook_node *rhn = NULL;
+	unsigned long ret;
+
+	if (WARN_ON_ONCE(!cur))
+		return 0;
+
+	if (tsk != current && task_is_running(tsk))
+		return 0;
+
+	do {
+		ret = __rethook_find_ret_addr(tsk, cur);
+		if (!ret)
+			break;
+		rhn = container_of(*cur, struct rethook_node, llist);
+	} while (rhn->frame != frame);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(rethook_find_ret_addr);
+
+void __weak arch_rethook_fixup_return(struct pt_regs *regs,
+				      unsigned long correct_ret_addr)
+{
+	/*
+	 * Do nothing by default. If the architecture which uses a
+	 * frame pointer to record real return address on the stack,
+	 * it should fill this function to fixup the return address
+	 * so that stacktrace works from the rethook handler.
+	 */
+}
+
+/* This function will be called from each arch-defined trampoline. */
+unsigned long rethook_trampoline_handler(struct pt_regs *regs,
+					 unsigned long frame)
+{
+	struct llist_node *first, *node = NULL;
+	unsigned long correct_ret_addr;
+	rethook_handler_t handler;
+	struct rethook_node *rhn;
+
+	correct_ret_addr = __rethook_find_ret_addr(current, &node);
+	if (!correct_ret_addr) {
+		pr_err("rethook: Return address not found! Maybe there is a bug in the kernel\n");
+		BUG_ON(1);
+	}
+
+	instruction_pointer_set(regs, correct_ret_addr);
+
+	/*
+	 * These loops must be protected from rethook_free_rcu() because those
+	 * are accessing 'rhn->rethook'.
+	 */
+	preempt_disable_notrace();
+
+	/*
+	 * Run the handler on the shadow stack. Do not unlink the list here because
+	 * stackdump inside the handlers needs to decode it.
+	 */
+	first = current->rethooks.first;
+	while (first) {
+		rhn = container_of(first, struct rethook_node, llist);
+		if (WARN_ON_ONCE(rhn->frame != frame))
+			break;
+		handler = rethook_get_handler(rhn->rethook);
+		if (handler)
+			handler(rhn, rhn->rethook->data,
+				correct_ret_addr, regs);
+
+		if (first == node)
+			break;
+		first = first->next;
+	}
+
+	/* Fixup registers for returning to correct address. */
+	arch_rethook_fixup_return(regs, correct_ret_addr);
+
+	/* Unlink used shadow stack */
+	first = current->rethooks.first;
+	current->rethooks.first = node->next;
+	node->next = NULL;
+
+	while (first) {
+		rhn = container_of(first, struct rethook_node, llist);
+		first = first->next;
+		rethook_recycle(rhn);
+	}
+	preempt_enable_notrace();
+
+	return correct_ret_addr;
+}
+NOKPROBE_SYMBOL(rethook_trampoline_handler);

linux-7.2.3/kernel/trace/ring_buffer_benchmark.c

@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ring buffer tester and benchmark
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
+#include <linux/module.h>
+#include <linux/ktime.h>
+#include <asm/local.h>
+
+struct rb_page {
+	u64		ts;
+	local_t		commit;
+	char		data[4080];
+};
+
+/* run time and sleep time in seconds */
+#define RUN_TIME	10ULL
+#define SLEEP_TIME	10
+
+/* number of events for writer to wake up the reader */
+static int wakeup_interval = 100;
+
+static int reader_finish;
+static DECLARE_COMPLETION(read_start);
+static DECLARE_COMPLETION(read_done);
+
+static struct trace_buffer *buffer;
+static struct task_struct *producer;
+static struct task_struct *consumer;
+static unsigned long read;
+
+static unsigned int disable_reader;
+module_param(disable_reader, uint, 0644);
+MODULE_PARM_DESC(disable_reader, "only run producer");
+
+static unsigned int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = MAX_NICE;
+static int consumer_nice = MAX_NICE;
+
+static int producer_fifo;
+static int consumer_fifo;
+
+module_param(producer_nice, int, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, int, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, int, 0644);
+MODULE_PARM_DESC(producer_fifo, "use fifo for producer: 0 - disabled, 1 - low prio, 2 - fifo");
+
+module_param(consumer_fifo, int, 0644);
+MODULE_PARM_DESC(consumer_fifo, "use fifo for consumer: 0 - disabled, 1 - low prio, 2 - fifo");
+
+static int read_events;
+
+static int test_error;
+
+#define TEST_ERROR()				\
+	do {					\
+		if (!test_error) {		\
+			test_error = 1;		\
+			WARN_ON(1);		\
+		}				\
+	} while (0)
+
+enum event_status {
+	EVENT_FOUND,
+	EVENT_DROPPED,
+};
+
+static bool break_test(void)
+{
+	return test_error || kthread_should_stop();
+}
+
+static enum event_status read_event(int cpu)
+{
+	struct ring_buffer_event *event;
+	int *entry;
+	u64 ts;
+
+	event = ring_buffer_consume(buffer, cpu, &ts, NULL);
+	if (!event)
+		return EVENT_DROPPED;
+
+	entry = ring_buffer_event_data(event);
+	if (*entry != cpu) {
+		TEST_ERROR();
+		return EVENT_DROPPED;
+	}
+
+	read++;
+	return EVENT_FOUND;
+}
+
+static enum event_status read_page(int cpu)
+{
+	struct buffer_data_read_page *bpage;
+	struct ring_buffer_event *event;
+	struct rb_page *rpage;
+	unsigned long commit;
+	int page_size;
+	int *entry;
+	int ret;
+	int inc;
+	int i;
+
+	bpage = ring_buffer_alloc_read_page(buffer, cpu);
+	if (IS_ERR(bpage))
+		return EVENT_DROPPED;
+
+	page_size = ring_buffer_subbuf_size_get(buffer);
+	ret = ring_buffer_read_page(buffer, bpage, page_size, cpu, 1);
+	if (ret >= 0) {
+		rpage = ring_buffer_read_page_data(bpage);
+		/* The commit may have missed event flags set, clear them */
+		commit = local_read(&rpage->commit) & 0xfffff;
+		for (i = 0; i < commit && !test_error ; i += inc) {
+
+			if (i >= (page_size - offsetof(struct rb_page, data))) {
+				TEST_ERROR();
+				break;
+			}
+
+			inc = -1;
+			event = (void *)&rpage->data[i];
+			switch (event->type_len) {
+			case RINGBUF_TYPE_PADDING:
+				/* failed writes may be discarded events */
+				if (!event->time_delta)
+					TEST_ERROR();
+				inc = event->array[0] + 4;
+				break;
+			case RINGBUF_TYPE_TIME_EXTEND:
+				inc = 8;
+				break;
+			case 0:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					TEST_ERROR();
+					break;
+				}
+				read++;
+				if (!event->array[0]) {
+					TEST_ERROR();
+					break;
+				}
+				inc = event->array[0] + 4;
+				break;
+			default:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					TEST_ERROR();
+					break;
+				}
+				read++;
+				inc = ((event->type_len + 1) * 4);
+			}
+			if (test_error)
+				break;
+
+			if (inc <= 0) {
+				TEST_ERROR();
+				break;
+			}
+		}
+	}
+	ring_buffer_free_read_page(buffer, cpu, bpage);
+
+	if (ret < 0)
+		return EVENT_DROPPED;
+	return EVENT_FOUND;
+}
+
+static void ring_buffer_consumer(void)
+{
+	/* toggle between reading pages and events */
+	read_events ^= 1;
+
+	read = 0;
+	/*
+	 * Continue running until the producer specifically asks to stop
+	 * and is ready for the completion.
+	 */
+	while (!READ_ONCE(reader_finish)) {
+		int found = 1;
+
+		while (found && !test_error) {
+			int cpu;
+
+			found = 0;
+			for_each_online_cpu(cpu) {
+				enum event_status stat;
+
+				if (read_events)
+					stat = read_event(cpu);
+				else
+					stat = read_page(cpu);
+
+				if (test_error)
+					break;
+
+				if (stat == EVENT_FOUND)
+					found = 1;
+
+			}
+		}
+
+		/* Wait till the producer wakes us up when there is more data
+		 * available or when the producer wants us to finish reading.
+		 */
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (reader_finish)
+			break;
+
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+	reader_finish = 0;
+	complete(&read_done);
+}
+
+static void ring_buffer_producer(void)
+{
+	ktime_t start_time, end_time, timeout;
+	unsigned long long time;
+	unsigned long long entries;
+	unsigned long long overruns;
+	unsigned long missed = 0;
+	unsigned long hit = 0;
+	unsigned long avg;
+	int cnt = 0;
+
+	/*
+	 * Hammer the buffer for 10 secs (this may
+	 * make the system stall)
+	 */
+	trace_printk("Starting ring buffer hammer\n");
+	start_time = ktime_get();
+	timeout = ktime_add_ns(start_time, RUN_TIME * NSEC_PER_SEC);
+	do {
+		struct ring_buffer_event *event;
+		int *entry;
+		int i;
+
+		for (i = 0; i < write_iteration; i++) {
+			event = ring_buffer_lock_reserve(buffer, 10);
+			if (!event) {
+				missed++;
+			} else {
+				hit++;
+				entry = ring_buffer_event_data(event);
+				*entry = smp_processor_id();
+				ring_buffer_unlock_commit(buffer);
+			}
+		}
+		end_time = ktime_get();
+
+		cnt++;
+		if (consumer && !(cnt % wakeup_interval))
+			wake_up_process(consumer);
+
+#ifndef CONFIG_PREEMPTION
+		/*
+		 * If we are a non preempt kernel, the 10 seconds run will
+		 * stop everything while it runs. Instead, we will call
+		 * cond_resched and also add any time that was lost by a
+		 * reschedule.
+		 *
+		 * Do a cond resched at the same frequency we would wake up
+		 * the reader.
+		 */
+		if (cnt % wakeup_interval)
+			cond_resched();
+#endif
+	} while (ktime_before(end_time, timeout) && !break_test());
+	trace_printk("End ring buffer hammer\n");
+
+	if (consumer) {
+		/* Init both completions here to avoid races */
+		init_completion(&read_start);
+		init_completion(&read_done);
+		/* the completions must be visible before the finish var */
+		smp_wmb();
+		reader_finish = 1;
+		wake_up_process(consumer);
+		wait_for_completion(&read_done);
+	}
+
+	time = ktime_us_delta(end_time, start_time);
+
+	entries = ring_buffer_entries(buffer);
+	overruns = ring_buffer_overruns(buffer);
+
+	if (test_error)
+		trace_printk("ERROR!\n");
+
+	if (!disable_reader) {
+		if (consumer_fifo)
+			trace_printk("Running Consumer at SCHED_FIFO %s\n",
+				     str_low_high(consumer_fifo == 1));
+		else
+			trace_printk("Running Consumer at nice: %d\n",
+				     consumer_nice);
+	}
+	if (producer_fifo)
+		trace_printk("Running Producer at SCHED_FIFO %s\n",
+			     str_low_high(producer_fifo == 1));
+	else
+		trace_printk("Running Producer at nice: %d\n",
+			     producer_nice);
+
+	/* Let the user know that the test is running at low priority */
+	if (!producer_fifo && !consumer_fifo &&
+	    producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
+		trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
+	trace_printk("Time:     %lld (usecs)\n", time);
+	trace_printk("Overruns: %lld\n", overruns);
+	if (disable_reader)
+		trace_printk("Read:     (reader disabled)\n");
+	else
+		trace_printk("Read:     %ld  (by %s)\n", read,
+			read_events ? "events" : "pages");
+	trace_printk("Entries:  %lld\n", entries);
+	trace_printk("Total:    %lld\n", entries + overruns + read);
+	trace_printk("Missed:   %ld\n", missed);
+	trace_printk("Hit:      %ld\n", hit);
+
+	/* Convert time from usecs to millisecs */
+	do_div(time, USEC_PER_MSEC);
+	if (time)
+		hit /= (long)time;
+	else
+		trace_printk("TIME IS ZERO??\n");
+
+	trace_printk("Entries per millisec: %ld\n", hit);
+
+	if (hit) {
+		/* Calculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / hit;
+		trace_printk("%ld ns per entry\n", avg);
+	}
+
+	if (missed) {
+		if (time)
+			missed /= (long)time;
+
+		trace_printk("Total iterations per millisec: %ld\n",
+			     hit + missed);
+
+		/* it is possible that hit + missed will overflow and be zero */
+		if (!(hit + missed)) {
+			trace_printk("hit + missed overflowed and totalled zero!\n");
+			hit--; /* make it non zero */
+		}
+
+		/* Calculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / (hit + missed);
+		trace_printk("%ld ns per entry\n", avg);
+	}
+}
+
+static void wait_to_die(void)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+static int ring_buffer_consumer_thread(void *arg)
+{
+	while (!break_test()) {
+		complete(&read_start);
+
+		ring_buffer_consumer();
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (break_test())
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (!kthread_should_stop())
+		wait_to_die();
+
+	return 0;
+}
+
+static int ring_buffer_producer_thread(void *arg)
+{
+	while (!break_test()) {
+		ring_buffer_reset(buffer);
+
+		if (consumer) {
+			wake_up_process(consumer);
+			wait_for_completion(&read_start);
+		}
+
+		ring_buffer_producer();
+		if (break_test())
+			goto out_kill;
+
+		trace_printk("Sleeping for 10 secs\n");
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (break_test())
+			goto out_kill;
+		schedule_timeout(HZ * SLEEP_TIME);
+	}
+
+out_kill:
+	__set_current_state(TASK_RUNNING);
+	if (!kthread_should_stop())
+		wait_to_die();
+
+	return 0;
+}
+
+static int __init ring_buffer_benchmark_init(void)
+{
+	int ret;
+
+	/* make a one meg buffer in overwrite mode */
+	buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
+	if (!buffer)
+		return -ENOMEM;
+
+	if (!disable_reader) {
+		consumer = kthread_create(ring_buffer_consumer_thread,
+					  NULL, "rb_consumer");
+		ret = PTR_ERR(consumer);
+		if (IS_ERR(consumer))
+			goto out_fail;
+	}
+
+	producer = kthread_run(ring_buffer_producer_thread,
+			       NULL, "rb_producer");
+	ret = PTR_ERR(producer);
+
+	if (IS_ERR(producer))
+		goto out_kill;
+
+	/*
+	 * Run them as low-prio background tasks by default:
+	 */
+	if (!disable_reader) {
+		if (consumer_fifo >= 2)
+			sched_set_fifo(consumer);
+		else if (consumer_fifo == 1)
+			sched_set_fifo_low(consumer);
+		else
+			set_user_nice(consumer, consumer_nice);
+	}
+
+	if (producer_fifo >= 2)
+		sched_set_fifo(producer);
+	else if (producer_fifo == 1)
+		sched_set_fifo_low(producer);
+	else
+		set_user_nice(producer, producer_nice);
+
+	return 0;
+
+ out_kill:
+	if (consumer)
+		kthread_stop(consumer);
+
+ out_fail:
+	ring_buffer_free(buffer);
+	return ret;
+}
+
+static void __exit ring_buffer_benchmark_exit(void)
+{
+	kthread_stop(producer);
+	if (consumer)
+		kthread_stop(consumer);
+	ring_buffer_free(buffer);
+}
+
+module_init(ring_buffer_benchmark_init);
+module_exit(ring_buffer_benchmark_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("ring_buffer_benchmark");
+MODULE_LICENSE("GPL");

linux-7.2.3/kernel/trace/rpm-traces.c

@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Ming Lei <ming.lei@canonical.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/rpm.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_return_int);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_suspend);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_resume);

linux-7.2.3/kernel/trace/rv/Kconfig

@@ -0,0 +1,113 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_EVENTS
+	bool
+
+config RV_MON_MAINTENANCE_EVENTS
+	bool
+
+config DA_MON_EVENTS_IMPLICIT
+	select RV_MON_EVENTS
+	select RV_MON_MAINTENANCE_EVENTS
+	bool
+
+config DA_MON_EVENTS_ID
+	select RV_MON_EVENTS
+	select RV_MON_MAINTENANCE_EVENTS
+	bool
+
+config LTL_MON_EVENTS_ID
+	select RV_MON_EVENTS
+	bool
+
+config RV_LTL_MONITOR
+	bool
+
+config RV_HA_MONITOR
+	bool
+
+config HA_MON_EVENTS_IMPLICIT
+	select DA_MON_EVENTS_IMPLICIT
+	select RV_HA_MONITOR
+	bool
+
+config HA_MON_EVENTS_ID
+	select DA_MON_EVENTS_ID
+	select RV_HA_MONITOR
+	bool
+
+menuconfig RV
+	bool "Runtime Verification"
+	select TRACING
+	help
+	  Enable the kernel runtime verification infrastructure. RV is a
+	  lightweight (yet rigorous) method that complements classical
+	  exhaustive verification techniques (such as model checking and
+	  theorem proving). RV works by analyzing the trace of the system's
+	  actual execution, comparing it against a formal specification of
+	  the system behavior.
+
+	  For further information, see:
+	    Documentation/trace/rv/runtime-verification.rst
+
+config RV_PER_TASK_MONITORS
+	int "Maximum number of per-task monitor"
+	depends on RV
+	range 1 8
+	default 2
+	help
+	  This option configures the maximum number of per-task RV monitors that can run
+	  simultaneously.
+
+source "kernel/trace/rv/monitors/wip/Kconfig"
+source "kernel/trace/rv/monitors/wwnr/Kconfig"
+
+source "kernel/trace/rv/monitors/sched/Kconfig"
+source "kernel/trace/rv/monitors/sco/Kconfig"
+source "kernel/trace/rv/monitors/snroc/Kconfig"
+source "kernel/trace/rv/monitors/scpd/Kconfig"
+source "kernel/trace/rv/monitors/snep/Kconfig"
+source "kernel/trace/rv/monitors/sts/Kconfig"
+source "kernel/trace/rv/monitors/nrp/Kconfig"
+source "kernel/trace/rv/monitors/sssw/Kconfig"
+source "kernel/trace/rv/monitors/opid/Kconfig"
+# Add new sched monitors here
+
+source "kernel/trace/rv/monitors/rtapp/Kconfig"
+source "kernel/trace/rv/monitors/pagefault/Kconfig"
+source "kernel/trace/rv/monitors/sleep/Kconfig"
+# Add new rtapp monitors here
+
+source "kernel/trace/rv/monitors/stall/Kconfig"
+source "kernel/trace/rv/monitors/deadline/Kconfig"
+source "kernel/trace/rv/monitors/nomiss/Kconfig"
+# Add new deadline monitors here
+
+# Add new monitors here
+
+config RV_REACTORS
+	bool "Runtime verification reactors"
+	default y
+	depends on RV
+	help
+	  Enables the online runtime verification reactors. A runtime
+	  monitor can cause a reaction to the detection of an exception
+	  on the model's execution. By default, the monitors have
+	  tracing reactions, printing the monitor output via tracepoints,
+	  but other reactions can be added (on-demand) via this interface.
+
+config RV_REACT_PRINTK
+	bool "Printk reactor"
+	depends on RV_REACTORS
+	default y
+	help
+	  Enables the printk reactor. The printk reactor emits a printk()
+	  message if an exception is found.
+
+config RV_REACT_PANIC
+	bool "Panic reactor"
+	depends on RV_REACTORS
+	default y
+	help
+	  Enables the panic reactor. The panic reactor emits a printk()
+	  message if an exception is found and panic()s the system.

linux-7.2.3/kernel/trace/rv/Makefile

@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ccflags-y += -I $(src)		# needed for trace events
+
+obj-$(CONFIG_RV) += rv.o
+obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o
+obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o
+obj-$(CONFIG_RV_MON_SCHED) += monitors/sched/sched.o
+obj-$(CONFIG_RV_MON_SCO) += monitors/sco/sco.o
+obj-$(CONFIG_RV_MON_SNROC) += monitors/snroc/snroc.o
+obj-$(CONFIG_RV_MON_SCPD) += monitors/scpd/scpd.o
+obj-$(CONFIG_RV_MON_SNEP) += monitors/snep/snep.o
+obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o
+obj-$(CONFIG_RV_MON_PAGEFAULT) += monitors/pagefault/pagefault.o
+obj-$(CONFIG_RV_MON_SLEEP) += monitors/sleep/sleep.o
+obj-$(CONFIG_RV_MON_STS) += monitors/sts/sts.o
+obj-$(CONFIG_RV_MON_NRP) += monitors/nrp/nrp.o
+obj-$(CONFIG_RV_MON_SSSW) += monitors/sssw/sssw.o
+obj-$(CONFIG_RV_MON_OPID) += monitors/opid/opid.o
+obj-$(CONFIG_RV_MON_STALL) += monitors/stall/stall.o
+obj-$(CONFIG_RV_MON_DEADLINE) += monitors/deadline/deadline.o
+obj-$(CONFIG_RV_MON_NOMISS) += monitors/nomiss/nomiss.o
+# Add new monitors here
+obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
+obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o
+obj-$(CONFIG_RV_REACT_PANIC) += reactor_panic.o

linux-7.2.3/kernel/trace/rv/monitors/deadline/Kconfig

@@ -0,0 +1,10 @@
+config RV_MON_DEADLINE
+	depends on RV
+	bool "deadline monitor"
+	help
+	  Collection of monitors to check the deadline scheduler and server
+	  behave according to specifications. Enable this to enable all
+	  scheduler specification supported by the current kernel.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_deadline.rst

linux-7.2.3/kernel/trace/rv/monitors/deadline/deadline.c

@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <linux/kallsyms.h>
+
+#define MODULE_NAME "deadline"
+
+#include "deadline.h"
+
+struct rv_monitor rv_deadline = {
+	.name = "deadline",
+	.description = "container for several deadline scheduler specifications.",
+	.enable = NULL,
+	.disable = NULL,
+	.reset = NULL,
+	.enabled = 0,
+};
+
+/* Used by other monitors */
+struct sched_class *rv_ext_sched_class;
+
+static int __init register_deadline(void)
+{
+	if (IS_ENABLED(CONFIG_SCHED_CLASS_EXT)) {
+		rv_ext_sched_class = (void *)kallsyms_lookup_name("ext_sched_class");
+		if (!rv_ext_sched_class)
+			pr_warn("rv: Missing ext_sched_class, monitors may not work.\n");
+	}
+	return rv_register_monitor(&rv_deadline, NULL);
+}
+
+static void __exit unregister_deadline(void)
+{
+	rv_unregister_monitor(&rv_deadline);
+}
+
+module_init(register_deadline);
+module_exit(unregister_deadline);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("deadline: container for several deadline scheduler specifications.");

linux-7.2.3/kernel/trace/rv/monitors/deadline/deadline.h

@@ -0,0 +1,203 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/sched/deadline.h>
+#include <asm/syscall.h>
+#include <uapi/linux/sched/types.h>
+#include <trace/events/sched.h>
+
+/*
+ * Dummy values if not available
+ */
+#ifndef __NR_sched_setscheduler
+#define __NR_sched_setscheduler -__COUNTER__
+#endif
+#ifndef __NR_sched_setattr
+#define __NR_sched_setattr -__COUNTER__
+#endif
+
+extern struct rv_monitor rv_deadline;
+/* Initialised when registering the deadline container */
+extern struct sched_class *rv_ext_sched_class;
+
+/*
+ * If both have dummy values, the syscalls are not supported and we don't even
+ * need to register the handler.
+ */
+static inline bool should_skip_syscall_handle(void)
+{
+	return __NR_sched_setattr < 0 && __NR_sched_setscheduler < 0;
+}
+
+/*
+ * is_supported_type - return true if @type is supported by the deadline monitors
+ */
+static inline bool is_supported_type(u8 type)
+{
+	return type == DL_TASK || type == DL_SERVER_FAIR || type == DL_SERVER_EXT;
+}
+
+/*
+ * is_server_type - return true if @type is a supported server
+ */
+static inline bool is_server_type(u8 type)
+{
+	return is_supported_type(type) && type != DL_TASK;
+}
+
+/*
+ * Use negative numbers for the server.
+ * Currently only one fair server per CPU, may change in the future.
+ */
+#define fair_server_id(cpu) (-cpu)
+#define ext_server_id(cpu) (-cpu - num_possible_cpus())
+#define NO_SERVER_ID (-2 * num_possible_cpus())
+/*
+ * Get a unique id used for dl entities
+ *
+ * The cpu is not required for tasks as the pid is used there, if this function
+ * is called on a dl_se that for sure corresponds to a task, DL_TASK can be
+ * used in place of cpu.
+ * We need the cpu for servers as it is provided in the tracepoint and we
+ * cannot easily retrieve it from the dl_se (requires the struct rq definition).
+ */
+static inline int get_entity_id(struct sched_dl_entity *dl_se, int cpu, u8 type)
+{
+	if (dl_server(dl_se) && type != DL_TASK) {
+		if (type == DL_SERVER_FAIR)
+			return fair_server_id(cpu);
+		if (type == DL_SERVER_EXT)
+			return ext_server_id(cpu);
+		return NO_SERVER_ID;
+	}
+	return dl_task_of(dl_se)->pid;
+}
+
+static inline bool task_is_scx_enabled(struct task_struct *tsk)
+{
+	return IS_ENABLED(CONFIG_SCHED_CLASS_EXT) &&
+	       tsk->sched_class == rv_ext_sched_class;
+}
+
+/* Expand id and target as arguments for da functions */
+#define EXPAND_ID(dl_se, cpu, type) get_entity_id(dl_se, cpu, type), dl_se
+#define EXPAND_ID_TASK(tsk) get_entity_id(&tsk->dl, task_cpu(tsk), DL_TASK), &tsk->dl
+
+static inline u8 get_server_type(struct task_struct *tsk)
+{
+	if (tsk->policy == SCHED_NORMAL || tsk->policy == SCHED_EXT ||
+	    tsk->policy == SCHED_BATCH || tsk->policy == SCHED_IDLE)
+		return task_is_scx_enabled(tsk) ? DL_SERVER_EXT : DL_SERVER_FAIR;
+	return DL_OTHER;
+}
+
+static inline int extract_params(struct pt_regs *regs, long id, pid_t *pid_out)
+{
+	size_t size = offsetofend(struct sched_attr, sched_flags);
+	struct sched_attr __user *uattr;
+	struct sched_attr attr;
+	int new_policy = -1, ret;
+	unsigned long args[6];
+
+	switch (id) {
+	case __NR_sched_setscheduler:
+		syscall_get_arguments(current, regs, args);
+		*pid_out = args[0];
+		new_policy = args[1];
+		break;
+	case __NR_sched_setattr:
+		syscall_get_arguments(current, regs, args);
+		*pid_out = args[0];
+		uattr = (struct sched_attr __user *)args[1];
+		/*
+		 * Just copy up to sched_flags, we are not interested after that
+		 */
+		ret = copy_struct_from_user(&attr, size, uattr, size);
+		if (ret)
+			return ret;
+		if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY)
+			return -EINVAL;
+		new_policy = attr.sched_policy;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return new_policy & ~SCHED_RESET_ON_FORK;
+}
+
+/* Helper functions requiring DA/HA utilities */
+#ifdef RV_MON_TYPE
+
+/*
+ * get_fair_server - get the fair server associated to a task
+ *
+ * If the task is a boosted task, the server is available in the task_struct,
+ * otherwise grab the dl entity saved for the CPU where the task is enqueued.
+ * This function assumes the task is enqueued somewhere.
+ */
+static inline struct sched_dl_entity *get_server(struct task_struct *tsk, u8 type)
+{
+	if (tsk->dl_server && get_server_type(tsk) == type)
+		return tsk->dl_server;
+	if (type == DL_SERVER_FAIR)
+		return da_get_target_by_id(fair_server_id(task_cpu(tsk)));
+	if (type == DL_SERVER_EXT)
+		return da_get_target_by_id(ext_server_id(task_cpu(tsk)));
+	return NULL;
+}
+
+/*
+ * Initialise monitors for all tasks and pre-allocate the storage for servers.
+ * This is necessary since we don't have access to the servers here and
+ * allocation can cause deadlocks from their tracepoints. We can only fill
+ * pre-initialised storage from there.
+ */
+static inline int init_storage(bool skip_tasks)
+{
+	struct task_struct *g, *p;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		if (!da_create_empty_storage(fair_server_id(cpu)))
+			goto fail;
+		if (IS_ENABLED(CONFIG_SCHED_CLASS_EXT) &&
+		    !da_create_empty_storage(ext_server_id(cpu)))
+			goto fail;
+	}
+
+	if (skip_tasks)
+		return 0;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
+		if (p->policy == SCHED_DEADLINE) {
+			if (!da_create_storage(EXPAND_ID_TASK(p), NULL)) {
+				read_unlock(&tasklist_lock);
+				goto fail;
+			}
+		}
+	}
+	read_unlock(&tasklist_lock);
+	return 0;
+
+fail:
+	da_monitor_destroy();
+	return -ENOMEM;
+}
+
+static void __maybe_unused handle_newtask(void *data, struct task_struct *task, u64 flags)
+{
+	/* Might be superfluous as tasks are not started with this policy.. */
+	if (task->policy == SCHED_DEADLINE)
+		da_create_storage(EXPAND_ID_TASK(task), NULL);
+}
+
+static void __maybe_unused handle_exit(void *data, struct task_struct *p, bool group_dead)
+{
+	if (p->policy == SCHED_DEADLINE)
+		da_destroy_storage(get_entity_id(&p->dl, DL_TASK, DL_TASK));
+}
+
+#endif

