summaryrefslogtreecommitdiffstats
path: root/kernel/samples/seccomp
diff options
context:
space:
mode:
authorYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 12:17:53 -0700
committerYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 15:44:42 -0700
commit9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (patch)
tree1c9cafbcd35f783a87880a10f85d1a060db1a563 /kernel/samples/seccomp
parent98260f3884f4a202f9ca5eabed40b1354c489b29 (diff)
Add the rt linux 4.1.3-rt3 as base
Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
Diffstat (limited to 'kernel/samples/seccomp')
-rw-r--r--kernel/samples/seccomp/.gitignore3
-rw-r--r--kernel/samples/seccomp/Makefile48
-rw-r--r--kernel/samples/seccomp/bpf-direct.c190
-rw-r--r--kernel/samples/seccomp/bpf-fancy.c104
-rw-r--r--kernel/samples/seccomp/bpf-helper.c95
-rw-r--r--kernel/samples/seccomp/bpf-helper.h243
-rw-r--r--kernel/samples/seccomp/dropper.c68
7 files changed, 751 insertions, 0 deletions
diff --git a/kernel/samples/seccomp/.gitignore b/kernel/samples/seccomp/.gitignore
new file mode 100644
index 000000000..78fb78184
--- /dev/null
+++ b/kernel/samples/seccomp/.gitignore
@@ -0,0 +1,3 @@
+bpf-direct
+bpf-fancy
+dropper
diff --git a/kernel/samples/seccomp/Makefile b/kernel/samples/seccomp/Makefile
new file mode 100644
index 000000000..1b4e4b8f5
--- /dev/null
+++ b/kernel/samples/seccomp/Makefile
@@ -0,0 +1,48 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+hostprogs-$(CONFIG_SECCOMP_FILTER) := bpf-fancy dropper bpf-direct
+
+HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include
+HOSTCFLAGS_bpf-fancy.o += -idirafter $(objtree)/include
+HOSTCFLAGS_bpf-helper.o += -I$(objtree)/usr/include
+HOSTCFLAGS_bpf-helper.o += -idirafter $(objtree)/include
+bpf-fancy-objs := bpf-fancy.o bpf-helper.o
+
+HOSTCFLAGS_dropper.o += -I$(objtree)/usr/include
+HOSTCFLAGS_dropper.o += -idirafter $(objtree)/include
+dropper-objs := dropper.o
+
+HOSTCFLAGS_bpf-direct.o += -I$(objtree)/usr/include
+HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include
+bpf-direct-objs := bpf-direct.o
+
+# Try to match the kernel target.
+ifndef CROSS_COMPILE
+ifndef CONFIG_64BIT
+
+# s390 has -m31 flag to build 31 bit binaries
+ifndef CONFIG_S390
+MFLAG = -m32
+else
+MFLAG = -m31
+endif
+
+HOSTCFLAGS_bpf-direct.o += $(MFLAG)
+HOSTCFLAGS_dropper.o += $(MFLAG)
+HOSTCFLAGS_bpf-helper.o += $(MFLAG)
+HOSTCFLAGS_bpf-fancy.o += $(MFLAG)
+HOSTLOADLIBES_bpf-direct += $(MFLAG)
+HOSTLOADLIBES_bpf-fancy += $(MFLAG)
+HOSTLOADLIBES_dropper += $(MFLAG)
+endif
+always := $(hostprogs-y)
+else
+# MIPS system calls are defined based on the -mabi that is passed
+# to the toolchain which may or may not be a valid option
+# for the host toolchain. So disable tests if target architecture
+# is MIPS but the host isn't.
