Add a new helper that allows to reserve a pidfd and allocates a new pidfd file that stashes the provided struct pid. This will allow us to remove places that either open code this function or that call pidfd_create() but then have to call close_fd() because there are still failure points after pidfd_create() has been called. Signed-off-by: Christian Brauner <brauner@xxxxxxxxxx> --- include/linux/pid.h | 1 + kernel/pid.c | 69 +++++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 58 insertions(+), 12 deletions(-) diff --git a/include/linux/pid.h b/include/linux/pid.h index 343abf22092e..b75de288a8c2 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -80,6 +80,7 @@ extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_create(struct pid *pid, unsigned int flags); +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); static inline struct pid *get_pid(struct pid *pid) { diff --git a/kernel/pid.c b/kernel/pid.c index 3fbc5e46b721..95e7e01574c8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -576,6 +576,56 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) return task; } +/** + * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd + * @pid: the struct pid for which to create a pidfd + * @flags: flags of the new @pidfd + * @pidfd: the pidfd to return + * + * Allocate a new file that stashes @pid and reserve a new pidfd number in the + * caller's file descriptor table. The pidfd is reserved but not installed yet. + * + * If this function returns successfully the caller is responsible to either + * call fd_install() passing the returned pidfd and pidfd file as arguments in + * order to install the pidfd into its file descriptor table or they must use + * put_unused_fd() and fput() on the returned pidfd and pidfd file + * respectively. + * + * This function is useful when a pidfd must already be reserved but there + * might still be points of failure afterwards and the caller wants to ensure + * that no pidfd is leaked into its file descriptor table. + * + * Return: On success, a reserved pidfd is returned from the function and a new + * pidfd file is returned in the last argument to the function. On + * error, a negative error code is returned from the function and the + * last argument remains unchanged. + */ +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) +{ + int pidfd; + struct file *pidfd_file; + + if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) + return -EINVAL; + + if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) + return -EINVAL; + + pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + if (pidfd < 0) + return pidfd; + + pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, + flags | O_RDWR | O_CLOEXEC); + if (IS_ERR(pidfd_file)) { + put_unused_fd(pidfd); + return PTR_ERR(pidfd_file); + } + get_pid(pid); /* held by pidfd_file now */ + *ret = pidfd_file; + return pidfd; +} + /** * pidfd_create() - Create a new pid file descriptor. * @@ -594,20 +644,15 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) */ int pidfd_create(struct pid *pid, unsigned int flags) { - int fd; + int pidfd; + struct file *pidfd_file; - if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) - return -EINVAL; - - if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) - return -EINVAL; - - fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), - flags | O_RDWR | O_CLOEXEC); - if (fd < 0) - put_pid(pid); + pidfd = pidfd_prepare(pid, flags, &pidfd_file); + if (pidfd < 0) + return pidfd; - return fd; + fd_install(pidfd, pidfd_file); + return pidfd; } /** -- 2.34.1