Unverified Commit 50f4f2d1 authored by Christian Brauner's avatar Christian Brauner
Browse files

pidfd: move struct pidfd_fops 

Move the pidfd file operations over to their own file in preparation of
implementing pidfs and to isolate them from other mostly unrelated
functionality in other files.

Link: https://lore.kernel.org/r/20240213-vfs-pidfd_fs-v1-1-f863f58cfce1@kernel.org


Signed-off-by: default avatarChristian Brauner <brauner@kernel.org>
parent e1fb1dc0

fs/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -15,7 +15,7 @@ obj-y := open.o read_write.o file_table.o super.o \ 
		pnode.o splice.o sync.o utimes.o d_path.o \

		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \

		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \

		kernel_read_file.o mnt_idmapping.o remap_range.o

		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o



obj-$(CONFIG_BUFFER_HEAD)	+= buffer.o mpage.o

obj-$(CONFIG_PROC_FS)		+= proc_namespace.o

fs/pidfs.c

0 → 100644
+122 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0

#include <linux/file.h>

#include <linux/fs.h>

#include <linux/magic.h>

#include <linux/mount.h>

#include <linux/pid.h>

#include <linux/pid_namespace.h>

#include <linux/poll.h>

#include <linux/proc_fs.h>

#include <linux/proc_ns.h>

#include <linux/pseudo_fs.h>

#include <linux/seq_file.h>

#include <uapi/linux/pidfd.h>



static int pidfd_release(struct inode *inode, struct file *file)

{

	struct pid *pid = file->private_data;



	file->private_data = NULL;

	put_pid(pid);

	return 0;

}



#ifdef CONFIG_PROC_FS

/**

 * pidfd_show_fdinfo - print information about a pidfd

 * @m: proc fdinfo file

 * @f: file referencing a pidfd

 *

 * Pid:

 * This function will print the pid that a given pidfd refers to in the

 * pid namespace of the procfs instance.

 * If the pid namespace of the process is not a descendant of the pid

 * namespace of the procfs instance 0 will be shown as its pid. This is

 * similar to calling getppid() on a process whose parent is outside of

 * its pid namespace.

 *

 * NSpid:

 * If pid namespaces are supported then this function will also print

 * the pid of a given pidfd refers to for all descendant pid namespaces

 * starting from the current pid namespace of the instance, i.e. the

 * Pid field and the first entry in the NSpid field will be identical.

 * If the pid namespace of the process is not a descendant of the pid

 * namespace of the procfs instance 0 will be shown as its first NSpid

 * entry and no others will be shown.

 * Note that this differs from the Pid and NSpid fields in

 * /proc/<pid>/status where Pid and NSpid are always shown relative to

 * the  pid namespace of the procfs instance. The difference becomes

 * obvious when sending around a pidfd between pid namespaces from a

 * different branch of the tree, i.e. where no ancestral relation is

 * present between the pid namespaces:

 * - create two new pid namespaces ns1 and ns2 in the initial pid

 *   namespace (also take care to create new mount namespaces in the

 *   new pid namespace and mount procfs)

 * - create a process with a pidfd in ns1

 * - send pidfd from ns1 to ns2

 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid

 *   have exactly one entry, which is 0

 */

static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)

{

	struct pid *pid = f->private_data;

	struct pid_namespace *ns;

	pid_t nr = -1;



	if (likely(pid_has_task(pid, PIDTYPE_PID))) {

		ns = proc_pid_ns(file_inode(m->file)->i_sb);

		nr = pid_nr_ns(pid, ns);

	}



	seq_put_decimal_ll(m, "Pid:\t", nr);



#ifdef CONFIG_PID_NS

	seq_put_decimal_ll(m, "\nNSpid:\t", nr);

	if (nr > 0) {

		int i;



		/* If nr is non-zero it means that 'pid' is valid and that

		 * ns, i.e. the pid namespace associated with the procfs

		 * instance, is in the pid namespace hierarchy of pid.

		 * Start at one below the already printed level.

		 */

		for (i = ns->level + 1; i <= pid->level; i++)

			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);

	}

#endif

	seq_putc(m, '\n');

}

#endif



/*

 * Poll support for process exit notification.

 */

static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)

{

	struct pid *pid = file->private_data;

	bool thread = file->f_flags & PIDFD_THREAD;

	struct task_struct *task;

	__poll_t poll_flags = 0;



	poll_wait(file, &pid->wait_pidfd, pts);

	/*

	 * Depending on PIDFD_THREAD, inform pollers when the thread

	 * or the whole thread-group exits.

