The means by which a pid is determined from a pidfd is duplicated, with some callers holding a reference to the (pid)fd, and others explicitly pinning the pid.

Introduce __pidfd_get_pid() which abstracts both approaches and provide optional output parameters for file->f_flags and the fd (the latter of which, if provided, prevents the function from decrementing the fd's refernce count).

Additionally, allow the ability to open a pidfd by opening a /proc/<pid> directory, utilised by the pidfd_send_signal() system call, providing a pidfd_get_pid_proc() helper function to do so.

Doing this allows us to eliminate open-coded pidfd pid lookup and to consistently handle this in one place.

This lays the groundwork for a subsequent patch which adds a new sentinel pidfd to explicitly reference the current process (i.e. thread group leader) without the need for a pidfd.

Signed-off-by: Lorenzo Stoakes lorenzo.stoakes@oracle.com --- include/linux/pid.h | 42 +++++++++++++++++++++++++++++++- kernel/pid.c | 58 ++++++++++++++++++++++++++++++--------------- kernel/signal.c | 22 ++++------------- 3 files changed, 84 insertions(+), 38 deletions(-)

diff --git a/include/linux/pid.h b/include/linux/pid.h index a3aad9b4074c..68b02eab7509 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -2,6 +2,7 @@ #ifndef _LINUX_PID_H #define _LINUX_PID_H

+#include <linux/file.h> #include <linux/pid_types.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -72,8 +73,47 @@ extern struct pid init_struct_pid;

struct file;

+ +/** + * __pidfd_get_pid() - Retrieve a pid associated with the specified pidfd. + * + * @pidfd: The pidfd whose pid we want, or the fd of a /proc/<pid> file if + * @alloc_proc is also set. + * @pin_pid: If set, then the reference counter of the returned pid is + * incremented. If not set, then @fd should be provided to pin the + * pidfd. + * @allow_proc: If set, then an fd of a /proc/<pid> file can be passed instead + * of a pidfd, and this will be used to determine the pid. + * @flags: Output variable, if non-NULL, then the file->f_flags of the + * pidfd will be set here. + * @fd: Output variable, if non-NULL, then the pidfd reference will + * remain elevated and the caller will need to decrement it + * themselves. + * + * Returns: If successful, the pid associated with the pidfd, otherwise an + * error. + */ +struct pid *__pidfd_get_pid(unsigned int pidfd, bool pin_pid, + bool allow_proc, unsigned int *flags, + struct fd *fd); + +static inline struct pid *pidfd_get_pid(unsigned int pidfd, unsigned int *flags) +{ + return __pidfd_get_pid(pidfd, /* pin_pid = */ true, + /* allow_proc = */ false, + flags, /* fd = */ NULL); +} + +static inline struct pid *pidfd_to_pid_proc(unsigned int pidfd, + unsigned int *flags, + struct fd *fd) +{ + return __pidfd_get_pid(pidfd, /* pin_pid = */ false, + /* allow_proc = */ true, + flags, fd); +} + 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_prepare(struct pid *pid, unsigned int flags, struct file **ret); void do_notify_pidfd(struct task_struct *task); diff --git a/kernel/pid.c b/kernel/pid.c index 2715afb77eab..25cc1c36a1b1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -36,6 +36,7 @@ #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> +#include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> @@ -534,22 +535,46 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) } EXPORT_SYMBOL_GPL(find_ge_pid);

-struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) +struct pid *__pidfd_get_pid(unsigned int pidfd, bool pin_pid, + bool allow_proc, unsigned int *flags, + struct fd *fd) { - struct fd f; + struct file *file; struct pid *pid; + struct fd f = fdget(pidfd);

- f = fdget(fd); - if (!fd_file(f)) + file = fd_file(f); + if (!file) return ERR_PTR(-EBADF);

- pid = pidfd_pid(fd_file(f)); - if (!IS_ERR(pid)) { - get_pid(pid); - *flags = fd_file(f)->f_flags; + pid = pidfd_pid(file); + /* If we allow opening a pidfd via /proc/<pid>, do so. */ + if (IS_ERR(pid) && allow_proc) + pid = tgid_pidfd_to_pid(file); + + if (IS_ERR(pid)) { + fdput(f); + return pid; }

- fdput(f); + if (pin_pid) + get_pid(pid); + else + WARN_ON_ONCE(!fd); /* Nothing to keep pid/pidfd around? */ + + if (flags) + *flags = file->f_flags; + + /* + * If the user provides an fd output then it will handle decrementing + * its reference counter. + */ + if (fd) + *fd = f; + else + /* Otherwise we release it. */ + fdput(f); + return pid; }

@@ -747,23 +772,18 @@ 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 (!fd_file(f)) - return -EBADF; - - pid = pidfd_pid(fd_file(f)); + pid = pidfd_get_pid(pidfd, NULL); if (IS_ERR(pid)) - ret = PTR_ERR(pid); - else - ret = pidfd_getfd(pid, fd); + return PTR_ERR(pid);