+ifndef CONFIG_MIPS
+always := $(hostprogs-y)
+endif
+endif
diff --git a/kernel/samples/seccomp/bpf-direct.c b/kernel/samples/seccomp/bpf-direct.c
new file mode 100644
index 000000000..151ec3f52
--- /dev/null
+++ b/kernel/samples/seccomp/bpf-direct.c
@@ -0,0 +1,190 @@
+/*
+ * Seccomp filter example for x86 (32-bit and 64-bit) with BPF macros
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ */
+#if defined(__i386__) || defined(__x86_64__)
+#define SUPPORTED_ARCH 1
+#endif
+
+#if defined(SUPPORTED_ARCH)
+#define __USE_GNU 1
+#define _GNU_SOURCE 1
+
+#include <linux/types.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
+#define syscall_nr (offsetof(struct seccomp_data, nr))
+
+#if defined(__i386__)
+#define REG_RESULT REG_EAX
+#define REG_SYSCALL REG_EAX
+#define REG_ARG0 REG_EBX
+#define REG_ARG1 REG_ECX
+#define REG_ARG2 REG_EDX
+#define REG_ARG3 REG_ESI
+#define REG_ARG4 REG_EDI
+#define REG_ARG5 REG_EBP
+#elif defined(__x86_64__)
+#define REG_RESULT REG_RAX
+#define REG_SYSCALL REG_RAX
+#define REG_ARG0 REG_RDI
+#define REG_ARG1 REG_RSI
+#define REG_ARG2 REG_RDX
+#define REG_ARG3 REG_R10
+#define REG_ARG4 REG_R8
+#define REG_ARG5 REG_R9
+#endif
+
+#ifndef PR_SET_NO_NEW_PRIVS
+#define PR_SET_NO_NEW_PRIVS 38
+#endif
+
+#ifndef SYS_SECCOMP
+#define SYS_SECCOMP 1
+#endif
+
+static void emulator(int nr, siginfo_t *info, void *void_context)
+{
+ ucontext_t *ctx = (ucontext_t *)(void_context);
+ int syscall;
+ char *buf;
+ ssize_t bytes;
+ size_t len;
+ if (info->si_code != SYS_SECCOMP)
+ return;
+ if (!ctx)
+ return;
+ syscall = ctx->uc_mcontext.gregs[REG_SYSCALL];
+ buf = (char *) ctx->uc_mcontext.gregs[REG_ARG1];
+ len = (size_t) ctx->uc_mcontext.gregs[REG_ARG2];
+
+ if (syscall != __NR_write)
+ return;
+ if (ctx->uc_mcontext.gregs[REG_ARG0] != STDERR_FILENO)
+ return;
+ /* Redirect stderr messages to stdout. Doesn't handle EINTR, etc */
+ ctx->uc_mcontext.gregs[REG_RESULT] = -1;
+ if (write(STDOUT_FILENO, "[ERR] ", 6) > 0) {
+ bytes = write(STDOUT_FILENO, buf, len);
+ ctx->uc_mcontext.gregs[REG_RESULT] = bytes;
+ }
+ return;
+}
+
+static int install_emulator(void)
+{
+ struct sigaction act;
+ sigset_t mask;
+ memset(&act, 0, sizeof(act));
+ sigemptyset(&mask);
+ sigaddset(&mask, SIGSYS);
+
+ act.sa_sigaction = &emulator;
+ act.sa_flags = SA_SIGINFO;
+ if (sigaction(SIGSYS, &act, NULL) < 0) {
+ perror("sigaction");
+ return -1;
+ }
+ if (sigprocmask(SIG_UNBLOCK, &mask, NULL)) {
+ perror("sigprocmask");
+ return -1;
+ }
+ return 0;
+}
+
+static int install_filter(void)
+{
+ struct sock_filter filter[] = {
+ /* Grab the system call number */
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_nr),
+ /* Jump table for the allowed syscalls */
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_rt_sigreturn, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+#ifdef __NR_sigreturn
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_sigreturn, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+#endif
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit_group, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_read, 1, 0),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_write, 3, 2),
+
+ /* Check that read is only using stdin. */
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDIN_FILENO, 4, 0),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL),
+
