[Devel] [PATCH 3/6] cr: capabilities: define checkpoint and restore fns

[Serge E. Hallyn]

An application checkpoint image will store capability sets
(and the bounding set) as __u64s.  Define checkpoint and
restart functions to translate between those and kernel_cap_t's.

Define a common function do_capset_tocred() which applies capability
set changes to a passed-in struct cred.

The restore function uses do_capset_tocred() to apply the restored
capabilities to the struct cred being crafted, subject to the
current task's (task executing sys_restart()) permissions.

TODO: one day we'll want to c/r the securebits as well.

Signed-off-by: Serge E. Hallyn <serue at us.ibm.com>
---
 include/linux/capability.h |    5 ++
 kernel/capability.c        |   94 +++++++++++++++++++++++++++++++++++++------
 2 files changed, 86 insertions(+), 13 deletions(-)

diff --git a/include/linux/capability.h b/include/linux/capability.h
index c302110..572b5a0 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -536,6 +536,11 @@ extern const kernel_cap_t __cap_empty_set;
 extern const kernel_cap_t __cap_full_set;
 extern const kernel_cap_t __cap_init_eff_set;
 
+extern void checkpoint_save_cap(__u64 *dest, kernel_cap_t src);
+struct cred;
+extern int checkpoint_restore_cap(__u64 e, __u64 i, __u64 p, __u64 x,
+				struct cred *cred);
+
 /**
  * has_capability - Determine if a task has a superior capability available
  * @t: The task in question
diff --git a/kernel/capability.c b/kernel/capability.c
index 4e17041..d2c9bb3 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -217,6 +217,45 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
 	return ret;
 }
 
+static int do_capset_tocred(kernel_cap_t *effective, kernel_cap_t *inheritable,
+			kernel_cap_t *permitted, struct cred *new)
+{
+	int ret;
+
+	ret = security_capset(new, current_cred(),
+			      effective, inheritable, permitted);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * for checkpoint-restart, do we want to wait until end of restart?
+	 * not sure we care */
+	audit_log_capset(current->pid, new, current_cred());
+
+	return 0;
+}
+
+static int do_capset(kernel_cap_t *effective, kernel_cap_t *inheritable,
+			kernel_cap_t *permitted)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = do_capset_tocred(effective, inheritable, permitted, new);
+	if (ret < 0)
+		goto error;
+
+	return commit_creds(new);
+
+error:
+	abort_creds(new);
+	return ret;
+}
+
 /**
  * sys_capset - set capabilities for a process or (*) a group of processes
  * @header: pointer to struct that contains capability version and
@@ -240,7 +279,6 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
 	unsigned i, tocopy;
 	kernel_cap_t inheritable, permitted, effective;
-	struct cred *new;
 	int ret;
 	pid_t pid;
 
@@ -271,22 +309,52 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 		i++;
 	}
 
-	new = prepare_creds();
-	if (!new)
-		return -ENOMEM;
+	return do_capset(&effective, &inheritable, &permitted);
 
-	ret = security_capset(new, current_cred(),
-			      &effective, &inheritable, &permitted);
-	if (ret < 0)
-		goto error;
+}
 
-	audit_log_capset(pid, new, current_cred());
 
-	return commit_creds(new);
+void checkpoint_save_cap(__u64 *dest, kernel_cap_t src)
+{
+	*dest = src.cap[0] | (src.cap[1] << sizeof(__u32));
+}
 
-error:
-	abort_creds(new);
-	return ret;
+static void do_capbset_drop(struct cred *cred, int cap)
+{
+	cap_lower(cred->cap_bset, cap);
+}
+
+int checkpoint_restore_cap(__u64 newe, __u64 newi, __u64 newp, __u64 newx,
+			struct cred *cred)
+{
+	kernel_cap_t effective, inheritable, permitted, bset;
+	int may_dropbcap = capable(CAP_SETPCAP);
+	int ret, i;
+
+	effective.cap[0] = newe;
+	effective.cap[1] = (newe >> sizeof(__u32));
+	inheritable.cap[0] = newi;
+	inheritable.cap[1] = (newi >> sizeof(__u32));
+	permitted.cap[0] = newp;
+	permitted.cap[1] = (newp >> sizeof(__u32));
+	bset.cap[0] = newx;
+	bset.cap[1] = (newx >> sizeof(__u32));
+
+	ret = do_capset_tocred(&effective, &inheritable, &permitted, cred);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < CAP_LAST_CAP; i++) {
+		if (cap_raised(bset, i))
+			continue;
+		if (!cap_raised(current_cred()->cap_bset, i))
+			continue;
+		if (!may_dropbcap)
+			return -EPERM;
+		do_capbset_drop(cred, i);
+	}
+
+	return 0;
 }
 
 /**
-- 
1.6.1

_______________________________________________
Containers mailing list
Containers at lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers