summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorCyrill Gorcunov <gorcunov@openvz.org>2012-05-31 16:26:45 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-05-31 17:49:32 -0700
commitfe8c7f5cbf91124987106faa3bdf0c8b955c4cf7 (patch)
tree3ddb0013465d7cd09ef6bc2fab18cb59055a309b
parent5b172087f99189416d5f47fd7ab5e6fb762a9ba3 (diff)
downloadlinux-fe8c7f5cbf91124987106faa3bdf0c8b955c4cf7.tar.bz2
c/r: prctl: extend PR_SET_MM to set up more mm_struct entries
During checkpoint we dump whole process memory to a file and the dump includes process stack memory. But among stack data itself, the stack carries additional parameters such as command line arguments, environment data and auxiliary vector. So when we do restore procedure and once we've restored stack data itself we need to setup mm_struct::arg_start/end, env_start/end, so restored process would be able to find command line arguments and environment data it had at checkpoint time. The same applies to auxiliary vector. For this reason additional PR_SET_MM_(ARG_START | ARG_END | ENV_START | ENV_END | AUXV) codes are introduced. Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Acked-by: Kees Cook <keescook@chromium.org> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Vagin <avagin@openvz.org> Cc: Serge Hallyn <serge.hallyn@canonical.com> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Vasiliy Kulikov <segoon@openwall.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/prctl.h5
-rw-r--r--kernel/sys.c134
2 files changed, 88 insertions, 51 deletions
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index 78b76e24cc7e..18d84c4b42d8 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -113,6 +113,11 @@
# define PR_SET_MM_START_STACK 5
# define PR_SET_MM_START_BRK 6
# define PR_SET_MM_BRK 7
+# define PR_SET_MM_ARG_START 8
+# define PR_SET_MM_ARG_END 9
+# define PR_SET_MM_ENV_START 10
+# define PR_SET_MM_ENV_END 11
+# define PR_SET_MM_AUXV 12
/*
* Set specific pid that is allowed to ptrace the current task.
diff --git a/kernel/sys.c b/kernel/sys.c
index 6e81aa7e4688..8b544972e46e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1784,17 +1784,23 @@ SYSCALL_DEFINE1(umask, int, mask)
}
#ifdef CONFIG_CHECKPOINT_RESTORE
+static bool vma_flags_mismatch(struct vm_area_struct *vma,
+ unsigned long required,
+ unsigned long banned)
+{
+ return (vma->vm_flags & required) != required ||
+ (vma->vm_flags & banned);
+}
+
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
unsigned long rlim = rlimit(RLIMIT_DATA);
- unsigned long vm_req_flags;
- unsigned long vm_bad_flags;
- struct vm_area_struct *vma;
- int error = 0;
struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int error;
- if (arg4 | arg5)
+ if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
return -EINVAL;
if (!capable(CAP_SYS_RESOURCE))
@@ -1803,58 +1809,23 @@ static int prctl_set_mm(int opt, unsigned long addr,
if (addr >= TASK_SIZE)
return -EINVAL;
+ error = -EINVAL;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, addr);
- if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) {
- /* It must be existing VMA */
- if (!vma || vma->vm_start > addr)
- goto out;
- }
-
- error = -EINVAL;
switch (opt) {
case PR_SET_MM_START_CODE:
+ mm->start_code = addr;
+ break;
case PR_SET_MM_END_CODE:
- vm_req_flags = VM_READ | VM_EXEC;
- vm_bad_flags = VM_WRITE | VM_MAYSHARE;
-
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
- (vma->vm_flags & vm_bad_flags))
- goto out;
-
- if (opt == PR_SET_MM_START_CODE)
- mm->start_code = addr;
- else
- mm->end_code = addr;
+ mm->end_code = addr;
break;
-
case PR_SET_MM_START_DATA:
- case PR_SET_MM_END_DATA:
- vm_req_flags = VM_READ | VM_WRITE;
- vm_bad_flags = VM_EXEC | VM_MAYSHARE;
-
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
- (vma->vm_flags & vm_bad_flags))
- goto out;
-
- if (opt == PR_SET_MM_START_DATA)
- mm->start_data = addr;
- else
- mm->end_data = addr;
+ mm->start_data = addr;
break;
-
- case PR_SET_MM_START_STACK:
-
-#ifdef CONFIG_STACK_GROWSUP
- vm_req_flags = VM_READ | VM_WRITE | VM_GROWSUP;
-#else
- vm_req_flags = VM_READ | VM_WRITE | VM_GROWSDOWN;
-#endif
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags)
- goto out;
-
- mm->start_stack = addr;
+ case PR_SET_MM_END_DATA:
+ mm->end_data = addr;
break;
case PR_SET_MM_START_BRK:
@@ -1881,16 +1852,77 @@ static int prctl_set_mm(int opt, unsigned long addr,
mm->brk = addr;
break;
+ /*
+ * If command line arguments and environment
+ * are placed somewhere else on stack, we can
+ * set them up here, ARG_START/END to setup
+ * command line argumets and ENV_START/END
+ * for environment.
+ */
+ case PR_SET_MM_START_STACK:
+ case PR_SET_MM_ARG_START:
+ case PR_SET_MM_ARG_END:
+ case PR_SET_MM_ENV_START:
+ case PR_SET_MM_ENV_END:
+ if (!vma) {
+ error = -EFAULT;
+ goto out;
+ }
+#ifdef CONFIG_STACK_GROWSUP
+ if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSUP, 0))
+#else
+ if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSDOWN, 0))
+#endif
+ goto out;
+ if (opt == PR_SET_MM_START_STACK)
+ mm->start_stack = addr;
+ else if (opt == PR_SET_MM_ARG_START)
+ mm->arg_start = addr;
+ else if (opt == PR_SET_MM_ARG_END)
+ mm->arg_end = addr;
+ else if (opt == PR_SET_MM_ENV_START)
+ mm->env_start = addr;
+ else if (opt == PR_SET_MM_ENV_END)
+ mm->env_end = addr;
+ break;
+
+ /*
+ * This doesn't move auxiliary vector itself
+ * since it's pinned to mm_struct, but allow
+ * to fill vector with new values. It's up
+ * to a caller to provide sane values here
+ * otherwise user space tools which use this
+ * vector might be unhappy.
+ */
+ case PR_SET_MM_AUXV: {
+ unsigned long user_auxv[AT_VECTOR_SIZE];
+
+ if (arg4 > sizeof(user_auxv))
+ goto out;
+ up_read(&mm->mmap_sem);
+
+ if (copy_from_user(user_auxv, (const void __user *)addr, arg4))
+ return -EFAULT;
+
+ /* Make sure the last entry is always AT_NULL */
+ user_auxv[AT_VECTOR_SIZE - 2] = 0;
+ user_auxv[AT_VECTOR_SIZE - 1] = 0;
+
+ BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+
+ task_lock(current);
+ memcpy(mm->saved_auxv, user_auxv, arg4);
+ task_unlock(current);
+
+ return 0;
+ }
default:
- error = -EINVAL;
goto out;
}
error = 0;
-
out:
up_read(&mm->mmap_sem);
-
return error;
}
#else /* CONFIG_CHECKPOINT_RESTORE */