fprobe: Add ftrace based probe APIs

The fprobe is a wrapper API for ftrace function tracer.
Unlike kprobes, this probes only supports the function entry, but this
can probe multiple functions by one fprobe. The usage is similar, user
will set their callback to fprobe::entry_handler and call
register_fprobe*() with probed functions.
There are 3 registration interfaces,

 - register_fprobe() takes filtering patterns of the functin names.
 - register_fprobe_ips() takes an array of ftrace-location addresses.
 - register_fprobe_syms() takes an array of function names.

The registered fprobes can be unregistered with unregister_fprobe().
e.g.

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

ret = register_fprobe_syms(&fp, targets, ARRAY_SIZE(targets));

...

unregister_fprobe(&fp);

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Tested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/164735283857.1084943.1154436951479395551.stgit@devnote2

3 files changed, 224 insertions, 0 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a5eb5e7fd624..7ce31abc542b 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -236,6 +236,18 @@ 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 (fprobe) based on ftrace,
+	  which is similar to kprobes, but probes only for kernel function
+	  entries and it can probe multiple functions by one fprobe.
+
+	  If unsure, say N.
+
 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..7e8ceee339a0
--- /dev/null
+++ b/kernel/trace/fprobe.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fprobe - Simple ftrace probe wrapper for function entry.
+ */
+#define pr_fmt(fmt) "fprobe: " fmt
+
+#include <linux/err.h>
+#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, ops);
+	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);
+
+/* Convert ftrace location address from symbols */
+static unsigned long *get_ftrace_locations(const char **syms, int num)
+{
+	unsigned long addr, size;
+	unsigned long *addrs;
+	int i;
+
+	/* Convert symbols to symbol address */
+	addrs = kcalloc(num, sizeof(*addrs), GFP_KERNEL);
+	if (!addrs)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < num; i++) {
+		addr = kallsyms_lookup_name(syms[i]);
+		if (!addr)	/* Maybe wrong symbol */
+			goto error;
+
+		/* Convert symbol address to ftrace location. */
+		if (!kallsyms_lookup_size_offset(addr, &size, NULL) || !size)
+			goto error;
+
+		addr = ftrace_location_range(addr, addr + size - 1);
+		if (!addr) /* No dynamic ftrace there. */
+			goto error;
+
+		addrs[i] = addr;
+	}
+
+	return addrs;
+
+error:
+	kfree(addrs);
+
+	return ERR_PTR(-ENOENT);
+}
+
+static void fprobe_init(struct fprobe *fp)
+{
+	fp->nmissed = 0;
+	fp->ops.func = fprobe_handler;
+	fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS;
+}
+
+/**
+ * register_fprobe() - Register fprobe to ftrace by pattern.
+ * @fp: A fprobe data structure to be registered.
+ * @filter: A wildcard pattern of probed symbols.
+ * @notfilter: A wildcard pattern of NOT probed symbols.
+ *
+ * Register @fp to ftrace for enabling the probe on the symbols matched to @filter.
+ * If @notfilter is not NULL, the symbols matched the @notfilter are not probed.
+ *
+ * Return 0 if @fp is registered successfully, -errno if not.
+ */
+int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
+{
+	unsigned char *str;
+	int ret, len;
+
+	if (!fp || !filter)
+		return -EINVAL;
+
+	fprobe_init(fp);
+
+	len = strlen(filter);
+	str = kstrdup(filter, GFP_KERNEL);
+	ret = ftrace_set_filter(&fp->ops, str, len, 0);
+	kfree(str);
+	if (ret)
+		return ret;
+
+	if (notfilter) {
+		len = strlen(notfilter);
+		str = kstrdup(notfilter, GFP_KERNEL);
+		ret = ftrace_set_notrace(&fp->ops, str, len, 0);
+		kfree(str);
+		if (ret)
+			goto out;
+	}
+
+	ret = register_ftrace_function(&fp->ops);
+out:
+	if (ret)
+		ftrace_free_filter(&fp->ops);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_fprobe);
+
+/**
+ * register_fprobe_ips() - Register fprobe to ftrace by address.
+ * @fp: A fprobe data structure to be registered.
+ * @addrs: An array of target ftrace location addresses.
+ * @num: The number of entries of @addrs.
+ *
+ * Register @fp to ftrace for enabling the probe on the address given by @addrs.
+ * The @addrs must be the addresses of ftrace location address, which may be
+ * the symbol address + arch-dependent offset.
+ * If you unsure what this mean, please use other registration functions.
+ *
+ * Return 0 if @fp is registered successfully, -errno if not.
+ */
+int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num)
+{
+	int ret;
+
+	if (!fp || !addrs || num <= 0)
+		return -EINVAL;
+
+	fprobe_init(fp);
+
+	ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0);
+	if (!ret)
+		ret = register_ftrace_function(&fp->ops);
+
+	if (ret)
+		ftrace_free_filter(&fp->ops);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_fprobe_ips);
+
+/**
+ * register_fprobe_syms() - Register fprobe to ftrace by symbols.
+ * @fp: A fprobe data structure to be registered.
+ * @syms: An array of target symbols.
+ * @num: The number of entries of @syms.
+ *
+ * Register @fp to the symbols given by @syms array. This will be useful if
+ * you are sure the symbols exist in the kernel.
+ *
+ * Return 0 if @fp is registered successfully, -errno if not.
+ */
+int register_fprobe_syms(struct fprobe *fp, const char **syms, int num)
+{
+	unsigned long *addrs;
+	int ret;
+
+	if (!fp || !syms || num <= 0)
+		return -EINVAL;
+
+	addrs = get_ftrace_locations(syms, num);
+	if (IS_ERR(addrs))
+		return PTR_ERR(addrs);
+
+	ret = register_fprobe_ips(fp, addrs, num);
+
+	kfree(addrs);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_fprobe_syms);
+
+/**
+ * unregister_fprobe() - Unregister fprobe from ftrace
+ * @fp: A fprobe data structure to be unregistered.
+ *
+ * Unregister fprobe (and remove ftrace hooks from the function entries).
+ *
+ * Return 0 if @fp is unregistered successfully, -errno if not.
+ */
+int unregister_fprobe(struct fprobe *fp)
+{
+	int ret;
+
+	if (!fp || fp->ops.func != fprobe_handler)
+		return -EINVAL;
+
+	ret = unregister_ftrace_function(&fp->ops);
+
+	if (!ret)
+		ftrace_free_filter(&fp->ops);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(unregister_fprobe);