linux-7.2.3/kernel/trace/rv/monitors/nomiss/Kconfig

@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_NOMISS
+	depends on RV
+	depends on HAVE_SYSCALL_TRACEPOINTS
+	depends on RV_MON_DEADLINE
+	default y
+	select HA_MON_EVENTS_ID
+	bool "nomiss monitor"
+	help
+	  Monitor to ensure dl entities run to completion before their deadiline.
+	  This monitor is part of the deadline monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_deadline.rst

linux-7.2.3/kernel/trace/rv/monitors/nomiss/nomiss.c

@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "nomiss"
+
+#include <uapi/linux/sched/types.h>
+#include <trace/events/syscalls.h>
+#include <trace/events/sched.h>
+#include <trace/events/task.h>
+#include <rv_trace.h>
+
+#define RV_MON_TYPE RV_MON_PER_OBJ
+#define HA_TIMER_TYPE HA_TIMER_WHEEL
+/* The start condition is on sched_switch, it's dangerous to allocate there */
+#define DA_SKIP_AUTO_ALLOC
+typedef struct sched_dl_entity *monitor_target;
+#include "nomiss.h"
+#include <rv/ha_monitor.h>
+#include <monitors/deadline/deadline.h>
+
+/*
+ * User configurable deadline threshold. If the total utilisation of deadline
+ * tasks is larger than 1, they are only guaranteed bounded tardiness. See
+ * Documentation/scheduler/sched-deadline.rst for more details.
+ * The minimum tardiness without sched_feat(HRTICK_DL) is 1 tick to accommodate
+ * for throttle enforced on the next tick.
+ */
+static u64 deadline_thresh = TICK_NSEC;
+module_param(deadline_thresh, ullong, 0644);
+#define DEADLINE_NS(ha_mon) (ha_get_target(ha_mon)->dl_deadline + deadline_thresh)
+
+static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs_nomiss env, u64 time_ns)
+{
+	if (env == clk_nomiss)
+		return ha_get_clk_ns(ha_mon, env, time_ns);
+	else if (env == is_constr_dl_nomiss)
+		return !dl_is_implicit(ha_get_target(ha_mon));
+	else if (env == is_defer_nomiss)
+		return ha_get_target(ha_mon)->dl_defer;
+	return ENV_INVALID_VALUE;
+}
+
+static void ha_reset_env(struct ha_monitor *ha_mon, enum envs_nomiss env, u64 time_ns)
+{
+	if (env == clk_nomiss)
+		ha_reset_clk_ns(ha_mon, env, time_ns);
+}
+
+static inline bool ha_verify_invariants(struct ha_monitor *ha_mon,
+					enum states curr_state, enum events event,
+					enum states next_state, u64 time_ns)
+{
+	if (curr_state == ready_nomiss)
+		return ha_check_invariant_ns(ha_mon, clk_nomiss, time_ns);
+	else if (curr_state == running_nomiss)
+		return ha_check_invariant_ns(ha_mon, clk_nomiss, time_ns);
+	return true;
+}
+
+static inline void ha_convert_inv_guard(struct ha_monitor *ha_mon,
+					enum states curr_state, enum events event,
+					enum states next_state, u64 time_ns)
+{
+	if (curr_state == next_state)
+		return;
+	if (curr_state == ready_nomiss)
+		ha_inv_to_guard(ha_mon, clk_nomiss, DEADLINE_NS(ha_mon), time_ns);
+	else if (curr_state == running_nomiss)
+		ha_inv_to_guard(ha_mon, clk_nomiss, DEADLINE_NS(ha_mon), time_ns);
+}
+
+static inline bool ha_verify_guards(struct ha_monitor *ha_mon,
+				    enum states curr_state, enum events event,
+				    enum states next_state, u64 time_ns)
+{
+	bool res = true;
+
+	if (curr_state == ready_nomiss && event == dl_replenish_nomiss)
+		ha_reset_env(ha_mon, clk_nomiss, time_ns);
+	else if (curr_state == ready_nomiss && event == dl_throttle_nomiss)
+		res = ha_get_env(ha_mon, is_defer_nomiss, time_ns) == 1ull;
+	else if (curr_state == idle_nomiss && event == dl_replenish_nomiss)
+		ha_reset_env(ha_mon, clk_nomiss, time_ns);
+	else if (curr_state == running_nomiss && event == dl_replenish_nomiss)
+		ha_reset_env(ha_mon, clk_nomiss, time_ns);
+	else if (curr_state == sleeping_nomiss && event == dl_replenish_nomiss)
+		ha_reset_env(ha_mon, clk_nomiss, time_ns);
+	else if (curr_state == sleeping_nomiss && event == dl_throttle_nomiss)
+		res = ha_get_env(ha_mon, is_constr_dl_nomiss, time_ns) == 1ull ||
+		      ha_get_env(ha_mon, is_defer_nomiss, time_ns) == 1ull;
+	else if (curr_state == throttled_nomiss && event == dl_replenish_nomiss)
+		ha_reset_env(ha_mon, clk_nomiss, time_ns);
+	return res;
+}
+
+static inline void ha_setup_invariants(struct ha_monitor *ha_mon,
+				       enum states curr_state, enum events event,
+				       enum states next_state, u64 time_ns)
+{
+	if (next_state == curr_state && event != dl_replenish_nomiss)
+		return;
+	if (next_state == ready_nomiss)
+		ha_start_timer_ns(ha_mon, clk_nomiss, DEADLINE_NS(ha_mon), time_ns);
+	else if (next_state == running_nomiss)
+		ha_start_timer_ns(ha_mon, clk_nomiss, DEADLINE_NS(ha_mon), time_ns);
+	else if (curr_state == ready_nomiss)
+		ha_cancel_timer(ha_mon);
+	else if (curr_state == running_nomiss)
+		ha_cancel_timer(ha_mon);
+}
+
+static bool ha_verify_constraint(struct ha_monitor *ha_mon,
+				 enum states curr_state, enum events event,
+				 enum states next_state, u64 time_ns)
+{
+	if (!ha_verify_invariants(ha_mon, curr_state, event, next_state, time_ns))
+		return false;
+
+	ha_convert_inv_guard(ha_mon, curr_state, event, next_state, time_ns);
+
+	if (!ha_verify_guards(ha_mon, curr_state, event, next_state, time_ns))
+		return false;
+
+	ha_setup_invariants(ha_mon, curr_state, event, next_state, time_ns);
+
+	return true;
+}
+
+static void handle_dl_replenish(void *data, struct sched_dl_entity *dl_se,
+				int cpu, u8 type)
+{
+	if (is_supported_type(type))
+		da_handle_event(EXPAND_ID(dl_se, cpu, type), dl_replenish_nomiss);
+}
+
+static void handle_dl_throttle(void *data, struct sched_dl_entity *dl_se,
+			       int cpu, u8 type)
+{
+	if (is_supported_type(type))
+		da_handle_event(EXPAND_ID(dl_se, cpu, type), dl_throttle_nomiss);
+}
+
+static void handle_dl_server_stop(void *data, struct sched_dl_entity *dl_se,
+				  int cpu, u8 type)
+{
+	/*
+	 * This isn't the standard use of da_handle_start_run_event since this
+	 * event cannot only occur from the initial state.
+	 * It is fine to use here because it always brings to a known state and
+	 * the fact we "pretend" the transition starts from the initial state
+	 * has no side effect.
+	 */
+	if (is_supported_type(type))
+		da_handle_start_run_event(EXPAND_ID(dl_se, cpu, type), dl_server_stop_nomiss);
+}
+
+static inline void handle_server_switch(struct task_struct *next, int cpu, u8 type)
+{
+	struct sched_dl_entity *dl_se = get_server(next, type);
+
+	if (dl_se && is_idle_task(next))
+		da_handle_event(EXPAND_ID(dl_se, cpu, type), dl_server_idle_nomiss);
+}
+
+static void handle_sched_switch(void *data, bool preempt,
+				struct task_struct *prev,
+				struct task_struct *next,
+				unsigned int prev_state)
+{
+	int cpu = task_cpu(next);
+
+	if (prev_state != TASK_RUNNING && !preempt && prev->policy == SCHED_DEADLINE)
+		da_handle_event(EXPAND_ID_TASK(prev), sched_switch_suspend_nomiss);
+	if (next->policy == SCHED_DEADLINE)
+		da_handle_start_run_event(EXPAND_ID_TASK(next), sched_switch_in_nomiss);
+
+	/*
+	 * The server is available in next only if the next task is boosted,
+	 * otherwise we need to retrieve it.
+	 * Here the server continues in the state running/armed until actually
+	 * stopped, this works since we continue expecting a throttle.
+	 */
+	if (next->dl_server)
+		da_handle_start_event(EXPAND_ID(next->dl_server, cpu,
+						get_server_type(next)),
+				      sched_switch_in_nomiss);
+	else {
+		handle_server_switch(next, cpu, DL_SERVER_FAIR);
+		if (IS_ENABLED(CONFIG_SCHED_CLASS_EXT))
+			handle_server_switch(next, cpu, DL_SERVER_EXT);
+	}
+}
+
+static void handle_sys_enter(void *data, struct pt_regs *regs, long id)
+{
+	struct task_struct *p;
+	int new_policy = -1;
+	pid_t pid = 0;
+
+	new_policy = extract_params(regs, id, &pid);
+	if (new_policy < 0)
+		return;
+	guard(rcu)();
+	p = pid ? find_task_by_vpid(pid) : current;
+	if (unlikely(!p) || new_policy == p->policy)
+		return;
+
+	if (p->policy == SCHED_DEADLINE)
+		da_reset(EXPAND_ID_TASK(p));
+	else if (new_policy == SCHED_DEADLINE)
+		da_create_or_get(EXPAND_ID_TASK(p));
+}
+
+static void handle_sched_wakeup(void *data, struct task_struct *tsk)
+{
+	if (tsk->policy == SCHED_DEADLINE)
+		da_handle_event(EXPAND_ID_TASK(tsk), sched_wakeup_nomiss);
+}
+
+static int enable_nomiss(void)
+{
+	int retval;
+
+	retval = ha_monitor_init();
+	if (retval)
+		return retval;
+
+	retval = init_storage(false);
+	if (retval)
+		return retval;
+	rv_attach_trace_probe("nomiss", sched_dl_replenish_tp, handle_dl_replenish);
+	rv_attach_trace_probe("nomiss", sched_dl_throttle_tp, handle_dl_throttle);
+	rv_attach_trace_probe("nomiss", sched_dl_server_stop_tp, handle_dl_server_stop);
+	rv_attach_trace_probe("nomiss", sched_switch, handle_sched_switch);
+	rv_attach_trace_probe("nomiss", sched_wakeup, handle_sched_wakeup);
+	if (!should_skip_syscall_handle())
+		rv_attach_trace_probe("nomiss", sys_enter, handle_sys_enter);
+	rv_attach_trace_probe("nomiss", task_newtask, handle_newtask);
+	rv_attach_trace_probe("nomiss", sched_process_exit, handle_exit);
+
+	return 0;
+}
+
+static void disable_nomiss(void)
+{
+	rv_this.enabled = 0;
+
+	/* Those are RCU writers, detach earlier hoping to close a bit faster */
+	rv_detach_trace_probe("nomiss", task_newtask, handle_newtask);
+	rv_detach_trace_probe("nomiss", sched_process_exit, handle_exit);
+	if (!should_skip_syscall_handle())
+		rv_detach_trace_probe("nomiss", sys_enter, handle_sys_enter);
+
+	rv_detach_trace_probe("nomiss", sched_dl_replenish_tp, handle_dl_replenish);
+	rv_detach_trace_probe("nomiss", sched_dl_throttle_tp, handle_dl_throttle);
+	rv_detach_trace_probe("nomiss", sched_dl_server_stop_tp, handle_dl_server_stop);
+	rv_detach_trace_probe("nomiss", sched_switch, handle_sched_switch);
+	rv_detach_trace_probe("nomiss", sched_wakeup, handle_sched_wakeup);
+
+	ha_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "nomiss",
+	.description = "dl entities run to completion before their deadline.",
+	.enable = enable_nomiss,
+	.disable = disable_nomiss,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_nomiss(void)
+{
+	return rv_register_monitor(&rv_this, &rv_deadline);
+}
+
+static void __exit unregister_nomiss(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_nomiss);
+module_exit(unregister_nomiss);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("nomiss: dl entities run to completion before their deadline.");

linux-7.2.3/kernel/trace/rv/monitors/nomiss/nomiss.h

@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of nomiss automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME nomiss
+
+enum states_nomiss {
+	ready_nomiss,
+	idle_nomiss,
+	running_nomiss,
+	sleeping_nomiss,
+	throttled_nomiss,
+	state_max_nomiss,
+};
+
+#define INVALID_STATE state_max_nomiss
+
+enum events_nomiss {
+	dl_replenish_nomiss,
+	dl_server_idle_nomiss,
+	dl_server_stop_nomiss,
+	dl_throttle_nomiss,
+	sched_switch_in_nomiss,
+	sched_switch_suspend_nomiss,
+	sched_wakeup_nomiss,
+	event_max_nomiss,
+};
+
+enum envs_nomiss {
+	clk_nomiss,
+	is_constr_dl_nomiss,
+	is_defer_nomiss,
+	env_max_nomiss,
+	env_max_stored_nomiss = is_constr_dl_nomiss,
+};
+
+_Static_assert(env_max_stored_nomiss <= MAX_HA_ENV_LEN, "Not enough slots");
+#define HA_CLK_NS
+
+struct automaton_nomiss {
+	char *state_names[state_max_nomiss];
+	char *event_names[event_max_nomiss];
+	char *env_names[env_max_nomiss];
+	unsigned char function[state_max_nomiss][event_max_nomiss];
+	unsigned char initial_state;
+	bool final_states[state_max_nomiss];
+};
+
+static const struct automaton_nomiss automaton_nomiss = {
+	.state_names = {
+		"ready",
+		"idle",
+		"running",
+		"sleeping",
+		"throttled",
+	},
+	.event_names = {
+		"dl_replenish",
+		"dl_server_idle",
+		"dl_server_stop",
+		"dl_throttle",
+		"sched_switch_in",
+		"sched_switch_suspend",
+		"sched_wakeup",
+	},
+	.env_names = {
+		"clk",
+		"is_constr_dl",
+		"is_defer",
+	},
+	.function = {
+		{
+			ready_nomiss,
+			idle_nomiss,
+			sleeping_nomiss,
+			throttled_nomiss,
+			running_nomiss,
+			INVALID_STATE,
+			ready_nomiss,
+		},
+		{
+			ready_nomiss,
+			idle_nomiss,
+			sleeping_nomiss,
+			throttled_nomiss,
+			running_nomiss,
+			INVALID_STATE,
+			INVALID_STATE,
+		},
+		{
+			running_nomiss,
+			idle_nomiss,
+			sleeping_nomiss,
+			throttled_nomiss,
+			running_nomiss,
+			sleeping_nomiss,
+			running_nomiss,
+		},
+		{
+			ready_nomiss,
+			sleeping_nomiss,
+			sleeping_nomiss,
+			throttled_nomiss,
+			running_nomiss,
+			INVALID_STATE,
+			ready_nomiss,
+		},
+		{
+			ready_nomiss,
+			throttled_nomiss,
+			INVALID_STATE,
+			throttled_nomiss,
+			INVALID_STATE,
+			throttled_nomiss,
+			throttled_nomiss,
+		},
+	},
+	.initial_state = ready_nomiss,
+	.final_states = { 1, 0, 0, 0, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/nomiss/nomiss_trace.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_NOMISS
+DEFINE_EVENT(event_da_monitor_id, event_nomiss,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_nomiss,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+
+DEFINE_EVENT(error_env_da_monitor_id, error_env_nomiss,
+	     TP_PROTO(int id, char *state, char *event, char *env),
+	     TP_ARGS(id, state, event, env));
+#endif /* CONFIG_RV_MON_NOMISS */

linux-7.2.3/kernel/trace/rv/monitors/nrp/Kconfig

@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_NRP
+	depends on RV
+	depends on RV_MON_SCHED
+	default y if !ARM64
+	select DA_MON_EVENTS_ID
+	bool "nrp monitor"
+	help
+	  Monitor to ensure preemption requires need resched.
+	  This monitor is part of the sched monitors collection.
+
+	  This monitor is unstable on arm64, say N unless you are testing it.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/nrp/nrp.c

@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "nrp"
+
+#include <trace/events/irq.h>
+#include <trace/events/sched.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_TASK
+#include "nrp.h"
+#include <rv/da_monitor.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <asm/trace/irq_vectors.h>
+
+static void handle_vector_irq_entry(void *data, int vector)
+{
+	da_handle_event(current, irq_entry_nrp);
+}
+
+static void attach_vector_irq(void)
+{
+	rv_attach_trace_probe("nrp", local_timer_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_IRQ_WORK))
+		rv_attach_trace_probe("nrp", irq_work_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_SMP)) {
+		rv_attach_trace_probe("nrp", reschedule_entry, handle_vector_irq_entry);
+		rv_attach_trace_probe("nrp", call_function_entry, handle_vector_irq_entry);
+		rv_attach_trace_probe("nrp", call_function_single_entry, handle_vector_irq_entry);
+	}
+}
+
+static void detach_vector_irq(void)
+{
+	rv_detach_trace_probe("nrp", local_timer_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_IRQ_WORK))
+		rv_detach_trace_probe("nrp", irq_work_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_SMP)) {
+		rv_detach_trace_probe("nrp", reschedule_entry, handle_vector_irq_entry);
+		rv_detach_trace_probe("nrp", call_function_entry, handle_vector_irq_entry);
+		rv_detach_trace_probe("nrp", call_function_single_entry, handle_vector_irq_entry);
+	}
+}
+
+#else
+/* We assume irq_entry tracepoints are sufficient on other architectures */
+static void attach_vector_irq(void) { }
+static void detach_vector_irq(void) { }
+#endif
+
+static void handle_irq_entry(void *data, int irq, struct irqaction *action)
+{
+	da_handle_event(current, irq_entry_nrp);
+}
+
+static void handle_sched_need_resched(void *data, struct task_struct *tsk,
+				      int cpu, int tif)
+{
+	/*
+	 * Although need_resched leads to both the rescheduling and preempt_irq
+	 * states, it is safer to start the monitor always in preempt_irq,
+	 * which may not mirror the system state but makes the monitor simpler,
+	 */
+	if (tif == TIF_NEED_RESCHED)
+		da_handle_start_event(tsk, sched_need_resched_nrp);
+}
+
+static void handle_schedule_entry(void *data, bool preempt)
+{
+	if (preempt)
+		da_handle_event(current, schedule_entry_preempt_nrp);
+	else
+		da_handle_event(current, schedule_entry_nrp);
+}
+
+static int enable_nrp(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("nrp", irq_handler_entry, handle_irq_entry);
+	rv_attach_trace_probe("nrp", sched_set_need_resched_tp, handle_sched_need_resched);
+	rv_attach_trace_probe("nrp", sched_entry_tp, handle_schedule_entry);
+	attach_vector_irq();
+
+	return 0;
+}
+
+static void disable_nrp(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("nrp", irq_handler_entry, handle_irq_entry);
+	rv_detach_trace_probe("nrp", sched_set_need_resched_tp, handle_sched_need_resched);
+	rv_detach_trace_probe("nrp", sched_entry_tp, handle_schedule_entry);
+	detach_vector_irq();
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "nrp",
+	.description = "need resched preempts.",
+	.enable = enable_nrp,
+	.disable = disable_nrp,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_nrp(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_nrp(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_nrp);
+module_exit(unregister_nrp);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("nrp: need resched preempts.");

linux-7.2.3/kernel/trace/rv/monitors/nrp/nrp.h

@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of nrp automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME nrp
+
+enum states_nrp {
+	preempt_irq_nrp,
+	any_thread_running_nrp,
+	nested_preempt_nrp,
+	rescheduling_nrp,
+	state_max_nrp,
+};
+
+#define INVALID_STATE state_max_nrp
+
+enum events_nrp {
+	irq_entry_nrp,
+	sched_need_resched_nrp,
+	schedule_entry_nrp,
+	schedule_entry_preempt_nrp,
+	event_max_nrp,
+};
+
+struct automaton_nrp {
+	char *state_names[state_max_nrp];
+	char *event_names[event_max_nrp];
+	unsigned char function[state_max_nrp][event_max_nrp];
+	unsigned char initial_state;
+	bool final_states[state_max_nrp];
+};
+
+static const struct automaton_nrp automaton_nrp = {
+	.state_names = {
+		"preempt_irq",
+		"any_thread_running",
+		"nested_preempt",
+		"rescheduling",
+	},
+	.event_names = {
+		"irq_entry",
+		"sched_need_resched",
+		"schedule_entry",
+		"schedule_entry_preempt",
+	},
+	.function = {
+		{
+			preempt_irq_nrp,
+			preempt_irq_nrp,
+			nested_preempt_nrp,
+			nested_preempt_nrp,
+		},
+		{
+			any_thread_running_nrp,
+			rescheduling_nrp,
+			any_thread_running_nrp,
+			INVALID_STATE,
+		},
+		{
+			nested_preempt_nrp,
+			preempt_irq_nrp,
+			any_thread_running_nrp,
+			any_thread_running_nrp,
+		},
+		{
+			preempt_irq_nrp,
+			rescheduling_nrp,
+			any_thread_running_nrp,
+			any_thread_running_nrp,
+		},
+	},
+	.initial_state = preempt_irq_nrp,
+	.final_states = { 0, 1, 0, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/nrp/nrp_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_NRP
+DEFINE_EVENT(event_da_monitor_id, event_nrp,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_nrp,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+#endif /* CONFIG_RV_MON_NRP */

linux-7.2.3/kernel/trace/rv/monitors/opid/Kconfig

@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_OPID
+	depends on RV
+	depends on RV_MON_SCHED
+	default y
+	select HA_MON_EVENTS_IMPLICIT
+	bool "opid monitor"
+	help
+	  Monitor to ensure operations like wakeup and need resched occur with
+	  interrupts and preemption disabled.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/opid/opid.c

