[RFC PATCH v3 2/9] fprobe: Add ftrace based probe APIs

[Masami Hiramatsu]

The fprobe is a wrapper API for ftrace function tracer.
Unlike kprobes, this probes only supports the function entry, but
it can probe multiple functions by one fprobe. The usage is almost
same as the kprobe, user will specify the function names by
fprobe::syms, the number of syms by fprobe::nentry,
and the user handler by fprobe::entry_handler.

struct fprobe fp = { 0 };
const char *targets[] = { "func1", "func2", "func3"};

fp.handler = user_handler;
fp.nentry = ARRAY_SIZE(targets);
fp.syms = targets;

ret = register_fprobe(&fp);

Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
---
 Changes in v3:
  - Update kerneldocs.
---
 include/linux/fprobe.h |   80 +++++++++++++++++++++++++++++++++
 kernel/trace/Kconfig   |   10 ++++
 kernel/trace/Makefile  |    1 
 kernel/trace/fprobe.c  |  117 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 208 insertions(+)
 create mode 100644 include/linux/fprobe.h
 create mode 100644 kernel/trace/fprobe.c

diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
new file mode 100644
index 000000000000..2fc487d933e3
--- /dev/null
+++ b/include/linux/fprobe.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Simple ftrace probe wrapper */
+#ifndef _LINUX_FPROBE_H
+#define _LINUX_FPROBE_H
+
+#include <linux/compiler.h>
+#include <linux/ftrace.h>
+
+/**
+ * struct fprobe - ftrace based probe.
+ * @syms: The array of symbols to probe.
+ * @addrs: The array of address of the symbols.
+ * @nentry: The number of entries of @syms or @addrs.
+ * @ftrace: The ftrace_ops.
+ * @nmissed: The counter for missing events.
+ * @flags: The status flag.
+ * @entry_handler: The callback function for function entry.
+ *
+ * User must set either @syms or @addrs, but not both. If user sets
+ * only @syms, the @addrs are generated when registering the fprobe.
+ * That auto-generated @addrs will be freed when unregistering.
+ */
+struct fprobe {
+	const char		**syms;
+	unsigned long		*addrs;
+	unsigned int		nentry;
+
+	struct ftrace_ops	ftrace;
+	unsigned long		nmissed;
+	unsigned int		flags;
+	void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs);
+};
+
+#define FPROBE_FL_DISABLED	1
+
+static inline bool fprobe_disabled(struct fprobe *fp)
+{
+	return (fp) ? fp->flags & FPROBE_FL_DISABLED : false;
+}
+
+#ifdef CONFIG_FPROBE
+int register_fprobe(struct fprobe *fp);
+int unregister_fprobe(struct fprobe *fp);
+#else
+static inline int register_fprobe(struct fprobe *fp)
+{
+	return -EOPNOTSUPP;
+}
+static inline int unregister_fprobe(struct fprobe *fp)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+/**
+ * disable_fprobe() - Disable fprobe
+ * @fp: The fprobe to be disabled.
+ *
+ * This will soft-disable @fp. Note that this doesn't remove the ftrace
+ * hooks from the function entry.
+ */
+static inline void disable_fprobe(struct fprobe *fp)
+{
+	if (fp)
+		fp->flags |= FPROBE_FL_DISABLED;
+}
+
+/**
+ * enable_fprobe() - Enable fprobe
+ * @fp: The fprobe to be enabled.
+ *
+ * This will soft-enable @fp.
+ */
+static inline void enable_fprobe(struct fprobe *fp)
+{
+	if (fp)
+		fp->flags &= ~FPROBE_FL_DISABLED;
+}
+
+#endif
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 420ff4bc67fd..6834b0272798 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -223,6 +223,16 @@ config DYNAMIC_FTRACE_WITH_ARGS
 	depends on DYNAMIC_FTRACE
 	depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
+config FPROBE
+	bool "Kernel Function Probe (fprobe)"
+	depends on FUNCTION_TRACER
+	depends on DYNAMIC_FTRACE_WITH_REGS
+	default n
+	help
+	  This option enables kernel function probe feature, which is
+	  similar to kprobes, but probes only for kernel function entries
+	  and it can probe multiple functions by one fprobe.
+
 config FUNCTION_PROFILER
 	bool "Kernel function profiler"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index bedc5caceec7..79255f9de9a4 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -97,6 +97,7 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(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_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
new file mode 100644
index 000000000000..8b068deadc48
--- /dev/null
+++ b/kernel/trace/fprobe.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fprobe - Simple ftrace probe wrapper for function entry.
+ */
+#define pr_fmt(fmt) "fprobe: " fmt
+
+#include <linux/fprobe.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+
+static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+	struct fprobe *fp;
+	int bit;
+
+	fp = container_of(ops, struct fprobe, ftrace);
+	if (fprobe_disabled(fp))
+		return;
+
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0) {
+		fp->nmissed++;
+		return;
+	}
+
+	if (fp->entry_handler)
+		fp->entry_handler(fp, ip, ftrace_get_regs(fregs));
+
+	ftrace_test_recursion_unlock(bit);
+}
+NOKPROBE_SYMBOL(fprobe_handler);
+
+static int convert_func_addresses(struct fprobe *fp)
+{
+	unsigned int i;
+
+	if (!fp->syms)
+		return 0;
+
+	fp->addrs = kcalloc(fp->nentry, sizeof(*fp->addrs), GFP_KERNEL);
+	if (!fp->addrs)
+		return -ENOMEM;
+
+	for (i = 0; i < fp->nentry; i++) {
+
+		fp->addrs[i] = kallsyms_lookup_name(fp->syms[i]);
+		if (!fp->addrs[i])
+			return -ENOENT;
+	}
+
+	return 0;
+}
+
+/**
+ * register_fprobe() - Register fprobe to ftrace
+ * @fp: A fprobe data structure to be registered.
+ *
+ * This expects the user set @fp::entry_handler, @fp::syms or @fp:addrs,
+ * and @fp::nentry.
+ * Note that you do not set both of @fp::addrs and @fp::syms.
+ */
+int register_fprobe(struct fprobe *fp)
+{
+	int ret;
+
+	if (!fp || !fp->nentry || (!fp->syms && !fp->addrs) ||
+	    (fp->syms && fp->addrs))
+		return -EINVAL;
+
+	ret = convert_func_addresses(fp);
+	if (ret < 0)
+		return ret;
+
+	fp->nmissed = 0;
+	fp->ftrace.func = fprobe_handler;
+	fp->ftrace.flags = FTRACE_OPS_FL_SAVE_REGS;
+
+	ret = ftrace_set_filter_ips(&fp->ftrace, fp->addrs, fp->nentry, 0, 0);
+	if (!ret)
+		ret = register_ftrace_function(&fp->ftrace);
+
+	if (ret < 0 && fp->syms) {
+		kfree(fp->addrs);
+		fp->addrs = NULL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_fprobe);
+
+/**
+ * unregister_fprobe() - Unregister fprobe from ftrace
+ * @fp: A fprobe data structure to be unregistered.
+ *
+ * Unregister fprobe (and remove ftrace hooks from the function entries).
+ * If the @fp::addrs are generated by register_fprobe(), it will be removed
+ * automatically.
+ */
+int unregister_fprobe(struct fprobe *fp)
+{
+	int ret;
+
+	if (!fp || !fp->nentry || !fp->addrs)
+		return -EINVAL;
+
+	ret = unregister_ftrace_function(&fp->ftrace);
+
+	if (!ret && fp->syms) {
+		kfree(fp->addrs);
+		fp->addrs = NULL;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(unregister_fprobe);