update vendor
Signed-off-by: Jess Frazelle <acidburn@microsoft.com>
This commit is contained in:
parent
19a32db84d
commit
94d1cfbfbf
10501 changed files with 2307943 additions and 29279 deletions
6
vendor/github.com/opencontainers/runc/libcontainer/nsenter/README.md
generated
vendored
6
vendor/github.com/opencontainers/runc/libcontainer/nsenter/README.md
generated
vendored
|
@ -10,8 +10,8 @@ The `nsenter` package will `import "C"` and it uses [cgo](https://golang.org/cmd
|
|||
package. In cgo, if the import of "C" is immediately preceded by a comment, that comment,
|
||||
called the preamble, is used as a header when compiling the C parts of the package.
|
||||
So every time we import package `nsenter`, the C code function `nsexec()` would be
|
||||
called. And package `nsenter` is now only imported in `main_unix.go`, so every time
|
||||
before we call `cmd.Start` on linux, that C code would run.
|
||||
called. And package `nsenter` is only imported in `init.go`, so every time the runc
|
||||
`init` command is invoked, that C code is run.
|
||||
|
||||
Because `nsexec()` must be run before the Go runtime in order to use the
|
||||
Linux kernel namespace, you must `import` this library into a package if
|
||||
|
@ -37,7 +37,7 @@ the parent `nsexec()` will exit and the child `nsexec()` process will
|
|||
return to allow the Go runtime take over.
|
||||
|
||||
NOTE: We do both `setns(2)` and `clone(2)` even if we don't have any
|
||||
CLONE_NEW* clone flags because we must fork a new process in order to
|
||||
`CLONE_NEW*` clone flags because we must fork a new process in order to
|
||||
enter the PID namespace.
|
||||
|
||||
|
||||
|
|
65
vendor/github.com/opencontainers/runc/libcontainer/nsenter/nsexec.c
generated
vendored
65
vendor/github.com/opencontainers/runc/libcontainer/nsenter/nsexec.c
generated
vendored
|
@ -211,7 +211,7 @@ static int try_mapping_tool(const char *app, int pid, char *map, size_t map_len)
|
|||
|
||||
/*
|
||||
* If @app is NULL, execve will segfault. Just check it here and bail (if
|
||||
* we're in this path, the caller is already getting desparate and there
|
||||
* we're in this path, the caller is already getting desperate and there
|
||||
* isn't a backup to this failing). This usually would be a configuration
|
||||
* or programming issue.
|
||||
*/
|
||||
|
@ -505,7 +505,8 @@ void join_namespaces(char *nslist)
|
|||
|
||||
ns->fd = fd;
|
||||
ns->ns = nsflag(namespace);
|
||||
strncpy(ns->path, path, PATH_MAX);
|
||||
strncpy(ns->path, path, PATH_MAX - 1);
|
||||
ns->path[PATH_MAX - 1] = '\0';
|
||||
} while ((namespace = strtok_r(NULL, ",", &saveptr)) != NULL);
|
||||
|
||||
/*
|
||||
|
@ -678,17 +679,15 @@ void nsexec(void)
|
|||
/*
|
||||
* Enable setgroups(2) if we've been asked to. But we also
|
||||
* have to explicitly disable setgroups(2) if we're
|
||||
* creating a rootless container (this is required since
|
||||
* Linux 3.19).
|
||||
* creating a rootless container for single-entry mapping.
|
||||
* i.e. config.is_setgroup == false.
|
||||
* (this is required since Linux 3.19).
|
||||
*
|
||||
* For rootless multi-entry mapping, config.is_setgroup shall be true and
|
||||
* newuidmap/newgidmap shall be used.
|
||||
*/
|
||||
if (config.is_rootless && config.is_setgroup) {
|
||||
kill(child, SIGKILL);
|
||||
bail("cannot allow setgroup in an unprivileged user namespace setup");
|
||||
}
|
||||
|
||||
if (config.is_setgroup)
|
||||
update_setgroups(child, SETGROUPS_ALLOW);
|
||||
if (config.is_rootless)
|
||||
if (config.is_rootless && !config.is_setgroup)
|
||||
update_setgroups(child, SETGROUPS_DENY);
|
||||
|
||||
/* Set up mappings. */
|
||||
|
@ -809,25 +808,30 @@ void nsexec(void)
|
|||
if (config.namespaces)
|
||||
join_namespaces(config.namespaces);
|
||||
|
||||
/*
|
||||
* Unshare all of the namespaces. Now, it should be noted that this
|
||||
* ordering might break in the future (especially with rootless
|
||||
* containers). But for now, it's not possible to split this into
|
||||
* CLONE_NEWUSER + [the rest] because of some RHEL SELinux issues.
|
||||
*
|
||||
* Note that we don't merge this with clone() because there were
|
||||
* some old kernel versions where clone(CLONE_PARENT | CLONE_NEWPID)
|
||||
* was broken, so we'll just do it the long way anyway.
|
||||
*/
|
||||
if (unshare(config.cloneflags) < 0)
|
||||
bail("failed to unshare namespaces");
|
||||
|
||||
/*
|
||||
* Deal with user namespaces first. They are quite special, as they
|
||||
* affect our ability to unshare other namespaces and are used as
|
||||
* context for privilege checks.
|
||||
*
|
||||
* We don't unshare all namespaces in one go. The reason for this
|
||||
* is that, while the kernel documentation may claim otherwise,
|
||||
* there are certain cases where unsharing all namespaces at once
|
||||
* will result in namespace objects being owned incorrectly.
|
||||
* Ideally we should just fix these kernel bugs, but it's better to
|
||||
* be safe than sorry, and fix them separately.
|
||||
*
|
||||
* A specific case of this is that the SELinux label of the
|
||||
* internal kern-mount that mqueue uses will be incorrect if the
|
||||
* UTS namespace is cloned before the USER namespace is mapped.
|
||||
* I've also heard of similar problems with the network namespace
|
||||
* in some scenarios. This also mirrors how LXC deals with this
|
||||
* problem.
|
||||
*/
|
||||
if (config.cloneflags & CLONE_NEWUSER) {
|
||||
if (unshare(CLONE_NEWUSER) < 0)
|
||||
bail("failed to unshare user namespace");
|
||||
config.cloneflags &= ~CLONE_NEWUSER;
|
||||
|
||||
/*
|
||||
* We don't have the privileges to do any mapping here (see the
|
||||
* clone_parent rant). So signal our parent to hook us up.
|
||||
|
@ -853,8 +857,21 @@ void nsexec(void)
|
|||
if (prctl(PR_SET_DUMPABLE, 0, 0, 0, 0) < 0)
|
||||
bail("failed to set process as dumpable");
|
||||
}
|
||||
|
||||
/* Become root in the namespace proper. */
|
||||
if (setresuid(0, 0, 0) < 0)
|
||||
bail("failed to become root in user namespace");
|
||||
}
|
||||
|
||||
/*
|
||||
* Unshare all of the namespaces. Note that we don't merge this
|
||||
* with clone() because there were some old kernel versions where
|
||||
* clone(CLONE_PARENT | CLONE_NEWPID) was broken, so we'll just do
|
||||
* it the long way.
|
||||
*/
|
||||
if (unshare(config.cloneflags) < 0)
|
||||
bail("failed to unshare namespaces");
|
||||
|
||||
/*
|
||||
* TODO: What about non-namespace clone flags that we're dropping here?
|
||||
*
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue