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.
Signed-off-by: Cyrill Gorcunov <[email protected]>
CC: "Eric W. Biederman" <[email protected]>
CC: Pavel Emelyanov <[email protected]>
CC: Andrey Vagin <[email protected]>
CC: KOSAKI Motohiro <[email protected]>
CC: Ingo Molnar <[email protected]>
CC: H. Peter Anvin <[email protected]>
CC: Thomas Gleixner <[email protected]>
CC: Glauber Costa <[email protected]>
CC: Andi Kleen <[email protected]>
CC: Tejun Heo <[email protected]>
CC: Matt Helsley <[email protected]>
CC: Pekka Enberg <[email protected]>
CC: Eric Dumazet <[email protected]>
CC: Vasiliy Kulikov <[email protected]>
CC: Andrew Morton <[email protected]>
CC: Alexey Dobriyan <[email protected]>
CC: [email protected]
CC: Michal Marek <[email protected]>
---
arch/x86/syscalls/syscall_32.tbl | 1
arch/x86/syscalls/syscall_64.tbl | 1
include/linux/kcmp.h | 17 +++
include/linux/syscalls.h | 2
kernel/Makefile | 3
kernel/kcmp.c | 158 +++++++++++++++++++++++++++++++
kernel/sys_ni.c | 3
tools/testing/selftests/kcmp/Makefile | 36 +++++++
tools/testing/selftests/kcmp/kcmp_test.c | 84 ++++++++++++++++
tools/testing/selftests/run_tests | 2
10 files changed, 306 insertions(+), 1 deletion(-)
Index: linux-2.6.git/arch/x86/syscalls/syscall_32.tbl
===================================================================
--- linux-2.6.git.orig/arch/x86/syscalls/syscall_32.tbl
+++ linux-2.6.git/arch/x86/syscalls/syscall_32.tbl
@@ -355,3 +355,4 @@
346 i386 setns sys_setns
347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
+349 i386 kcmp sys_kcmp
Index: linux-2.6.git/arch/x86/syscalls/syscall_64.tbl
===================================================================
--- linux-2.6.git.orig/arch/x86/syscalls/syscall_64.tbl
+++ linux-2.6.git/arch/x86/syscalls/syscall_64.tbl
@@ -318,3 +318,4 @@
309 64 getcpu sys_getcpu
310 64 process_vm_readv sys_process_vm_readv
311 64 process_vm_writev sys_process_vm_writev
+312 64 kcmp sys_kcmp
Index: linux-2.6.git/include/linux/kcmp.h
===================================================================
--- /dev/null
+++ linux-2.6.git/include/linux/kcmp.h
@@ -0,0 +1,17 @@
+#ifndef _LINUX_KCMP_H
+#define _LINUX_KCMP_H
+
+/* Comparison type */
+enum kcmp_type {
+ KCMP_FILE,
+ KCMP_VM,
+ KCMP_FILES,
+ KCMP_FS,
+ KCMP_SIGHAND,
+ KCMP_IO,
+ KCMP_SYSVSEM,
+
+ KCMP_TYPES,
+};
+
+#endif /* _LINUX_KCMP_H */
Index: linux-2.6.git/include/linux/syscalls.h
===================================================================
--- linux-2.6.git.orig/include/linux/syscalls.h
+++ linux-2.6.git/include/linux/syscalls.h
@@ -857,4 +857,6 @@ asmlinkage long sys_process_vm_writev(pi
unsigned long riovcnt,
unsigned long flags);
+asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
+ unsigned long idx1, unsigned long idx2);
#endif
Index: linux-2.6.git/kernel/Makefile
===================================================================
--- linux-2.6.git.orig/kernel/Makefile
+++ linux-2.6.git/kernel/Makefile
@@ -25,6 +25,9 @@ endif
obj-y += sched/
obj-y += power/
+ifeq ($(CONFIG_CHECKPOINT_RESTORE),y)
+obj-$(CONFIG_X86) += kcmp.o
+endif
obj-$(CONFIG_FREEZER) += freezer.o
obj-$(CONFIG_PROFILING) += profile.o
obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
Index: linux-2.6.git/kernel/kcmp.c
===================================================================
--- /dev/null
+++ linux-2.6.git/kernel/kcmp.c
@@ -0,0 +1,158 @@
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/fdtable.h>
+#include <linux/string.h>
+#include <linux/random.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cache.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/kcmp.h>
+
+#include <asm/unistd.h>
+
+/*
+ * We don't expose real in-memory order of objects for security
+ * reasons, still the comparison results should be suitable for
+ * sorting. Thus, we obfuscate kernel pointers values and compare
+ * the production instead.
+ */
+static unsigned long cookies[KCMP_TYPES][2] __read_mostly;
+
+static long kptr_obfuscate(long v, int type)
+{
+ return (v ^ cookies[type][0]) * cookies[type][1];
+}
+
+/*
+ * 0 - equal, i.e. v1 = v2
+ * 1 - less than, i.e. v1 < v2
+ * 2 - greater than, i.e. v1 > v2
+ * 3 - not equal but ordering unavailable (reserved for future)
+ */
+static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
+{
+ long ret;
+
+ ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+
+ return (ret < 0) | ((ret > 0) << 1);
+}
+
+/* The caller must have pinned the task */
+static struct file *
+get_file_raw_ptr(struct task_struct *task, unsigned int idx)
+{
+ struct fdtable *fdt;
+ struct file *file;
+
+ spin_lock(&task->files->file_lock);
+ fdt = files_fdtable(task->files);
+ if (idx < fdt->max_fds)
+ file = fdt->fd[idx];
+ else
+ file = NULL;
+ spin_unlock(&task->files->file_lock);
+
+ return file;
+}
+
+SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
+ unsigned long, idx1, unsigned long, idx2)
+{
+ struct task_struct *task1, *task2;
+ int ret;
+
+ rcu_read_lock();
+
+ /*
+ * Tasks are looked up in caller's PID namespace only.