- fdput(f); + ret = pidfd_getfd(pid, fd); + + put_pid(pid); return ret; } diff --git a/kernel/signal.c b/kernel/signal.c index 4344860ffcac..868bfa674c62 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3875,17 +3875,6 @@ static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, return copy_siginfo_from_user(kinfo, info); }

-static struct pid *pidfd_to_pid(const struct file *file) -{ - struct pid *pid; - - pid = pidfd_pid(file); - if (!IS_ERR(pid)) - return pid; - - return tgid_pidfd_to_pid(file); -} - #define PIDFD_SEND_SIGNAL_FLAGS \ (PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \ PIDFD_SIGNAL_PROCESS_GROUP) @@ -3908,10 +3897,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, siginfo_t __user *, info, unsigned int, flags) { int ret; - struct fd f; struct pid *pid; kernel_siginfo_t kinfo; enum pid_type type; + unsigned int f_flags; + struct fd f;

/* Enforce flags be set to 0 until we add an extension. */ if (flags & ~PIDFD_SEND_SIGNAL_FLAGS) @@ -3921,12 +3911,8 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1) return -EINVAL;

- f = fdget(pidfd); - if (!fd_file(f)) - return -EBADF; - /* Is this a pidfd? */ - pid = pidfd_to_pid(fd_file(f)); + pid = pidfd_to_pid_proc(pidfd, &f_flags, &f); if (IS_ERR(pid)) { ret = PTR_ERR(pid); goto err; @@ -3939,7 +3925,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, switch (flags) { case 0: /* Infer scope from the type of pidfd. */ - if (fd_file(f)->f_flags & PIDFD_THREAD) + if (f_flags & PIDFD_THREAD) type = PIDTYPE_PID; else type = PIDTYPE_TGID;

It is useful to be able to utilise pidfd mechanisms to reference the current thread or process (from a userland point of view - thread group leader from the kernel's point of view).

Therefore introduce PIDFD_SELF_THREAD to refer to the current thread, and PIDFD_SELF_THREAD_GROUP to refer to the current thread group leader.

For convenience and to avoid confusion from userland's perspective we alias these:

* PIDFD_SELF is an alias for PIDFD_SELF_THREAD - This is nearly always what the user will want to use, as they would find it surprising if for instance fd's were unshared()'d and they wanted to invoke pidfd_getfd() and that failed.

* PIDFD_SELF_PROCESS is an alias for PIDFD_SELF_THREAD_GROUP - Most users have no concept of thread groups or what a thread group leader is, and from userland's perspective and nomenclature this is what userland considers to be a process.

Due to the refactoring of the central __pidfd_get_pid() function we can implement this functionality centrally, providing the use of this sentinel in most functionality which utilises pidfd's.

We need to explicitly adjust kernel_waitid_prepare() to permit this (though it wouldn't really make sense to use this there, we provide the ability for consistency).

We explicitly disallow use of this in setns(), which would otherwise have required explicit custom handling, as it doesn't make sense to set the current calling thread to join the namespace of itself.

As the callers of pidfd_get_pid() expect an increased reference count on the pid we do so in the self case, reducing churn and avoiding any breakage from existing logic which decrements this reference count.

In the pidfd_send_signal() system call, we can continue to fdput() the struct fd output by pidfs_to_pid_proc() even if PIDFD_SELF_* is specified, as this will be empty and the invocation will be a no-op.

This change implicitly provides PIDFD_SELF_* support in the waitid(P_PIDFS, ...), process_madvise(), process_mrelease(), pidfd_send_signal(), and pidfd_getfd() system calls.

Things such as polling a pidfs and general fd operations are not supported, this strictly provides the sentinel for APIs which explicitly accept a pidfd.

Signed-off-by: Lorenzo Stoakes lorenzo.stoakes@oracle.com --- include/linux/pid.h | 9 +++--- include/uapi/linux/pidfd.h | 15 +++++++++ kernel/exit.c | 3 +- kernel/nsproxy.c | 1 + kernel/pid.c | 65 +++++++++++++++++++++++--------------- 5 files changed, 62 insertions(+), 31 deletions(-)

