kernel/trace/bpf_trace.c

/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/uaccess.h>
#include "trace.h"

static DEFINE_PER_CPU(int, bpf_prog_active);

/**
 * trace_call_bpf - invoke BPF program
 * @prog: BPF program
 * @ctx: opaque context pointer
 *
 * kprobe handlers execute BPF programs via this helper.
 * Can be used from static tracepoints in the future.
 *
 * Return: BPF programs always return an integer which is interpreted by
 * kprobe handler as:
 * 0 - return from kprobe (event is filtered out)
 * 1 - store kprobe event into ring buffer
 * Other values are reserved and currently alias to 1
 */
unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
{
	unsigned int ret;

	if (in_nmi()) /* not supported yet */
		return 1;

	preempt_disable();

	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
		/*
		 * since some bpf program is already running on this cpu,
		 * don't call into another bpf program (same or different)
		 * and don't send kprobe event into ring-buffer,
		 * so return zero here
		 */
		ret = 0;
		goto out;
	}

	rcu_read_lock();
	ret = BPF_PROG_RUN(prog, ctx);
	rcu_read_unlock();

 out:
	__this_cpu_dec(bpf_prog_active);
	preempt_enable();

	return ret;
}
EXPORT_SYMBOL_GPL(trace_call_bpf);

static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
	void *dst = (void *) (long) r1;
	int size = (int) r2;
	void *unsafe_ptr = (void *) (long) r3;

	return probe_kernel_read(dst, unsafe_ptr, size);
}

static const struct bpf_func_proto bpf_probe_read_proto = {
	.func		= bpf_probe_read,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
	.arg1_type	= ARG_PTR_TO_STACK,
	.arg2_type	= ARG_CONST_STACK_SIZE,
	.arg3_type	= ARG_ANYTHING,
};

static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
	/* NMI safe access to clock monotonic */
	return ktime_get_mono_fast_ns();
}

static const struct bpf_func_proto bpf_ktime_get_ns_proto = {
	.func		= bpf_ktime_get_ns,
	.gpl_only	= true,
	.ret_type	= RET_INTEGER,
};

static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
{
	switch (func_id) {
	case BPF_FUNC_map_lookup_elem:
		return &bpf_map_lookup_elem_proto;
	case BPF_FUNC_map_update_elem:
		return &bpf_map_update_elem_proto;
	case BPF_FUNC_map_delete_elem:
		return &bpf_map_delete_elem_proto;
	case BPF_FUNC_probe_read:
		return &bpf_probe_read_proto;
	case BPF_FUNC_ktime_get_ns:
		return &bpf_ktime_get_ns_proto;
	default:
		return NULL;
	}
}

/* bpf+kprobe programs can access fields of 'struct pt_regs' */
static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type)
{
	/* check bounds */
	if (off < 0 || off >= sizeof(struct pt_regs))
		return false;

	/* only read is allowed */
	if (type != BPF_READ)
		return false;

	/* disallow misaligned access */
	if (off % size != 0)
		return false;

	return true;
}

static struct bpf_verifier_ops kprobe_prog_ops = {
	.get_func_proto  = kprobe_prog_func_proto,
	.is_valid_access = kprobe_prog_is_valid_access,
};

static struct bpf_prog_type_list kprobe_tl = {
	.ops	= &kprobe_prog_ops,
	.type	= BPF_PROG_TYPE_KPROBE,
};

static int __init register_kprobe_prog_ops(void)
{
	bpf_register_prog_type(&kprobe_tl);
	return 0;
}
late_initcall(register_kprobe_prog_ops);