Linux Kernel Markers

The marker activation functions sits in kernel/marker.c.  A hash table is used
to keep track of the registered probes and armed markers, so the markers
within a newly loaded module that should be active can be activated at module
load time.

marker_query has been removed. marker_get_first, marker_get_next and
marker_release should be used as iterators on the markers.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Mike Mason <mmlnx@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/asm-generic/vmlinux.lds.h

@@ -12,7 +12,11 @@
 /* .data section */
 #define DATA_DATA							\
 	*(.data)							\
-	*(.data.init.refok)
+	*(.data.init.refok)						\
+	. = ALIGN(8);							\
+	VMLINUX_SYMBOL(__start___markers) = .;				\
+	*(__markers)							\
+	VMLINUX_SYMBOL(__stop___markers) = .;
 
 #define RO_DATA(align)							\
 	. = ALIGN((align));						\
@@ -20,6 +24,7 @@
 		VMLINUX_SYMBOL(__start_rodata) = .;			\
 		*(.rodata) *(.rodata.*)					\
 		*(__vermagic)		/* Kernel version magic */	\
+		*(__markers_strings)	/* Markers: strings */		\
 	}								\
 									\
 	.rodata1          : AT(ADDR(.rodata1) - LOAD_OFFSET) {		\

include/linux/marker.h

@@ -0,0 +1,130 @@
+#ifndef _LINUX_MARKER_H
+#define _LINUX_MARKER_H
+
+/*
+ * Code markup for dynamic and static tracing.
+ *
+ * See Documentation/marker.txt.
+ *
+ * (C) Copyright 2006 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+
+struct module;
+struct marker;
+
+/**
+ * marker_probe_func - Type of a marker probe function
+ * @mdata: pointer of type struct marker
+ * @private_data: caller site private data
+ * @fmt: format string
+ * @...: variable argument list
+ *
+ * Type of marker probe functions. They receive the mdata and need to parse the
+ * format string to recover the variable argument list.
+ */
+typedef void marker_probe_func(const struct marker *mdata,
+	void *private_data, const char *fmt, ...);
+
+struct marker {
+	const char *name;	/* Marker name */
+	const char *format;	/* Marker format string, describing the
+				 * variable argument list.
+				 */
+	char state;		/* Marker state. */
+	marker_probe_func *call;/* Probe handler function pointer */
+	void *private;		/* Private probe data */
+} __attribute__((aligned(8)));
+
+#ifdef CONFIG_MARKERS
+
+/*
+ * Note : the empty asm volatile with read constraint is used here instead of a
+ * "used" attribute to fix a gcc 4.1.x bug.
+ * Make sure the alignment of the structure in the __markers section will
+ * not add unwanted padding between the beginning of the section and the
+ * structure. Force alignment to the same alignment as the section start.
+ */
+#define __trace_mark(name, call_data, format, args...)			\
+	do {								\
+		static const char __mstrtab_name_##name[]		\
+		__attribute__((section("__markers_strings")))		\
+		= #name;						\
+		static const char __mstrtab_format_##name[]		\
+		__attribute__((section("__markers_strings")))		\
+		= format;						\
+		static struct marker __mark_##name			\
+		__attribute__((section("__markers"), aligned(8))) =	\
+		{ __mstrtab_name_##name, __mstrtab_format_##name,	\
+		0, __mark_empty_function, NULL };			\
+		asm volatile("" : : "i" (&__mark_##name));		\
+		__mark_check_format(format, ## args);			\
+		if (unlikely(__mark_##name.state)) {			\
+			preempt_disable();				\
+			(*__mark_##name.call)				\
+				(&__mark_##name, call_data,		\
+				format, ## args);			\
+			preempt_enable();				\
+		}							\
+	} while (0)
+
+extern void marker_update_probe_range(struct marker *begin,
+	struct marker *end, struct module *probe_module, int *refcount);
+#else /* !CONFIG_MARKERS */
+#define __trace_mark(name, call_data, format, args...) \
+		__mark_check_format(format, ## args)
+static inline void marker_update_probe_range(struct marker *begin,
+	struct marker *end, struct module *probe_module, int *refcount)
+{ }
+#endif /* CONFIG_MARKERS */
+
+/**
+ * trace_mark - Marker
+ * @name: marker name, not quoted.
+ * @format: format string
+ * @args...: variable argument list
+ *
+ * Places a marker.
+ */
+#define trace_mark(name, format, args...) \
+	__trace_mark(name, NULL, format, ## args)
+
+#define MARK_MAX_FORMAT_LEN	1024
+
+/**
+ * MARK_NOARGS - Format string for a marker with no argument.
+ */
+#define MARK_NOARGS " "
+
+/* To be used for string format validity checking with gcc */
+static inline void __printf(1, 2) __mark_check_format(const char *fmt, ...)
+{
+}
+
+extern marker_probe_func __mark_empty_function;
+
+/*
+ * Connect a probe to a marker.
+ * private data pointer must be a valid allocated memory address, or NULL.
+ */
+extern int marker_probe_register(const char *name, const char *format,
+				marker_probe_func *probe, void *private);
+
+/*
+ * Returns the private data given to marker_probe_register.
+ */
+extern void *marker_probe_unregister(const char *name);
+/*
+ * Unregister a marker by providing the registered private data.
+ */
+extern void *marker_probe_unregister_private_data(void *private);
+
+extern int marker_arm(const char *name);
+extern int marker_disarm(const char *name);
+extern void *marker_get_private_data(const char *name);
+
+#endif

