syscalls, x86: add __NR_kcmp syscall

While doing the checkpoint-restore in the user space one need to determine
whether various kernel objects (like mm_struct-s of file_struct-s) are
shared between tasks and restore this state.

The 2nd step can be solved by using appropriate CLONE_ flags and the
unshare syscall, while there's currently no ways for solving the 1st one.

One of the ways for checking whether two tasks share e.g.  mm_struct is to
provide some mm_struct ID of a task to its proc file, but showing such
info considered to be not that good for security reasons.

Thus after some debates we end up in conclusion that using that named
'comparison' syscall might be the best candidate.  So here is it --
__NR_kcmp.

It takes up to 5 arguments - the pids of the two tasks (which
characteristics should be compared), the comparison type and (in case of
comparison of files) two file descriptors.

Lookups for pids are done in the caller's PID namespace only.

At moment only x86 is supported and tested.

[akpm@linux-foundation.org: fix up selftests, warnings]
[akpm@linux-foundation.org: include errno.h]
[akpm@linux-foundation.org: tweak comment text]
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Matt Helsley <matthltc@us.ibm.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Valdis.Kletnieks@vt.edu
Cc: Michal Marek <mmarek@suse.cz>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 123 insertions, 0 deletions

diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile
new file mode 100644
index 000000000000..dc79b86ea65c
--- /dev/null
+++ b/tools/testing/selftests/kcmp/Makefile
@@ -0,0 +1,29 @@
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
+ifeq ($(ARCH),i386)
+        ARCH := X86
+	CFLAGS := -DCONFIG_X86_32 -D__i386__
+endif
+ifeq ($(ARCH),x86_64)
+	ARCH := X86
+	CFLAGS := -DCONFIG_X86_64 -D__x86_64__
+endif
+
+CFLAGS += -I../../../../arch/x86/include/generated/
+CFLAGS += -I../../../../include/
+CFLAGS += -I../../../../usr/include/
+CFLAGS += -I../../../../arch/x86/include/
+
+all:
+ifeq ($(ARCH),X86)
+	gcc $(CFLAGS) kcmp_test.c -o run_test
+else
+	echo "Not an x86 target, can't build kcmp selftest"
+endif
+
+run-tests: all
+	./kcmp_test
+
+clean:
+	rm -fr ./run_test
+	rm -fr ./test-file
diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c
new file mode 100644
index 000000000000..358cc6bfa35d
--- /dev/null
+++ b/tools/testing/selftests/kcmp/kcmp_test.c
@@ -0,0 +1,94 @@
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <limits.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <fcntl.h>
+
+#include <linux/unistd.h>
+#include <linux/kcmp.h>
+
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+static long sys_kcmp(int pid1, int pid2, int type, int fd1, int fd2)
+{
+	return syscall(__NR_kcmp, pid1, pid2, type, fd1, fd2);
+}
+
+int main(int argc, char **argv)
+{
+	const char kpath[] = "kcmp-test-file";
+	int pid1, pid2;
+	int fd1, fd2;
+	int status;
+
+	fd1 = open(kpath, O_RDWR | O_CREAT | O_TRUNC, 0644);
+	pid1 = getpid();
+
+	if (fd1 < 0) {
+		perror("Can't create file");
+		exit(1);
+	}
+
+	pid2 = fork();
+	if (pid2 < 0) {
+		perror("fork failed");
+		exit(1);
+	}
+
+	if (!pid2) {
+		int pid2 = getpid();
+		int ret;
+
+		fd2 = open(kpath, O_RDWR, 0644);
+		if (fd2 < 0) {
+			perror("Can't open file");
+			exit(1);
+		}
+
+		/* An example of output and arguments */
+		printf("pid1: %6d pid2: %6d FD: %2ld FILES: %2ld VM: %2ld "
+		       "FS: %2ld SIGHAND: %2ld IO: %2ld SYSVSEM: %2ld "
+		       "INV: %2ld\n",
+		       pid1, pid2,
+		       sys_kcmp(pid1, pid2, KCMP_FILE,		fd1, fd2),
+		       sys_kcmp(pid1, pid2, KCMP_FILES,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_VM,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_FS,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_SIGHAND,	0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_IO,		0, 0),
+		       sys_kcmp(pid1, pid2, KCMP_SYSVSEM,	0, 0),
+
+			/* This one should fail */
+		       sys_kcmp(pid1, pid2, KCMP_TYPES + 1,	0, 0));
+
+		/* This one should return same fd */
+		ret = sys_kcmp(pid1, pid2, KCMP_FILE, fd1, fd1);
+		if (ret) {
+			printf("FAIL: 0 expected but %d returned\n", ret);
+			ret = -1;
+		} else
+			printf("PASS: 0 returned as expected\n");
+
+		/* Compare with self */
+		ret = sys_kcmp(pid1, pid1, KCMP_VM, 0, 0);
+		if (ret) {
+			printf("FAIL: 0 expected but %li returned\n", ret);
+			ret = -1;
+		} else
+			printf("PASS: 0 returned as expected\n");
+
+		exit(ret);
+	}
+
+	waitpid(pid2, &status, P_ALL);
+
+	return 0;
+}