Documentation: prctl/seccomp_filter

Documents how system call filtering using Berkeley Packet
Filter programs works and how it may be used.
Includes an example for x86 and a semi-generic
example using a macro-based code generator.

Acked-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Kees Cook <keescook@chromium.org>

v18: - added acked by
     - update no new privs numbers
v17: - remove @compat note and add Pitfalls section for arch checking
       (keescook@chromium.org)
v16: -
v15: -
v14: - rebase/nochanges
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
v12: - comment on the ptrace_event use
     - update arch support comment
     - note the behavior of SECCOMP_RET_DATA when there are multiple filters
       (keescook@chromium.org)
     - lots of samples/ clean up incl 64-bit bpf-direct support
       (markus@chromium.org)
     - rebase to linux-next
v11: - overhaul return value language, updates (keescook@chromium.org)
     - comment on do_exit(SIGSYS)
v10: - update for SIGSYS
     - update for new seccomp_data layout
     - update for ptrace option use
v9: - updated bpf-direct.c for SIGILL
v8: - add PR_SET_NO_NEW_PRIVS to the samples.
v7: - updated for all the new stuff in v7: TRAP, TRACE
    - only talk about PR_SET_SECCOMP now
    - fixed bad JLE32 check (coreyb@linux.vnet.ibm.com)
    - adds dropper.c: a simple system call disabler
v6: - tweak the language to note the requirement of
      PR_SET_NO_NEW_PRIVS being called prior to use. (luto@mit.edu)
v5: - update sample to use system call arguments
    - adds a "fancy" example using a macro-based generator
    - cleaned up bpf in the sample
    - update docs to mention arguments
    - fix prctl value (eparis@redhat.com)
    - language cleanup (rdunlap@xenotime.net)
v4: - update for no_new_privs use
    - minor tweaks
v3: - call out BPF <-> Berkeley Packet Filter (rdunlap@xenotime.net)
    - document use of tentative always-unprivileged
    - guard sample compilation for i386 and x86_64
v2: - move code to samples (corbet@lwn.net)
Signed-off-by: James Morris <james.l.morris@oracle.com>

1 files changed, 102 insertions, 0 deletions

diff --git a/samples/seccomp/bpf-fancy.c b/samples/seccomp/bpf-fancy.c
new file mode 100644
index 000000000000..8eb483aaec46
--- /dev/null
+++ b/samples/seccomp/bpf-fancy.c
@@ -0,0 +1,102 @@
+/*
+ * 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;
+        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;
+}