include/linux/module.h

@@ -15,6 +15,7 @@
 #include <linux/stringify.h>
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
+#include <linux/marker.h>
 #include <asm/local.h>
 
 #include <asm/module.h>
@@ -354,6 +355,10 @@ struct module
 	/* The command line arguments (may be mangled).  People like
 	   keeping pointers to this stuff */
 	char *args;
+#ifdef CONFIG_MARKERS
+	struct marker *markers;
+	unsigned int num_markers;
+#endif
 };
 #ifndef MODULE_ARCH_INIT
 #define MODULE_ARCH_INIT {}
@@ -457,6 +462,8 @@ int unregister_module_notifier(struct notifier_block * nb);
 
 extern void print_modules(void);
 
+extern void module_update_markers(struct module *probe_module, int *refcount);
+
 #else /* !CONFIG_MODULES... */
 #define EXPORT_SYMBOL(sym)
 #define EXPORT_SYMBOL_GPL(sym)
@@ -556,6 +563,11 @@ static inline void print_modules(void)
 {
 }
 
+static inline void module_update_markers(struct module *probe_module,
+		int *refcount)
+{
+}
+
 #endif /* CONFIG_MODULES */
 
 struct device_driver;

kernel/Kconfig.instrumentation

@@ -40,4 +40,10 @@ config KPROBES
 	  for kernel debugging, non-intrusive instrumentation and testing.
 	  If in doubt, say "N".
 
+config MARKERS
+	bool "Activate markers"
+	help
+	  Place an empty function call at each marker site. Can be
+	  dynamically changed for a probe function.
+
 endif # INSTRUMENTATION

kernel/Makefile

@@ -55,6 +55,7 @@ obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
+obj-$(CONFIG_MARKERS) += marker.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is

kernel/module.c

@@ -1673,6 +1673,8 @@ static struct module *load_module(void __user *umod,
 	unsigned int unusedcrcindex;
 	unsigned int unusedgplindex;
 	unsigned int unusedgplcrcindex;
+	unsigned int markersindex;
+	unsigned int markersstringsindex;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
@@ -1939,6 +1941,9 @@ static struct module *load_module(void __user *umod,
 		add_taint_module(mod, TAINT_FORCED_MODULE);
 	}
 #endif
+	markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
+ 	markersstringsindex = find_sec(hdr, sechdrs, secstrings,
+					"__markers_strings");
 
 	/* Now do relocations. */
 	for (i = 1; i < hdr->e_shnum; i++) {
@@ -1961,6 +1966,11 @@ static struct module *load_module(void __user *umod,
 		if (err < 0)
 			goto cleanup;
 	}
+#ifdef CONFIG_MARKERS
+	mod->markers = (void *)sechdrs[markersindex].sh_addr;
+	mod->num_markers =
+		sechdrs[markersindex].sh_size / sizeof(*mod->markers);
+#endif
 
         /* Find duplicate symbols */
 	err = verify_export_symbols(mod);
@@ -1979,6 +1989,11 @@ static struct module *load_module(void __user *umod,
 
 	add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
 
+#ifdef CONFIG_MARKERS
+	if (!mod->taints)
+		marker_update_probe_range(mod->markers,
+			mod->markers + mod->num_markers, NULL, NULL);
+#endif
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
 		goto cleanup;
@@ -2570,3 +2585,18 @@ EXPORT_SYMBOL(module_remove_driver);
 void struct_module(struct module *mod) { return; }
 EXPORT_SYMBOL(struct_module);
 #endif
+
+#ifdef CONFIG_MARKERS
+void module_update_markers(struct module *probe_module, int *refcount)
+{
+	struct module *mod;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(mod, &modules, list)
+		if (!mod->taints)
+			marker_update_probe_range(mod->markers,
+				mod->markers + mod->num_markers,
+				probe_module, refcount);
+	mutex_unlock(&module_mutex);
+}
+#endif