2 files changed, 216 insertions, 1 deletions

diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 58afc04c107e..513df75d0fc9 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_PRCTL_H
 #define _LINUX_PRCTL_H
 
+#include <linux/types.h>
+
 /* Values to pass as first argument to prctl() */
 
 #define PR_SET_PDEATHSIG  1  /* Second arg is a signal */
@@ -119,6 +121,31 @@
 # define PR_SET_MM_ENV_END		11
 # define PR_SET_MM_AUXV			12
 # define PR_SET_MM_EXE_FILE		13
+# define PR_SET_MM_MAP			14
+# define PR_SET_MM_MAP_SIZE		15
+
+/*
+ * This structure provides new memory descriptor
+ * map which mostly modifies /proc/pid/stat[m]
+ * output for a task. This mostly done in a
+ * sake of checkpoint/restore functionality.
+ */
+struct prctl_mm_map {
+	__u64	start_code;		/* code section bounds */
+	__u64	end_code;
+	__u64	start_data;		/* data section bounds */
+	__u64	end_data;
+	__u64	start_brk;		/* heap for brk() syscall */
+	__u64	brk;
+	__u64	start_stack;		/* stack starts at */
+	__u64	arg_start;		/* command line arguments bounds */
+	__u64	arg_end;
+	__u64	env_start;		/* environment variables bounds */
+	__u64	env_end;
+	__u64	*auxv;			/* auxiliary vector */
+	__u32	auxv_size;		/* vector size */
+	__u32	exe_fd;			/* /proc/$pid/exe link file */
+};
 
