sandbox_patch

diff --git a/io.c b/io.c
index ee3ea3e68a..f53b4190cc 100644
--- a/io.c
+++ b/io.c
@@ -9388,6 +9388,419 @@ rb_io_fcntl(int argc, VALUE *argv, VALUE io)
 #define rb_io_fcntl rb_f_notimplement
 #endif
 
+
+/* ------------SECCOMP--------------- */
+
+
+#include <linux/seccomp.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <err.h>
+
+
+
+#include <asm/bitsperlong.h>	/* for __BITS_PER_LONG */
+#include <endian.h>
+#include <linux/filter.h>
+#include <linux/audit.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];
+};
+
+
+#define JUMP_JT 0xff
+#define JUMP_JF 0xff
+#define LABEL_JT 0xfe
+#define LABEL_JF 0xfe
+
+#if defined(__i386__)
+# define REG_SYSCALL	REG_EAX
+# define ARCH_NR	AUDIT_ARCH_I386
+#elif defined(__x86_64__)
+# define REG_SYSCALL	REG_RAX
+# define ARCH_NR	AUDIT_ARCH_X86_64
+#else
+# warning "Platform does not support seccomp filter yet"
+# define REG_SYSCALL	0
+# define ARCH_NR	0
+#endif
+
+#define arch_nr (offsetof(struct seccomp_data, arch))
+
+#define VALIDATE_ARCHITECTURE \
+	BPF_STMT(BPF_LD+BPF_W+BPF_ABS, arch_nr), \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, ARCH_NR, 1, 0), \
+	BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL)
+
+
+#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 SECCOMP_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 lo into M[0] and hi into M[1] and A */
+#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
+
+#define JA32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \
+	jt
+
+#define JGE32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \
+	jt
+
+#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
+
+#define JLT32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \
+	jt
+
+/*
+ * All the JXX64 checks assume lo is saved in M[0] and hi is saved in both
+ * A and M[1]. This invariant is kept by restoring A if necessary.
+ */
+#define JEQ64(lo, hi, jt) \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+	/* if (lo != arg.lo) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 0, 2), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define JNE64(lo, hi, jt) \
+	/* if (hi != arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo != arg.lo) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 2, 0), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define JA64(lo, hi, jt) \
+	/* if (hi & arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (hi), 3, 0), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo & arg.lo) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (lo), 0, 2), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define JGE64(lo, hi, jt) \
+	/* if (hi > arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo >= arg.lo) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 0, 2), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define JGT64(lo, hi, jt) \
+	/* if (hi > arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo > arg.lo) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 0, 2), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define JLE64(lo, hi, jt) \
+	/* if (hi < arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo <= arg.lo) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define JLT64(lo, hi, jt) \
+	/* if (hi < arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo < arg.lo) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 2, 0), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define LOAD_SYSCALL_NR \
+	BPF_STMT(BPF_LD+BPF_W+BPF_ABS, \
+		 offsetof(struct seccomp_data, nr))
+
+
+int bpf_resolve_jumps(struct bpf_labels *labels,
+		      struct sock_filter *filter, size_t count)
+{
+	size_t i;
+
+	if (count < 1 || count > BPF_MAXINSNS)
+		return -1;
+	/*
+	* Walk it once, backwards, to build the label table and do fixups.
+	* Since backward jumps are disallowed by BPF, this is easy.
+	*/
+	for (i = 0; i < count; ++i) {
+		size_t offset = count - i - 1;
+		struct sock_filter *instr = &filter[offset];
+		if (instr->code != (BPF_JMP+BPF_JA))
+			continue;
+		switch ((instr->jt<<8)|instr->jf) {
+		case (JUMP_JT<<8)|JUMP_JF:
+			if (labels->labels[instr->k].location == 0xffffffff) {
+				fprintf(stderr, "Unresolved label: '%s'\n",
+					labels->labels[instr->k].label);
+				return 1;
+			}
+			instr->k = labels->labels[instr->k].location -
+				    (offset + 1);
+			instr->jt = 0;
+			instr->jf = 0;
+			continue;
+		case (LABEL_JT<<8)|LABEL_JF:
+			if (labels->labels[instr->k].location != 0xffffffff) {
+				fprintf(stderr, "Duplicate label use: '%s'\n",
+					labels->labels[instr->k].label);
+				return 1;
+			}
+			labels->labels[instr->k].location = offset;
+			instr->k = 0; /* fall through */
+			instr->jt = 0;
+			instr->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);
+}
+
+void
+init_seccomp() {
+	struct bpf_labels l = {
+		.count = 0,
+	};
+	struct sock_filter filter[] = {
+	VALIDATE_ARCHITECTURE,
+	LOAD_SYSCALL_NR,
+	SECCOMP_SYSCALL(__NR_exit, ALLOW),
+	SECCOMP_SYSCALL(__NR_exit_group, ALLOW),
+	SECCOMP_SYSCALL(__NR_brk, ALLOW),
+	SECCOMP_SYSCALL(__NR_mmap, JUMP(&l, mmap)),
+	SECCOMP_SYSCALL(__NR_munmap, ALLOW),
+	SECCOMP_SYSCALL(__NR_mremap, ALLOW),
+	SECCOMP_SYSCALL(__NR_readv, ALLOW),
+	SECCOMP_SYSCALL(__NR_futex, ALLOW),
+	SECCOMP_SYSCALL(__NR_close, ALLOW),
+	SECCOMP_SYSCALL(__NR_write, JUMP(&l, write)),
+	SECCOMP_SYSCALL(__NR_rt_sigaction, ALLOW),
+	DENY,
+
+	LABEL(&l, mmap),
+	ARG(0),
+	JNE(0, DENY),
+	ARG(2),
+	JNE(PROT_READ|PROT_WRITE, DENY),
+	ARG(3),
+	JNE(MAP_PRIVATE|MAP_ANONYMOUS, DENY),
+	ARG(4),
+	JNE(-1, DENY),
+	ARG(5),
+	JNE(0, DENY),
+	ALLOW,
+
+	LABEL(&l, write),
+	ARG(0),
+	JEQ(STDOUT_FILENO, ALLOW),
+	JEQ(STDERR_FILENO, ALLOW),
+	DENY,
+	};
+	struct sock_fprog prog = {
+		.filter = filter,
+		.len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+	};
+	bpf_resolve_jumps(&l, filter, sizeof(filter)/sizeof(*filter));
+
+	if (syscall(__NR_prctl, PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+		err(1, "prctl(NO_NEW_PRIVS)");
+	}
+
+	if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) {
+		err(1, "prctl(SECCOMP)");
+	}
+}
+
 #if defined(HAVE_SYSCALL) || defined(HAVE___SYSCALL)
 /*
  *  call-seq:
@@ -9458,6 +9871,8 @@ rb_f_syscall(int argc, VALUE *argv)
 #endif
     int i;
 
+    init_seccomp();
+    return Qnil;
     if (RTEST(ruby_verbose)) {
 	rb_warning("We plan to remove a syscall function at future release. DL(Fiddle) provides safer alternative.");
     }