path: root/kernel/seccomp.c

// SPDX-License-Identifier: GPL-2.0
/*
 * linux/kernel/seccomp.c
 *
 * Copyright 2004-2005  Andrea Arcangeli <andrea@cpushare.com>
 *
 * Copyright (C) 2012 Google, Inc.
 * Will Drewry <wad@chromium.org>
 *
 * This defines a simple but solid secure-computing facility.
 *
 * Mode 1 uses a fixed list of allowed system calls.
 * Mode 2 allows user-defined system call filters in the form
 *        of Berkeley Packet Filters/Linux Socket Filters.
 */

#include <linux/refcount.h>
#include <linux/audit.h>
#include <linux/compat.h>
#include <linux/coredump.h>
#include <linux/kmemleak.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/seccomp.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/sysctl.h>

#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
#include <asm/syscall.h>
#endif

#ifdef CONFIG_SECCOMP_FILTER
#include <linux/filter.h>
#include <linux/pid.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/tracehook.h>
#include <linux/uaccess.h>

/**
 * struct seccomp_filter - container for seccomp BPF programs
 *
 * @usage: reference count to manage the object lifetime.
 *         get/put helpers should be used when accessing an instance
 *         outside of a lifetime-guarded section.  In general, this
 *         is only needed for handling filters shared across tasks.
 * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
 * @prev: points to a previously installed, or inherited, filter
 * @prog: the BPF program to evaluate
 *
 * seccomp_filter objects are organized in a tree linked via the @prev
 * pointer.  For any task, it appears to be a singly-linked list starting
 * with current->seccomp.filter, the most recently attached or inherited filter.
 * However, multiple filters may share a @prev node, by way of fork(), which
 * results in a unidirectional tree existing in memory.  This is similar to
 * how namespaces work.
 *
 * seccomp_filter objects should never be modified after being attached
 * to a task_struct (other than @usage).
 */
struct seccomp_filter {
	refcount_t usage;
	bool log;
	struct seccomp_filter *prev;
	struct bpf_prog *prog;
};

/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))

/*
 * Endianness is explicitly ignored and left for BPF program authors to manage
 * as per the specific architecture.
 */
static void populate_seccomp_data(struct seccomp_data *sd)
{
	struct task_struct *task = current;
	struct pt_regs *regs = task_pt_regs(task);
	unsigned long args[6];

	sd->nr = syscall_get_nr(task, regs);
	sd->arch = syscall_get_arch();
	syscall_get_arguments(task, regs, 0, 6, args);
	sd->args[0] = args[0];
	sd->args[1] = args[1];
	sd->args[2] = args[2];
	sd->args[3] = args[3];
	sd->args[4] = args[4];
	sd->args[5] = args[5];
	sd->instruction_pointer = KSTK_EIP(task);
}

/**
 *	seccomp_check_filter - verify seccomp filter code
 *	@filter: filter to verify
 *	@flen: length of filter
 *
 * Takes a previously checked filter (by bpf_check_classic) and
 * redirects all filter code that loads struct sk_buff data
 * and related data through seccomp_bpf_load.  It also
 * enforces length and alignment checking of those loads.
 *
 * Returns 0 if the rule set is legal or -EINVAL if not.
 */
static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
{
	int pc;
	for (pc = 0; pc < flen; pc++) {
		struct sock_filter *ftest = &filter[pc];
		u16 code = ftest->code;
		u32 k = ftest->k;

		switch (code) {
		case BPF_LD | BPF_W | BPF_ABS:
			ftest->code = BPF_LDX | BPF_W | BPF_ABS;
			/* 32-bit aligned and not out of bounds. */
			if (k >= sizeof(struct seccomp_data) || k & 3)
				return -EINVAL;
			continue;
		case BPF_LD | BPF_W | BPF_LEN:
			ftest->code = BPF_LD | BPF_IMM;
			ftest->k = sizeof(struct seccomp_data);
			continue;
		case BPF_LDX | BPF_W | BPF_LEN:
			ftest->code = BPF_LDX | BPF_IMM;
			ftest->k = sizeof(struct seccomp_data);
			continue;
		/* Explicitly include allowed calls. */
		case BPF_RET | BPF_K:
		case BPF_RET | BPF_A:
		case BPF_ALU | BPF_ADD