 /*
  * Set specific pid that is allowed to ptrace the current task.
diff --git a/kernel/sys.c b/kernel/sys.c
index 14222a1699c0..f7030b060018 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1687,6 +1687,187 @@ exit:
 	return err;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+/*
+ * WARNING: we don't require any capability here so be very careful
+ * in what is allowed for modification from userspace.
+ */
+static int validate_prctl_map(struct prctl_mm_map *prctl_map)
+{
+	unsigned long mmap_max_addr = TASK_SIZE;
+	struct mm_struct *mm = current->mm;
+	int error = -EINVAL, i;
+
+	static const unsigned char offsets[] = {
+		offsetof(struct prctl_mm_map, start_code),
+		offsetof(struct prctl_mm_map, end_code),
+		offsetof(struct prctl_mm_map, start_data),
+		offsetof(struct prctl_mm_map, end_data),
+		offsetof(struct prctl_mm_map, start_brk),
+		offsetof(struct prctl_mm_map, brk),
+		offsetof(struct prctl_mm_map, start_stack),
+		offsetof(struct prctl_mm_map, arg_start),
+		offsetof(struct prctl_mm_map, arg_end),
+		offsetof(struct prctl_mm_map, env_start),
+		offsetof(struct prctl_mm_map, env_end),
+	};
+
+	/*
+	 * Make sure the members are not somewhere outside
+	 * of allowed address space.
+	 */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		u64 val = *(u64 *)((char *)prctl_map + offsets[i]);
+
+		if ((unsigned long)val >= mmap_max_addr ||
+		    (unsigned long)val < mmap_min_addr)
+			goto out;
+	}
+
+	/*
+	 * Make sure the pairs are ordered.
+	 */
+#define __prctl_check_order(__m1, __op, __m2)				\
+	((unsigned long)prctl_map->__m1 __op				\
+	 (unsigned long)prctl_map->__m2) ? 0 : -EINVAL
+	error  = __prctl_check_order(start_code, <, end_code);
+	error |= __prctl_check_order(start_data, <, end_data);
+	error |= __prctl_check_order(start_brk, <=, brk);
+	error |= __prctl_check_order(arg_start, <=, arg_end);
+	error |= __prctl_check_order(env_start, <=, env_end);
+	if (error)
+		goto out;
+#undef __prctl_check_order
+
+	error = -EINVAL;
+
+	/*
+	 * @brk should be after @end_data in traditional maps.
+	 */
+	if (prctl_map->start_brk <= prctl_map->end_data ||
+	    prctl_map->brk <= prctl_map->end_data)
+		goto out;
+
+	/*
+	 * Neither we should allow to override limits if they set.
+	 */
+	if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk,
+			      prctl_map->start_brk, prctl_map->end_data,
+			      prctl_map->start_data))
+			goto out;
+
+	/*
+	 * Someone is trying to cheat the auxv vector.
+	 */
+	if (prctl_map->auxv_size) {
+		if (!prctl_map->auxv || prctl_map->auxv_size > sizeof(mm->saved_auxv))
+			goto out;
+	}
+
+	/*
+	 * Finally, make sure the caller has the rights to
+	 * change /proc/pid/exe link: only local root should
+	 * be allowed to.
+	 */
+	if (prctl_map->exe_fd != (u32)-1) {
+		struct user_namespace *ns = current_user_ns();
+		const struct cred *cred = current_cred();
+
+		if (!uid_eq(cred->uid, make_kuid(ns, 0)) ||
+		    !gid_eq(cred->gid, make_kgid(ns, 0)))
+			goto out;
+	}
+
+	error = 0;
+out:
+	return error;
+}
+
+static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size)
+{
+	struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, };
+	unsigned long user_auxv[AT_VECTOR_SIZE];
+	struct mm_struct *mm = current->mm;
+	int error;
+
+	BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+	BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256);
+
+	if (opt == PR_SET_MM_MAP_SIZE)
+		return put_user((unsigned int)sizeof(prctl_map),
+				(unsigned int __user *)addr);
+
+	if (data_size != sizeof(prctl_map))
+		return -EINVAL;
+
+	if (copy_from_user(&prctl_map, addr, sizeof(prctl_map)))
+		return -EFAULT;
+
+	error = validate_prctl_map(&prctl_map);
+	if (error)
+		return error;
+
+	if (prctl_map.auxv_size) {
+		memset(user_auxv, 0, sizeof(user_auxv));
+		if (copy_from_user(user_auxv,
+				   (const void __user *)prctl_map.auxv,
+				   prctl_map.auxv_size))
+			return -EFAULT;
+
+		/* Last entry must be AT_NULL as specification requires */
+		user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL;
+		user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
+	}
+
+	down_write(&mm->mmap_sem);
+	if (prctl_map.exe_fd != (u32)-1)
+		error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd);
+	downgrade_write(&mm->mmap_sem);
+	if (error)
+		goto out;
+
+	/*
+	 * We don't validate if these members are pointing to
+	 * real present VMAs because application may have correspond
+	 * VMAs already unmapped and kernel uses these members for statistics
+	 * output in procfs mostly, except
+	 *
+	 *  - @start_brk/@brk which are used in do_brk but kernel lookups
+	 *    for VMAs when updating these memvers so anything wrong written
+	 *    here cause kernel to swear at userspace program but won't lead
+	 *    to any problem in kernel itself
+	 */
+
+	mm->start_code	= prctl_map.start_code;
+	mm->end_code	= prctl_map.end_code;
+	mm->start_data	= prctl_map.start_data;
+	mm->end_data	= prctl_map.end_data;
+	mm->start_brk	= prctl_map.start_brk;
+	mm->brk		= prctl_map.brk;
+	mm->start_stack	= prctl_map.start_stack;
+	mm->arg_start	= prctl_map.arg_start;
+	mm->arg_end	= prctl_map.arg_end;
+	mm->env_start	= prctl_map.env_start;
+	mm->env_end	= prctl_map.env_end;
+
+	/*
+	 * Note this update of @saved_auxv is lockless thus
+	 * if someone reads this member in procfs while we're
+	 * updating -- it may get partly updated results. It's
+	 * known and acceptable trade off: we leave it as is to
+	 * not introduce additional locks here making the kernel
+	 * more complex.
+	 */
+	if (prctl_map.auxv_size)
+		memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
+
+	error = 0;
+out:
+	up_read(&mm->mmap_sem);
+	return error;
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
@@ -1694,9 +1875,16 @@ static int prctl_set_mm(int opt, unsigned long addr,
 	struct vm_area_struct *vma;
 	int error;
 
-	if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
+	if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV &&
+			      opt != PR_SET_MM_MAP &&
+			      opt != PR_SET_MM_MAP_SIZE)))
 		return -EINVAL;
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE)
+		return prctl_set_mm_map(opt, (const void __user *)addr, arg4);
+#endif
+
 	if (!capable(CAP_SYS_RESOURCE))
 		return -EPERM;