Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754242Ab2BPTwM (ORCPT ); Thu, 16 Feb 2012 14:52:12 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:36714 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751114Ab2BPTwL (ORCPT ); Thu, 16 Feb 2012 14:52:11 -0500 Date: Thu, 16 Feb 2012 11:52:08 -0800 From: Andrew Morton To: Cyrill Gorcunov Cc: Oleg Nesterov , Vasiliy Kulikov , "Eric W. Biederman" , Pavel Emelyanov , Andrey Vagin , KOSAKI Motohiro , Ingo Molnar , "H. Peter Anvin" , Thomas Gleixner , Glauber Costa , Andi Kleen , Tejun Heo , Matt Helsley , Pekka Enberg , Eric Dumazet , Alexey Dobriyan , Valdis.Kletnieks@vt.edu, Michal Marek , Frederic Weisbecker , linux-kernel@vger.kernel.org Subject: Re: + syscalls-x86-add-__nr_kcmp-syscall-v8.patch added to -mm tree Message-Id: <20120216115208.a488e10e.akpm@linux-foundation.org> In-Reply-To: <20120216192952.GN1905@moon> References: <20120215200533.GQ1894@moon> <20120215202538.GK4533@moon> <20120215210934.GL4533@moon> <20120215215807.GM4533@moon> <20120216144954.GA11953@redhat.com> <20120216151340.GI1905@moon> <20120216164901.GD3849@moon> <20120216174047.GA31176@redhat.com> <20120216175809.GJ1905@moon> <20120216190321.GA2216@redhat.com> <20120216192952.GN1905@moon> X-Mailer: Sylpheed 3.0.2 (GTK+ 2.20.1; x86_64-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 13044 Lines: 480 On Thu, 16 Feb 2012 23:29:52 +0400 Cyrill Gorcunov wrote: > Final one ;) syscalls-x86-add-__nr_kcmp-syscall-v8-fix-fix-fix-fix-fix.patch is a tie for the world record! I folded everything back into a single patch. Here's what we currently have: From: Cyrill Gorcunov Subject: 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] Signed-off-by: Cyrill Gorcunov Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Andrey Vagin Cc: KOSAKI Motohiro Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Thomas Gleixner Cc: Glauber Costa Cc: Andi Kleen Cc: Tejun Heo Cc: Matt Helsley Cc: Pekka Enberg Cc: Eric Dumazet Cc: Vasiliy Kulikov Cc: Alexey Dobriyan Cc: Valdis.Kletnieks@vt.edu Cc: Michal Marek Cc: Frederic Weisbecker Signed-off-by: Andrew Morton --- 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 | 186 +++++++++++++++++++++ kernel/sys_ni.c | 3 tools/testing/selftests/Makefile | 2 tools/testing/selftests/kcmp/Makefile | 29 +++ tools/testing/selftests/kcmp/kcmp_test.c | 94 ++++++++++ 10 files changed, 337 insertions(+), 1 deletion(-) diff -puN arch/x86/syscalls/syscall_32.tbl~syscalls-x86-add-__nr_kcmp-syscall-v8 arch/x86/syscalls/syscall_32.tbl --- a/arch/x86/syscalls/syscall_32.tbl~syscalls-x86-add-__nr_kcmp-syscall-v8 +++ a/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 diff -puN arch/x86/syscalls/syscall_64.tbl~syscalls-x86-add-__nr_kcmp-syscall-v8 arch/x86/syscalls/syscall_64.tbl --- a/arch/x86/syscalls/syscall_64.tbl~syscalls-x86-add-__nr_kcmp-syscall-v8 +++ a/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 diff -puN /dev/null include/linux/kcmp.h --- /dev/null +++ a/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 */ diff -puN include/linux/syscalls.h~syscalls-x86-add-__nr_kcmp-syscall-v8 include/linux/syscalls.h --- a/include/linux/syscalls.h~syscalls-x86-add-__nr_kcmp-syscall-v8 +++ a/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 diff -puN kernel/Makefile~syscalls-x86-add-__nr_kcmp-syscall-v8 kernel/Makefile --- a/kernel/Makefile~syscalls-x86-add-__nr_kcmp-syscall-v8 +++ a/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_STACKTRACE) += stacktrace.o diff -puN /dev/null kernel/kcmp.c --- /dev/null +++ a/kernel/kcmp.c @@ -0,0 +1,186 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* + * 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 file *file = NULL; + + task_lock(task); + rcu_read_lock(); + + if (task->files) + file = fcheck_files(task->files, idx); + + rcu_read_unlock(); + task_unlock(task); + + return file; +} + +static void kcmp_unlock(struct mutex *m1, struct mutex *m2) +{ + if (likely(m2 != m1)) + mutex_unlock(m2); + mutex_unlock(m1); +} + +static int kcmp_lock(struct mutex *m1, struct mutex *m2) +{ + int err; + + if (m2 > m1) + swap(m1, m2); + + err = mutex_lock_killable(m1); + if (!err && likely(m1 != m2)) { + err = mutex_lock_killable_nested(m2, SINGLE_DEPTH_NESTING); + if (err) + mutex_unlock(m1); + } + + return err; +} + +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. + */ + ret = kcmp_lock(&task1->signal->cred_guard_mutex, + &task2->signal->cred_guard_mutex); + if (ret) + goto err; + if (!ptrace_may_access(task1, PTRACE_MODE_READ) || + !ptrace_may_access(task2, PTRACE_MODE_READ)) { + ret = -EPERM; + goto err_unlock; + } + + 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_unlock: + kcmp_unlock(&task1->signal->cred_guard_mutex, + &task2->signal->cred_guard_mutex); +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) +{ + int i; + + get_random_bytes(cookies, sizeof(cookies)); + + for (i = 0; i < KCMP_TYPES; i++) + cookies[i][1] |= (~(~0UL >> 1) | 1); + + return 0; +} +arch_initcall(kcmp_cookies_init); diff -puN kernel/sys_ni.c~syscalls-x86-add-__nr_kcmp-syscall-v8 kernel/sys_ni.c --- a/kernel/sys_ni.c~syscalls-x86-add-__nr_kcmp-syscall-v8 +++ a/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); diff -puN /dev/null tools/testing/selftests/kcmp/Makefile --- /dev/null +++ a/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 -puN /dev/null tools/testing/selftests/kcmp/kcmp_test.c --- /dev/null +++ a/tools/testing/selftests/kcmp/kcmp_test.c @@ -0,0 +1,94 @@ +#define _GNU_SOURCE + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include +#include +#include + +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; +} diff -puN tools/testing/selftests/Makefile~syscalls-x86-add-__nr_kcmp-syscall-v8 tools/testing/selftests/Makefile --- a/tools/testing/selftests/Makefile~syscalls-x86-add-__nr_kcmp-syscall-v8 +++ a/tools/testing/selftests/Makefile @@ -1,4 +1,4 @@ -TARGETS = breakpoints vm +TARGETS = breakpoints vm kcmp all: for TARGET in $(TARGETS); do \ _ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/