@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "opid"
+
+#include <trace/events/sched.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_CPU
+#include "opid.h"
+#include <rv/ha_monitor.h>
+
+static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs_opid env, u64 time_ns)
+{
+	if (env == irq_off_opid)
+		return irqs_disabled();
+	else if (env == preempt_off_opid) {
+		if (IS_ENABLED(CONFIG_PREEMPTION))
+			return (preempt_count() & PREEMPT_MASK) > 0;
+		return true;
+	}
+	return ENV_INVALID_VALUE;
+}
+
+static inline bool ha_verify_guards(struct ha_monitor *ha_mon,
+				    enum states curr_state, enum events event,
+				    enum states next_state, u64 time_ns)
+{
+	bool res = true;
+
+	if (curr_state == any_opid && event == sched_need_resched_opid)
+		res = ha_get_env(ha_mon, irq_off_opid, time_ns) == 1ull;
+	else if (curr_state == any_opid && event == sched_waking_opid)
+		res = ha_get_env(ha_mon, irq_off_opid, time_ns) == 1ull &&
+		      ha_get_env(ha_mon, preempt_off_opid, time_ns) == 1ull;
+	return res;
+}
+
+static bool ha_verify_constraint(struct ha_monitor *ha_mon,
+				 enum states curr_state, enum events event,
+				 enum states next_state, u64 time_ns)
+{
+	if (!ha_verify_guards(ha_mon, curr_state, event, next_state, time_ns))
+		return false;
+
+	return true;
+}
+
+static void handle_sched_need_resched(void *data, struct task_struct *tsk, int cpu, int tif)
+{
+	da_handle_start_run_event(sched_need_resched_opid);
+}
+
+static void handle_sched_waking(void *data, struct task_struct *p)
+{
+	da_handle_start_run_event(sched_waking_opid);
+}
+
+static int enable_opid(void)
+{
+	int retval;
+
+	retval = ha_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("opid", sched_set_need_resched_tp, handle_sched_need_resched);
+	rv_attach_trace_probe("opid", sched_waking, handle_sched_waking);
+
+	return 0;
+}
+
+static void disable_opid(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("opid", sched_set_need_resched_tp, handle_sched_need_resched);
+	rv_detach_trace_probe("opid", sched_waking, handle_sched_waking);
+
+	ha_monitor_destroy();
+}
+
+/*
+ * This is the monitor register section.
+ */
+static struct rv_monitor rv_this = {
+	.name = "opid",
+	.description = "operations with preemption and irq disabled.",
+	.enable = enable_opid,
+	.disable = disable_opid,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_opid(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_opid(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_opid);
+module_exit(unregister_opid);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("opid: operations with preemption and irq disabled.");

linux-7.2.3/kernel/trace/rv/monitors/opid/opid.h

@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of opid automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME opid
+
+enum states_opid {
+	any_opid,
+	state_max_opid,
+};
+
+#define INVALID_STATE state_max_opid
+
+enum events_opid {
+	sched_need_resched_opid,
+	sched_waking_opid,
+	event_max_opid,
+};
+
+enum envs_opid {
+	irq_off_opid,
+	preempt_off_opid,
+	env_max_opid,
+	env_max_stored_opid = irq_off_opid,
+};
+
+_Static_assert(env_max_stored_opid <= MAX_HA_ENV_LEN, "Not enough slots");
+
+struct automaton_opid {
+	char *state_names[state_max_opid];
+	char *event_names[event_max_opid];
+	char *env_names[env_max_opid];
+	unsigned char function[state_max_opid][event_max_opid];
+	unsigned char initial_state;
+	bool final_states[state_max_opid];
+};
+
+static const struct automaton_opid automaton_opid = {
+	.state_names = {
+		"any",
+	},
+	.event_names = {
+		"sched_need_resched",
+		"sched_waking",
+	},
+	.env_names = {
+		"irq_off",
+		"preempt_off",
+	},
+	.function = {
+		{           any_opid,           any_opid },
+	},
+	.initial_state = any_opid,
+	.final_states = { 1 },
+};

linux-7.2.3/kernel/trace/rv/monitors/opid/opid_trace.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_OPID
+DEFINE_EVENT(event_da_monitor, event_opid,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_opid,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+
+DEFINE_EVENT(error_env_da_monitor, error_env_opid,
+	     TP_PROTO(char *state, char *event, char *env),
+	     TP_ARGS(state, event, env));
+#endif /* CONFIG_RV_MON_OPID */

linux-7.2.3/kernel/trace/rv/monitors/pagefault/Kconfig

@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_PAGEFAULT
+	depends on RV
+	select RV_LTL_MONITOR
+	depends on RV_MON_RTAPP
+	depends on X86 || RISCV
+	depends on MMU
+	default y
+	select LTL_MON_EVENTS_ID
+	bool "pagefault monitor"
+	help
+	  Monitor that real-time tasks do not raise page faults, causing
+	  undesirable latency.
+
+	  If you are developing a real-time system and not entirely sure whether
+	  the applications are designed correctly for real-time, you want to say
+	  Y here.
+
+	  This monitor does not affect execution speed while it is not running,
+	  therefore it is safe to enable this in production kernel.

linux-7.2.3/kernel/trace/rv/monitors/pagefault/pagefault.c

@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rv.h>
+#include <linux/sched/deadline.h>
+#include <linux/sched/rt.h>
+#include <linux/tracepoint.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "pagefault"
+
+#include <rv_trace.h>
+#include <trace/events/exceptions.h>
+#include <monitors/rtapp/rtapp.h>
+
+#include "pagefault.h"
+#include <rv/ltl_monitor.h>
+
+static void ltl_atoms_fetch(struct task_struct *task, struct ltl_monitor *mon)
+{
+	/*
+	 * This includes "actual" real-time tasks and also PI-boosted
+	 * tasks. A task being PI-boosted means it is blocking an "actual"
+	 * real-task, therefore it should also obey the monitor's rule,
+	 * otherwise the "actual" real-task may be delayed.
+	 */
+	ltl_atom_set(mon, LTL_RT, rt_or_dl_task(task));
+}
+
+static void ltl_atoms_init(struct task_struct *task, struct ltl_monitor *mon, bool task_creation)
+{
+	if (task_creation)
+		ltl_atom_set(mon, LTL_PAGEFAULT, false);
+}
+
+static void handle_page_fault(void *data, unsigned long address, struct pt_regs *regs,
+			      unsigned long error_code)
+{
+	ltl_atom_pulse(current, LTL_PAGEFAULT, true);
+}
+
+static int enable_pagefault(void)
+{
+	int retval;
+
+	retval = ltl_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("rtapp_pagefault", page_fault_kernel, handle_page_fault);
+	rv_attach_trace_probe("rtapp_pagefault", page_fault_user, handle_page_fault);
+
+	return 0;
+}
+
+static void disable_pagefault(void)
+{
+	rv_detach_trace_probe("rtapp_pagefault", page_fault_kernel, handle_page_fault);
+	rv_detach_trace_probe("rtapp_pagefault", page_fault_user, handle_page_fault);
+
+	ltl_monitor_destroy();
+}
+
+static struct rv_monitor rv_pagefault = {
+	.name = "pagefault",
+	.description = "Monitor that RT tasks do not raise page faults",
+	.enable = enable_pagefault,
+	.disable = disable_pagefault,
+};
+
+static int __init register_pagefault(void)
+{
+	return rv_register_monitor(&rv_pagefault, &rv_rtapp);
+}
+
+static void __exit unregister_pagefault(void)
+{
+	rv_unregister_monitor(&rv_pagefault);
+}
+
+module_init(register_pagefault);
+module_exit(unregister_pagefault);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nam Cao <namcao@linutronix.de>");
+MODULE_DESCRIPTION("pagefault: Monitor that RT tasks do not raise page faults");

linux-7.2.3/kernel/trace/rv/monitors/pagefault/pagefault.h

@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * C implementation of Buchi automaton, automatically generated by
+ * tools/verification/rvgen from the linear temporal logic specification.
+ * For further information, see kernel documentation:
+ *   Documentation/trace/rv/linear_temporal_logic.rst
+ */
+
+#include <linux/rv.h>
+
+#define MONITOR_NAME pagefault
+
+enum ltl_atom {
+	LTL_PAGEFAULT,
+	LTL_RT,
+	LTL_NUM_ATOM
+};
+static_assert(LTL_NUM_ATOM <= RV_MAX_LTL_ATOM);
+
+static const char *ltl_atom_str(enum ltl_atom atom)
+{
+	static const char *const names[] = {
+		"pa",
+		"rt",
+	};
+
+	return names[atom];
+}
+
+enum ltl_buchi_state {
+	S0,
+	RV_NUM_BA_STATES
+};
+static_assert(RV_NUM_BA_STATES <= RV_MAX_BA_STATES);
+
+static void ltl_start(struct task_struct *task, struct ltl_monitor *mon)
+{
+	bool pagefault = test_bit(LTL_PAGEFAULT, mon->atoms);
+	bool val3 = !pagefault;
+	bool rt = test_bit(LTL_RT, mon->atoms);
+	bool val1 = !rt;
+	bool val4 = val1 || val3;
+
+	if (val4)
+		__set_bit(S0, mon->states);
+}
+
+static void
+ltl_possible_next_states(struct ltl_monitor *mon, unsigned int state, unsigned long *next)
+{
+	bool pagefault = test_bit(LTL_PAGEFAULT, mon->atoms);
+	bool val3 = !pagefault;
+	bool rt = test_bit(LTL_RT, mon->atoms);
+	bool val1 = !rt;
+	bool val4 = val1 || val3;
+
+	switch (state) {
+	case S0:
+		if (val4)
+			__set_bit(S0, next);
+		break;
+	}
+}

linux-7.2.3/kernel/trace/rv/monitors/pagefault/pagefault_trace.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_PAGEFAULT
+DEFINE_EVENT(event_ltl_monitor_id, event_pagefault,
+	     TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next),
+	     TP_ARGS(task, states, atoms, next));
+DEFINE_EVENT(error_ltl_monitor_id, error_pagefault,
+	     TP_PROTO(struct task_struct *task),
+	     TP_ARGS(task));
+#endif /* CONFIG_RV_MON_PAGEFAULT */

linux-7.2.3/kernel/trace/rv/monitors/rtapp/Kconfig

@@ -0,0 +1,11 @@
+config RV_MON_RTAPP
+	depends on RV
+	depends on RV_PER_TASK_MONITORS >= 2
+	bool "rtapp monitor"
+	help
+	  Collection of monitors to check for common problems with real-time
+	  application that may cause unexpected latency.
+
+	  If you are developing a real-time system and not entirely sure whether
+	  the applications are designed correctly for real-time, you want to say
+	  Y here.

linux-7.2.3/kernel/trace/rv/monitors/rtapp/rtapp.c

@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+
+#define MODULE_NAME "rtapp"
+
+#include "rtapp.h"
+
+struct rv_monitor rv_rtapp = {
+	.name = "rtapp",
+	.description = "Collection of monitors for detecting problems with real-time applications",
+};
+
+static int __init register_rtapp(void)
+{
+	return rv_register_monitor(&rv_rtapp, NULL);
+}
+
+static void __exit unregister_rtapp(void)
+{
+	rv_unregister_monitor(&rv_rtapp);
+}
+
+module_init(register_rtapp);
+module_exit(unregister_rtapp);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nam Cao <namcao@linutronix.de>");
+MODULE_DESCRIPTION("Collection of monitors for detecting problems with real-time applications");

linux-7.2.3/kernel/trace/rv/monitors/rtapp/rtapp.h

@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+extern struct rv_monitor rv_rtapp;

linux-7.2.3/kernel/trace/rv/monitors/sched/Kconfig

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SCHED
+	depends on RV
+	depends on RV_PER_TASK_MONITORS >= 3
+	bool "sched monitor"
+	help
+	  Collection of monitors to check the scheduler behaves according to specifications.
+	  Enable this to enable all scheduler specification supported by the current kernel.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/sched/sched.c

@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+
+#define MODULE_NAME "sched"
+
+#include "sched.h"
+
+struct rv_monitor rv_sched = {
+	.name = "sched",
+	.description = "container for several scheduler monitor specifications.",
+	.enable = NULL,
+	.disable = NULL,
+	.reset = NULL,
+	.enabled = 0,
+};
+
+static int __init register_sched(void)
+{
+	return rv_register_monitor(&rv_sched, NULL);
+}
+
+static void __exit unregister_sched(void)
+{
+	rv_unregister_monitor(&rv_sched);
+}
+
+module_init(register_sched);
+module_exit(unregister_sched);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("sched: container for several scheduler monitor specifications.");

linux-7.2.3/kernel/trace/rv/monitors/sched/sched.h

@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+extern struct rv_monitor rv_sched;

linux-7.2.3/kernel/trace/rv/monitors/sco/Kconfig

@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SCO
+	depends on RV
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_IMPLICIT
+	bool "sco monitor"
+	help
+	  Monitor to ensure sched_set_state happens only in thread context.
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/sco/sco.c

@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "sco"
+
+#include <trace/events/sched.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_CPU
+#include "sco.h"
+#include <rv/da_monitor.h>
+
+static void handle_sched_set_state(void *data, struct task_struct *tsk, int state)
+{
+	da_handle_start_event(sched_set_state_sco);
+}
+
+static void handle_schedule_entry(void *data, bool preempt)
+{
+	da_handle_event(schedule_entry_sco);
+}
+
+static void handle_schedule_exit(void *data, bool is_switch)
+{
+	da_handle_start_event(schedule_exit_sco);
+}
+
+static int enable_sco(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("sco", sched_set_state_tp, handle_sched_set_state);
+	rv_attach_trace_probe("sco", sched_entry_tp, handle_schedule_entry);
+	rv_attach_trace_probe("sco", sched_exit_tp, handle_schedule_exit);
+
+	return 0;
+}
+
+static void disable_sco(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("sco", sched_set_state_tp, handle_sched_set_state);
+	rv_detach_trace_probe("sco", sched_entry_tp, handle_schedule_entry);
+	rv_detach_trace_probe("sco", sched_exit_tp, handle_schedule_exit);
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "sco",
+	.description = "scheduling context operations.",
+	.enable = enable_sco,
+	.disable = disable_sco,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_sco(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_sco(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_sco);
+module_exit(unregister_sco);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("sco: scheduling context operations.");

linux-7.2.3/kernel/trace/rv/monitors/sco/sco.h

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of sco automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME sco
+
+enum states_sco {
+	thread_context_sco,
+	scheduling_context_sco,
+	state_max_sco,
+};
+
+#define INVALID_STATE state_max_sco
+
+enum events_sco {
+	sched_set_state_sco,
+	schedule_entry_sco,
+	schedule_exit_sco,
+	event_max_sco,
+};
+
+struct automaton_sco {
+	char *state_names[state_max_sco];
+	char *event_names[event_max_sco];
+	unsigned char function[state_max_sco][event_max_sco];
+	unsigned char initial_state;
+	bool final_states[state_max_sco];
+};
+
+static const struct automaton_sco automaton_sco = {
+	.state_names = {
+		"thread_context",
+		"scheduling_context",
+	},
+	.event_names = {
+		"sched_set_state",
+		"schedule_entry",
+		"schedule_exit",
+	},
+	.function = {
+		{     thread_context_sco, scheduling_context_sco,          INVALID_STATE },
+		{          INVALID_STATE,          INVALID_STATE,     thread_context_sco },
+	},
+	.initial_state = thread_context_sco,
+	.final_states = { 1, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/sco/sco_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_SCO
+DEFINE_EVENT(event_da_monitor, event_sco,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_sco,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+#endif /* CONFIG_RV_MON_SCO */

linux-7.2.3/kernel/trace/rv/monitors/scpd/Kconfig

@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SCPD
+	depends on RV
+	depends on TRACE_PREEMPT_TOGGLE
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_IMPLICIT
+	bool "scpd monitor"
+	help
+	  Monitor to ensure schedule is called with preemption disabled.
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/scpd/scpd.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "scpd"
+
+#include <trace/events/sched.h>
+#include <trace/events/preemptirq.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_CPU
+#include "scpd.h"
+#include <rv/da_monitor.h>
+
+static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event(preempt_disable_scpd);
+}
+
+static void handle_preempt_enable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_start_event(preempt_enable_scpd);
+}
+
+static void handle_schedule_entry(void *data, bool preempt)
+{
+	da_handle_event(schedule_entry_scpd);
+}
+
+static void handle_schedule_exit(void *data, bool is_switch)
+{
+	da_handle_event(schedule_exit_scpd);
+}
+
+static int enable_scpd(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("scpd", preempt_disable, handle_preempt_disable);
+	rv_attach_trace_probe("scpd", preempt_enable, handle_preempt_enable);
+	rv_attach_trace_probe("scpd", sched_entry_tp, handle_schedule_entry);
+	rv_attach_trace_probe("scpd", sched_exit_tp, handle_schedule_exit);
+
+	return 0;
+}
+
+static void disable_scpd(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("scpd", preempt_disable, handle_preempt_disable);
+	rv_detach_trace_probe("scpd", preempt_enable, handle_preempt_enable);
+	rv_detach_trace_probe("scpd", sched_entry_tp, handle_schedule_entry);
+	rv_detach_trace_probe("scpd", sched_exit_tp, handle_schedule_exit);
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "scpd",
+	.description = "schedule called with preemption disabled.",
+	.enable = enable_scpd,
+	.disable = disable_scpd,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_scpd(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_scpd(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_scpd);
+module_exit(unregister_scpd);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("scpd: schedule called with preemption disabled.");

linux-7.2.3/kernel/trace/rv/monitors/scpd/scpd.h

@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of scpd automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME scpd
+
+enum states_scpd {
+	cant_sched_scpd,
+	can_sched_scpd,
+	state_max_scpd,
+};
+
+#define INVALID_STATE state_max_scpd
+
+enum events_scpd {
+	preempt_disable_scpd,
+	preempt_enable_scpd,
+	schedule_entry_scpd,
+	schedule_exit_scpd,
+	event_max_scpd,
+};
+
+struct automaton_scpd {
+	char *state_names[state_max_scpd];
+	char *event_names[event_max_scpd];
+	unsigned char function[state_max_scpd][event_max_scpd];
+	unsigned char initial_state;
+	bool final_states[state_max_scpd];
+};
+
+static const struct automaton_scpd automaton_scpd = {
+	.state_names = {
+		"cant_sched",
+		"can_sched",
+	},
+	.event_names = {
+		"preempt_disable",
+		"preempt_enable",
+		"schedule_entry",
+		"schedule_exit",
+	},
+	.function = {
+		{     can_sched_scpd,     INVALID_STATE,     INVALID_STATE,     INVALID_STATE },
+		{     INVALID_STATE,    cant_sched_scpd,     can_sched_scpd,     can_sched_scpd },
+	},
+	.initial_state = cant_sched_scpd,
+	.final_states = { 1, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/scpd/scpd_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_SCPD
+DEFINE_EVENT(event_da_monitor, event_scpd,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_scpd,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+#endif /* CONFIG_RV_MON_SCPD */

linux-7.2.3/kernel/trace/rv/monitors/sleep/Kconfig

@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SLEEP
+	depends on RV
+	select RV_LTL_MONITOR
+	depends on HAVE_SYSCALL_TRACEPOINTS
+	depends on RV_MON_RTAPP
+	select TRACE_IRQFLAGS
+	default y
+	select LTL_MON_EVENTS_ID
+	bool "sleep monitor"
+	help
+	  Monitor that real-time tasks do not sleep in a manner that may
+	  cause undesirable latency.
+
+	  If you are developing a real-time system and not entirely sure whether
+	  the applications are designed correctly for real-time, you want to say
+	  Y here.
+
+	  Enabling this monitor may have performance impact (due to select
+	  TRACE_IRQFLAGS). Therefore, you probably should say N for
+	  production kernel.

linux-7.2.3/kernel/trace/rv/monitors/sleep/sleep.c

@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/init.h>
+#include <linux/irqflags.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rv.h>
+#include <linux/sched/deadline.h>
+#include <linux/sched/rt.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "sleep"
+
+#include <trace/events/syscalls.h>
+#include <trace/events/sched.h>
+#include <trace/events/lock.h>
+#include <uapi/linux/futex.h>
+#include <rv_trace.h>
+#include <monitors/rtapp/rtapp.h>
+
+#include "sleep.h"
+#include <rv/ltl_monitor.h>
+
+static void ltl_atoms_fetch(struct task_struct *task, struct ltl_monitor *mon)
+{
+	/*
+	 * This includes "actual" real-time tasks and also PI-boosted
+	 * tasks. A task being PI-boosted means it is blocking an "actual"
+	 * real-task, therefore it should also obey the monitor's rule,
+	 * otherwise the "actual" real-task may be delayed.
+	 */
+	ltl_atom_set(mon, LTL_RT, rt_or_dl_task(task));
+}
+
+static void ltl_atoms_init(struct task_struct *task, struct ltl_monitor *mon, bool task_creation)
+{
+	ltl_atom_set(mon, LTL_SLEEP, false);
+	ltl_atom_set(mon, LTL_WAKE, false);
+	ltl_atom_set(mon, LTL_ABORT_SLEEP, false);
+	ltl_atom_set(mon, LTL_WOKEN_BY_HARDIRQ, false);
+	ltl_atom_set(mon, LTL_WOKEN_BY_NMI, false);
+	ltl_atom_set(mon, LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO, false);
+
+	if (task_creation) {
+		ltl_atom_set(mon, LTL_KTHREAD_SHOULD_STOP, false);
+		ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, false);
+		ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, false);
+		ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, false);
+		ltl_atom_set(mon, LTL_CLOCK_NANOSLEEP, false);
+		ltl_atom_set(mon, LTL_FUTEX_WAIT, false);
+		ltl_atom_set(mon, LTL_EPOLL_WAIT, false);
+		ltl_atom_set(mon, LTL_FUTEX_LOCK_PI, false);
+		ltl_atom_set(mon, LTL_BLOCK_ON_RT_MUTEX, false);
+	}
+
+	if (task->flags & PF_KTHREAD) {
+		ltl_atom_set(mon, LTL_KERNEL_THREAD, true);
+
+		/* kernel tasks do not do syscall */
+		ltl_atom_set(mon, LTL_FUTEX_WAIT, false);
+		ltl_atom_set(mon, LTL_FUTEX_LOCK_PI, false);
+		ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, false);
+		ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, false);
+		ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, false);
+		ltl_atom_set(mon, LTL_CLOCK_NANOSLEEP, false);
+		ltl_atom_set(mon, LTL_EPOLL_WAIT, false);
+
+		if (strstarts(task->comm, "migration/"))
+			ltl_atom_set(mon, LTL_TASK_IS_MIGRATION, true);
+		else
+			ltl_atom_set(mon, LTL_TASK_IS_MIGRATION, false);
+
+		if (strstarts(task->comm, "rcu"))
+			ltl_atom_set(mon, LTL_TASK_IS_RCU, true);
+		else
+			ltl_atom_set(mon, LTL_TASK_IS_RCU, false);
+	} else {
+		ltl_atom_set(mon, LTL_KTHREAD_SHOULD_STOP, false);
+		ltl_atom_set(mon, LTL_KERNEL_THREAD, false);
+		ltl_atom_set(mon, LTL_TASK_IS_RCU, false);
+		ltl_atom_set(mon, LTL_TASK_IS_MIGRATION, false);
+	}
+
+}
+
+static void handle_sched_set_state(void *data, struct task_struct *task, int state)
+{
+	if (state & TASK_INTERRUPTIBLE)
+		ltl_atom_pulse(task, LTL_SLEEP, true);
+	else if (state == TASK_RUNNING)
+		ltl_atom_pulse(task, LTL_ABORT_SLEEP, true);
+}
+
+static void handle_sched_wakeup(void *data, struct task_struct *task)
+{
+	ltl_atom_pulse(task, LTL_WAKE, true);
+}
+
+static void handle_sched_waking(void *data, struct task_struct *task)
+{
+	if (this_cpu_read(hardirq_context)) {
+		ltl_atom_pulse(task, LTL_WOKEN_BY_HARDIRQ, true);
+	} else if (in_task()) {
+		if (current->prio <= task->prio)
+			ltl_atom_pulse(task, LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO, true);
+	} else if (in_nmi()) {
+		ltl_atom_pulse(task, LTL_WOKEN_BY_NMI, true);
+	}
+}
+
+static void handle_contention_begin(void *data, void *lock, unsigned int flags)
+{
+	if (flags & LCB_F_RT)
+		ltl_atom_update(current, LTL_BLOCK_ON_RT_MUTEX, true);
+}
+
+static void handle_contention_end(void *data, void *lock, int ret)
+{
+	ltl_atom_update(current, LTL_BLOCK_ON_RT_MUTEX, false);
+}
+
+static void handle_sys_enter(void *data, struct pt_regs *regs, long id)
+{
+	struct ltl_monitor *mon;
+	unsigned long args[6];
+	int op, cmd;
+
+	mon = ltl_get_monitor(current);
+
+	switch (id) {
+#ifdef __NR_clock_nanosleep
+	case __NR_clock_nanosleep:
+#endif
+#ifdef __NR_clock_nanosleep_time64
+	case __NR_clock_nanosleep_time64:
+#endif
+		syscall_get_arguments(current, regs, args);
+		ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, args[0] == CLOCK_MONOTONIC);
+		ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, args[0] == CLOCK_TAI);
+		ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, args[1] == TIMER_ABSTIME);
+		ltl_atom_update(current, LTL_CLOCK_NANOSLEEP, true);
+		break;
+
+#ifdef __NR_futex
+	case __NR_futex:
+#endif
+#ifdef __NR_futex_time64
+	case __NR_futex_time64:
+#endif
+		syscall_get_arguments(current, regs, args);
+		op = args[1];
+		cmd = op & FUTEX_CMD_MASK;
+
+		switch (cmd) {
+		case FUTEX_LOCK_PI:
+		case FUTEX_LOCK_PI2:
+			ltl_atom_update(current, LTL_FUTEX_LOCK_PI, true);
+			break;
+		case FUTEX_WAIT:
+		case FUTEX_WAIT_BITSET:
+		case FUTEX_WAIT_REQUEUE_PI:
+			ltl_atom_update(current, LTL_FUTEX_WAIT, true);
+			break;
+		}
+		break;
+#ifdef __NR_epoll_wait
+	case __NR_epoll_wait:
+		ltl_atom_update(current, LTL_EPOLL_WAIT, true);
+		break;
+#endif
+	}
+}
+
+static void handle_sys_exit(void *data, struct pt_regs *regs, long ret)
+{
+	struct ltl_monitor *mon = ltl_get_monitor(current);
+
+	ltl_atom_set(mon, LTL_FUTEX_LOCK_PI, false);
+	ltl_atom_set(mon, LTL_FUTEX_WAIT, false);
+	ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, false);
+	ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, false);
+	ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, false);
+	ltl_atom_set(mon, LTL_EPOLL_WAIT, false);
+	ltl_atom_update(current, LTL_CLOCK_NANOSLEEP, false);
+}
+
+static void handle_kthread_stop(void *data, struct task_struct *task)
+{
+	/* FIXME: this could race with other tracepoint handlers */
+	ltl_atom_update(task, LTL_KTHREAD_SHOULD_STOP, true);
+}
+
+static int enable_sleep(void)
+{
+	int retval;
+
+	retval = ltl_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("rtapp_sleep", sched_waking, handle_sched_waking);
+	rv_attach_trace_probe("rtapp_sleep", sched_wakeup, handle_sched_wakeup);
+	rv_attach_trace_probe("rtapp_sleep", sched_set_state_tp, handle_sched_set_state);
+	rv_attach_trace_probe("rtapp_sleep", contention_begin, handle_contention_begin);
+	rv_attach_trace_probe("rtapp_sleep", contention_end, handle_contention_end);
+	rv_attach_trace_probe("rtapp_sleep", sched_kthread_stop, handle_kthread_stop);
+	rv_attach_trace_probe("rtapp_sleep", sys_enter, handle_sys_enter);
+	rv_attach_trace_probe("rtapp_sleep", sys_exit, handle_sys_exit);
+	return 0;
+}
+
+static void disable_sleep(void)
+{
+	rv_detach_trace_probe("rtapp_sleep", sched_waking, handle_sched_waking);
+	rv_detach_trace_probe("rtapp_sleep", sched_wakeup, handle_sched_wakeup);
+	rv_detach_trace_probe("rtapp_sleep", sched_set_state_tp, handle_sched_set_state);
+	rv_detach_trace_probe("rtapp_sleep", contention_begin, handle_contention_begin);
+	rv_detach_trace_probe("rtapp_sleep", contention_end, handle_contention_end);
+	rv_detach_trace_probe("rtapp_sleep", sched_kthread_stop, handle_kthread_stop);
+	rv_detach_trace_probe("rtapp_sleep", sys_enter, handle_sys_enter);
+	rv_detach_trace_probe("rtapp_sleep", sys_exit, handle_sys_exit);
+
+	ltl_monitor_destroy();
+}
+
+static struct rv_monitor rv_sleep = {
+	.name = "sleep",
+	.description = "Monitor that RT tasks do not undesirably sleep",
+	.enable = enable_sleep,
+	.disable = disable_sleep,
+};
+
+static int __init register_sleep(void)
+{
+	return rv_register_monitor(&rv_sleep, &rv_rtapp);
+}
+
+static void __exit unregister_sleep(void)
+{
+	rv_unregister_monitor(&rv_sleep);
+}
+
+module_init(register_sleep);
+module_exit(unregister_sleep);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nam Cao <namcao@linutronix.de>");
+MODULE_DESCRIPTION("sleep: Monitor that RT tasks do not undesirably sleep");

