summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorChristian Brauner <brauner@kernel.org>2024-02-12 16:32:38 +0100
committerChristian Brauner <brauner@kernel.org>2024-03-01 12:23:37 +0100
commitcb12fd8e0dabb9a1c8aef55a6a41e2c255fcdf4b (patch)
treee5e957643dfd8dff83de3eec242e69678463cdbd /kernel
parentpidfd: move struct pidfd_fops (diff)
downloadlinux-cb12fd8e0dabb9a1c8aef55a6a41e2c255fcdf4b.tar.xz
linux-cb12fd8e0dabb9a1c8aef55a6a41e2c255fcdf4b.zip
pidfd: add pidfs
This moves pidfds from the anonymous inode infrastructure to a tiny pseudo filesystem. This has been on my todo for quite a while as it will unblock further work that we weren't able to do simply because of the very justified limitations of anonymous inodes. Moving pidfds to a tiny pseudo filesystem allows: * statx() on pidfds becomes useful for the first time. * pidfds can be compared simply via statx() and then comparing inode numbers. * pidfds have unique inode numbers for the system lifetime. * struct pid is now stashed in inode->i_private instead of file->private_data. This means it is now possible to introduce concepts that operate on a process once all file descriptors have been closed. A concrete example is kill-on-last-close. * file->private_data is freed up for per-file options for pidfds. * Each struct pid will refer to a different inode but the same struct pid will refer to the same inode if it's opened multiple times. In contrast to now where each struct pid refers to the same inode. Even if we were to move to anon_inode_create_getfile() which creates new inodes we'd still be associating the same struct pid with multiple different inodes. The tiny pseudo filesystem is not visible anywhere in userspace exactly like e.g., pipefs and sockfs. There's no lookup, there's no complex inode operations, nothing. Dentries and inodes are always deleted when the last pidfd is closed. We allocate a new inode for each struct pid and we reuse that inode for all pidfds. We use iget_locked() to find that inode again based on the inode number which isn't recycled. We allocate a new dentry for each pidfd that uses the same inode. That is similar to anonymous inodes which reuse the same inode for thousands of dentries. For pidfds we're talking way less than that. There usually won't be a lot of concurrent openers of the same struct pid. They can probably often be counted on two hands. I know that systemd does use separate pidfd for the same struct pid for various complex process tracking issues. So I think with that things actually become way simpler. Especially because we don't have to care about lookup. Dentries and inodes continue to be always deleted. The code is entirely optional and fairly small. If it's not selected we fallback to anonymous inodes. Heavily inspired by nsfs which uses a similar stashing mechanism just for namespaces. Link: https://lore.kernel.org/r/20240213-vfs-pidfd_fs-v1-2-f863f58cfce1@kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/fork.c13
-rw-r--r--kernel/nsproxy.c2
-rw-r--r--kernel/pid.c11
3 files changed, 14 insertions, 12 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 662a61f340ce..2f839c290dcf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -102,6 +102,7 @@
#include <linux/iommu.h>
#include <linux/rseq.h>
#include <uapi/linux/pidfd.h>
+#include <linux/pidfs.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
@@ -1985,14 +1986,6 @@ static inline void rcu_copy_process(struct task_struct *p)
#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
}
-struct pid *pidfd_pid(const struct file *file)
-{
- if (file->f_op == &pidfd_fops)
- return file->private_data;
-
- return ERR_PTR(-EBADF);
-}
-
/**
* __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
* @pid: the struct pid for which to create a pidfd
@@ -2030,13 +2023,11 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
if (pidfd < 0)
return pidfd;
- pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
- flags | O_RDWR);
+ pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
if (IS_ERR(pidfd_file)) {
put_unused_fd(pidfd);
return PTR_ERR(pidfd_file);
}
- get_pid(pid); /* held by pidfd_file now */
/*
* anon_inode_getfile() ignores everything outside of the
* O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually.
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 15781acaac1c..6ec3deec68c2 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -573,7 +573,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags)
if (proc_ns_file(f.file))
err = validate_ns(&nsset, ns);
else
- err = validate_nsset(&nsset, f.file->private_data);
+ err = validate_nsset(&nsset, pidfd_pid(f.file));
if (!err) {
commit_nsset(&nsset);
perf_event_namespaces(current);
diff --git a/kernel/pid.c b/kernel/pid.c
index c1d940fbd314..581cc34341fd 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -42,6 +42,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/idr.h>
+#include <linux/pidfs.h>
#include <net/sock.h>
#include <uapi/linux/pidfd.h>
@@ -65,6 +66,13 @@ int pid_max = PID_MAX_DEFAULT;
int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;
+#ifdef CONFIG_FS_PID
+/*
+ * Pseudo filesystems start inode numbering after one. We use Reserved
+ * PIDs as a natural offset.
+ */
+static u64 pidfs_ino = RESERVED_PIDS;
+#endif
/*
* PID-map pages start out as NULL, they get allocated upon
@@ -272,6 +280,9 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
spin_lock_irq(&pidmap_lock);
if (!(ns->pid_allocated & PIDNS_ADDING))
goto out_unlock;
+#ifdef CONFIG_FS_PID
+ pid->ino = ++pidfs_ino;
+#endif
for ( ; upid >= pid->numbers; --upid) {
/* Make the PID visible to find_pid_ns. */
idr_replace(&upid->ns->idr, pid, upid->nr);