+ /* Check that write is only using stdout */
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDOUT_FILENO, 1, 0),
+ /* Trap attempts to write to stderr */
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDERR_FILENO, 1, 2),
+
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_TRAP),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL),
+ };
+ struct sock_fprog prog = {
+ .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+ .filter = filter,
+ };
+
+ if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ perror("prctl(NO_NEW_PRIVS)");
+ return 1;
+ }
+
+
+ if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) {
+ perror("prctl");
+ return 1;
+ }
+ return 0;
+}
+
+#define payload(_c) (_c), sizeof((_c))
+int main(int argc, char **argv)
+{
+ char buf[4096];
+ ssize_t bytes = 0;
+ if (install_emulator())
+ return 1;
+ if (install_filter())
+ return 1;
+ syscall(__NR_write, STDOUT_FILENO,
+ payload("OHAI! WHAT IS YOUR NAME? "));
+ bytes = syscall(__NR_read, STDIN_FILENO, buf, sizeof(buf));
+ syscall(__NR_write, STDOUT_FILENO, payload("HELLO, "));
+ syscall(__NR_write, STDOUT_FILENO, buf, bytes);
+ syscall(__NR_write, STDERR_FILENO,
+ payload("Error message going to STDERR\n"));
+ return 0;
+}
+#else /* SUPPORTED_ARCH */
+/*
+ * This sample is x86-only. Since kernel samples are compiled with the
+ * host toolchain, a non-x86 host will result in using only the main()
+ * below.
+ */
+int main(void)
+{
+ return 1;
+}
+#endif /* SUPPORTED_ARCH */
diff --git a/kernel/samples/seccomp/bpf-fancy.c b/kernel/samples/seccomp/bpf-fancy.c
new file mode 100644
index 000000000..e8b24f443
--- /dev/null
+++ b/kernel/samples/seccomp/bpf-fancy.c
@@ -0,0 +1,104 @@
+/*
+ * Seccomp BPF example using a macro-based generator.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_ATTACH_SECCOMP_FILTER).
+ */
+
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "bpf-helper.h"
+
+#ifndef PR_SET_NO_NEW_PRIVS
+#define PR_SET_NO_NEW_PRIVS 38
+#endif
+
+int main(int argc, char **argv)
+{
+ struct bpf_labels l = {
+ .count = 0,
+ };
+ static const char msg1[] = "Please type something: ";
+ static const char msg2[] = "You typed: ";
+ char buf[256];
+ struct sock_filter filter[] = {
+ /* TODO: LOAD_SYSCALL_NR(arch) and enforce an arch */
+ LOAD_SYSCALL_NR,
+ SYSCALL(__NR_exit, ALLOW),
+ SYSCALL(__NR_exit_group, ALLOW),
+ SYSCALL(__NR_write, JUMP(&l, write_fd)),
+ SYSCALL(__NR_read, JUMP(&l, read)),
+ DENY, /* Don't passthrough into a label */
+
+ LABEL(&l, read),
+ ARG(0),
+ JNE(STDIN_FILENO, DENY),
+ ARG(1),
+ JNE((unsigned long)buf, DENY),
+ ARG(2),
+ JGE(sizeof(buf), DENY),
+ ALLOW,
+
+ LABEL(&l, write_fd),
+ ARG(0),
+ JEQ(STDOUT_FILENO, JUMP(&l, write_buf)),
+ JEQ(STDERR_FILENO, JUMP(&l, write_buf)),
+ DENY,
+
+ LABEL(&l, write_buf),
+ ARG(1),
+ JEQ((unsigned long)msg1, JUMP(&l, msg1_len)),
+ JEQ((unsigned long)msg2, JUMP(&l, msg2_len)),
+ JEQ((unsigned long)buf, JUMP(&l, buf_len)),
+ DENY,
+
+ LABEL(&l, msg1_len),
+ ARG(2),
+ JLT(sizeof(msg1), ALLOW),
+ DENY,
+
+ LABEL(&l, msg2_len),
+ ARG(2),
+ JLT(sizeof(msg2), ALLOW),
+ DENY,
+
+ LABEL(&l, buf_len),
+ ARG(2),
+ JLT(sizeof(buf), ALLOW),
+ DENY,
+ };
+ struct sock_fprog prog = {
+ .filter = filter,
+ .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+ };
+ ssize_t bytes;
+ bpf_resolve_jumps(&l, filter, sizeof(filter)/sizeof(*filter));
+