linux-7.2.3/kernel/trace/rv/monitors/sleep/sleep.h

@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * C implementation of Buchi automaton, automatically generated by
+ * tools/verification/rvgen from the linear temporal logic specification.
+ * For further information, see kernel documentation:
+ *   Documentation/trace/rv/linear_temporal_logic.rst
+ */
+
+#include <linux/rv.h>
+
+#define MONITOR_NAME sleep
+
+enum ltl_atom {
+	LTL_ABORT_SLEEP,
+	LTL_BLOCK_ON_RT_MUTEX,
+	LTL_CLOCK_NANOSLEEP,
+	LTL_EPOLL_WAIT,
+	LTL_FUTEX_LOCK_PI,
+	LTL_FUTEX_WAIT,
+	LTL_KERNEL_THREAD,
+	LTL_KTHREAD_SHOULD_STOP,
+	LTL_NANOSLEEP_CLOCK_MONOTONIC,
+	LTL_NANOSLEEP_CLOCK_TAI,
+	LTL_NANOSLEEP_TIMER_ABSTIME,
+	LTL_RT,
+	LTL_SLEEP,
+	LTL_TASK_IS_MIGRATION,
+	LTL_TASK_IS_RCU,
+	LTL_WAKE,
+	LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO,
+	LTL_WOKEN_BY_HARDIRQ,
+	LTL_WOKEN_BY_NMI,
+	LTL_NUM_ATOM
+};
+static_assert(LTL_NUM_ATOM <= RV_MAX_LTL_ATOM);
+
+static const char *ltl_atom_str(enum ltl_atom atom)
+{
+	static const char *const names[] = {
+		"ab_sl",
+		"bl_on_rt_mu",
+		"cl_na",
+		"ep_wa",
+		"fu_lo_pi",
+		"fu_wa",
+		"ker_th",
+		"kth_sh_st",
+		"na_cl_mo",
+		"na_cl_ta",
+		"na_ti_ab",
+		"rt",
+		"sl",
+		"ta_mi",
+		"ta_rc",
+		"wak",
+		"wo_eq_hi_pr",
+		"wo_ha",
+		"wo_nm",
+	};
+
+	return names[atom];
+}
+
+enum ltl_buchi_state {
+	S0,
+	S1,
+	S2,
+	S3,
+	S4,
+	S5,
+	S6,
+	S7,
+	RV_NUM_BA_STATES
+};
+static_assert(RV_NUM_BA_STATES <= RV_MAX_BA_STATES);
+
+static void ltl_start(struct task_struct *task, struct ltl_monitor *mon)
+{
+	bool woken_by_nmi = test_bit(LTL_WOKEN_BY_NMI, mon->atoms);
+	bool woken_by_hardirq = test_bit(LTL_WOKEN_BY_HARDIRQ, mon->atoms);
+	bool woken_by_equal_or_higher_prio = test_bit(LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO,
+	     mon->atoms);
+	bool wake = test_bit(LTL_WAKE, mon->atoms);
+	bool task_is_rcu = test_bit(LTL_TASK_IS_RCU, mon->atoms);
+	bool task_is_migration = test_bit(LTL_TASK_IS_MIGRATION, mon->atoms);
+	bool sleep = test_bit(LTL_SLEEP, mon->atoms);
+	bool rt = test_bit(LTL_RT, mon->atoms);
+	bool nanosleep_timer_abstime = test_bit(LTL_NANOSLEEP_TIMER_ABSTIME, mon->atoms);
+	bool nanosleep_clock_tai = test_bit(LTL_NANOSLEEP_CLOCK_TAI, mon->atoms);
+	bool nanosleep_clock_monotonic = test_bit(LTL_NANOSLEEP_CLOCK_MONOTONIC, mon->atoms);
+	bool kthread_should_stop = test_bit(LTL_KTHREAD_SHOULD_STOP, mon->atoms);
+	bool kernel_thread = test_bit(LTL_KERNEL_THREAD, mon->atoms);
+	bool futex_wait = test_bit(LTL_FUTEX_WAIT, mon->atoms);
+	bool futex_lock_pi = test_bit(LTL_FUTEX_LOCK_PI, mon->atoms);
+	bool epoll_wait = test_bit(LTL_EPOLL_WAIT, mon->atoms);
+	bool clock_nanosleep = test_bit(LTL_CLOCK_NANOSLEEP, mon->atoms);
+	bool block_on_rt_mutex = test_bit(LTL_BLOCK_ON_RT_MUTEX, mon->atoms);
+	bool abort_sleep = test_bit(LTL_ABORT_SLEEP, mon->atoms);
+	bool val42 = task_is_rcu || task_is_migration;
+	bool val43 = futex_lock_pi || val42;
+	bool val5 = block_on_rt_mutex || val43;
+	bool val34 = abort_sleep || kthread_should_stop;
+	bool val35 = woken_by_nmi || val34;
+	bool val36 = woken_by_hardirq || val35;
+	bool val14 = woken_by_equal_or_higher_prio || val36;
+	bool val13 = !wake;
+	bool val26 = nanosleep_clock_monotonic || nanosleep_clock_tai;
+	bool val27 = nanosleep_timer_abstime && val26;
+	bool val18 = clock_nanosleep && val27;
+	bool val20 = val18 || epoll_wait;
+	bool val9 = futex_wait || val20;
+	bool val11 = val9 || kernel_thread;
+	bool val2 = !sleep;
+	bool val1 = !rt;
+	bool val3 = val1 || val2;
+
+	if (val3)
+		__set_bit(S0, mon->states);
+	if (val11 && val13)
+		__set_bit(S1, mon->states);
+	if (val11 && val14)
+		__set_bit(S4, mon->states);
+	if (val5)
+		__set_bit(S5, mon->states);
+}
+
+static void
+ltl_possible_next_states(struct ltl_monitor *mon, unsigned int state, unsigned long *next)
+{
+	bool woken_by_nmi = test_bit(LTL_WOKEN_BY_NMI, mon->atoms);
+	bool woken_by_hardirq = test_bit(LTL_WOKEN_BY_HARDIRQ, mon->atoms);
+	bool woken_by_equal_or_higher_prio = test_bit(LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO,
+	     mon->atoms);
+	bool wake = test_bit(LTL_WAKE, mon->atoms);
+	bool task_is_rcu = test_bit(LTL_TASK_IS_RCU, mon->atoms);
+	bool task_is_migration = test_bit(LTL_TASK_IS_MIGRATION, mon->atoms);
+	bool sleep = test_bit(LTL_SLEEP, mon->atoms);
+	bool rt = test_bit(LTL_RT, mon->atoms);
+	bool nanosleep_timer_abstime = test_bit(LTL_NANOSLEEP_TIMER_ABSTIME, mon->atoms);
+	bool nanosleep_clock_tai = test_bit(LTL_NANOSLEEP_CLOCK_TAI, mon->atoms);
+	bool nanosleep_clock_monotonic = test_bit(LTL_NANOSLEEP_CLOCK_MONOTONIC, mon->atoms);
+	bool kthread_should_stop = test_bit(LTL_KTHREAD_SHOULD_STOP, mon->atoms);
+	bool kernel_thread = test_bit(LTL_KERNEL_THREAD, mon->atoms);
+	bool futex_wait = test_bit(LTL_FUTEX_WAIT, mon->atoms);
+	bool futex_lock_pi = test_bit(LTL_FUTEX_LOCK_PI, mon->atoms);
+	bool epoll_wait = test_bit(LTL_EPOLL_WAIT, mon->atoms);
+	bool clock_nanosleep = test_bit(LTL_CLOCK_NANOSLEEP, mon->atoms);
+	bool block_on_rt_mutex = test_bit(LTL_BLOCK_ON_RT_MUTEX, mon->atoms);
+	bool abort_sleep = test_bit(LTL_ABORT_SLEEP, mon->atoms);
+	bool val42 = task_is_rcu || task_is_migration;
+	bool val43 = futex_lock_pi || val42;
+	bool val5 = block_on_rt_mutex || val43;
+	bool val34 = abort_sleep || kthread_should_stop;
+	bool val35 = woken_by_nmi || val34;
+	bool val36 = woken_by_hardirq || val35;
+	bool val14 = woken_by_equal_or_higher_prio || val36;
+	bool val13 = !wake;
+	bool val26 = nanosleep_clock_monotonic || nanosleep_clock_tai;
+	bool val27 = nanosleep_timer_abstime && val26;
+	bool val18 = clock_nanosleep && val27;
+	bool val20 = val18 || epoll_wait;
+	bool val9 = futex_wait || val20;
+	bool val11 = val9 || kernel_thread;
+	bool val2 = !sleep;
+	bool val1 = !rt;
+	bool val3 = val1 || val2;
+
+	switch (state) {
+	case S0:
+		if (val3)
+			__set_bit(S0, next);
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val5)
+			__set_bit(S5, next);
+		break;
+	case S1:
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val13 && val3)
+			__set_bit(S2, next);
+		if (val14 && val3)
+			__set_bit(S3, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val13 && val5)
+			__set_bit(S6, next);
+		if (val14 && val5)
+			__set_bit(S7, next);
+		break;
+	case S2:
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val13 && val3)
+			__set_bit(S2, next);
+		if (val14 && val3)
+			__set_bit(S3, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val13 && val5)
+			__set_bit(S6, next);
+		if (val14 && val5)
+			__set_bit(S7, next);
+		break;
+	case S3:
+		if (val3)
+			__set_bit(S0, next);
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val5)
+			__set_bit(S5, next);
+		break;
+	case S4:
+		if (val3)
+			__set_bit(S0, next);
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val5)
+			__set_bit(S5, next);
+		break;
+	case S5:
+		if (val3)
+			__set_bit(S0, next);
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val5)
+			__set_bit(S5, next);
+		break;
+	case S6:
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val13 && val3)
+			__set_bit(S2, next);
+		if (val14 && val3)
+			__set_bit(S3, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val13 && val5)
+			__set_bit(S6, next);
+		if (val14 && val5)
+			__set_bit(S7, next);
+		break;
+	case S7:
+		if (val3)
+			__set_bit(S0, next);
+		if (val11 && val13)
+			__set_bit(S1, next);
+		if (val11 && val14)
+			__set_bit(S4, next);
+		if (val5)
+			__set_bit(S5, next);
+		break;
+	}
+}

linux-7.2.3/kernel/trace/rv/monitors/sleep/sleep_trace.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_SLEEP
+DEFINE_EVENT(event_ltl_monitor_id, event_sleep,
+	     TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next),
+	     TP_ARGS(task, states, atoms, next));
+DEFINE_EVENT(error_ltl_monitor_id, error_sleep,
+	     TP_PROTO(struct task_struct *task),
+	     TP_ARGS(task));
+#endif /* CONFIG_RV_MON_SLEEP */

linux-7.2.3/kernel/trace/rv/monitors/snep/Kconfig

@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SNEP
+	depends on RV
+	depends on TRACE_PREEMPT_TOGGLE
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_IMPLICIT
+	bool "snep monitor"
+	help
+	  Monitor to ensure schedule does not enable preempt.
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/snep/snep.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "snep"
+
+#include <trace/events/sched.h>
+#include <trace/events/preemptirq.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_CPU
+#include "snep.h"
+#include <rv/da_monitor.h>
+
+static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_start_event(preempt_disable_snep);
+}
+
+static void handle_preempt_enable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_start_event(preempt_enable_snep);
+}
+
+static void handle_schedule_entry(void *data, bool preempt)
+{
+	da_handle_event(schedule_entry_snep);
+}
+
+static void handle_schedule_exit(void *data, bool is_switch)
+{
+	da_handle_start_event(schedule_exit_snep);
+}
+
+static int enable_snep(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("snep", preempt_disable, handle_preempt_disable);
+	rv_attach_trace_probe("snep", preempt_enable, handle_preempt_enable);
+	rv_attach_trace_probe("snep", sched_entry_tp, handle_schedule_entry);
+	rv_attach_trace_probe("snep", sched_exit_tp, handle_schedule_exit);
+
+	return 0;
+}
+
+static void disable_snep(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("snep", preempt_disable, handle_preempt_disable);
+	rv_detach_trace_probe("snep", preempt_enable, handle_preempt_enable);
+	rv_detach_trace_probe("snep", sched_entry_tp, handle_schedule_entry);
+	rv_detach_trace_probe("snep", sched_exit_tp, handle_schedule_exit);
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "snep",
+	.description = "schedule does not enable preempt.",
+	.enable = enable_snep,
+	.disable = disable_snep,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_snep(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_snep(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_snep);
+module_exit(unregister_snep);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("snep: schedule does not enable preempt.");

linux-7.2.3/kernel/trace/rv/monitors/snep/snep.h

@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of snep automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME snep
+
+enum states_snep {
+	non_scheduling_context_snep,
+	scheduling_contex_snep,
+	state_max_snep,
+};
+
+#define INVALID_STATE state_max_snep
+
+enum events_snep {
+	preempt_disable_snep,
+	preempt_enable_snep,
+	schedule_entry_snep,
+	schedule_exit_snep,
+	event_max_snep,
+};
+
+struct automaton_snep {
+	char *state_names[state_max_snep];
+	char *event_names[event_max_snep];
+	unsigned char function[state_max_snep][event_max_snep];
+	unsigned char initial_state;
+	bool final_states[state_max_snep];
+};
+
+static const struct automaton_snep automaton_snep = {
+	.state_names = {
+		"non_scheduling_context",
+		"scheduling_contex",
+	},
+	.event_names = {
+		"preempt_disable",
+		"preempt_enable",
+		"schedule_entry",
+		"schedule_exit",
+	},
+	.function = {
+		{
+			non_scheduling_context_snep,
+			non_scheduling_context_snep,
+			scheduling_contex_snep,
+			INVALID_STATE,
+		},
+		{
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			non_scheduling_context_snep,
+		},
+	},
+	.initial_state = non_scheduling_context_snep,
+	.final_states = { 1, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/snep/snep_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_SNEP
+DEFINE_EVENT(event_da_monitor, event_snep,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_snep,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+#endif /* CONFIG_RV_MON_SNEP */

linux-7.2.3/kernel/trace/rv/monitors/snroc/Kconfig

@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SNROC
+	depends on RV
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_ID
+	bool "snroc monitor"
+	help
+	  Monitor to ensure sched_set_state happens only in the respective task's context.
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/snroc/snroc.c

@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "snroc"
+
+#include <trace/events/sched.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_TASK
+#include "snroc.h"
+#include <rv/da_monitor.h>
+
+static void handle_sched_set_state(void *data, struct task_struct *tsk, int state)
+{
+	da_handle_event(tsk, sched_set_state_snroc);
+}
+
+static void handle_sched_switch(void *data, bool preempt,
+				struct task_struct *prev,
+				struct task_struct *next,
+				unsigned int prev_state)
+{
+	da_handle_start_event(prev, sched_switch_out_snroc);
+	da_handle_event(next, sched_switch_in_snroc);
+}
+
+static int enable_snroc(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("snroc", sched_set_state_tp, handle_sched_set_state);
+	rv_attach_trace_probe("snroc", sched_switch, handle_sched_switch);
+
+	return 0;
+}
+
+static void disable_snroc(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("snroc", sched_set_state_tp, handle_sched_set_state);
+	rv_detach_trace_probe("snroc", sched_switch, handle_sched_switch);
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "snroc",
+	.description = "set non runnable on its own context.",
+	.enable = enable_snroc,
+	.disable = disable_snroc,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_snroc(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_snroc(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_snroc);
+module_exit(unregister_snroc);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("snroc: set non runnable on its own context.");

linux-7.2.3/kernel/trace/rv/monitors/snroc/snroc.h

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of snroc automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME snroc
+
+enum states_snroc {
+	other_context_snroc,
+	own_context_snroc,
+	state_max_snroc,
+};
+
+#define INVALID_STATE state_max_snroc
+
+enum events_snroc {
+	sched_set_state_snroc,
+	sched_switch_in_snroc,
+	sched_switch_out_snroc,
+	event_max_snroc,
+};
+
+struct automaton_snroc {
+	char *state_names[state_max_snroc];
+	char *event_names[event_max_snroc];
+	unsigned char function[state_max_snroc][event_max_snroc];
+	unsigned char initial_state;
+	bool final_states[state_max_snroc];
+};
+
+static const struct automaton_snroc automaton_snroc = {
+	.state_names = {
+		"other_context",
+		"own_context",
+	},
+	.event_names = {
+		"sched_set_state",
+		"sched_switch_in",
+		"sched_switch_out",
+	},
+	.function = {
+		{      INVALID_STATE,  own_context_snroc,       INVALID_STATE },
+		{  own_context_snroc,      INVALID_STATE, other_context_snroc },
+	},
+	.initial_state = other_context_snroc,
+	.final_states = { 1, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/snroc/snroc_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_SNROC
+DEFINE_EVENT(event_da_monitor_id, event_snroc,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_snroc,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+#endif /* CONFIG_RV_MON_SNROC */

linux-7.2.3/kernel/trace/rv/monitors/sssw/Kconfig

@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SSSW
+	depends on RV
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_ID
+	bool "sssw monitor"
+	help
+	  Monitor to ensure sched_set_state to sleepable leads to sleeping and
+	  sleeping tasks require wakeup.
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/sssw/sssw.c

@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "sssw"
+
+#include <trace/events/sched.h>
+#include <trace/events/signal.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_TASK
+#include "sssw.h"
+#include <rv/da_monitor.h>
+
+static void handle_sched_set_state(void *data, struct task_struct *tsk, int state)
+{
+	if (state == TASK_RUNNING)
+		da_handle_start_event(tsk, sched_set_state_runnable_sssw);
+	else
+		da_handle_event(tsk, sched_set_state_sleepable_sssw);
+}
+
+static void handle_sched_switch(void *data, bool preempt,
+				struct task_struct *prev,
+				struct task_struct *next,
+				unsigned int prev_state)
+{
+	if (preempt)
+		da_handle_event(prev, sched_switch_preempt_sssw);
+	else if (prev_state == TASK_RUNNING)
+		da_handle_event(prev, sched_switch_yield_sssw);
+	else if (prev_state == TASK_RTLOCK_WAIT)
+		/* special case of sleeping task with racy conditions */
+		da_handle_event(prev, sched_switch_blocking_sssw);
+	else
+		da_handle_event(prev, sched_switch_suspend_sssw);
+	da_handle_event(next, sched_switch_in_sssw);
+}
+
+static void handle_sched_wakeup(void *data, struct task_struct *p)
+{
+	/*
+	 * Wakeup can also lead to signal_wakeup although the system is
+	 * actually runnable. The monitor can safely start with this event.
+	 */
+	da_handle_start_event(p, sched_wakeup_sssw);
+}
+
+static void handle_signal_deliver(void *data, int sig,
+				   struct kernel_siginfo *info,
+				   struct k_sigaction *ka)
+{
+	da_handle_event(current, signal_deliver_sssw);
+}
+
+static int enable_sssw(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("sssw", sched_set_state_tp, handle_sched_set_state);
+	rv_attach_trace_probe("sssw", sched_switch, handle_sched_switch);
+	rv_attach_trace_probe("sssw", sched_wakeup, handle_sched_wakeup);
+	rv_attach_trace_probe("sssw", signal_deliver, handle_signal_deliver);
+
+	return 0;
+}
+
+static void disable_sssw(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("sssw", sched_set_state_tp, handle_sched_set_state);
+	rv_detach_trace_probe("sssw", sched_switch, handle_sched_switch);
+	rv_detach_trace_probe("sssw", sched_wakeup, handle_sched_wakeup);
+	rv_detach_trace_probe("sssw", signal_deliver, handle_signal_deliver);
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "sssw",
+	.description = "set state sleep and wakeup.",
+	.enable = enable_sssw,
+	.disable = disable_sssw,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_sssw(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_sssw(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_sssw);
+module_exit(unregister_sssw);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("sssw: set state sleep and wakeup.");

linux-7.2.3/kernel/trace/rv/monitors/sssw/sssw.h

@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of sssw automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME sssw
+
+enum states_sssw {
+	runnable_sssw,
+	signal_wakeup_sssw,
+	sleepable_sssw,
+	sleeping_sssw,
+	state_max_sssw,
+};
+
+#define INVALID_STATE state_max_sssw
+
+enum events_sssw {
+	sched_set_state_runnable_sssw,
+	sched_set_state_sleepable_sssw,
+	sched_switch_blocking_sssw,
+	sched_switch_in_sssw,
+	sched_switch_preempt_sssw,
+	sched_switch_suspend_sssw,
+	sched_switch_yield_sssw,
+	sched_wakeup_sssw,
+	signal_deliver_sssw,
+	event_max_sssw,
+};
+
+struct automaton_sssw {
+	char *state_names[state_max_sssw];
+	char *event_names[event_max_sssw];
+	unsigned char function[state_max_sssw][event_max_sssw];
+	unsigned char initial_state;
+	bool final_states[state_max_sssw];
+};
+
+static const struct automaton_sssw automaton_sssw = {
+	.state_names = {
+		"runnable",
+		"signal_wakeup",
+		"sleepable",
+		"sleeping",
+	},
+	.event_names = {
+		"sched_set_state_runnable",
+		"sched_set_state_sleepable",
+		"sched_switch_blocking",
+		"sched_switch_in",
+		"sched_switch_preempt",
+		"sched_switch_suspend",
+		"sched_switch_yield",
+		"sched_wakeup",
+		"signal_deliver",
+	},
+	.function = {
+		{
+			runnable_sssw,
+			sleepable_sssw,
+			sleeping_sssw,
+			runnable_sssw,
+			runnable_sssw,
+			INVALID_STATE,
+			runnable_sssw,
+			runnable_sssw,
+			runnable_sssw,
+		},
+		{
+			INVALID_STATE,
+			sleepable_sssw,
+			INVALID_STATE,
+			signal_wakeup_sssw,
+			signal_wakeup_sssw,
+			INVALID_STATE,
+			signal_wakeup_sssw,
+			signal_wakeup_sssw,
+			runnable_sssw,
+		},
+		{
+			runnable_sssw,
+			sleepable_sssw,
+			sleeping_sssw,
+			sleepable_sssw,
+			sleepable_sssw,
+			sleeping_sssw,
+			signal_wakeup_sssw,
+			runnable_sssw,
+			sleepable_sssw,
+		},
+		{
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			runnable_sssw,
+			INVALID_STATE,
+		},
+	},
+	.initial_state = runnable_sssw,
+	.final_states = { 1, 0, 0, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/sssw/sssw_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_SSSW
+DEFINE_EVENT(event_da_monitor_id, event_sssw,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_sssw,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+#endif /* CONFIG_RV_MON_SSSW */

linux-7.2.3/kernel/trace/rv/monitors/stall/Kconfig

@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_STALL
+	depends on RV
+	select HA_MON_EVENTS_ID
+	bool "stall monitor"
+	help
+	  Enable the stall sample monitor that illustrates the usage of hybrid
+	  automata monitors. It can be used to identify tasks stalled for
+	  longer than a threshold.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_stall.rst

linux-7.2.3/kernel/trace/rv/monitors/stall/stall.c

@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "stall"
+
+#include <trace/events/sched.h>
+#include <rv_trace.h>
+
+#define RV_MON_TYPE RV_MON_PER_TASK
+#define HA_TIMER_TYPE HA_TIMER_WHEEL
+#include "stall.h"
+#include <rv/ha_monitor.h>
+
+static u64 threshold_jiffies = 1000;
+module_param(threshold_jiffies, ullong, 0644);
+
+static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs_stall env, u64 time_ns)
+{
+	if (env == clk_stall)
+		return ha_get_clk_jiffy(ha_mon, env);
+	return ENV_INVALID_VALUE;
+}
+
+static void ha_reset_env(struct ha_monitor *ha_mon, enum envs_stall env, u64 time_ns)
+{
+	if (env == clk_stall)
+		ha_reset_clk_jiffy(ha_mon, env);
+}
+
+static inline bool ha_verify_invariants(struct ha_monitor *ha_mon,
+					enum states curr_state, enum events event,
+					enum states next_state, u64 time_ns)
+{
+	if (curr_state == enqueued_stall)
+		return ha_check_invariant_jiffy(ha_mon, clk_stall, time_ns);
+	return true;
+}
+
+static inline bool ha_verify_guards(struct ha_monitor *ha_mon,
+				    enum states curr_state, enum events event,
+				    enum states next_state, u64 time_ns)
+{
+	bool res = true;
+
+	if (curr_state == dequeued_stall && event == sched_wakeup_stall)
+		ha_reset_env(ha_mon, clk_stall, time_ns);
+	else if (curr_state == running_stall && event == sched_switch_preempt_stall)
+		ha_reset_env(ha_mon, clk_stall, time_ns);
+	return res;
+}
+
+static inline void ha_setup_invariants(struct ha_monitor *ha_mon,
+				       enum states curr_state, enum events event,
+				       enum states next_state, u64 time_ns)
+{
+	if (next_state == curr_state)
+		return;
+	if (next_state == enqueued_stall)
+		ha_start_timer_jiffy(ha_mon, clk_stall, threshold_jiffies, time_ns);
+	else if (curr_state == enqueued_stall)
+		ha_cancel_timer(ha_mon);
+}
+
+static bool ha_verify_constraint(struct ha_monitor *ha_mon,
+				 enum states curr_state, enum events event,
+				 enum states next_state, u64 time_ns)
+{
+	if (!ha_verify_invariants(ha_mon, curr_state, event, next_state, time_ns))
+		return false;
+
+	if (!ha_verify_guards(ha_mon, curr_state, event, next_state, time_ns))
+		return false;
+
+	ha_setup_invariants(ha_mon, curr_state, event, next_state, time_ns);
+
+	return true;
+}
+
+static void handle_sched_switch(void *data, bool preempt,
+				struct task_struct *prev,
+				struct task_struct *next,
+				unsigned int prev_state)
+{
+	if (!preempt && prev_state != TASK_RUNNING)
+		da_handle_start_event(prev, sched_switch_wait_stall);
+	else
+		da_handle_event(prev, sched_switch_preempt_stall);
+	da_handle_event(next, sched_switch_in_stall);
+}
+
+static void handle_sched_wakeup(void *data, struct task_struct *p)
+{
+	da_handle_event(p, sched_wakeup_stall);
+}
+
+static int enable_stall(void)
+{
+	int retval;
+
+	retval = ha_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("stall", sched_switch, handle_sched_switch);
+	rv_attach_trace_probe("stall", sched_wakeup, handle_sched_wakeup);
+
+	return 0;
+}
+
+static void disable_stall(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("stall", sched_switch, handle_sched_switch);
+	rv_detach_trace_probe("stall", sched_wakeup, handle_sched_wakeup);
+
+	ha_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "stall",
+	.description = "identify tasks stalled for longer than a threshold.",
+	.enable = enable_stall,
+	.disable = disable_stall,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_stall(void)
+{
+	return rv_register_monitor(&rv_this, NULL);
+}
+
+static void __exit unregister_stall(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_stall);
+module_exit(unregister_stall);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("stall: identify tasks stalled for longer than a threshold.");

