From 477058411c45f225ddfbb4769e35a9a5a95cb826 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 25 Apr 2025 10:11:30 +0200 Subject: pidfs: register pid in pidfs Add simple helpers that allow a struct pid to be pinned via a pidfs dentry/inode. If no pidfs dentry exists a new one will be allocated for it. A reference is taken by pidfs on @pid. The reference must be released via pidfs_put_pid(). This will allow AF_UNIX sockets to allocate a dentry for the peer credentials pid at the time they are recorded where we know the task is still alive. When the task gets reaped its exit status is guaranteed to be recorded and a pidfd can be handed out for the reaped task. Link: https://lore.kernel.org/20250425-work-pidfs-net-v2-1-450a19461e75@kernel.org Reviewed-by: Oleg Nesterov Reviewed-by: David Rheinsberg Signed-off-by: Christian Brauner --- include/linux/pidfs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 05e6f8f4a026..2676890c4d0d 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -8,5 +8,8 @@ void pidfs_add_pid(struct pid *pid); void pidfs_remove_pid(struct pid *pid); void pidfs_exit(struct task_struct *tsk); extern const struct dentry_operations pidfs_dentry_operations; +int pidfs_register_pid(struct pid *pid); +void pidfs_get_pid(struct pid *pid); +void pidfs_put_pid(struct pid *pid); #endif /* _LINUX_PID_FS_H */ -- cgit v1.2.3 From a71f402acd71a942e59c16270ad61dee06de6e24 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 25 Apr 2025 10:11:32 +0200 Subject: pidfs: get rid of __pidfd_prepare() Fold it into pidfd_prepare() and rename PIDFD_CLONE to PIDFD_STALE to indicate that the passed pid might not have task linkage and no explicit check for that should be performed. Link: https://lore.kernel.org/20250425-work-pidfs-net-v2-3-450a19461e75@kernel.org Reviewed-by: Oleg Nesterov Reviewed-by: David Rheinsberg Signed-off-by: Christian Brauner --- include/linux/pid.h | 2 +- include/uapi/linux/pidfd.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pid.h b/include/linux/pid.h index 311ecebd7d56..453ae6d8a68d 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -77,7 +77,7 @@ struct file; 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); +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file); void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 2970ef44655a..8c1511edd0e9 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -12,7 +12,7 @@ #define PIDFD_THREAD O_EXCL #ifdef __KERNEL__ #include -#define PIDFD_CLONE CLONE_PIDFD +#define PIDFD_STALE CLONE_PIDFD #endif /* Flags for pidfd_send_signal(). */ -- cgit v1.2.3 From b5325b2a270fcaf7b2a9a0f23d422ca8a5a8bdea Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 14 Apr 2025 15:55:07 +0200 Subject: coredump: hand a pidfd to the usermode coredump helper Give userspace a way to instruct the kernel to install a pidfd into the usermode helper process. This makes coredump handling a lot more reliable for userspace. In parallel with this commit we already have systemd adding support for this in [1]. We create a pidfs file for the coredumping process when we process the corename pattern. When the usermode helper process is forked we then install the pidfs file as file descriptor three into the usermode helpers file descriptor table so it's available to the exec'd program. Since usermode helpers are either children of the system_unbound_wq workqueue or kthreadd we know that the file descriptor table is empty and can thus always use three as the file descriptor number. Note, that we'll install a pidfd for the thread-group leader even if a subthread is calling do_coredump(). We know that task linkage hasn't been removed due to delay_group_leader() and even if this @current isn't the actual thread-group leader we know that the thread-group leader cannot be reaped until @current has exited. Link: https://github.com/systemd/systemd/pull/37125 [1] Link: https://lore.kernel.org/20250414-work-coredump-v2-3-685bf231f828@kernel.org Tested-by: Luca Boccassi Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- include/linux/coredump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 77e6e195d1d6..76e41805b92d 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -28,6 +28,7 @@ struct coredump_params { int vma_count; size_t vma_data_size; struct core_vma_metadata *vma_meta; + struct pid *pid; }; extern unsigned int core_file_note_size_limit; -- cgit v1.2.3