summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-01-30 06:38:34 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-01-30 06:38:34 +0300
commit83fa805bcbfc53ae82eedd65132794ae324798e5 (patch)
treeff4b2ba048bb5f14194110aedb09c85aab159d4a /kernel
parent896f8d23d0cb5889021d66eab6107e97109c5459 (diff)
parent8d19f1c8e1937baf74e1962aae9f90fa3aeab463 (diff)
downloadlinux-83fa805bcbfc53ae82eedd65132794ae324798e5.tar.xz
Merge tag 'threads-v5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull thread management updates from Christian Brauner: "Sargun Dhillon over the last cycle has worked on the pidfd_getfd() syscall. This syscall allows for the retrieval of file descriptors of a process based on its pidfd. A task needs to have ptrace_may_access() permissions with PTRACE_MODE_ATTACH_REALCREDS (suggested by Oleg and Andy) on the target. One of the main use-cases is in combination with seccomp's user notification feature. As a reminder, seccomp's user notification feature was made available in v5.0. It allows a task to retrieve a file descriptor for its seccomp filter. The file descriptor is usually handed of to a more privileged supervising process. The supervisor can then listen for syscall events caught by the seccomp filter of the supervisee and perform actions in lieu of the supervisee, usually emulating syscalls. pidfd_getfd() is needed to expand its uses. There are currently two major users that wait on pidfd_getfd() and one future user: - Netflix, Sargun said, is working on a service mesh where users should be able to connect to a dns-based VIP. When a user connects to e.g. 1.2.3.4:80 that runs e.g. service "foo" they will be redirected to an envoy process. This service mesh uses seccomp user notifications and pidfd to intercept all connect calls and instead of connecting them to 1.2.3.4:80 connects them to e.g. 127.0.0.1:8080. - LXD uses the seccomp notifier heavily to intercept and emulate mknod() and mount() syscalls for unprivileged containers/processes. With pidfd_getfd() more uses-cases e.g. bridging socket connections will be possible. - The patchset has also seen some interest from the browser corner. Right now, Firefox is using a SECCOMP_RET_TRAP sandbox managed by a broker process. In the future glibc will start blocking all signals during dlopen() rendering this type of sandbox impossible. Hence, in the future Firefox will switch to a seccomp-user-nofication based sandbox which also makes use of file descriptor retrieval. The thread for this can be found at https://sourceware.org/ml/libc-alpha/2019-12/msg00079.html With pidfd_getfd() it is e.g. possible to bridge socket connections for the supervisee (binding to a privileged port) and taking actions on file descriptors on behalf of the supervisee in general. Sargun's first version was using an ioctl on pidfds but various people pushed for it to be a proper syscall which he duely implemented as well over various review cycles. Selftests are of course included. I've also added instructions how to deal with merge conflicts below. There's also a small fix coming from the kernel mentee project to correctly annotate struct sighand_struct with __rcu to fix various sparse warnings. We've received a few more such fixes and even though they are mostly trivial I've decided to postpone them until after -rc1 since they came in rather late and I don't want to risk introducing build warnings. Finally, there's a new prctl() command PR_{G,S}ET_IO_FLUSHER which is needed to avoid allocation recursions triggerable by storage drivers that have userspace parts that run in the IO path (e.g. dm-multipath, iscsi, etc). These allocation recursions deadlock the device. The new prctl() allows such privileged userspace components to avoid allocation recursions by setting the PF_MEMALLOC_NOIO and PF_LESS_THROTTLE flags. The patch carries the necessary acks from the relevant maintainers and is routed here as part of prctl() thread-management." * tag 'threads-v5.6' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux: prctl: PR_{G,S}ET_IO_FLUSHER to support controlling memory reclaim sched.h: Annotate sighand_struct with __rcu test: Add test for pidfd getfd arch: wire up pidfd_getfd syscall pid: Implement pidfd_getfd syscall vfs, fdtable: Add fget_task helper
Diffstat (limited to 'kernel')
-rw-r--r--kernel/pid.c90
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/sys.c25
3 files changed, 116 insertions, 1 deletions
diff --git a/kernel/pid.c b/kernel/pid.c
index 2278e249141d..0f4ecb57214c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -578,3 +578,93 @@ void __init pid_idr_init(void)
init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
}
+
+static struct file *__pidfd_fget(struct task_struct *task, int fd)
+{
+ struct file *file;
+ int ret;
+
+ ret = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
+ file = fget_task(task, fd);
+ else
+ file = ERR_PTR(-EPERM);
+
+ mutex_unlock(&task->signal->cred_guard_mutex);
+
+ return file ?: ERR_PTR(-EBADF);
+}
+
+static int pidfd_getfd(struct pid *pid, int fd)
+{
+ struct task_struct *task;
+ struct file *file;
+ int ret;
+
+ task = get_pid_task(pid, PIDTYPE_PID);
+ if (!task)
+ return -ESRCH;
+
+ file = __pidfd_fget(task, fd);
+ put_task_struct(task);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ ret = security_file_receive(file);
+ if (ret) {
+ fput(file);
+ return ret;
+ }
+
+ ret = get_unused_fd_flags(O_CLOEXEC);
+ if (ret < 0)
+ fput(file);
+ else
+ fd_install(ret, file);
+
+ return ret;
+}
+
+/**
+ * sys_pidfd_getfd() - Get a file descriptor from another process
+ *
+ * @pidfd: the pidfd file descriptor of the process
+ * @fd: the file descriptor number to get
+ * @flags: flags on how to get the fd (reserved)
+ *
+ * This syscall gets a copy of a file descriptor from another process
+ * based on the pidfd, and file descriptor number. It requires that
+ * the calling process has the ability to ptrace the process represented
+ * by the pidfd. The process which is having its file descriptor copied
+ * is otherwise unaffected.
+ *
+ * Return: On success, a cloexec file descriptor is returned.
+ * On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
+ unsigned int, flags)
+{
+ struct pid *pid;
+ struct fd f;
+ int ret;
+
+ /* flags is currently unused - make sure it's unset */
+ if (flags)
+ return -EINVAL;
+
+ f = fdget(pidfd);
+ if (!f.file)
+ return -EBADF;
+
+ pid = pidfd_pid(f.file);
+ if (IS_ERR(pid))
+ ret = PTR_ERR(pid);
+ else
+ ret = pidfd_getfd(pid, fd);
+
+ fdput(f);
+ return ret;
+}
diff --git a/kernel/signal.c b/kernel/signal.c
index bcd46f547db3..9ad8dea93dbb 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1383,7 +1383,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
* must see ->sighand == NULL.
*/
spin_lock_irqsave(&sighand->siglock, *flags);
- if (likely(sighand == tsk->sighand))
+ if (likely(sighand == rcu_access_pointer(tsk->sighand)))
break;
spin_unlock_irqrestore(&sighand->siglock, *flags);
}
diff --git a/kernel/sys.c b/kernel/sys.c
index a9331f101883..f9bc5c303e3f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2261,6 +2261,8 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
return -EINVAL;
}
+#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE)
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -2488,6 +2490,29 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = GET_TAGGED_ADDR_CTRL();
break;
+ case PR_SET_IO_FLUSHER:
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ if (arg2 == 1)
+ current->flags |= PR_IO_FLUSHER;
+ else if (!arg2)
+ current->flags &= ~PR_IO_FLUSHER;
+ else
+ return -EINVAL;
+ break;
+ case PR_GET_IO_FLUSHER:
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
+ break;
default:
error = -EINVAL;
break;