linux-7.2.3/kernel/trace/rv/monitors/stall/stall.h

@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of stall automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME stall
+
+enum states_stall {
+	dequeued_stall,
+	enqueued_stall,
+	running_stall,
+	state_max_stall,
+};
+
+#define INVALID_STATE state_max_stall
+
+enum events_stall {
+	sched_switch_in_stall,
+	sched_switch_preempt_stall,
+	sched_switch_wait_stall,
+	sched_wakeup_stall,
+	event_max_stall,
+};
+
+enum envs_stall {
+	clk_stall,
+	env_max_stall,
+	env_max_stored_stall = env_max_stall,
+};
+
+_Static_assert(env_max_stored_stall <= MAX_HA_ENV_LEN, "Not enough slots");
+
+struct automaton_stall {
+	char *state_names[state_max_stall];
+	char *event_names[event_max_stall];
+	char *env_names[env_max_stall];
+	unsigned char function[state_max_stall][event_max_stall];
+	unsigned char initial_state;
+	bool final_states[state_max_stall];
+};
+
+static const struct automaton_stall automaton_stall = {
+	.state_names = {
+		"dequeued",
+		"enqueued",
+		"running",
+	},
+	.event_names = {
+		"sched_switch_in",
+		"sched_switch_preempt",
+		"sched_switch_wait",
+		"sched_wakeup",
+	},
+	.env_names = {
+		"clk",
+	},
+	.function = {
+		{
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			enqueued_stall,
+		},
+		{
+			running_stall,
+			INVALID_STATE,
+			INVALID_STATE,
+			enqueued_stall,
+		},
+		{
+			running_stall,
+			enqueued_stall,
+			dequeued_stall,
+			running_stall,
+		},
+	},
+	.initial_state = dequeued_stall,
+	.final_states = { 1, 0, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/stall/stall_trace.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_STALL
+DEFINE_EVENT(event_da_monitor_id, event_stall,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_stall,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+
+DEFINE_EVENT(error_env_da_monitor_id, error_env_stall,
+	     TP_PROTO(int id, char *state, char *event, char *env),
+	     TP_ARGS(id, state, event, env));
+#endif /* CONFIG_RV_MON_STALL */

linux-7.2.3/kernel/trace/rv/monitors/sts/Kconfig

@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_STS
+	depends on RV
+	depends on TRACE_IRQFLAGS
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_IMPLICIT
+	bool "sts monitor"
+	help
+	  Monitor to ensure relationships between scheduler and task switches
+	   * the scheduler is called and returns with interrupts disabled
+	   * each call to the scheduler has up to one switch
+	   * switches only happen inside the scheduler
+	   * each call to the scheduler disables interrupts to switch
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst

linux-7.2.3/kernel/trace/rv/monitors/sts/sts.c

@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "sts"
+
+#include <trace/events/sched.h>
+#include <trace/events/irq.h>
+#include <trace/events/preemptirq.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_CPU
+#include "sts.h"
+#include <rv/da_monitor.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <asm/trace/irq_vectors.h>
+
+static void handle_vector_irq_entry(void *data, int vector)
+{
+	da_handle_event(irq_entry_sts);
+}
+
+static void attach_vector_irq(void)
+{
+	rv_attach_trace_probe("sts", local_timer_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_IRQ_WORK))
+		rv_attach_trace_probe("sts", irq_work_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_SMP)) {
+		rv_attach_trace_probe("sts", reschedule_entry, handle_vector_irq_entry);
+		rv_attach_trace_probe("sts", call_function_entry, handle_vector_irq_entry);
+		rv_attach_trace_probe("sts", call_function_single_entry, handle_vector_irq_entry);
+	}
+}
+
+static void detach_vector_irq(void)
+{
+	rv_detach_trace_probe("sts", local_timer_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_IRQ_WORK))
+		rv_detach_trace_probe("sts", irq_work_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_SMP)) {
+		rv_detach_trace_probe("sts", reschedule_entry, handle_vector_irq_entry);
+		rv_detach_trace_probe("sts", call_function_entry, handle_vector_irq_entry);
+		rv_detach_trace_probe("sts", call_function_single_entry, handle_vector_irq_entry);
+	}
+}
+
+#else
+/* We assume irq_entry tracepoints are sufficient on other architectures */
+static void attach_vector_irq(void) { }
+static void detach_vector_irq(void) { }
+#endif
+
+static void handle_irq_disable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event(irq_disable_sts);
+}
+
+static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event(irq_enable_sts);
+}
+
+static void handle_irq_entry(void *data, int irq, struct irqaction *action)
+{
+	da_handle_event(irq_entry_sts);
+}
+
+static void handle_sched_switch(void *data, bool preempt,
+				struct task_struct *prev,
+				struct task_struct *next,
+				unsigned int prev_state)
+{
+	da_handle_event(sched_switch_sts);
+}
+
+static void handle_schedule_entry(void *data, bool preempt)
+{
+	da_handle_event(schedule_entry_sts);
+}
+
+static void handle_schedule_exit(void *data, bool is_switch)
+{
+	da_handle_start_event(schedule_exit_sts);
+}
+
+static int enable_sts(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("sts", irq_disable, handle_irq_disable);
+	rv_attach_trace_probe("sts", irq_enable, handle_irq_enable);
+	rv_attach_trace_probe("sts", irq_handler_entry, handle_irq_entry);
+	rv_attach_trace_probe("sts", sched_switch, handle_sched_switch);
+	rv_attach_trace_probe("sts", sched_entry_tp, handle_schedule_entry);
+	rv_attach_trace_probe("sts", sched_exit_tp, handle_schedule_exit);
+	attach_vector_irq();
+
+	return 0;
+}
+
+static void disable_sts(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("sts", irq_disable, handle_irq_disable);
+	rv_detach_trace_probe("sts", irq_enable, handle_irq_enable);
+	rv_detach_trace_probe("sts", irq_handler_entry, handle_irq_entry);
+	rv_detach_trace_probe("sts", sched_switch, handle_sched_switch);
+	rv_detach_trace_probe("sts", sched_entry_tp, handle_schedule_entry);
+	rv_detach_trace_probe("sts", sched_exit_tp, handle_schedule_exit);
+	detach_vector_irq();
+
+	da_monitor_destroy();
+}
+
+/*
+ * This is the monitor register section.
+ */
+static struct rv_monitor rv_this = {
+	.name = "sts",
+	.description = "schedule implies task switch.",
+	.enable = enable_sts,
+	.disable = disable_sts,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_sts(void)
+{
+	return rv_register_monitor(&rv_this, &rv_sched);
+}
+
+static void __exit unregister_sts(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_sts);
+module_exit(unregister_sts);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("sts: schedule implies task switch.");

linux-7.2.3/kernel/trace/rv/monitors/sts/sts.h

@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of sts automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME sts
+
+enum states_sts {
+	can_sched_sts,
+	cant_sched_sts,
+	disable_to_switch_sts,
+	enable_to_exit_sts,
+	in_irq_sts,
+	scheduling_sts,
+	switching_sts,
+	state_max_sts,
+};
+
+#define INVALID_STATE state_max_sts
+
+enum events_sts {
+	irq_disable_sts,
+	irq_enable_sts,
+	irq_entry_sts,
+	sched_switch_sts,
+	schedule_entry_sts,
+	schedule_exit_sts,
+	event_max_sts,
+};
+
+struct automaton_sts {
+	char *state_names[state_max_sts];
+	char *event_names[event_max_sts];
+	unsigned char function[state_max_sts][event_max_sts];
+	unsigned char initial_state;
+	bool final_states[state_max_sts];
+};
+
+static const struct automaton_sts automaton_sts = {
+	.state_names = {
+		"can_sched",
+		"cant_sched",
+		"disable_to_switch",
+		"enable_to_exit",
+		"in_irq",
+		"scheduling",
+		"switching",
+	},
+	.event_names = {
+		"irq_disable",
+		"irq_enable",
+		"irq_entry",
+		"sched_switch",
+		"schedule_entry",
+		"schedule_exit",
+	},
+	.function = {
+		{
+			cant_sched_sts,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			scheduling_sts,
+			INVALID_STATE,
+		},
+		{
+			INVALID_STATE,
+			can_sched_sts,
+			cant_sched_sts,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+		},
+		{
+			INVALID_STATE,
+			enable_to_exit_sts,
+			in_irq_sts,
+			switching_sts,
+			INVALID_STATE,
+			INVALID_STATE,
+		},
+		{
+			enable_to_exit_sts,
+			enable_to_exit_sts,
+			enable_to_exit_sts,
+			INVALID_STATE,
+			INVALID_STATE,
+			can_sched_sts,
+		},
+		{
+			INVALID_STATE,
+			scheduling_sts,
+			in_irq_sts,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+		},
+		{
+			disable_to_switch_sts,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+		},
+		{
+			INVALID_STATE,
+			enable_to_exit_sts,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+		},
+	},
+	.initial_state = can_sched_sts,
+	.final_states = { 1, 0, 0, 0, 0, 0, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/sts/sts_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_STS
+DEFINE_EVENT(event_da_monitor, event_sts,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_sts,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+#endif /* CONFIG_RV_MON_STS */

linux-7.2.3/kernel/trace/rv/monitors/wip/Kconfig

@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_WIP
+	depends on RV
+	depends on TRACE_PREEMPT_TOGGLE
+	select DA_MON_EVENTS_IMPLICIT
+	bool "wip monitor"
+	help
+	  Enable wip (wakeup in preemptive) sample monitor that illustrates
+	  the usage of per-cpu monitors, and one limitation of the
+	  preempt_disable/enable events.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_wip.rst

linux-7.2.3/kernel/trace/rv/monitors/wip/wip.c

@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "wip"
+
+#include <rv_trace.h>
+#include <trace/events/sched.h>
+#include <trace/events/preemptirq.h>
+
+#define RV_MON_TYPE RV_MON_PER_CPU
+#include "wip.h"
+#include <rv/da_monitor.h>
+
+static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event(preempt_disable_wip);
+}
+
+static void handle_preempt_enable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_start_event(preempt_enable_wip);
+}
+
+static void handle_sched_waking(void *data, struct task_struct *task)
+{
+	da_handle_event(sched_waking_wip);
+}
+
+static int enable_wip(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("wip", preempt_enable, handle_preempt_enable);
+	rv_attach_trace_probe("wip", sched_waking, handle_sched_waking);
+	rv_attach_trace_probe("wip", preempt_disable, handle_preempt_disable);
+
+	return 0;
+}
+
+static void disable_wip(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("wip", preempt_disable, handle_preempt_disable);
+	rv_detach_trace_probe("wip", preempt_enable, handle_preempt_enable);
+	rv_detach_trace_probe("wip", sched_waking, handle_sched_waking);
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "wip",
+	.description = "wakeup in preemptive per-cpu testing monitor.",
+	.enable = enable_wip,
+	.disable = disable_wip,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_wip(void)
+{
+	return rv_register_monitor(&rv_this, NULL);
+}
+
+static void __exit unregister_wip(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_wip);
+module_exit(unregister_wip);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Bristot de Oliveira <bristot@kernel.org>");
+MODULE_DESCRIPTION("wip: wakeup in preemptive - per-cpu sample monitor.");

linux-7.2.3/kernel/trace/rv/monitors/wip/wip.h

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of wip automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME wip
+
+enum states_wip {
+	preemptive_wip,
+	non_preemptive_wip,
+	state_max_wip,
+};
+
+#define INVALID_STATE state_max_wip
+
+enum events_wip {
+	preempt_disable_wip,
+	preempt_enable_wip,
+	sched_waking_wip,
+	event_max_wip,
+};
+
+struct automaton_wip {
+	char *state_names[state_max_wip];
+	char *event_names[event_max_wip];
+	unsigned char function[state_max_wip][event_max_wip];
+	unsigned char initial_state;
+	bool final_states[state_max_wip];
+};
+
+static const struct automaton_wip automaton_wip = {
+	.state_names = {
+		"preemptive",
+		"non_preemptive",
+	},
+	.event_names = {
+		"preempt_disable",
+		"preempt_enable",
+		"sched_waking",
+	},
+	.function = {
+		{ non_preemptive_wip,      INVALID_STATE,      INVALID_STATE },
+		{      INVALID_STATE,     preemptive_wip, non_preemptive_wip },
+	},
+	.initial_state = preemptive_wip,
+	.final_states = { 1, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/wip/wip_trace.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_WIP
+DEFINE_EVENT(event_da_monitor, event_wip,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_wip,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+#endif /* CONFIG_RV_MON_WIP */

linux-7.2.3/kernel/trace/rv/monitors/wwnr/Kconfig

@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_WWNR
+	depends on RV
+	select DA_MON_EVENTS_ID
+	bool "wwnr monitor"
+	help
+	  Enable wwnr (wakeup while not running) sample monitor, this is a
+	  sample monitor that illustrates the usage of per-task monitor.
+	  The model is borken on purpose: it serves to test reactors.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_wwnr.rst

linux-7.2.3/kernel/trace/rv/monitors/wwnr/wwnr.c

@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+
+#define MODULE_NAME "wwnr"
+
+#include <rv_trace.h>
+#include <trace/events/sched.h>
+
+#define RV_MON_TYPE RV_MON_PER_TASK
+#include "wwnr.h"
+#include <rv/da_monitor.h>
+
+static void handle_switch(void *data, bool preempt, struct task_struct *p,
+			  struct task_struct *n, unsigned int prev_state)
+{
+	/* start monitoring only after the first suspension */
+	if (prev_state == TASK_INTERRUPTIBLE)
+		da_handle_start_event(p, switch_out_wwnr);
+	else
+		da_handle_event(p, switch_out_wwnr);
+
+	da_handle_event(n, switch_in_wwnr);
+}
+
+static void handle_wakeup(void *data, struct task_struct *p)
+{
+	da_handle_event(p, wakeup_wwnr);
+}
+
+static int enable_wwnr(void)
+{
+	int retval;
+
+	retval = da_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("wwnr", sched_switch, handle_switch);
+	rv_attach_trace_probe("wwnr", sched_wakeup, handle_wakeup);
+
+	return 0;
+}
+
+static void disable_wwnr(void)
+{
+	rv_this.enabled = 0;
+
+	rv_detach_trace_probe("wwnr", sched_switch, handle_switch);
+	rv_detach_trace_probe("wwnr", sched_wakeup, handle_wakeup);
+
+	da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+	.name = "wwnr",
+	.description = "wakeup while not running per-task testing model.",
+	.enable = enable_wwnr,
+	.disable = disable_wwnr,
+	.reset = da_monitor_reset_all,
+	.enabled = 0,
+};
+
+static int __init register_wwnr(void)
+{
+	return rv_register_monitor(&rv_this, NULL);
+}
+
+static void __exit unregister_wwnr(void)
+{
+	rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_wwnr);
+module_exit(unregister_wwnr);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Bristot de Oliveira <bristot@kernel.org>");
+MODULE_DESCRIPTION("wwnr: wakeup while not running monitor");

linux-7.2.3/kernel/trace/rv/monitors/wwnr/wwnr.h

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of wwnr automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME wwnr
+
+enum states_wwnr {
+	not_running_wwnr,
+	running_wwnr,
+	state_max_wwnr,
+};
+
+#define INVALID_STATE state_max_wwnr
+
+enum events_wwnr {
+	switch_in_wwnr,
+	switch_out_wwnr,
+	wakeup_wwnr,
+	event_max_wwnr,
+};
+
+struct automaton_wwnr {
+	char *state_names[state_max_wwnr];
+	char *event_names[event_max_wwnr];
+	unsigned char function[state_max_wwnr][event_max_wwnr];
+	unsigned char initial_state;
+	bool final_states[state_max_wwnr];
+};
+
+static const struct automaton_wwnr automaton_wwnr = {
+	.state_names = {
+		"not_running",
+		"running",
+	},
+	.event_names = {
+		"switch_in",
+		"switch_out",
+		"wakeup",
+	},
+	.function = {
+		{       running_wwnr,      INVALID_STATE,   not_running_wwnr },
+		{      INVALID_STATE,   not_running_wwnr,      INVALID_STATE },
+	},
+	.initial_state = not_running_wwnr,
+	.final_states = { 1, 0 },
+};

linux-7.2.3/kernel/trace/rv/monitors/wwnr/wwnr_trace.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_WWNR
+/* id is the pid of the task */
+DEFINE_EVENT(event_da_monitor_id, event_wwnr,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_wwnr,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+#endif /* CONFIG_RV_MON_WWNR */

linux-7.2.3/kernel/trace/rv/reactor_panic.c

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * Panic RV reactor:
+ *   Prints the exception msg to the kernel message log and panic().
+ */
+
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+
+__printf(1, 0) static void rv_panic_reaction(const char *msg, va_list args)
+{
+	vpanic(msg, args);
+}
+
+static struct rv_reactor rv_panic = {
+	.name = "panic",
+	.description = "panic the system if an exception is found.",
+	.react = rv_panic_reaction
+};
+
+static int __init register_react_panic(void)
+{
+	rv_register_reactor(&rv_panic);
+	return 0;
+}
+
+static void __exit unregister_react_panic(void)
+{
+	rv_unregister_reactor(&rv_panic);
+}
+
+module_init(register_react_panic);
+module_exit(unregister_react_panic);
+
+MODULE_AUTHOR("Daniel Bristot de Oliveira");
+MODULE_DESCRIPTION("panic rv reactor: panic if an exception is found.");

linux-7.2.3/kernel/trace/rv/reactor_printk.c

@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * Printk RV reactor:
+ *   Prints the exception msg to the kernel message log.
+ */
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+
+__printf(1, 0) static void rv_printk_reaction(const char *msg, va_list args)
+{
+	vprintk_deferred(msg, args);
+}
+
+static struct rv_reactor rv_printk = {
+	.name = "printk",
+	.description = "prints the exception msg to the kernel message log.",
+	.react = rv_printk_reaction
+};
+
+static int __init register_react_printk(void)
+{
+	rv_register_reactor(&rv_printk);
+	return 0;
+}
+
+static void __exit unregister_react_printk(void)
+{
+	rv_unregister_reactor(&rv_printk);
+}
+
+module_init(register_react_printk);
+module_exit(unregister_react_printk);
+
+MODULE_AUTHOR("Daniel Bristot de Oliveira");
+MODULE_DESCRIPTION("printk rv reactor: printk if an exception is hit.");