+ if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ perror("prctl(NO_NEW_PRIVS)");
+ return 1;
+ }
+
+ if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) {
+ perror("prctl(SECCOMP)");
+ return 1;
+ }
+ syscall(__NR_write, STDOUT_FILENO, msg1, strlen(msg1));
+ bytes = syscall(__NR_read, STDIN_FILENO, buf, sizeof(buf)-1);
+ bytes = (bytes > 0 ? bytes : 0);
+ syscall(__NR_write, STDERR_FILENO, msg2, strlen(msg2));
+ syscall(__NR_write, STDERR_FILENO, buf, bytes);
+ /* Now get killed */
+ syscall(__NR_write, STDERR_FILENO, msg2, strlen(msg2)+2);
+ return 0;
+}
diff --git a/kernel/samples/seccomp/bpf-helper.c b/kernel/samples/seccomp/bpf-helper.c
new file mode 100644
index 000000000..05cb4d5ff
--- /dev/null
+++ b/kernel/samples/seccomp/bpf-helper.c
@@ -0,0 +1,95 @@
+/*
+ * Seccomp BPF helper functions
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_ATTACH_SECCOMP_FILTER).
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "bpf-helper.h"
+
+int bpf_resolve_jumps(struct bpf_labels *labels,
+ struct sock_filter *filter, size_t count)
+{
+ struct sock_filter *begin = filter;
+ __u8 insn = count - 1;
+
+ if (count < 1)
+ return -1;
+ /*
+ * Walk it once, backwards, to build the label table and do fixups.
+ * Since backward jumps are disallowed by BPF, this is easy.
+ */
+ filter += insn;
+ for (; filter >= begin; --insn, --filter) {
+ if (filter->code != (BPF_JMP+BPF_JA))
+ continue;
+ switch ((filter->jt<<8)|filter->jf) {
+ case (JUMP_JT<<8)|JUMP_JF:
+ if (labels->labels[filter->k].location == 0xffffffff) {
+ fprintf(stderr, "Unresolved label: '%s'\n",
+ labels->labels[filter->k].label);
+ return 1;
+ }
+ filter->k = labels->labels[filter->k].location -
+ (insn + 1);
+ filter->jt = 0;
+ filter->jf = 0;
+ continue;
+ case (LABEL_JT<<8)|LABEL_JF:
+ if (labels->labels[filter->k].location != 0xffffffff) {
+ fprintf(stderr, "Duplicate label use: '%s'\n",
+ labels->labels[filter->k].label);
+ return 1;
+ }
+ labels->labels[filter->k].location = insn;
+ filter->k = 0; /* fall through */
+ filter->jt = 0;
+ filter->jf = 0;
+ continue;
+ }
+ }
+ return 0;
+}
+
+/* Simple lookup table for labels. */
+__u32 seccomp_bpf_label(struct bpf_labels *labels, const char *label)
+{
+ struct __bpf_label *begin = labels->labels, *end;
+ int id;
+
+ if (labels->count == BPF_LABELS_MAX) {
+ fprintf(stderr, "Too many labels\n");
+ exit(1);
+ }
+ if (labels->count == 0) {
+ begin->label = label;
+ begin->location = 0xffffffff;
+ labels->count++;
+ return 0;
+ }
+ end = begin + labels->count;
+ for (id = 0; begin < end; ++begin, ++id) {
+ if (!strcmp(label, begin->label))
+ return id;
+ }
+ begin->label = label;
+ begin->location = 0xffffffff;
+ labels->count++;
+ return id;
+}
+
+void seccomp_bpf_print(struct sock_filter *filter, size_t count)
+{
+ struct sock_filter *end = filter + count;
+ for ( ; filter < end; ++filter)
+ printf("{ code=%u,jt=%u,jf=%u,k=%u },\n",
+ filter->code, filter->jt, filter->jf, filter->k);
+}
diff --git a/kernel/samples/seccomp/bpf-helper.h b/kernel/samples/seccomp/bpf-helper.h
new file mode 100644
index 000000000..38ee70f3c
--- /dev/null
+++ b/kernel/samples/seccomp/bpf-helper.h
@@ -0,0 +1,243 @@
+/*
+ * Example wrapper around BPF macros.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ *
+ * No guarantees are provided with respect to the correctness
+ * or functionality of this code.