	 */

	guard(rcu)();

	task = pid_task(pid, PIDTYPE_PID);

	if (!task)

		poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP;

	else if (task->exit_state && (thread || thread_group_empty(task)))

		poll_flags = EPOLLIN | EPOLLRDNORM;



	return poll_flags;

}



const struct file_operations pidfd_fops = {

	.release	= pidfd_release,

	.poll		= pidfd_poll,

#ifdef CONFIG_PROC_FS

	.show_fdinfo	= pidfd_show_fdinfo,

#endif

};

kernel/fork.c

+0 −110
Original line number Diff line number Diff line
@@ -1993,116 +1993,6 @@ struct pid *pidfd_pid(const struct file *file) 
	return ERR_PTR(-EBADF);

}



static int pidfd_release(struct inode *inode, struct file *file)

{

	struct pid *pid = file->private_data;



	file->private_data = NULL;

	put_pid(pid);

	return 0;

}



#ifdef CONFIG_PROC_FS

/**

 * pidfd_show_fdinfo - print information about a pidfd

 * @m: proc fdinfo file

 * @f: file referencing a pidfd

 *

 * Pid:

 * This function will print the pid that a given pidfd refers to in the

 * pid namespace of the procfs instance.

 * If the pid namespace of the process is not a descendant of the pid

 * namespace of the procfs instance 0 will be shown as its pid. This is

 * similar to calling getppid() on a process whose parent is outside of

 * its pid namespace.

 *

 * NSpid:

 * If pid namespaces are supported then this function will also print

 * the pid of a given pidfd refers to for all descendant pid namespaces

 * starting from the current pid namespace of the instance, i.e. the

 * Pid field and the first entry in the NSpid field will be identical.

 * If the pid namespace of the process is not a descendant of the pid

 * namespace of the procfs instance 0 will be shown as its first NSpid

 * entry and no others will be shown.

 * Note that this differs from the Pid and NSpid fields in

 * /proc/<pid>/status where Pid and NSpid are always shown relative to

 * the  pid namespace of the procfs instance. The difference becomes

 * obvious when sending around a pidfd between pid namespaces from a

 * different branch of the tree, i.e. where no ancestral relation is

 * present between the pid namespaces:

 * - create two new pid namespaces ns1 and ns2 in the initial pid

 *   namespace (also take care to create new mount namespaces in the

 *   new pid namespace and mount procfs)

 * - create a process with a pidfd in ns1

 * - send pidfd from ns1 to ns2

 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid

 *   have exactly one entry, which is 0

 */

static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)

{

	struct pid *pid = f->private_data;

	struct pid_namespace *ns;

	pid_t nr = -1;



	if (likely(pid_has_task(pid, PIDTYPE_PID))) {

		ns = proc_pid_ns(file_inode(m->file)->i_sb);

		nr = pid_nr_ns(pid, ns);

	}



	seq_put_decimal_ll(m, "Pid:\t", nr);



#ifdef CONFIG_PID_NS

	seq_put_decimal_ll(m, "\nNSpid:\t", nr);

	if (nr > 0) {

		int i;



		/* If nr is non-zero it means that 'pid' is valid and that

		 * ns, i.e. the pid namespace associated with the procfs

		 * instance, is in the pid namespace hierarchy of pid.

		 * Start at one below the already printed level.

		 */

		for (i = ns->level + 1; i <= pid->level; i++)

			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);

	}

#endif

	seq_putc(m, '\n');

}

#endif



/*

 * Poll support for process exit notification.

 */

static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)

{

	struct pid *pid = file->private_data;

	bool thread = file->f_flags & PIDFD_THREAD;

	struct task_struct *task;

	__poll_t poll_flags = 0;



	poll_wait(file, &pid->wait_pidfd, pts);

	/*

	 * Depending on PIDFD_THREAD, inform pollers when the thread

	 * or the whole thread-group exits.

	 */

	rcu_read_lock();

	task = pid_task(pid, PIDTYPE_PID);

	if (!task)

		poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP;

	else if (task->exit_state && (thread || thread_group_empty(task)))

		poll_flags = EPOLLIN | EPOLLRDNORM;

	rcu_read_unlock();



	return poll_flags;

}



const struct file_operations pidfd_fops = {

	.release = pidfd_release,

	.poll = pidfd_poll,

#ifdef CONFIG_PROC_FS

	.show_fdinfo = pidfd_show_fdinfo,

#endif

};



/**

 * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd

 * @pid:   the struct pid for which to create a pidfd