linux-7.2.3/kernel/trace/rv/rv.c

@@ -0,0 +1,854 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * This is the online Runtime Verification (RV) interface.
+ *
+ * RV is a lightweight (yet rigorous) method that complements classical
+ * exhaustive verification techniques (such as model checking and
+ * theorem proving) with a more practical approach to complex systems.
+ *
+ * RV works by analyzing the trace of the system's actual execution,
+ * comparing it against a formal specification of the system behavior.
+ * RV can give precise information on the runtime behavior of the
+ * monitored system while enabling the reaction for unexpected
+ * events, avoiding, for example, the propagation of a failure on
+ * safety-critical systems.
+ *
+ * The development of this interface roots in the development of the
+ * paper:
+ *
+ * De Oliveira, Daniel Bristot; Cucinotta, Tommaso; De Oliveira, Romulo
+ * Silva. Efficient formal verification for the Linux kernel. In:
+ * International Conference on Software Engineering and Formal Methods.
+ * Springer, Cham, 2019. p. 315-332.
+ *
+ * And:
+ *
+ * De Oliveira, Daniel Bristot, et al. Automata-based formal analysis
+ * and verification of the real-time Linux kernel. PhD Thesis, 2020.
+ *
+ * == Runtime monitor interface ==
+ *
+ * A monitor is the central part of the runtime verification of a system.
+ *
+ * The monitor stands in between the formal specification of the desired
+ * (or undesired) behavior, and the trace of the actual system.
+ *
+ * In Linux terms, the runtime verification monitors are encapsulated
+ * inside the "RV monitor" abstraction. A RV monitor includes a reference
+ * model of the system, a set of instances of the monitor (per-cpu monitor,
+ * per-task monitor, and so on), and the helper functions that glue the
+ * monitor to the system via trace. Generally, a monitor includes some form
+ * of trace output as a reaction for event parsing and exceptions,
+ * as depicted below:
+ *
+ * Linux  +----- RV Monitor ----------------------------------+ Formal
+ *  Realm |                                                   |  Realm
+ *  +-------------------+     +----------------+     +-----------------+
+ *  |   Linux kernel    |     |     Monitor    |     |     Reference   |
+ *  |     Tracing       |  -> |   Instance(s)  | <-  |       Model     |
+ *  | (instrumentation) |     | (verification) |     | (specification) |
+ *  +-------------------+     +----------------+     +-----------------+
+ *         |                          |                       |
+ *         |                          V                       |
+ *         |                     +----------+                 |
+ *         |                     | Reaction |                 |
+ *         |                     +--+--+--+-+                 |
+ *         |                        |  |  |                   |
+ *         |                        |  |  +-> trace output ?  |
+ *         +------------------------|--|----------------------+
+ *                                  |  +----> panic ?
+ *                                  +-------> <user-specified>
+ *
+ * This file implements the interface for loading RV monitors, and
+ * to control the verification session.
+ *
+ * == Registering monitors ==
+ *
+ * The struct rv_monitor defines a set of callback functions to control
+ * a verification session. For instance, when a given monitor is enabled,
+ * the "enable" callback function is called to hook the instrumentation
+ * functions to the kernel trace events. The "disable" function is called
+ * when disabling the verification session.
+ *
+ * A RV monitor is registered via:
+ *   int rv_register_monitor(struct rv_monitor *monitor);
+ * And unregistered via:
+ *   int rv_unregister_monitor(struct rv_monitor *monitor);
+ *
+ * == User interface ==
+ *
+ * The user interface resembles kernel tracing interface. It presents
+ * these files:
+ *
+ *  "available_monitors"
+ *    - List the available monitors, one per line.
+ *
+ *    For example:
+ *      # cat available_monitors
+ *      wip
+ *      wwnr
+ *
+ *  "enabled_monitors"
+ *    - Lists the enabled monitors, one per line;
+ *    - Writing to it enables a given monitor;
+ *    - Writing a monitor name with a '!' prefix disables it;
+ *    - Truncating the file disables all enabled monitors.
+ *
+ *    For example:
+ *      # cat enabled_monitors
+ *      # echo wip > enabled_monitors
+ *      # echo wwnr >> enabled_monitors
+ *      # cat enabled_monitors
+ *      wip
+ *      wwnr
+ *      # echo '!wip' >> enabled_monitors
+ *      # cat enabled_monitors
+ *      wwnr
+ *      # echo > enabled_monitors
+ *      # cat enabled_monitors
+ *      #
+ *
+ *    Note that more than one monitor can be enabled concurrently.
+ *
+ *  "monitoring_on"
+ *    - It is an on/off general switcher for monitoring. Note
+ *    that it does not disable enabled monitors or detach events,
+ *    but stops the per-entity monitors from monitoring the events
+ *    received from the instrumentation. It resembles the "tracing_on"
+ *    switcher.
+ *
+ *  "monitors/"
+ *    Each monitor will have its own directory inside "monitors/". There
+ *    the monitor specific files will be presented.
+ *    The "monitors/" directory resembles the "events" directory on
+ *    tracefs.
+ *
+ *    For example:
+ *      # cd monitors/wip/
+ *      # ls
+ *      desc  enable
+ *      # cat desc
+ *      auto-generated wakeup in preemptive monitor.
+ *      # cat enable
+ *      0
+ *
+ *  For further information, see:
+ *   Documentation/trace/rv/runtime-verification.rst
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+
+#ifdef CONFIG_RV_MON_EVENTS
+#define CREATE_TRACE_POINTS
+#include <rv_trace.h>
+#endif
+
+#include "rv.h"
+
+DEFINE_MUTEX(rv_interface_lock);
+
+static struct rv_interface rv_root;
+
+struct dentry *get_monitors_root(void)
+{
+	return rv_root.monitors_dir;
+}
+
+/*
+ * Interface for the monitor register.
+ */
+LIST_HEAD(rv_monitors_list);
+
+static int task_monitor_count;
+static bool task_monitor_slots[CONFIG_RV_PER_TASK_MONITORS];
+
+int rv_get_task_monitor_slot(void)
+{
+	int i;
+
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (task_monitor_count == CONFIG_RV_PER_TASK_MONITORS)
+		return -EBUSY;
+
+	task_monitor_count++;
+
+	for (i = 0; i < CONFIG_RV_PER_TASK_MONITORS; i++) {
+		if (task_monitor_slots[i] == false) {
+			task_monitor_slots[i] = true;
+			return i;
+		}
+	}
+
+	WARN_ONCE(1, "RV task_monitor_count and slots are out of sync\n");
+
+	return -EINVAL;
+}
+
+void rv_put_task_monitor_slot(int slot)
+{
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (slot < 0 || slot >= CONFIG_RV_PER_TASK_MONITORS) {
+		WARN_ONCE(1, "RV releasing an invalid slot!: %d\n", slot);
+		return;
+	}
+
+	WARN_ONCE(!task_monitor_slots[slot], "RV releasing unused task_monitor_slots: %d\n",
+		  slot);
+
+	task_monitor_count--;
+	task_monitor_slots[slot] = false;
+}
+
+/*
+ * Monitors with a parent are nested,
+ * Monitors without a parent could be standalone or containers.
+ */
+bool rv_is_nested_monitor(struct rv_monitor *mon)
+{
+	return mon->parent != NULL;
+}
+
+/*
+ * We set our list to have nested monitors listed after their parent
+ * if a monitor has a child element its a container.
+ * Containers can be also identified based on their function pointers:
+ * as they are not real monitors they do not need function definitions
+ * for enable()/disable(). Use this condition to find empty containers.
+ * Keep both conditions in case we have some non-compliant containers.
+ */
+bool rv_is_container_monitor(struct rv_monitor *mon)
+{
+	struct rv_monitor *next;
+
+	if (list_is_last(&mon->list, &rv_monitors_list))
+		return false;
+
+	next = list_next_entry(mon, list);
+
+	return next->parent == mon || !mon->enable;
+}
+
+/*
+ * This section collects the monitor/ files and folders.
+ */
+static ssize_t monitor_enable_read_data(struct file *filp, char __user *user_buf, size_t count,
+					loff_t *ppos)
+{
+	struct rv_monitor *mon = filp->private_data;
+	const char *buff;
+
+	buff = mon->enabled ? "1\n" : "0\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff)+1);
+}
+
+/*
+ * __rv_disable_monitor - disabled an enabled monitor
+ */
+static int __rv_disable_monitor(struct rv_monitor *mon, bool sync)
+{
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (mon->enabled) {
+		mon->enabled = 0;
+		if (mon->disable)
+			mon->disable();
+
+		/*
+		 * Wait for the execution of all events to finish.
+		 * Otherwise, the data used by the monitor could
+		 * be inconsistent. i.e., if the monitor is re-enabled.
+		 */
+		if (sync)
+			tracepoint_synchronize_unregister();
+		return 1;
+	}
+	return 0;
+}
+
+static void rv_disable_single(struct rv_monitor *mon)
+{
+	__rv_disable_monitor(mon, true);
+}
+
+static int rv_enable_single(struct rv_monitor *mon)
+{
+	int retval;
+
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (mon->enabled)
+		return 0;
+
+	retval = mon->enable();
+
+	if (!retval)
+		mon->enabled = 1;
+
+	return retval;
+}
+
+static void rv_disable_container(struct rv_monitor *mon)
+{
+	struct rv_monitor *p = mon;
+	int enabled = 0;
+
+	list_for_each_entry_continue(p, &rv_monitors_list, list) {
+		if (p->parent != mon)
+			break;
+		enabled += __rv_disable_monitor(p, false);
+	}
+	if (enabled)
+		tracepoint_synchronize_unregister();
+	mon->enabled = 0;
+}
+
+static int rv_enable_container(struct rv_monitor *mon)
+{
+	struct rv_monitor *p = mon;
+	int retval = 0;
+
+	list_for_each_entry_continue(p, &rv_monitors_list, list) {
+		if (retval || p->parent != mon)
+			break;
+		retval = rv_enable_single(p);
+	}
+	if (retval)
+		rv_disable_container(mon);
+	else
+		mon->enabled = 1;
+	return retval;
+}
+
+/**
+ * rv_disable_monitor - disable a given runtime monitor
+ * @mon: Pointer to the monitor definition structure.
+ *
+ * Returns 0 on success.
+ */
+int rv_disable_monitor(struct rv_monitor *mon)
+{
+	if (rv_is_container_monitor(mon))
+		rv_disable_container(mon);
+	else
+		rv_disable_single(mon);
+
+	return 0;
+}
+
+/**
+ * rv_enable_monitor - enable a given runtime monitor
+ * @mon: Pointer to the monitor definition structure.
+ *
+ * Returns 0 on success, error otherwise.
+ */
+int rv_enable_monitor(struct rv_monitor *mon)
+{
+	int retval;
+
+	if (rv_is_container_monitor(mon))
+		retval = rv_enable_container(mon);
+	else
+		retval = rv_enable_single(mon);
+
+	return retval;
+}
+
+/*
+ * interface for enabling/disabling a monitor.
+ */
+static ssize_t monitor_enable_write_data(struct file *filp, const char __user *user_buf,
+					 size_t count, loff_t *ppos)
+{
+	struct rv_monitor *mon = filp->private_data;
+	int retval;
+	bool val;
+
+	retval = kstrtobool_from_user(user_buf, count, &val);
+	if (retval)
+		return retval;
+
+	guard(mutex)(&rv_interface_lock);
+
+	if (val)
+		retval = rv_enable_monitor(mon);
+	else
+		retval = rv_disable_monitor(mon);
+
+	return retval ? : count;
+}
+
+static const struct file_operations interface_enable_fops = {
+	.open   = simple_open,
+	.write  = monitor_enable_write_data,
+	.read   = monitor_enable_read_data,
+};
+
+/*
+ * Interface to read monitors description.
+ */
+static ssize_t monitor_desc_read_data(struct file *filp, char __user *user_buf, size_t count,
+				      loff_t *ppos)
+{
+	struct rv_monitor *mon = filp->private_data;
+	char buff[256];
+
+	memset(buff, 0, sizeof(buff));
+
+	snprintf(buff, sizeof(buff), "%s\n", mon->description);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff) + 1);
+}
+
+static const struct file_operations interface_desc_fops = {
+	.open   = simple_open,
+	.read	= monitor_desc_read_data,
+};
+
+/*
+ * During the registration of a monitor, this function creates
+ * the monitor dir, where the specific options of the monitor
+ * are exposed.
+ */
+static int create_monitor_dir(struct rv_monitor *mon, struct rv_monitor *parent)
+{
+	struct dentry *root = parent ? parent->root_d : get_monitors_root();
+	struct dentry *dir __free(rv_remove) = rv_create_dir(mon->name, root);
+	struct dentry *tmp;
+	int retval;
+
+	if (!dir)
+		return -ENOMEM;
+
+	tmp = rv_create_file("enable", RV_MODE_WRITE, dir, mon, &interface_enable_fops);
+	if (!tmp)
+		return -ENOMEM;
+
+	tmp = rv_create_file("desc", RV_MODE_READ, dir, mon, &interface_desc_fops);
+	if (!tmp)
+		return -ENOMEM;
+
+	retval = reactor_populate_monitor(mon, dir);
+	if (retval)
+		return retval;
+
+	mon->root_d = no_free_ptr(dir);
+	return 0;
+}
+
+/*
+ * Available/Enable monitor shared seq functions.
+ */
+static int monitors_show(struct seq_file *m, void *p)
+{
+	struct rv_monitor *mon = container_of(p, struct rv_monitor, list);
+
+	if (mon->parent)
+		seq_printf(m, "%s:%s\n", mon->parent->name, mon->name);
+	else
+		seq_printf(m, "%s\n", mon->name);
+	return 0;
+}
+
+/*
+ * Used by the seq file operations at the end of a read
+ * operation.
+ */
+static void monitors_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&rv_interface_lock);
+}
+
+/*
+ * Available monitor seq functions.
+ */
+static void *available_monitors_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&rv_interface_lock);
+	return seq_list_start(&rv_monitors_list, *pos);
+}
+
+static void *available_monitors_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &rv_monitors_list, pos);
+}
+
+/*
+ * Enable monitor seq functions.
+ */
+static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct rv_monitor *mon = container_of(p, struct rv_monitor, list);
+
+	(*pos)++;
+
+	list_for_each_entry_continue(mon, &rv_monitors_list, list) {
+		if (mon->enabled)
+			return &mon->list;
+	}
+
+	return NULL;
+}
+
+static void *enabled_monitors_start(struct seq_file *m, loff_t *pos)
+{
+	struct list_head *head;
+	loff_t l;
+
+	mutex_lock(&rv_interface_lock);
+
+	if (list_empty(&rv_monitors_list))
+		return NULL;
+
+	head = &rv_monitors_list;
+
+	for (l = 0; l <= *pos; ) {
+		head = enabled_monitors_next(m, head, &l);
+		if (!head)
+			break;
+	}
+
+	return head;
+}
+
+/*
+ * available/enabled monitors seq definition.
+ */
+static const struct seq_operations available_monitors_seq_ops = {
+	.start	= available_monitors_start,
+	.next	= available_monitors_next,
+	.stop	= monitors_stop,
+	.show	= monitors_show
+};
+
+static const struct seq_operations enabled_monitors_seq_ops = {
+	.start  = enabled_monitors_start,
+	.next   = enabled_monitors_next,
+	.stop   = monitors_stop,
+	.show   = monitors_show
+};
+
+/*
+ * available_monitors interface.
+ */
+static int available_monitors_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &available_monitors_seq_ops);
+};
+
+static const struct file_operations available_monitors_ops = {
+	.open    = available_monitors_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+/*
+ * enabled_monitors interface.
+ */
+static void disable_all_monitors(void)
+{
+	struct rv_monitor *mon;
+	int enabled = 0;
+
+	guard(mutex)(&rv_interface_lock);
+
+	list_for_each_entry(mon, &rv_monitors_list, list)
+		enabled += __rv_disable_monitor(mon, false);
+
+	if (enabled) {
+		/*
+		 * Wait for the execution of all events to finish.
+		 * Otherwise, the data used by the monitor could
+		 * be inconsistent. i.e., if the monitor is re-enabled.
+		 */
+		tracepoint_synchronize_unregister();
+	}
+}
+
+static int enabled_monitors_open(struct inode *inode, struct file *file)
+{
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC))
+		disable_all_monitors();
+
+	return seq_open(file, &enabled_monitors_seq_ops);
+};
+
+static ssize_t enabled_monitors_write(struct file *filp, const char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	char buff[MAX_RV_MONITOR_NAME_SIZE + 2];
+	struct rv_monitor *mon;
+	int retval = -EINVAL;
+	bool enable = true;
+	char *ptr, *tmp;
+	int len;
+
+	if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1)
+		return -EINVAL;
+
+	memset(buff, 0, sizeof(buff));
+
+	retval = simple_write_to_buffer(buff, sizeof(buff) - 1, ppos, user_buf, count);
+	if (retval < 0)
+		return -EFAULT;
+
+	ptr = strim(buff);
+
+	if (ptr[0] == '!') {
+		enable = false;
+		ptr++;
+	}
+
+	len = strlen(ptr);
+	if (!len)
+		return count;
+
+	guard(mutex)(&rv_interface_lock);
+
+	retval = -EINVAL;
+
+	/* we support 1 nesting level, trim the parent */
+	tmp = strstr(ptr, ":");
+	if (tmp)
+		ptr = tmp+1;
+
+	list_for_each_entry(mon, &rv_monitors_list, list) {
+		if (strcmp(ptr, mon->name) != 0)
+			continue;
+
+		/*
+		 * Monitor found!
+		 */
+		if (enable)
+			retval = rv_enable_monitor(mon);
+		else
+			retval = rv_disable_monitor(mon);
+
+		if (retval)
+			return retval;
+		return count;
+	}
+
+	return retval;
+}
+
+static const struct file_operations enabled_monitors_ops = {
+	.open		= enabled_monitors_open,
+	.read		= seq_read,
+	.write		= enabled_monitors_write,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * Monitoring on global switcher!
+ */
+static bool __read_mostly monitoring_on;
+
+/**
+ * rv_monitoring_on - checks if monitoring is on
+ *
+ * Returns 1 if on, 0 otherwise.
+ */
+bool rv_monitoring_on(void)
+{
+	return READ_ONCE(monitoring_on);
+}
+
+/*
+ * monitoring_on general switcher.
+ */
+static ssize_t monitoring_on_read_data(struct file *filp, char __user *user_buf,
+				       size_t count, loff_t *ppos)
+{
+	const char *buff;
+
+	buff = rv_monitoring_on() ? "1\n" : "0\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff) + 1);
+}
+
+static void turn_monitoring_off(void)
+{
+	WRITE_ONCE(monitoring_on, false);
+}
+
+static void reset_all_monitors(void)
+{
+	struct rv_monitor *mon;
+
+	list_for_each_entry(mon, &rv_monitors_list, list) {
+		if (mon->enabled && mon->reset)
+			mon->reset();
+	}
+}
+
+static void turn_monitoring_on(void)
+{
+	WRITE_ONCE(monitoring_on, true);
+}
+
+static void turn_monitoring_on_with_reset(void)
+{
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (rv_monitoring_on())
+		return;
+
+	/*
+	 * Monitors might be out of sync with the system if events were not
+	 * processed because of !rv_monitoring_on().
+	 *
+	 * Reset all monitors, forcing a re-sync.
+	 */
+	reset_all_monitors();
+	turn_monitoring_on();
+}
+
+static ssize_t monitoring_on_write_data(struct file *filp, const char __user *user_buf,
+					size_t count, loff_t *ppos)
+{
+	int retval;
+	bool val;
+
+	retval = kstrtobool_from_user(user_buf, count, &val);
+	if (retval)
+		return retval;
+
+	guard(mutex)(&rv_interface_lock);
+
+	if (val)
+		turn_monitoring_on_with_reset();
+	else
+		turn_monitoring_off();
+
+	/*
+	 * Wait for the execution of all events to finish
+	 * before returning to user-space.
+	 */
+	tracepoint_synchronize_unregister();
+
+	return count;
+}
+
+static const struct file_operations monitoring_on_fops = {
+	.open   = simple_open,
+	.write  = monitoring_on_write_data,
+	.read   = monitoring_on_read_data,
+};
+
+static void destroy_monitor_dir(struct rv_monitor *mon)
+{
+	rv_remove(mon->root_d);
+}
+
+/**
+ * rv_register_monitor - register a rv monitor.
+ * @monitor:    The rv_monitor to be registered.
+ * @parent:     The parent of the monitor to be registered, NULL if not nested.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent)
+{
+	struct rv_monitor *r;
+	int retval = 0;
+
+	if (strlen(monitor->name) >= MAX_RV_MONITOR_NAME_SIZE) {
+		pr_info("Monitor %s has a name longer than %d\n", monitor->name,
+			MAX_RV_MONITOR_NAME_SIZE);
+		return -EINVAL;
+	}
+
+	guard(mutex)(&rv_interface_lock);
+
+	list_for_each_entry(r, &rv_monitors_list, list) {
+		if (strcmp(monitor->name, r->name) == 0) {
+			pr_info("Monitor %s is already registered\n", monitor->name);
+			return -EEXIST;
+		}
+	}
+
+	if (parent && rv_is_nested_monitor(parent)) {
+		pr_info("Parent monitor %s is already nested, cannot nest further\n",
+			parent->name);
+		return -EINVAL;
+	}
+
+	monitor->parent = parent;
+
+	retval = create_monitor_dir(monitor, parent);
+	if (retval)
+		return retval;
+
+	/* keep children close to the parent for easier visualisation */
+	if (parent)
+		list_add(&monitor->list, &parent->list);
+	else
+		list_add_tail(&monitor->list, &rv_monitors_list);
+
+	return 0;
+}
+
+/**
+ * rv_unregister_monitor - unregister a rv monitor.
+ * @monitor:    The rv_monitor to be unregistered.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_unregister_monitor(struct rv_monitor *monitor)
+{
+	guard(mutex)(&rv_interface_lock);
+
+	rv_disable_monitor(monitor);
+	list_del(&monitor->list);
+	destroy_monitor_dir(monitor);
+
+	return 0;
+}
+
+int __init rv_init_interface(void)
+{
+	struct dentry *tmp;
+	int retval;
+	struct dentry *root_dir __free(rv_remove) = rv_create_dir("rv", NULL);
+
+	if (!root_dir)
+		return 1;
+
+	rv_root.monitors_dir = rv_create_dir("monitors", root_dir);
+	if (!rv_root.monitors_dir)
+		return 1;
+
+	tmp = rv_create_file("available_monitors", RV_MODE_READ, root_dir, NULL,
+			     &available_monitors_ops);
+	if (!tmp)
+		return 1;
+
+	tmp = rv_create_file("enabled_monitors", RV_MODE_WRITE, root_dir, NULL,
+			     &enabled_monitors_ops);
+	if (!tmp)
+		return 1;
+
+	tmp = rv_create_file("monitoring_on", RV_MODE_WRITE, root_dir, NULL,
+			     &monitoring_on_fops);
+	if (!tmp)
+		return 1;
+	retval = init_rv_reactors(root_dir);
+	if (retval)
+		return 1;
+
+	turn_monitoring_on();
+
+	rv_root.root_dir = no_free_ptr(root_dir);
+
+	return 0;
+}

linux-7.2.3/kernel/trace/rv/rv.h

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/mutex.h>
+
+struct rv_interface {
+	struct dentry		*root_dir;
+	struct dentry		*monitors_dir;
+};
+
+#include "../trace.h"
+#include <linux/tracefs.h>
+#include <linux/rv.h>
+
+#define RV_MODE_WRITE			TRACE_MODE_WRITE
+#define RV_MODE_READ			TRACE_MODE_READ
+
+#define rv_create_dir			tracefs_create_dir
+#define rv_create_file			tracefs_create_file
+#define rv_remove			tracefs_remove
+
+DEFINE_FREE(rv_remove, struct dentry *, if (_T) rv_remove(_T));
+
+#define MAX_RV_MONITOR_NAME_SIZE	32
+#define MAX_RV_REACTOR_NAME_SIZE	32
+
+extern struct mutex rv_interface_lock;
+extern struct list_head rv_monitors_list;
+
+struct dentry *get_monitors_root(void);
+int rv_disable_monitor(struct rv_monitor *mon);
+int rv_enable_monitor(struct rv_monitor *mon);
+bool rv_is_container_monitor(struct rv_monitor *mon);
+bool rv_is_nested_monitor(struct rv_monitor *mon);
+
+#ifdef CONFIG_RV_REACTORS
+int reactor_populate_monitor(struct rv_monitor *mon, struct dentry *root);
+int init_rv_reactors(struct dentry *root_dir);
+#else
+static inline int reactor_populate_monitor(struct rv_monitor *mon, struct dentry *root)
+{
+	return 0;
+}
+
+static inline int init_rv_reactors(struct dentry *root_dir)
+{
+	return 0;
+}
+#endif

linux-7.2.3/kernel/trace/rv/rv_reactors.c

@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * Runtime reactor interface.
+ *
+ * A runtime monitor can cause a reaction to the detection of an
+ * exception on the model's execution. By default, the monitors have
+ * tracing reactions, printing the monitor output via tracepoints.
+ * But other reactions can be added (on-demand) via this interface.
+ *
+ * == Registering reactors ==
+ *
+ * The struct rv_reactor defines a callback function to be executed
+ * in case of a model exception happens. The callback function
+ * receives a message to be (optionally) printed before executing
+ * the reaction.
+ *
+ * A RV reactor is registered via:
+ *   int rv_register_reactor(struct rv_reactor *reactor)
+ * And unregistered via:
+ *   int rv_unregister_reactor(struct rv_reactor *reactor)
+ *
+ * These functions are exported to modules, enabling reactors to be
+ * dynamically loaded.
+ *
+ * == User interface ==
+ *
+ * The user interface resembles the kernel tracing interface and
+ * presents these files:
+ *
+ *  "available_reactors"
+ *    - List the available reactors, one per line.
+ *
+ *    For example:
+ *      # cat available_reactors
+ *      nop
+ *      panic
+ *      printk
+ *
+ *  "reacting_on"
+ *    - It is an on/off general switch for reactors, disabling
+ *    all reactions.
+ *
+ *  "monitors/MONITOR/reactors"
+ *    - List available reactors, with the select reaction for the given
+ *    MONITOR inside []. The default one is the nop (no operation)
+ *    reactor.
+ *    - Writing the name of an reactor enables it to the given
+ *    MONITOR.
+ *
+ *    For example:
+ *      # cat monitors/wip/reactors
+ *      [nop]
+ *      panic
+ *      printk
+ *      # echo panic > monitors/wip/reactors
+ *      # cat monitors/wip/reactors
+ *      nop
+ *      [panic]
+ *      printk
+ */
+
+#include <linux/lockdep.h>
+#include <linux/slab.h>
+
+#include "rv.h"
+
+/*
+ * Interface for the reactor register.
+ */
+static LIST_HEAD(rv_reactors_list);
+
+static struct rv_reactor *get_reactor_rdef_by_name(char *name)
+{
+	struct rv_reactor *r;
+
+	list_for_each_entry(r, &rv_reactors_list, list) {
+		if (strcmp(name, r->name) == 0)
+			return r;
+	}
+	return NULL;
+}
+
+/*
+ * Available reactors seq functions.
+ */
+static int reactors_show(struct seq_file *m, void *p)
+{
+	struct rv_reactor *reactor = container_of(p, struct rv_reactor, list);
+
+	seq_printf(m, "%s\n", reactor->name);
+	return 0;
+}
+
+static void reactors_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&rv_interface_lock);
+}
+
+static void *reactors_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&rv_interface_lock);
+	return seq_list_start(&rv_reactors_list, *pos);
+}
+
+static void *reactors_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &rv_reactors_list, pos);
+}
+
+/*
+ * available_reactors seq definition.
+ */
+static const struct seq_operations available_reactors_seq_ops = {
+	.start	= reactors_start,
+	.next	= reactors_next,
+	.stop	= reactors_stop,
+	.show	= reactors_show
+};
+
+/*
+ * available_reactors interface.
+ */
+static int available_reactors_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &available_reactors_seq_ops);
+};
+
+static const struct file_operations available_reactors_ops = {
+	.open    = available_reactors_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+/*
+ * Monitor's reactor file.
+ */
+static int monitor_reactor_show(struct seq_file *m, void *p)
+{
+	struct rv_monitor *mon = m->private;
+	struct rv_reactor *reactor = container_of(p, struct rv_reactor, list);
+
+	if (mon->reactor == reactor)
+		seq_printf(m, "[%s]\n", reactor->name);
+	else
+		seq_printf(m, "%s\n", reactor->name);
+	return 0;
+}
+
+/*
+ * available_reactors seq definition.
+ */
+static const struct seq_operations monitor_reactors_seq_ops = {
+	.start	= reactors_start,
+	.next	= reactors_next,
+	.stop	= reactors_stop,
+	.show	= monitor_reactor_show
+};
+
+static void monitor_swap_reactors_single(struct rv_monitor *mon,
+					 struct rv_reactor *reactor,
+					 bool nested)
+{
+	bool monitor_enabled;
+
+	/* nothing to do */
+	if (mon->reactor == reactor)
+		return;
+
+	monitor_enabled = mon->enabled;
+	if (monitor_enabled)
+		rv_disable_monitor(mon);
+
+	mon->reactor = reactor;
+	mon->react = reactor->react;
+
+	/* enable only once if iterating through a container */
+	if (monitor_enabled && !nested)
+		rv_enable_monitor(mon);
+}
+
+static void monitor_swap_reactors(struct rv_monitor *mon, struct rv_reactor *reactor)
+{
+	struct rv_monitor *p = mon;
+
+	if (rv_is_container_monitor(mon))
+		list_for_each_entry_continue(p, &rv_monitors_list, list) {
+			if (p->parent != mon)
+				break;
+			monitor_swap_reactors_single(p, reactor, true);
+		}
+	/*
+	 * This call enables and disables the monitor if they were active.
+	 * In case of a container, we already disabled all and will enable all.
+	 * All nested monitors are enabled also if they were off, we may refine
+	 * this logic in the future.
+	 */
+	monitor_swap_reactors_single(mon, reactor, false);
+}
+
+static ssize_t
+monitor_reactors_write(struct file *file, const char __user *user_buf,
+		      size_t count, loff_t *ppos)
+{
+	char buff[MAX_RV_REACTOR_NAME_SIZE + 2];
+	struct rv_monitor *mon;
+	struct rv_reactor *reactor;
+	struct seq_file *seq_f;
+	int retval = -EINVAL;
+	char *ptr;
+	int len;
+
+	if (count < 1 || count > MAX_RV_REACTOR_NAME_SIZE + 1)
+		return -EINVAL;
+
+	memset(buff, 0, sizeof(buff));
+
+	retval = simple_write_to_buffer(buff, sizeof(buff) - 1, ppos, user_buf, count);
+	if (retval < 0)
+		return -EFAULT;
+
+	ptr = strim(buff);
+
+	len = strlen(ptr);
+	if (!len)
+		return count;
+
+	/*
+	 * See monitor_reactors_open()
+	 */
+	seq_f = file->private_data;
+	mon = seq_f->private;
+
+	guard(mutex)(&rv_interface_lock);
+
+	list_for_each_entry(reactor, &rv_reactors_list, list) {
+		if (strcmp(ptr, reactor->name) != 0)
+			continue;
+
+		monitor_swap_reactors(mon, reactor);
+
+		return count;
+	}
+
+	return -EINVAL;
+}
+
+/*
+ * available_reactors interface.
+ */
+static int monitor_reactors_open(struct inode *inode, struct file *file)
+{
+	struct rv_monitor *mon = inode->i_private;
+	struct seq_file *seq_f;
+	int ret;
+
+	ret = seq_open(file, &monitor_reactors_seq_ops);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * seq_open stores the seq_file on the file->private data.
+	 */
+	seq_f = file->private_data;
+
+	/*
+	 * Copy the create file "private" data to the seq_file private data.
+	 */
+	seq_f->private = mon;
+
+	return 0;
+};
+
+static const struct file_operations monitor_reactors_ops = {
+	.open    = monitor_reactors_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+	.write = monitor_reactors_write
+};
+
+static int __rv_register_reactor(struct rv_reactor *reactor)
+{
+	struct rv_reactor *r;
+
+	list_for_each_entry(r, &rv_reactors_list, list) {
+		if (strcmp(reactor->name, r->name) == 0) {
+			pr_info("Reactor %s is already registered\n", reactor->name);
+			return -EINVAL;
+		}
+	}
+
+	list_add_tail(&reactor->list, &rv_reactors_list);
+
+	return 0;
+}
+
+/**
+ * rv_register_reactor - register a rv reactor.
+ * @reactor:	The rv_reactor to be registered.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_register_reactor(struct rv_reactor *reactor)
+{
+	if (strlen(reactor->name) >= MAX_RV_REACTOR_NAME_SIZE) {
+		pr_info("Reactor %s has a name longer than %d\n",
+			reactor->name, MAX_RV_MONITOR_NAME_SIZE);
+		return -EINVAL;
+	}
+
+	guard(mutex)(&rv_interface_lock);
+	return __rv_register_reactor(reactor);
+}
+
+/**
+ * rv_unregister_reactor - unregister a rv reactor.
+ * @reactor:	The rv_reactor to be unregistered.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_unregister_reactor(struct rv_reactor *reactor)
+{
+	guard(mutex)(&rv_interface_lock);
+	list_del(&reactor->list);
+	return 0;
+}
+
+/*
+ * reacting_on interface.
+ */
+static bool __read_mostly reacting_on;
+
+/**
+ * rv_reacting_on - checks if reacting is on
+ *
+ * Returns 1 if on, 0 otherwise.
+ */
+static bool rv_reacting_on(void)
+{
+	/* Ensures that concurrent monitors read consistent reacting_on */
+	smp_rmb();
+	return READ_ONCE(reacting_on);
+}
+
+static ssize_t reacting_on_read_data(struct file *filp,
+				     char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	char *buff;
+
+	buff = rv_reacting_on() ? "1\n" : "0\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff)+1);
+}
+
+static void turn_reacting_off(void)
+{
+	WRITE_ONCE(reacting_on, false);
+	/* Ensures that concurrent monitors read consistent reacting_on */
+	smp_wmb();
+}
+
+static void turn_reacting_on(void)
+{
+	WRITE_ONCE(reacting_on, true);
+	/* Ensures that concurrent monitors read consistent reacting_on */
+	smp_wmb();
+}
+
+static ssize_t reacting_on_write_data(struct file *filp, const char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	int retval;
+	bool val;
+
+	retval = kstrtobool_from_user(user_buf, count, &val);
+	if (retval)
+		return retval;
+
+	guard(mutex)(&rv_interface_lock);
+
+	if (val)
+		turn_reacting_on();
+	else
+		turn_reacting_off();
+
+	/*
+	 * Wait for the execution of all events to finish
+	 * before returning to user-space.
+	 */
+	tracepoint_synchronize_unregister();
+
+	return count;
+}
+
+static const struct file_operations reacting_on_fops = {
+	.open   = simple_open,
+	.write  = reacting_on_write_data,
+	.read   = reacting_on_read_data,
+};
+
+/**
+ * reactor_populate_monitor - creates per monitor reactors file
+ * @mon:	The monitor.
+ * @root:	The directory of the monitor.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int reactor_populate_monitor(struct rv_monitor *mon, struct dentry *root)
+{
+	struct dentry *tmp;
+
+	tmp = rv_create_file("reactors", RV_MODE_WRITE, root, mon, &monitor_reactors_ops);
+	if (!tmp)
+		return -ENOMEM;
+
+	/*
+	 * Configure as the rv_nop reactor.
+	 */
+	mon->reactor = get_reactor_rdef_by_name("nop");
+
+	return 0;
+}
+
+/*
+ * Nop reactor register
+ */
+__printf(1, 0) static void rv_nop_reaction(const char *msg, va_list args)
+{
+}
+
+static struct rv_reactor rv_nop = {
+	.name = "nop",
+	.description = "no-operation reactor: do nothing.",
+	.react = rv_nop_reaction
+};
+
+int init_rv_reactors(struct dentry *root_dir)
+{
+	int retval;
+
+	struct dentry *available __free(rv_remove) =
+		rv_create_file("available_reactors", RV_MODE_READ, root_dir,
+				NULL, &available_reactors_ops);
+
+	struct dentry *reacting __free(rv_remove) =
+		rv_create_file("reacting_on", RV_MODE_WRITE, root_dir, NULL, &reacting_on_fops);
+
+	if (!reacting || !available)
+		return -ENOMEM;
+
+	retval = __rv_register_reactor(&rv_nop);
+	if (retval)
+		return retval;
+
+	turn_reacting_on();
+
+	retain_and_null_ptr(available);
+	retain_and_null_ptr(reacting);
+	return 0;
+}
+
+void rv_react(struct rv_monitor *monitor, const char *msg, ...)
+{
+	static DEFINE_WAIT_OVERRIDE_MAP(rv_react_map, LD_WAIT_FREE);
+	va_list args;
+
+	if (!rv_reacting_on() || !monitor->react)
+		return;
+
+	va_start(args, msg);
+
+	lock_map_acquire_try(&rv_react_map);
+	monitor->react(msg, args);
+	lock_map_release(&rv_react_map);
+
+	va_end(args);
+}