+ */
+#ifndef __BPF_HELPER_H__
+#define __BPF_HELPER_H__
+
+#include <asm/bitsperlong.h> /* for __BITS_PER_LONG */
+#include <endian.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h> /* for seccomp_data */
+#include <linux/types.h>
+#include <linux/unistd.h>
+#include <stddef.h>
+
+#define BPF_LABELS_MAX 256
+struct bpf_labels {
+ int count;
+ struct __bpf_label {
+ const char *label;
+ __u32 location;
+ } labels[BPF_LABELS_MAX];
+};
+
+int bpf_resolve_jumps(struct bpf_labels *labels,
+ struct sock_filter *filter, size_t count);
+__u32 seccomp_bpf_label(struct bpf_labels *labels, const char *label);
+void seccomp_bpf_print(struct sock_filter *filter, size_t count);
+
+#define JUMP_JT 0xff
+#define JUMP_JF 0xff
+#define LABEL_JT 0xfe
+#define LABEL_JF 0xfe
+
+#define ALLOW \
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW)
+#define DENY \
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL)
+#define JUMP(labels, label) \
+ BPF_JUMP(BPF_JMP+BPF_JA, FIND_LABEL((labels), (label)), \
+ JUMP_JT, JUMP_JF)
+#define LABEL(labels, label) \
+ BPF_JUMP(BPF_JMP+BPF_JA, FIND_LABEL((labels), (label)), \
+ LABEL_JT, LABEL_JF)
+#define SYSCALL(nr, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (nr), 0, 1), \
+ jt
+
+/* Lame, but just an example */
+#define FIND_LABEL(labels, label) seccomp_bpf_label((labels), #label)
+
+#define EXPAND(...) __VA_ARGS__
+
+/* Ensure that we load the logically correct offset. */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define LO_ARG(idx) offsetof(struct seccomp_data, args[(idx)])
+#elif __BYTE_ORDER == __BIG_ENDIAN
+#define LO_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) + sizeof(__u32)
+#else
+#error "Unknown endianness"
+#endif
+
+/* Map all width-sensitive operations */
+#if __BITS_PER_LONG == 32
+
+#define JEQ(x, jt) JEQ32(x, EXPAND(jt))
+#define JNE(x, jt) JNE32(x, EXPAND(jt))
+#define JGT(x, jt) JGT32(x, EXPAND(jt))
+#define JLT(x, jt) JLT32(x, EXPAND(jt))
+#define JGE(x, jt) JGE32(x, EXPAND(jt))
+#define JLE(x, jt) JLE32(x, EXPAND(jt))
+#define JA(x, jt) JA32(x, EXPAND(jt))
+#define ARG(i) ARG_32(i)
+
+#elif __BITS_PER_LONG == 64
+
+/* Ensure that we load the logically correct offset. */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define ENDIAN(_lo, _hi) _lo, _hi
+#define HI_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) + sizeof(__u32)
+#elif __BYTE_ORDER == __BIG_ENDIAN
+#define ENDIAN(_lo, _hi) _hi, _lo
+#define HI_ARG(idx) offsetof(struct seccomp_data, args[(idx)])
+#endif
+
+union arg64 {
+ struct {
+ __u32 ENDIAN(lo32, hi32);
+ };
+ __u64 u64;
+};
+
+#define JEQ(x, jt) \
+ JEQ64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JGT(x, jt) \
+ JGT64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JGE(x, jt) \
+ JGE64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JNE(x, jt) \
+ JNE64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JLT(x, jt) \
+ JLT64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JLE(x, jt) \
+ JLE64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+
+#define JA(x, jt) \
+ JA64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define ARG(i) ARG_64(i)
+
+#else
+#error __BITS_PER_LONG value unusable.