+ */
+ task1 = find_task_by_vpid(pid1);
+ task2 = find_task_by_vpid(pid2);
+ if (!task1 || !task2)
+ goto err_no_task;
+
+ get_task_struct(task1);
+ get_task_struct(task2);
+
+ rcu_read_unlock();
+
+ /*
+ * One should have enough rights to inspect task details.
+ */
+ if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
+ !ptrace_may_access(task2, PTRACE_MODE_READ)) {
+ ret = -EACCES;
+ goto err;
+ }
+
+ switch (type) {
+ case KCMP_FILE: {
+ struct file *filp1, *filp2;
+
+ filp1 = get_file_raw_ptr(task1, idx1);
+ filp2 = get_file_raw_ptr(task2, idx2);
+
+ if (filp1 && filp2)
+ ret = kcmp_ptr(filp1, filp2, KCMP_FILE);
+ else
+ ret = -EBADF;
+ break;
+ }
+ case KCMP_VM:
+ ret = kcmp_ptr(task1->mm, task2->mm, KCMP_VM);
+ break;
+ case KCMP_FILES:
+ ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES);
+ break;
+ case KCMP_FS:
+ ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS);
+ break;
+ case KCMP_SIGHAND:
+ ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND);
+ break;
+ case KCMP_IO:
+ ret = kcmp_ptr(task1->io_context, task2->io_context, KCMP_IO);
+ break;
+ case KCMP_SYSVSEM:
+#ifdef CONFIG_SYSVIPC
+ ret = kcmp_ptr(task1->sysvsem.undo_list,
+ task2->sysvsem.undo_list,
+ KCMP_SYSVSEM);
+#else
+ ret = -EOPNOTSUP;
+#endif
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+err:
+ put_task_struct(task1);
+ put_task_struct(task2);
+
+ return ret;
+
+err_no_task:
+ rcu_read_unlock();
+ return -ESRCH;
+}
+
+static __init int kcmp_cookies_init(void)
+{
+ const int size = sizeof(cookies[0][0]);
+ int i, j;
+
+ for (i = 0; i < KCMP_TYPES; i++) {
+ for (j = 0; j < 2; j++)
+ get_random_bytes(&cookies[i][j], size);
+
+ cookies[i][1] |= (~(~0UL >> 1) | 1);
+ }
+
+ return 0;
+}
+arch_initcall(kcmp_cookies_init);
Index: linux-2.6.git/kernel/sys_ni.c
===================================================================
--- linux-2.6.git.orig/kernel/sys_ni.c
+++ linux-2.6.git/kernel/sys_ni.c
@@ -203,3 +203,6 @@ cond_syscall(sys_fanotify_mark);
cond_syscall(sys_name_to_handle_at);
cond_syscall(sys_open_by_handle_at);
cond_syscall(compat_sys_open_by_handle_at);
+
+/* compare kernel pointers */
+cond_syscall(sys_kcmp);
Index: linux-2.6.git/tools/testing/selftests/kcmp/Makefile
===================================================================
--- /dev/null
+++ linux-2.6.git/tools/testing/selftests/kcmp/Makefile
@@ -0,0 +1,36 @@
+ifeq ($(strip $(V)),)
+ E = @echo
+ Q = @
+else
+ E = @\#
+ Q =
+endif
+export E Q
+
+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 ($(ARCH),x86_64)
+ ARCH := X86
+ CFLAGS := -DCONFIG_X86_64 -D__x86_64__
+endif
+
+CFLAGS += -I../../../../arch/x86/include/generated/
+CFLAGS += -I../../../../include/
+CFLAGS += -I../../../../usr/include/
+
+all:
+ifeq ($(ARCH),X86)
+ $(E) " CC run_test"
+ $(Q) gcc $(CFLAGS) kcmp_test.c -o run_test
+else
+ $(E) "Not an x86 target, can't build kcmp selftest"
+endif
+
+clean:
+ $(E) " CLEAN"
+ $(Q) rm -fr ./run_test
+ $(Q) rm -fr ./test-file
Index: linux-2.6.git/tools/testing/selftests/kcmp/kcmp_test.c
===================================================================
--- /dev/null
+++ linux-2.6.git/tools/testing/selftests/kcmp/kcmp_test.c
@@ -0,0 +1,84 @@
+#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: %2d FILES: %2d VM: %2d FS: %2d "
+ "SIGHAND: %2d IO: %2d SYSVSEM: %2d INV: %2d\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");
+ exit(ret);
+ }
+
+ waitpid(pid2, &status, P_ALL);
+
+ return 0;
+}
Index: linux-2.6.git/tools/testing/selftests/run_tests
===================================================================
--- linux-2.6.git.orig/tools/testing/selftests/run_tests
+++ linux-2.6.git/tools/testing/selftests/run_tests
@@ -1,6 +1,6 @@
#!/bin/bash
-TARGETS=breakpoints
+TARGETS="breakpoints kcmp"
for TARGET in $TARGETS
do