linux-7.2.3/kernel/trace/rv/rv_trace.h

@@ -0,0 +1,277 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rv
+
+#if !defined(_TRACE_RV_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RV_H
+
+#include <linux/rv.h>
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_DA_MON_EVENTS_IMPLICIT
+DECLARE_EVENT_CLASS(event_da_monitor,
+
+	TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+
+	TP_ARGS(state, event, next_state, final_state),
+
+	TP_STRUCT__entry(
+		__string(	state,		state		)
+		__string(	event,		event		)
+		__string(	next_state,	next_state	)
+		__field(	bool,		final_state	)
+	),
+
+	TP_fast_assign(
+		__assign_str(state);
+		__assign_str(event);
+		__assign_str(next_state);
+		__entry->final_state = final_state;
+	),
+
+	TP_printk("%s x %s -> %s%s",
+		__get_str(state),
+		__get_str(event),
+		__get_str(next_state),
+		__entry->final_state ? " (final)" : "")
+);
+
+DECLARE_EVENT_CLASS(error_da_monitor,
+
+	TP_PROTO(char *state, char *event),
+
+	TP_ARGS(state, event),
+
+	TP_STRUCT__entry(
+		__string(	state,	state	)
+		__string(	event,	event	)
+	),
+
+	TP_fast_assign(
+		__assign_str(state);
+		__assign_str(event);
+	),
+
+	TP_printk("event %s not expected in the state %s",
+		__get_str(event),
+		__get_str(state))
+);
+
+#include <monitors/wip/wip_trace.h>
+#include <monitors/sco/sco_trace.h>
+#include <monitors/scpd/scpd_trace.h>
+#include <monitors/snep/snep_trace.h>
+#include <monitors/sts/sts_trace.h>
+// Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here
+
+#ifdef CONFIG_HA_MON_EVENTS_IMPLICIT
+/* For simplicity this class is marked as DA although relevant only for HA */
+DECLARE_EVENT_CLASS(error_env_da_monitor,
+
+	TP_PROTO(char *state, char *event, char *env),
+
+	TP_ARGS(state, event, env),
+
+	TP_STRUCT__entry(
+		__string(	state,	state	)
+		__string(	event,	event	)
+		__string(	env,	env	)
+	),
+
+	TP_fast_assign(
+		__assign_str(state);
+		__assign_str(event);
+		__assign_str(env);
+	),
+
+	TP_printk("event %s not expected in the state %s with env %s",
+		__get_str(event),
+		__get_str(state),
+		__get_str(env))
+);
+
+#include <monitors/opid/opid_trace.h>
+// Add new monitors based on CONFIG_HA_MON_EVENTS_IMPLICIT here
+
+#endif
+
+#endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */
+
+#ifdef CONFIG_DA_MON_EVENTS_ID
+DECLARE_EVENT_CLASS(event_da_monitor_id,
+
+	TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+
+	TP_ARGS(id, state, event, next_state, final_state),
+
+	TP_STRUCT__entry(
+		__field(	int,		id		)
+		__string(	state,		state		)
+		__string(	event,		event		)
+		__string(	next_state,	next_state	)
+		__field(	bool,		final_state	)
+	),
+
+	TP_fast_assign(
+		__assign_str(state);
+		__assign_str(event);
+		__assign_str(next_state);
+		__entry->id		= id;
+		__entry->final_state	= final_state;
+	),
+
+	TP_printk("%d: %s x %s -> %s%s",
+		__entry->id,
+		__get_str(state),
+		__get_str(event),
+		__get_str(next_state),
+		__entry->final_state ? " (final)" : "")
+);
+
+DECLARE_EVENT_CLASS(error_da_monitor_id,
+
+	TP_PROTO(int id, char *state, char *event),
+
+	TP_ARGS(id, state, event),
+
+	TP_STRUCT__entry(
+		__field(	int,	id	)
+		__string(	state,	state	)
+		__string(	event,	event	)
+	),
+
+	TP_fast_assign(
+		__assign_str(state);
+		__assign_str(event);
+		__entry->id	= id;
+	),
+
+	TP_printk("%d: event %s not expected in the state %s",
+		__entry->id,
+		__get_str(event),
+		__get_str(state))
+);
+
+#include <monitors/wwnr/wwnr_trace.h>
+#include <monitors/snroc/snroc_trace.h>
+#include <monitors/nrp/nrp_trace.h>
+#include <monitors/sssw/sssw_trace.h>
+// Add new monitors based on CONFIG_DA_MON_EVENTS_ID here
+
+#ifdef CONFIG_HA_MON_EVENTS_ID
+/* For simplicity this class is marked as DA although relevant only for HA */
+DECLARE_EVENT_CLASS(error_env_da_monitor_id,
+
+	TP_PROTO(int id, char *state, char *event, char *env),
+
+	TP_ARGS(id, state, event, env),
+
+	TP_STRUCT__entry(
+		__field(	int,	id	)
+		__string(	state,	state	)
+		__string(	event,	event	)
+		__string(	env,	env	)
+	),
+
+	TP_fast_assign(
+		__assign_str(state);
+		__assign_str(event);
+		__assign_str(env);
+		__entry->id	= id;
+	),
+
+	TP_printk("%d: event %s not expected in the state %s with env %s",
+		__entry->id,
+		__get_str(event),
+		__get_str(state),
+		__get_str(env))
+);
+
+#include <monitors/stall/stall_trace.h>
+#include <monitors/nomiss/nomiss_trace.h>
+// Add new monitors based on CONFIG_HA_MON_EVENTS_ID here
+
+#endif
+
+#endif /* CONFIG_DA_MON_EVENTS_ID */
+#ifdef CONFIG_LTL_MON_EVENTS_ID
+DECLARE_EVENT_CLASS(event_ltl_monitor_id,
+
+	TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next),
+
+	TP_ARGS(task, states, atoms, next),
+
+	TP_STRUCT__entry(
+		__string(comm, task->comm)
+		__field(pid_t, pid)
+		__string(states, states)
+		__string(atoms, atoms)
+		__string(next, next)
+	),
+
+	TP_fast_assign(
+		__assign_str(comm);
+		__entry->pid = task->pid;
+		__assign_str(states);
+		__assign_str(atoms);
+		__assign_str(next);
+	),
+
+	TP_printk("%s[%d]: (%s) x (%s) -> (%s)", __get_str(comm), __entry->pid,
+		  __get_str(states), __get_str(atoms), __get_str(next))
+);
+
+DECLARE_EVENT_CLASS(error_ltl_monitor_id,
+
+	TP_PROTO(struct task_struct *task),
+
+	TP_ARGS(task),
+
+	TP_STRUCT__entry(
+		__string(comm, task->comm)
+		__field(pid_t, pid)
+	),
+
+	TP_fast_assign(
+		__assign_str(comm);
+		__entry->pid = task->pid;
+	),
+
+	TP_printk("%s[%d]: violation detected", __get_str(comm), __entry->pid)
+);
+#include <monitors/pagefault/pagefault_trace.h>
+#include <monitors/sleep/sleep_trace.h>
+// Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here
+#endif /* CONFIG_LTL_MON_EVENTS_ID */
+
+#ifdef CONFIG_RV_MON_MAINTENANCE_EVENTS
+/* Tracepoint useful for monitors development, currenly only used in DA */
+TRACE_EVENT(rv_retries_error,
+
+	TP_PROTO(char *name, char *event),
+
+	TP_ARGS(name, event),
+
+	TP_STRUCT__entry(
+		__string(	name,	name	)
+		__string(	event,	event	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__assign_str(event);
+	),
+
+	TP_printk(__stringify(MAX_DA_RETRY_RACING_EVENTS)
+		" retries reached for event %s, resetting monitor %s",
+		__get_str(event), __get_str(name))
+);
+#endif /* CONFIG_RV_MON_MAINTENANCE_EVENTS */
+#endif /* _TRACE_RV_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE rv_trace
+#include <trace/define_trace.h>

linux-7.2.3/kernel/trace/simple_ring_buffer.c

@@ -0,0 +1,517 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 - Google LLC
+ * Author: Vincent Donnefort <vdonnefort@google.com>
+ */
+
+#include <linux/atomic.h>
+#include <linux/simple_ring_buffer.h>
+
+#include <asm/barrier.h>
+#include <asm/local.h>
+
+enum simple_rb_link_type {
+	SIMPLE_RB_LINK_NORMAL		= 0,
+	SIMPLE_RB_LINK_HEAD		= 1,
+	SIMPLE_RB_LINK_HEAD_MOVING
+};
+
+#define SIMPLE_RB_LINK_MASK ~(SIMPLE_RB_LINK_HEAD | SIMPLE_RB_LINK_HEAD_MOVING)
+
+static void simple_bpage_set_head_link(struct simple_buffer_page *bpage)
+{
+	unsigned long link = (unsigned long)bpage->link.next;
+
+	link &= SIMPLE_RB_LINK_MASK;
+	link |= SIMPLE_RB_LINK_HEAD;
+
+	/*
+	 * Paired with simple_rb_find_head() to order access between the head
+	 * link and overrun. It ensures we always report an up-to-date value
+	 * after swapping the reader page.
+	 */
+	smp_store_release(&bpage->link.next, (struct list_head *)link);
+}
+
+static bool simple_bpage_unset_head_link(struct simple_buffer_page *bpage,
+					 struct simple_buffer_page *dst,
+					 enum simple_rb_link_type new_type)
+{
+	unsigned long *link = (unsigned long *)(&bpage->link.next);
+	unsigned long old = (*link & SIMPLE_RB_LINK_MASK) | SIMPLE_RB_LINK_HEAD;
+	unsigned long new = (unsigned long)(&dst->link) | new_type;
+
+	return try_cmpxchg(link, &old, new);
+}
+
+static void simple_bpage_set_normal_link(struct simple_buffer_page *bpage)
+{
+	unsigned long link = (unsigned long)bpage->link.next;
+
+	WRITE_ONCE(bpage->link.next, (struct list_head *)(link & SIMPLE_RB_LINK_MASK));
+}
+
+static struct simple_buffer_page *simple_bpage_from_link(struct list_head *link)
+{
+	unsigned long ptr = (unsigned long)link & SIMPLE_RB_LINK_MASK;
+
+	return container_of((struct list_head *)ptr, struct simple_buffer_page, link);
+}
+
+static struct simple_buffer_page *simple_bpage_next_page(struct simple_buffer_page *bpage)
+{
+	return simple_bpage_from_link(bpage->link.next);
+}
+
+static void simple_bpage_reset(struct simple_buffer_page *bpage)
+{
+	bpage->write = 0;
+	bpage->entries = 0;
+
+	local_set(&bpage->page->commit, 0);
+}
+
+static void simple_bpage_init(struct simple_buffer_page *bpage, void *page)
+{
+	INIT_LIST_HEAD(&bpage->link);
+	bpage->page = (struct buffer_data_page *)page;
+
+	simple_bpage_reset(bpage);
+}
+
+#define simple_rb_meta_inc(__meta, __inc)		\
+	WRITE_ONCE((__meta), (__meta + __inc))
+
+static bool simple_rb_loaded(struct simple_rb_per_cpu *cpu_buffer)
+{
+	return !!cpu_buffer->bpages;
+}
+
+static int simple_rb_find_head(struct simple_rb_per_cpu *cpu_buffer)
+{
+	int retry = cpu_buffer->nr_pages * 2;
+	struct simple_buffer_page *head;
+
+	head = cpu_buffer->head_page;
+
+	while (retry--) {
+		unsigned long link;
+
+spin:
+		/* See smp_store_release in simple_bpage_set_head_link() */
+		link = (unsigned long)smp_load_acquire(&head->link.prev->next);
+
+		switch (link & ~SIMPLE_RB_LINK_MASK) {
+		/* Found the head */
+		case SIMPLE_RB_LINK_HEAD:
+			cpu_buffer->head_page = head;
+			return 0;
+		/* The writer caught the head, we can spin, that won't be long */
+		case SIMPLE_RB_LINK_HEAD_MOVING:
+			goto spin;
+		}
+
+		head = simple_bpage_next_page(head);
+	}
+
+	return -EBUSY;
+}
+
+/**
+ * simple_ring_buffer_swap_reader_page - Swap ring-buffer head with the reader
+ * @cpu_buffer: A simple_rb_per_cpu
+ *
+ * This function enables consuming reading. It ensures the current head page will not be overwritten
+ * and can be safely read.
+ *
+ * Returns 0 on success, -ENODEV if @cpu_buffer was unloaded or -EBUSY if we failed to catch the
+ * head page.
+ */
+int simple_ring_buffer_swap_reader_page(struct simple_rb_per_cpu *cpu_buffer)
+{
+	struct simple_buffer_page *last, *head, *reader;
+	unsigned long overrun;
+	int retry = 8;
+	int ret;
+
+	if (!simple_rb_loaded(cpu_buffer))
+		return -ENODEV;
+
+	reader = cpu_buffer->reader_page;
+
+	do {
+		/* Run after the writer to find the head */
+		ret = simple_rb_find_head(cpu_buffer);
+		if (ret)
+			return ret;
+
+		head = cpu_buffer->head_page;
+
+		/* Connect the reader page around the header page */
+		reader->link.next = head->link.next;
+		reader->link.prev = head->link.prev;
+
+		/* The last page before the head */
+		last = simple_bpage_from_link(head->link.prev);
+
+		/* The reader page points to the new header page */
+		simple_bpage_set_head_link(reader);
+
+		overrun = cpu_buffer->meta->overrun;
+	} while (!simple_bpage_unset_head_link(last, reader, SIMPLE_RB_LINK_NORMAL) && retry--);
+
+	if (!retry)
+		return -EINVAL;
+
+	cpu_buffer->head_page = simple_bpage_from_link(reader->link.next);
+	cpu_buffer->head_page->link.prev = &reader->link;
+	cpu_buffer->reader_page = head;
+	cpu_buffer->meta->reader.lost_events = overrun - cpu_buffer->last_overrun;
+	cpu_buffer->meta->reader.id = cpu_buffer->reader_page->id;
+	cpu_buffer->last_overrun = overrun;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(simple_ring_buffer_swap_reader_page);
+
+static struct simple_buffer_page *simple_rb_move_tail(struct simple_rb_per_cpu *cpu_buffer)
+{
+	struct simple_buffer_page *tail, *new_tail;
+
+	tail = cpu_buffer->tail_page;
+	new_tail = simple_bpage_next_page(tail);
+
+	if (simple_bpage_unset_head_link(tail, new_tail, SIMPLE_RB_LINK_HEAD_MOVING)) {
+		/*
+		 * Oh no! we've caught the head. There is none anymore and
+		 * swap_reader will spin until we set the new one. Overrun must
+		 * be written first, to make sure we report the correct number
+		 * of lost events.
+		 */
+		simple_rb_meta_inc(cpu_buffer->meta->overrun, new_tail->entries);
+		simple_rb_meta_inc(cpu_buffer->meta->pages_lost, 1);
+
+		simple_bpage_set_head_link(new_tail);
+		simple_bpage_set_normal_link(tail);
+	}
+
+	simple_bpage_reset(new_tail);
+	cpu_buffer->tail_page = new_tail;
+
+	simple_rb_meta_inc(cpu_buffer->meta->pages_touched, 1);
+
+	return new_tail;
+}
+
+static unsigned long rb_event_size(unsigned long length)
+{
+	struct ring_buffer_event *event;
+
+	return length + RB_EVNT_HDR_SIZE + sizeof(event->array[0]);
+}
+
+static struct ring_buffer_event *
+rb_event_add_ts_extend(struct ring_buffer_event *event, u64 delta)
+{
+	event->type_len = RINGBUF_TYPE_TIME_EXTEND;
+	event->time_delta = delta & TS_MASK;
+	event->array[0] = delta >> TS_SHIFT;
+
+	return (struct ring_buffer_event *)((unsigned long)event + 8);
+}
+
+static struct ring_buffer_event *
+simple_rb_reserve_next(struct simple_rb_per_cpu *cpu_buffer, unsigned long length, u64 timestamp)
+{
+	unsigned long ts_ext_size = 0, event_size = rb_event_size(length);
+	struct simple_buffer_page *tail = cpu_buffer->tail_page;
+	struct ring_buffer_event *event;
+	u32 write, prev_write;
+	u64 time_delta;
+
+	time_delta = timestamp - cpu_buffer->write_stamp;
+
+	if (test_time_stamp(time_delta))
+		ts_ext_size = 8;
+
+	prev_write = tail->write;
+	write = prev_write + event_size + ts_ext_size;
+
+	if (unlikely(write > (PAGE_SIZE - BUF_PAGE_HDR_SIZE)))
+		tail = simple_rb_move_tail(cpu_buffer);
+
+	if (!tail->entries) {
+		tail->page->time_stamp = timestamp;
+		time_delta = 0;
+		ts_ext_size = 0;
+		write = event_size;
+		prev_write = 0;
+	}
+
+	tail->write = write;
+	tail->entries++;
+
+	cpu_buffer->write_stamp = timestamp;
+
+	event = (struct ring_buffer_event *)(tail->page->data + prev_write);
+	if (ts_ext_size) {
+		event = rb_event_add_ts_extend(event, time_delta);
+		time_delta = 0;
+	}
+
+	event->type_len = 0;
+	event->time_delta = time_delta;
+	event->array[0] = event_size - RB_EVNT_HDR_SIZE;
+
+	return event;
+}
+
+/**
+ * simple_ring_buffer_reserve - Reserve an entry in @cpu_buffer
+ * @cpu_buffer:	A simple_rb_per_cpu
+ * @length:	Size of the entry in bytes
+ * @timestamp:	Timestamp of the entry
+ *
+ * Returns the address of the entry where to write data or NULL
+ */
+void *simple_ring_buffer_reserve(struct simple_rb_per_cpu *cpu_buffer, unsigned long length,
+				 u64 timestamp)
+{
+	struct ring_buffer_event *rb_event;
+
+	if (cmpxchg(&cpu_buffer->status, SIMPLE_RB_READY, SIMPLE_RB_WRITING) != SIMPLE_RB_READY)
+		return NULL;
+
+	rb_event = simple_rb_reserve_next(cpu_buffer, length, timestamp);
+
+	return &rb_event->array[1];
+}
+EXPORT_SYMBOL_GPL(simple_ring_buffer_reserve);
+
+/**
+ * simple_ring_buffer_commit - Commit the entry reserved with simple_ring_buffer_reserve()
+ * @cpu_buffer:	The simple_rb_per_cpu where the entry has been reserved
+ */
+void simple_ring_buffer_commit(struct simple_rb_per_cpu *cpu_buffer)
+{
+	local_set(&cpu_buffer->tail_page->page->commit,
+		  cpu_buffer->tail_page->write);
+	simple_rb_meta_inc(cpu_buffer->meta->entries, 1);
+
+	/*
+	 * Paired with simple_rb_enable_tracing() to ensure data is
+	 * written to the ring-buffer before teardown.
+	 */
+	smp_store_release(&cpu_buffer->status, SIMPLE_RB_READY);
+}
+EXPORT_SYMBOL_GPL(simple_ring_buffer_commit);
+
+static u32 simple_rb_enable_tracing(struct simple_rb_per_cpu *cpu_buffer, bool enable)
+{
+	u32 prev_status;
+
+	if (enable)
+		return cmpxchg(&cpu_buffer->status, SIMPLE_RB_UNAVAILABLE, SIMPLE_RB_READY);
+
+	/* Wait for the buffer to be released */
+	do {
+		prev_status = cmpxchg_acquire(&cpu_buffer->status,
+					      SIMPLE_RB_READY,
+					      SIMPLE_RB_UNAVAILABLE);
+	} while (prev_status == SIMPLE_RB_WRITING);
+
+	return prev_status;
+}
+
+/**
+ * simple_ring_buffer_reset - Reset @cpu_buffer
+ * @cpu_buffer: A simple_rb_per_cpu
+ *
+ * This will not clear the content of the data, only reset counters and pointers
+ *
+ * Returns 0 on success or -ENODEV if @cpu_buffer was unloaded.
+ */
+int simple_ring_buffer_reset(struct simple_rb_per_cpu *cpu_buffer)
+{
+	struct simple_buffer_page *bpage;
+	u32 prev_status;
+	int ret;
+
+	if (!simple_rb_loaded(cpu_buffer))
+		return -ENODEV;
+
+	prev_status = simple_rb_enable_tracing(cpu_buffer, false);
+
+	ret = simple_rb_find_head(cpu_buffer);
+	if (ret)
+		return ret;
+
+	bpage = cpu_buffer->tail_page = cpu_buffer->head_page;
+	do {
+		simple_bpage_reset(bpage);
+		bpage = simple_bpage_next_page(bpage);
+	} while (bpage != cpu_buffer->head_page);
+
+	simple_bpage_reset(cpu_buffer->reader_page);
+
+	cpu_buffer->last_overrun = 0;
+	cpu_buffer->write_stamp = 0;
+
+	cpu_buffer->meta->reader.read = 0;
+	cpu_buffer->meta->reader.lost_events = 0;
+	cpu_buffer->meta->entries = 0;
+	cpu_buffer->meta->overrun = 0;
+	cpu_buffer->meta->read = 0;
+	cpu_buffer->meta->pages_lost = 0;
+	cpu_buffer->meta->pages_touched = 0;
+
+	if (prev_status == SIMPLE_RB_READY)
+		simple_rb_enable_tracing(cpu_buffer, true);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(simple_ring_buffer_reset);
+
+int simple_ring_buffer_init_mm(struct simple_rb_per_cpu *cpu_buffer,
+			       struct simple_buffer_page *bpages,
+			       const struct ring_buffer_desc *desc,
+			       void *(*load_page)(unsigned long va),
+			       void (*unload_page)(void *va))
+{
+	struct simple_buffer_page *bpage = bpages;
+	int ret = 0;
+	void *page;
+	int i;
+
+	/* At least 1 reader page and two pages in the ring-buffer */
+	if (desc->nr_page_va < 3)
+		return -EINVAL;
+
+	memset(cpu_buffer, 0, sizeof(*cpu_buffer));
+
+	cpu_buffer->meta = load_page(desc->meta_va);
+	if (!cpu_buffer->meta)
+		return -EINVAL;
+
+	memset(cpu_buffer->meta, 0, sizeof(*cpu_buffer->meta));
+	cpu_buffer->meta->meta_page_size = PAGE_SIZE;
+
+	/* The reader page is not part of the ring initially */
+	page = load_page(desc->page_va[0]);
+	if (!page) {
+		unload_page(cpu_buffer->meta);
+		return -EINVAL;
+	}
+
+	simple_bpage_init(bpage, page);
+	bpage->id = 0;
+
+	cpu_buffer->nr_pages = 1;
+
+	cpu_buffer->reader_page = bpage;
+	cpu_buffer->tail_page = bpage + 1;
+	cpu_buffer->head_page = bpage + 1;
+
+	for (i = 1; i < desc->nr_page_va; i++) {
+		page = load_page(desc->page_va[i]);
+		if (!page) {
+			ret = -EINVAL;
+			break;
+		}
+
+		simple_bpage_init(++bpage, page);
+
+		bpage->link.next = &(bpage + 1)->link;
+		bpage->link.prev = &(bpage - 1)->link;
+		bpage->id = i;
+
+		cpu_buffer->nr_pages = i + 1;
+	}
+
+	if (ret) {
+		for (i--; i >= 0; i--)
+			unload_page(bpages[i].page);
+		unload_page(cpu_buffer->meta);
+
+		return ret;
+	}
+
+	cpu_buffer->meta->nr_subbufs = cpu_buffer->nr_pages;
+	/* Close the ring */
+	bpage->link.next = &cpu_buffer->tail_page->link;
+	cpu_buffer->tail_page->link.prev = &bpage->link;
+
+	/* The last init'ed page points to the head page */
+	simple_bpage_set_head_link(bpage);
+
+	cpu_buffer->bpages = bpages;
+
+	return 0;
+}
+
+static void *__load_page(unsigned long page)
+{
+	return (void *)page;
+}
+
+static void __unload_page(void *page) { }
+
+/**
+ * simple_ring_buffer_init - Init @cpu_buffer based on @desc
+ * @cpu_buffer:	A simple_rb_per_cpu buffer to init, allocated by the caller.
+ * @bpages:	Array of simple_buffer_pages, with as many elements as @desc->nr_page_va
+ * @desc:	A ring_buffer_desc
+ *
+ * Returns 0 on success or -EINVAL if the content of @desc is invalid
+ */
+int simple_ring_buffer_init(struct simple_rb_per_cpu *cpu_buffer, struct simple_buffer_page *bpages,
+			    const struct ring_buffer_desc *desc)
+{
+	return simple_ring_buffer_init_mm(cpu_buffer, bpages, desc, __load_page, __unload_page);
+}
+EXPORT_SYMBOL_GPL(simple_ring_buffer_init);
+
+void simple_ring_buffer_unload_mm(struct simple_rb_per_cpu *cpu_buffer,
+				  void (*unload_page)(void *))
+{
+	int p;
+
+	if (!simple_rb_loaded(cpu_buffer))
+		return;
+
+	simple_rb_enable_tracing(cpu_buffer, false);
+
+	unload_page(cpu_buffer->meta);
+	for (p = 0; p < cpu_buffer->nr_pages; p++)
+		unload_page(cpu_buffer->bpages[p].page);
+
+	cpu_buffer->bpages = NULL;
+}
+
+/**
+ * simple_ring_buffer_unload - Prepare @cpu_buffer for deletion
+ * @cpu_buffer:	A simple_rb_per_cpu that will be deleted.
+ */
+void simple_ring_buffer_unload(struct simple_rb_per_cpu *cpu_buffer)
+{
+	return simple_ring_buffer_unload_mm(cpu_buffer, __unload_page);
+}
+EXPORT_SYMBOL_GPL(simple_ring_buffer_unload);
+
+/**
+ * simple_ring_buffer_enable_tracing - Enable or disable writing to @cpu_buffer
+ * @cpu_buffer: A simple_rb_per_cpu
+ * @enable:	True to enable tracing, False to disable it
+ *
+ * Returns 0 on success or -ENODEV if @cpu_buffer was unloaded
+ */
+int simple_ring_buffer_enable_tracing(struct simple_rb_per_cpu *cpu_buffer, bool enable)
+{
+	if (!simple_rb_loaded(cpu_buffer))
+		return -ENODEV;
+
+	simple_rb_enable_tracing(cpu_buffer, enable);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(simple_ring_buffer_enable_tracing);