+#endif
+
+/* Loads the arg into A */
+#define ARG_32(idx) \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx))
+
+/* Loads hi into A and lo in X */
+#define ARG_64(idx) \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx)), \
+ BPF_STMT(BPF_ST, 0), /* lo -> M[0] */ \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, HI_ARG(idx)), \
+ BPF_STMT(BPF_ST, 1) /* hi -> M[1] */
+
+#define JEQ32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 0, 1), \
+ jt
+
+#define JNE32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 1, 0), \
+ jt
+
+/* Checks the lo, then swaps to check the hi. A=lo,X=hi */
+#define JEQ64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JNE64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 5, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 2, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JA32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \
+ jt
+
+#define JA64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (hi), 3, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JGE32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \
+ jt
+
+#define JLT32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \
+ jt
+
+/* Shortcut checking if hi > arg.hi. */
+#define JGE64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JLT64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JGT32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 0, 1), \
+ jt
+
+#define JLE32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 1, 0), \
+ jt
+
+/* Check hi > args.hi first, then do the GE checking */
+#define JGT64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JLE64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 6, 0), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define LOAD_SYSCALL_NR \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, \
+ offsetof(struct seccomp_data, nr))
+
+#endif /* __BPF_HELPER_H__ */
diff --git a/kernel/samples/seccomp/dropper.c b/kernel/samples/seccomp/dropper.c
new file mode 100644
index 000000000..c69c347c7
--- /dev/null
+++ b/kernel/samples/seccomp/dropper.c
@@ -0,0 +1,68 @@
+/*
+ * Naive system call dropper built on seccomp_filter.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ *
+ * When run, returns the specified errno for the specified
+ * system call number against the given architecture.
+ *
+ * Run this one as root as PR_SET_NO_NEW_PRIVS is not called.
+ */
+
+#include <errno.h>
+#include <linux/audit.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+static int install_filter(int nr, int arch, int error)
+{
+ struct sock_filter filter[] = {
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+ (offsetof(struct seccomp_data, arch))),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, arch, 0, 3),
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+ (offsetof(struct seccomp_data, nr))),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K,
+ SECCOMP_RET_ERRNO|(error & SECCOMP_RET_DATA)),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_fprog prog = {
+ .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+ .filter = filter,
+ };
+ if (prctl(PR_SET_SECCOMP, 2, &prog)) {
+ perror("prctl");
+ return 1;
+ }
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ if (argc < 5) {
+ fprintf(stderr, "Usage:\n"
+ "dropper <syscall_nr> <arch> <errno> <prog> [<args>]\n"
+ "Hint: AUDIT_ARCH_I386: 0x%X\n"
+ " AUDIT_ARCH_X86_64: 0x%X\n"
+ "\n", AUDIT_ARCH_I386, AUDIT_ARCH_X86_64);
+ return 1;
+ }
+ if (install_filter(strtol(argv[1], NULL, 0), strtol(argv[2], NULL, 0),
+ strtol(argv[3], NULL, 0)))
+ return 1;
+ execv(argv[4], &argv[4]);
+ printf("Failed to execv\n");
+ return 255;
+}