diff --git a/include/linux/pid.h b/include/linux/pid.h index 68b02eab7509..7c9ed1b5d16f 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -77,18 +77,19 @@ struct file; /** * __pidfd_get_pid() - Retrieve a pid associated with the specified pidfd. * - * @pidfd: The pidfd whose pid we want, or the fd of a /proc/<pid> file if - * @alloc_proc is also set. + * @pidfd: The pidfd whose pid we want, the fd of a /proc/<pid> file if + * @alloc_proc is also set, or PIDFD_SELF_* to refer to the current + * thread or thread group leader. * @pin_pid: If set, then the reference counter of the returned pid is * incremented. If not set, then @fd should be provided to pin the * pidfd. * @allow_proc: If set, then an fd of a /proc/<pid> file can be passed instead * of a pidfd, and this will be used to determine the pid. * @flags: Output variable, if non-NULL, then the file->f_flags of the - * pidfd will be set here. + * pidfd will be set here. If PIDFD_SELF_* set, this is zero. * @fd: Output variable, if non-NULL, then the pidfd reference will * remain elevated and the caller will need to decrement it - * themselves. + * themselves. If PIDFD_SELF_* set, this is empty. * * Returns: If successful, the pid associated with the pidfd, otherwise an * error. diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 565fc0629fff..f4db20d76f4b 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -29,4 +29,19 @@ #define PIDFD_GET_USER_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 9) #define PIDFD_GET_UTS_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 10)

+/* + * Special sentinel values which can be used to refer to the current thread or + * thread group leader (which from a userland perspective is the process). + */ +#define PIDFD_SELF PIDFD_SELF_THREAD +#define PIDFD_SELF_PROCESS PIDFD_SELF_THREAD_GROUP + +#define PIDFD_SELF_THREAD -100 /* Current thread. */ +#define PIDFD_SELF_THREAD_GROUP -200 /* Current thread group leader. */ + +static inline bool pidfd_is_self_sentinel(pid_t pid) +{ + return pid == PIDFD_SELF_THREAD || pid == PIDFD_SELF_THREAD_GROUP; +} + #endif /* _UAPI_LINUX_PIDFD_H */ diff --git a/kernel/exit.c b/kernel/exit.c index 619f0014c33b..3eb20f8252ee 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -71,6 +71,7 @@ #include <linux/user_events.h> #include <linux/uaccess.h>

+#include <uapi/linux/pidfd.h> #include <uapi/linux/wait.h>

#include <asm/unistd.h> @@ -1739,7 +1740,7 @@ int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid, break; case P_PIDFD: type = PIDTYPE_PID; - if (upid < 0) + if (upid < 0 && !pidfd_is_self_sentinel(upid)) return -EINVAL;

pid = pidfd_get_pid(upid, &f_flags); diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index dc952c3b05af..d239f7eeaa1f 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -550,6 +550,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags) struct nsset nsset = {}; int err = 0;

+ /* If fd is PIDFD_SELF_*, implicitly fail here, as invalid. */ if (!fd_file(f)) return -EBADF;

diff --git a/kernel/pid.c b/kernel/pid.c index 25cc1c36a1b1..0f8943ecc471 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -539,22 +539,31 @@ struct pid *__pidfd_get_pid(unsigned int pidfd, bool pin_pid, bool allow_proc, unsigned int *flags, struct fd *fd) { - struct file *file; + struct file *file = NULL; struct pid *pid; - struct fd f = fdget(pidfd); - - file = fd_file(f); - if (!file) - return ERR_PTR(-EBADF); - - pid = pidfd_pid(file); - /* If we allow opening a pidfd via /proc/<pid>, do so. */ - if (IS_ERR(pid) && allow_proc) - pid = tgid_pidfd_to_pid(file); - - if (IS_ERR(pid)) { - fdput(f); - return pid; + unsigned int f_flags = 0; + struct fd f = {}; + + if (pidfd == PIDFD_SELF_THREAD) { + pid = *task_pid_ptr(current, PIDTYPE_PID); + f_flags = PIDFD_THREAD; + } else if (pidfd == PIDFD_SELF_THREAD_GROUP) { + pid = *task_pid_ptr(current, PIDTYPE_TGID); + } else { + f = fdget(pidfd); + file = fd_file(f); + if (!file) + return ERR_PTR(-EBADF); + + pid = pidfd_pid(file); + /* If we allow opening a pidfd via /proc/<pid>, do so. */ + if (IS_ERR(pid) && allow_proc) + pid = tgid_pidfd_to_pid(file); + + if (IS_ERR(pid)) { + fdput(f); + return pid; + } }

if (pin_pid) @@ -562,18 +571,22 @@ struct pid *__pidfd_get_pid(unsigned int pidfd, bool pin_pid, else WARN_ON_ONCE(!fd); /* Nothing to keep pid/pidfd around? */

- if (flags) - *flags = file->f_flags; + if (file) { + f_flags = file->f_flags;

- /* - * If the user provides an fd output then it will handle decrementing - * its reference counter. - */ - if (fd) - *fd = f; - else - /* Otherwise we release it. */ - fdput(f); + /* + * If the user provides an fd output then it will handle decrementing + * its reference counter. + */ + if (fd) + *fd = f; + else + /* Otherwise we release it. */ + fdput(f); + } + + if (flags) + *flags = f_flags;

return pid; }