linux-7.2.3/kernel/trace/synth_event_gen_test.c

@@ -0,0 +1,536 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test module for in-kernel synthetic event creation and generation.
+ *
+ * Copyright (C) 2019 Tom Zanussi <zanussi@kernel.org>
+ */
+
+#include <linux/module.h>
+#include <linux/trace_events.h>
+
+/*
+ * This module is a simple test of basic functionality for in-kernel
+ * synthetic event creation and generation, the first and second tests
+ * using synth_event_gen_cmd_start() and synth_event_add_field(), the
+ * third uses synth_event_create() to do it all at once with a static
+ * field array.
+ *
+ * Following that are a few examples using the created events to test
+ * various ways of tracing a synthetic event.
+ *
+ * To test, select CONFIG_SYNTH_EVENT_GEN_TEST and build the module.
+ * Then:
+ *
+ * # insmod kernel/trace/synth_event_gen_test.ko
+ * # cat /sys/kernel/tracing/trace
+ *
+ * You should see several events in the trace buffer -
+ * "create_synth_test", "empty_synth_test", and several instances of
+ * "gen_synth_test".
+ *
+ * To remove the events, remove the module:
+ *
+ * # rmmod synth_event_gen_test
+ *
+ */
+
+static struct trace_event_file *create_synth_test;
+static struct trace_event_file *empty_synth_test;
+static struct trace_event_file *gen_synth_test;
+
+/*
+ * Test to make sure we can create a synthetic event, then add more
+ * fields.
+ */
+static int __init test_gen_synth_cmd(void)
+{
+	struct dynevent_cmd cmd;
+	u64 vals[7];
+	char *buf;
+	int ret;
+
+	/* Create a buffer to hold the generated command */
+	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Before generating the command, initialize the cmd object */
+	synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
+
+	/*
+	 * Create the empty gen_synth_test synthetic event with the
+	 * first 4 fields.
+	 */
+	ret = synth_event_gen_cmd_start(&cmd, "gen_synth_test", THIS_MODULE,
+					"pid_t", "next_pid_field",
+					"char[16]", "next_comm_field",
+					"u64", "ts_ns",
+					"u64", "ts_ms");
+	if (ret)
+		goto free;
+
+	/* Use synth_event_add_field to add the rest of the fields */
+
+	ret = synth_event_add_field(&cmd, "unsigned int", "cpu");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "char[64]", "my_string_field");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "int", "my_int_field");
+	if (ret)
+		goto free;
+
+	ret = synth_event_gen_cmd_end(&cmd);
+	if (ret)
+		goto free;
+
+	/*
+	 * Now get the gen_synth_test event file.  We need to prevent
+	 * the instance and event from disappearing from underneath
+	 * us, which trace_get_event_file() does (though in this case
+	 * we're using the top-level instance which never goes away).
+	 */
+	gen_synth_test = trace_get_event_file(NULL, "synthetic",
+					      "gen_synth_test");
+	if (IS_ERR(gen_synth_test)) {
+		ret = PTR_ERR(gen_synth_test);
+		goto delete;
+	}
+
+	/* Enable the event or you won't see anything */
+	ret = trace_array_set_clr_event(gen_synth_test->tr,
+					"synthetic", "gen_synth_test", true);
+	if (ret) {
+		trace_put_event_file(gen_synth_test);
+		goto delete;
+	}
+
+	/* Create some bogus values just for testing */
+
+	vals[0] = 777;			/* next_pid_field */
+	vals[1] = (u64)(long)"hula hoops";	/* next_comm_field */
+	vals[2] = 1000000;		/* ts_ns */
+	vals[3] = 1000;			/* ts_ms */
+	vals[4] = raw_smp_processor_id(); /* cpu */
+	vals[5] = (u64)(long)"thneed";	/* my_string_field */
+	vals[6] = 598;			/* my_int_field */
+
+	/* Now generate a gen_synth_test event */
+	ret = synth_event_trace_array(gen_synth_test, vals, ARRAY_SIZE(vals));
+ free:
+	kfree(buf);
+	return ret;
+ delete:
+	/* We got an error after creating the event, delete it */
+	synth_event_delete("gen_synth_test");
+	goto free;
+}
+
+/*
+ * Test to make sure we can create an initially empty synthetic event,
+ * then add all the fields.
+ */
+static int __init test_empty_synth_event(void)
+{
+	struct dynevent_cmd cmd;
+	u64 vals[7];
+	char *buf;
+	int ret;
+
+	/* Create a buffer to hold the generated command */
+	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Before generating the command, initialize the cmd object */
+	synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
+
+	/*
+	 * Create the empty_synth_test synthetic event with no fields.
+	 */
+	ret = synth_event_gen_cmd_start(&cmd, "empty_synth_test", THIS_MODULE);
+	if (ret)
+		goto free;
+
+	/* Use synth_event_add_field to add all of the fields */
+
+	ret = synth_event_add_field(&cmd, "pid_t", "next_pid_field");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "char[16]", "next_comm_field");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "u64", "ts_ns");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "u64", "ts_ms");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "unsigned int", "cpu");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "char[64]", "my_string_field");
+	if (ret)
+		goto free;
+
+	ret = synth_event_add_field(&cmd, "int", "my_int_field");
+	if (ret)
+		goto free;
+
+	/* All fields have been added, close and register the synth event */
+
+	ret = synth_event_gen_cmd_end(&cmd);
+	if (ret)
+		goto free;
+
+	/*
+	 * Now get the empty_synth_test event file.  We need to
+	 * prevent the instance and event from disappearing from
+	 * underneath us, which trace_get_event_file() does (though in
+	 * this case we're using the top-level instance which never
+	 * goes away).
+	 */
+	empty_synth_test = trace_get_event_file(NULL, "synthetic",
+						"empty_synth_test");
+	if (IS_ERR(empty_synth_test)) {
+		ret = PTR_ERR(empty_synth_test);
+		goto delete;
+	}
+
+	/* Enable the event or you won't see anything */
+	ret = trace_array_set_clr_event(empty_synth_test->tr,
+					"synthetic", "empty_synth_test", true);
+	if (ret) {
+		trace_put_event_file(empty_synth_test);
+		goto delete;
+	}
+
+	/* Create some bogus values just for testing */
+
+	vals[0] = 777;			/* next_pid_field */
+	vals[1] = (u64)(long)"tiddlywinks";	/* next_comm_field */
+	vals[2] = 1000000;		/* ts_ns */
+	vals[3] = 1000;			/* ts_ms */
+	vals[4] = raw_smp_processor_id(); /* cpu */
+	vals[5] = (u64)(long)"thneed_2.0";	/* my_string_field */
+	vals[6] = 399;			/* my_int_field */
+
+	/* Now trace an empty_synth_test event */
+	ret = synth_event_trace_array(empty_synth_test, vals, ARRAY_SIZE(vals));
+ free:
+	kfree(buf);
+	return ret;
+ delete:
+	/* We got an error after creating the event, delete it */
+	synth_event_delete("empty_synth_test");
+	goto free;
+}
+
+static struct synth_field_desc create_synth_test_fields[] = {
+	{ .type = "pid_t",		.name = "next_pid_field" },
+	{ .type = "char[16]",		.name = "next_comm_field" },
+	{ .type = "u64",		.name = "ts_ns" },
+	{ .type = "char[]",		.name = "dynstring_field_1" },
+	{ .type = "u64",		.name = "ts_ms" },
+	{ .type = "unsigned int",	.name = "cpu" },
+	{ .type = "char[64]",		.name = "my_string_field" },
+	{ .type = "char[]",		.name = "dynstring_field_2" },
+	{ .type = "int",		.name = "my_int_field" },
+};
+
+/*
+ * Test synthetic event creation all at once from array of field
+ * descriptors.
+ */
+static int __init test_create_synth_event(void)
+{
+	u64 vals[9];
+	int ret;
+
+	/* Create the create_synth_test event with the fields above */
+	ret = synth_event_create("create_synth_test",
+				 create_synth_test_fields,
+				 ARRAY_SIZE(create_synth_test_fields),
+				 THIS_MODULE);
+	if (ret)
+		goto out;
+
+	/*
+	 * Now get the create_synth_test event file.  We need to
+	 * prevent the instance and event from disappearing from
+	 * underneath us, which trace_get_event_file() does (though in
+	 * this case we're using the top-level instance which never
+	 * goes away).
+	 */
+	create_synth_test = trace_get_event_file(NULL, "synthetic",
+						 "create_synth_test");
+	if (IS_ERR(create_synth_test)) {
+		ret = PTR_ERR(create_synth_test);
+		goto delete;
+	}
+
+	/* Enable the event or you won't see anything */
+	ret = trace_array_set_clr_event(create_synth_test->tr,
+					"synthetic", "create_synth_test", true);
+	if (ret) {
+		trace_put_event_file(create_synth_test);
+		goto delete;
+	}
+
+	/* Create some bogus values just for testing */
+
+	vals[0] = 777;			/* next_pid_field */
+	vals[1] = (u64)(long)"tiddlywinks";	/* next_comm_field */
+	vals[2] = 1000000;		/* ts_ns */
+	vals[3] = (u64)(long)"xrayspecs";	/* dynstring_field_1 */
+	vals[4] = 1000;			/* ts_ms */
+	vals[5] = raw_smp_processor_id(); /* cpu */
+	vals[6] = (u64)(long)"thneed";	/* my_string_field */
+	vals[7] = (u64)(long)"kerplunk";	/* dynstring_field_2 */
+	vals[8] = 398;			/* my_int_field */
+
+	/* Now generate a create_synth_test event */
+	ret = synth_event_trace_array(create_synth_test, vals, ARRAY_SIZE(vals));
+ out:
+	return ret;
+ delete:
+	/* We got an error after creating the event, delete it */
+	synth_event_delete("create_synth_test");
+
+	goto out;
+}
+
+/*
+ * Test tracing a synthetic event by reserving trace buffer space,
+ * then filling in fields one after another.
+ */
+static int __init test_add_next_synth_val(void)
+{
+	struct synth_event_trace_state trace_state;
+	int ret;
+
+	/* Start by reserving space in the trace buffer */
+	ret = synth_event_trace_start(gen_synth_test, &trace_state);
+	if (ret)
+		return ret;
+
+	/* Write some bogus values into the trace buffer, one after another */
+
+	/* next_pid_field */
+	ret = synth_event_add_next_val(777, &trace_state);
+	if (ret)
+		goto out;
+
+	/* next_comm_field */
+	ret = synth_event_add_next_val((u64)(long)"slinky", &trace_state);
+	if (ret)
+		goto out;
+
+	/* ts_ns */
+	ret = synth_event_add_next_val(1000000, &trace_state);
+	if (ret)
+		goto out;
+
+	/* ts_ms */
+	ret = synth_event_add_next_val(1000, &trace_state);
+	if (ret)
+		goto out;
+
+	/* cpu */
+	ret = synth_event_add_next_val(raw_smp_processor_id(), &trace_state);
+	if (ret)
+		goto out;
+
+	/* my_string_field */
+	ret = synth_event_add_next_val((u64)(long)"thneed_2.01", &trace_state);
+	if (ret)
+		goto out;
+
+	/* my_int_field */
+	ret = synth_event_add_next_val(395, &trace_state);
+ out:
+	/* Finally, commit the event */
+	ret = synth_event_trace_end(&trace_state);
+
+	return ret;
+}
+
+/*
+ * Test tracing a synthetic event by reserving trace buffer space,
+ * then filling in fields using field names, which can be done in any
+ * order.
+ */
+static int __init test_add_synth_val(void)
+{
+	struct synth_event_trace_state trace_state;
+	int ret;
+
+	/* Start by reserving space in the trace buffer */
+	ret = synth_event_trace_start(gen_synth_test, &trace_state);
+	if (ret)
+		return ret;
+
+	/* Write some bogus values into the trace buffer, using field names */
+
+	ret = synth_event_add_val("ts_ns", 1000000, &trace_state);
+	if (ret)
+		goto out;
+
+	ret = synth_event_add_val("ts_ms", 1000, &trace_state);
+	if (ret)
+		goto out;
+
+	ret = synth_event_add_val("cpu", raw_smp_processor_id(), &trace_state);
+	if (ret)
+		goto out;
+
+	ret = synth_event_add_val("next_pid_field", 777, &trace_state);
+	if (ret)
+		goto out;
+
+	ret = synth_event_add_val("next_comm_field", (u64)(long)"silly putty",
+				  &trace_state);
+	if (ret)
+		goto out;
+
+	ret = synth_event_add_val("my_string_field", (u64)(long)"thneed_9",
+				  &trace_state);
+	if (ret)
+		goto out;
+
+	ret = synth_event_add_val("my_int_field", 3999, &trace_state);
+ out:
+	/* Finally, commit the event */
+	ret = synth_event_trace_end(&trace_state);
+
+	return ret;
+}
+
+/*
+ * Test tracing a synthetic event all at once from array of values.
+ */
+static int __init test_trace_synth_event(void)
+{
+	int ret;
+
+	/* Trace some bogus values just for testing */
+	ret = synth_event_trace(create_synth_test, 9,	/* number of values */
+				(u64)444,		/* next_pid_field */
+				(u64)(long)"clackers",	/* next_comm_field */
+				(u64)1000000,		/* ts_ns */
+				(u64)(long)"viewmaster",/* dynstring_field_1 */
+				(u64)1000,		/* ts_ms */
+				(u64)raw_smp_processor_id(), /* cpu */
+				(u64)(long)"Thneed",	/* my_string_field */
+				(u64)(long)"yoyos",	/* dynstring_field_2 */
+				(u64)999);		/* my_int_field */
+	return ret;
+}
+
+static int __init synth_event_gen_test_init(void)
+{
+	int ret;
+
+	ret = test_gen_synth_cmd();
+	if (ret)
+		return ret;
+
+	ret = test_empty_synth_event();
+	if (ret) {
+		WARN_ON(trace_array_set_clr_event(gen_synth_test->tr,
+						  "synthetic",
+						  "gen_synth_test", false));
+		trace_put_event_file(gen_synth_test);
+		WARN_ON(synth_event_delete("gen_synth_test"));
+		goto out;
+	}
+
+	ret = test_create_synth_event();
+	if (ret) {
+		WARN_ON(trace_array_set_clr_event(gen_synth_test->tr,
+						  "synthetic",
+						  "gen_synth_test", false));
+		trace_put_event_file(gen_synth_test);
+		WARN_ON(synth_event_delete("gen_synth_test"));
+
+		WARN_ON(trace_array_set_clr_event(empty_synth_test->tr,
+						  "synthetic",
+						  "empty_synth_test", false));
+		trace_put_event_file(empty_synth_test);
+		WARN_ON(synth_event_delete("empty_synth_test"));
+		goto out;
+	}
+
+	ret = test_add_next_synth_val();
+	WARN_ON(ret);
+
+	ret = test_add_synth_val();
+	WARN_ON(ret);
+
+	ret = test_trace_synth_event();
+	WARN_ON(ret);
+
+	/* Disable when done */
+	trace_array_set_clr_event(gen_synth_test->tr,
+				  "synthetic",
+				  "gen_synth_test", false);
+	trace_array_set_clr_event(empty_synth_test->tr,
+				  "synthetic",
+				  "empty_synth_test", false);
+	trace_array_set_clr_event(create_synth_test->tr,
+				  "synthetic",
+				  "create_synth_test", false);
+ out:
+	return ret;
+}
+
+static void __exit synth_event_gen_test_exit(void)
+{
+	/* Disable the event or you can't remove it */
+	WARN_ON(trace_array_set_clr_event(gen_synth_test->tr,
+					  "synthetic",
+					  "gen_synth_test", false));
+
+	/* Now give the file and instance back */
+	trace_put_event_file(gen_synth_test);
+
+	/* Now unregister and free the synthetic event */
+	WARN_ON(synth_event_delete("gen_synth_test"));
+
+	/* Disable the event or you can't remove it */
+	WARN_ON(trace_array_set_clr_event(empty_synth_test->tr,
+					  "synthetic",
+					  "empty_synth_test", false));
+
+	/* Now give the file and instance back */
+	trace_put_event_file(empty_synth_test);
+
+	/* Now unregister and free the synthetic event */
+	WARN_ON(synth_event_delete("empty_synth_test"));
+
+	/* Disable the event or you can't remove it */
+	WARN_ON(trace_array_set_clr_event(create_synth_test->tr,
+					  "synthetic",
+					  "create_synth_test", false));
+
+	/* Now give the file and instance back */
+	trace_put_event_file(create_synth_test);
+
+	/* Now unregister and free the synthetic event */
+	WARN_ON(synth_event_delete("create_synth_test"));
+}
+
+module_init(synth_event_gen_test_init)
+module_exit(synth_event_gen_test_exit)
+
+MODULE_AUTHOR("Tom Zanussi");
+MODULE_DESCRIPTION("synthetic event generation test");
+MODULE_LICENSE("GPL v2");

linux-7.2.3/kernel/trace/trace_benchmark.c

@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/trace_clock.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace_benchmark.h"
+
+static struct task_struct *bm_event_thread;
+
+static char bm_str[BENCHMARK_EVENT_STRLEN] = "START";
+
+static u64 bm_total;
+static u64 bm_totalsq;
+static u64 bm_last;
+static u64 bm_max;
+static u64 bm_min;
+static u64 bm_first;
+static u64 bm_cnt;
+static u64 bm_stddev;
+static unsigned int bm_avg;
+static unsigned int bm_std;
+
+static bool ok_to_run;
+
+/*
+ * This gets called in a loop recording the time it took to write
+ * the tracepoint. What it writes is the time statistics of the last
+ * tracepoint write. As there is nothing to write the first time
+ * it simply writes "START". As the first write is cold cache and
+ * the rest is hot, we save off that time in bm_first and it is
+ * reported as "first", which is shown in the second write to the
+ * tracepoint. The "first" field is written within the statics from
+ * then on but never changes.
+ */
+static void trace_do_benchmark(void)
+{
+	u64 start;
+	u64 stop;
+	u64 delta;
+	u64 stddev;
+	u64 seed;
+	u64 last_seed;
+	unsigned int avg;
+	unsigned int std = 0;
+
+	/* Only run if the tracepoint is actually active */
+	if (!trace_benchmark_event_enabled() || !tracing_is_on())
+		return;
+
+	local_irq_disable();
+	start = trace_clock_local();
+	trace_benchmark_event(bm_str, bm_last);
+	stop = trace_clock_local();
+	local_irq_enable();
+
+	bm_cnt++;
+
+	delta = stop - start;
+
+	/*
+	 * The first read is cold cached, keep it separate from the
+	 * other calculations.
+	 */
+	if (bm_cnt == 1) {
+		bm_first = delta;
+		scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+			  "first=%llu [COLD CACHED]", bm_first);
+		return;
+	}
+
+	bm_last = delta;
+
+	if (delta > bm_max)
+		bm_max = delta;
+	if (!bm_min || delta < bm_min)
+		bm_min = delta;
+
+	/*
+	 * When bm_cnt is greater than UINT_MAX, it breaks the statistics
+	 * accounting. Freeze the statistics when that happens.
+	 * We should have enough data for the avg and stddev anyway.
+	 */
+	if (bm_cnt > UINT_MAX) {
+		scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+		    "last=%llu first=%llu max=%llu min=%llu ** avg=%u std=%d std^2=%lld",
+			  bm_last, bm_first, bm_max, bm_min, bm_avg, bm_std, bm_stddev);
+		return;
+	}
+
+	bm_total += delta;
+	bm_totalsq += delta * delta;
+
+	if (bm_cnt > 1) {
+		/*
+		 * Apply Welford's method to calculate standard deviation:
+		 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+		 */
+		stddev = (u64)bm_cnt * bm_totalsq - bm_total * bm_total;
+		do_div(stddev, (u32)bm_cnt);
+		do_div(stddev, (u32)bm_cnt - 1);
+	} else
+		stddev = 0;
+
+	delta = bm_total;
+	do_div(delta, (u32)bm_cnt);
+	avg = delta;
+
+	if (stddev > 0) {
+		int i = 0;
+		/*
+		 * stddev is the square of standard deviation but
+		 * we want the actually number. Use the average
+		 * as our seed to find the std.
+		 *
+		 * The next try is:
+		 *  x = (x + N/x) / 2
+		 *
+		 * Where N is the squared number to find the square
+		 * root of.
+		 */
+		seed = avg;
+		do {
+			last_seed = seed;
+			seed = stddev;
+			if (!last_seed)
+				break;
+			seed = div64_u64(seed, last_seed);
+			seed += last_seed;
+			do_div(seed, 2);
+		} while (i++ < 10 && last_seed != seed);
+
+		std = seed;
+	}
+
+	scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+		  "last=%llu first=%llu max=%llu min=%llu avg=%u std=%d std^2=%lld",
+		  bm_last, bm_first, bm_max, bm_min, avg, std, stddev);
+
+	bm_std = std;
+	bm_avg = avg;
+	bm_stddev = stddev;
+}
+
+static int benchmark_event_kthread(void *arg)
+{
+	/* sleep a bit to make sure the tracepoint gets activated */
+	msleep(100);
+
+	while (!kthread_should_stop()) {
+
+		trace_do_benchmark();
+
+		/*
+		 * We don't go to sleep, but let others run as well.
+		 * This is basically a "yield()" to let any task that
+		 * wants to run, schedule in, but if the CPU is idle,
+		 * we'll keep burning cycles.
+		 *
+		 * Note the tasks_rcu_qs() version of cond_resched() will
+		 * notify synchronize_rcu_tasks() that this thread has
+		 * passed a quiescent state for rcu_tasks. Otherwise
+		 * this thread will never voluntarily schedule which would
+		 * block synchronize_rcu_tasks() indefinitely.
+		 */
+		cond_resched_tasks_rcu_qs();
+	}
+
+	return 0;
+}
+
+/*
+ * When the benchmark tracepoint is enabled, it calls this
+ * function and the thread that calls the tracepoint is created.
+ */
+int trace_benchmark_reg(void)
+{
+	if (!ok_to_run) {
+		pr_warn("trace benchmark cannot be started via kernel command line\n");
+		return -EBUSY;
+	}
+
+	bm_event_thread = kthread_run(benchmark_event_kthread,
+				      NULL, "event_benchmark");
+	if (IS_ERR(bm_event_thread)) {
+		pr_warn("trace benchmark failed to create kernel thread\n");
+		return PTR_ERR(bm_event_thread);
+	}
+
+	return 0;
+}
+
+/*
+ * When the benchmark tracepoint is disabled, it calls this
+ * function and the thread that calls the tracepoint is deleted
+ * and all the numbers are reset.
+ */
+void trace_benchmark_unreg(void)
+{
+	if (!bm_event_thread)
+		return;
+
+	kthread_stop(bm_event_thread);
+	bm_event_thread = NULL;
+
+	strcpy(bm_str, "START");
+	bm_total = 0;
+	bm_totalsq = 0;
+	bm_last = 0;
+	bm_max = 0;
+	bm_min = 0;
+	bm_cnt = 0;
+	/* These don't need to be reset but reset them anyway */
+	bm_first = 0;
+	bm_std = 0;
+	bm_avg = 0;
+	bm_stddev = 0;
+}
+
+static __init int ok_to_run_trace_benchmark(void)
+{
+	ok_to_run = true;
+
+	return 0;
+}
+
+early_initcall(ok_to_run_trace_benchmark);

linux-7.2.3/kernel/trace/trace_benchmark.h

@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM benchmark
+
+#if !defined(_TRACE_BENCHMARK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BENCHMARK_H
+
+#include <linux/tracepoint.h>
+
+extern int trace_benchmark_reg(void);
+extern void trace_benchmark_unreg(void);
+
+#define BENCHMARK_EVENT_STRLEN		128
+
+TRACE_EVENT_FN(benchmark_event,
+
+	TP_PROTO(const char *str, u64 delta),
+
+	TP_ARGS(str, delta),
+
+	TP_STRUCT__entry(
+		__array(	char,	str,	BENCHMARK_EVENT_STRLEN	)
+		__field(	u64,	delta)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN);
+		__entry->delta = delta;
+	),
+
+	TP_printk("%s delta=%llu", __entry->str, __entry->delta),
+
+	trace_benchmark_reg, trace_benchmark_unreg
+);
+
+#endif /* _TRACE_BENCHMARK_H */
+
+#undef TRACE_INCLUDE_FILE
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_benchmark
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>