From 3d6d8da48d0b214d65ea0227d47228abc75d7c88 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 17 Oct 2019 12:18:28 +0200 Subject: pidfd: check pid has attached task in fdinfo Currently, when a task is dead we still print the pid it used to use in the fdinfo files of its pidfds. This doesn't make much sense since the pid may have already been reused. So verify that the task is still alive by introducing the pid_has_task() helper which will be used by other callers in follow-up patches. If the task is not alive anymore, we will print -1. This allows us to differentiate between a task not being present in a given pid namespace - in which case we already print 0 - and a task having been reaped. Note that this uses PIDTYPE_PID for the check. Technically, we could've checked PIDTYPE_TGID since pidfds currently only refer to thread-group leaders but if they won't anymore in the future then this check becomes problematic without it being immediately obvious to non-experts imho. If a thread is created via clone(CLONE_THREAD) than struct pid has a single non-empty list pid->tasks[PIDTYPE_PID] and this pid can't be used as a PIDTYPE_TGID meaning pid->tasks[PIDTYPE_TGID] will return NULL even though the thread-group leader might still be very much alive. So checking PIDTYPE_PID is fine and is easier to maintain should we ever allow pidfds to refer to threads. Cc: Jann Horn Cc: Christian Kellner Cc: linux-api@vger.kernel.org Signed-off-by: Christian Brauner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20191017101832.5985-1-christian.brauner@ubuntu.com --- include/linux/pid.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 9645b1194c98..034e3cd60dc0 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -85,6 +85,10 @@ static inline struct pid *get_pid(struct pid *pid) extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); +static inline bool pid_has_task(struct pid *pid, enum pid_type type) +{ + return !hlist_empty(&pid->tasks[type]); +} extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); -- cgit v1.2.3 From 49cb2fc42ce4b7a656ee605e30c302efaa39c1a7 Mon Sep 17 00:00:00 2001 From: Adrian Reber Date: Fri, 15 Nov 2019 13:36:20 +0100 Subject: fork: extend clone3() to support setting a PID The main motivation to add set_tid to clone3() is CRIU. To restore a process with the same PID/TID CRIU currently uses /proc/sys/kernel/ns_last_pid. It writes the desired (PID - 1) to ns_last_pid and then (quickly) does a clone(). This works most of the time, but it is racy. It is also slow as it requires multiple syscalls. Extending clone3() to support *set_tid makes it possible restore a process using CRIU without accessing /proc/sys/kernel/ns_last_pid and race free (as long as the desired PID/TID is available). This clone3() extension places the same restrictions (CAP_SYS_ADMIN) on clone3() with *set_tid as they are currently in place for ns_last_pid. The original version of this change was using a single value for set_tid. At the 2019 LPC, after presenting set_tid, it was, however, decided to change set_tid to an array to enable setting the PID of a process in multiple PID namespaces at the same time. If a process is created in a PID namespace it is possible to influence the PID inside and outside of the PID namespace. Details also in the corresponding selftest. To create a process with the following PIDs: PID NS level Requested PID 0 (host) 31496 1 42 2 1 For that example the two newly introduced parameters to struct clone_args (set_tid and set_tid_size) would need to be: set_tid[0] = 1; set_tid[1] = 42; set_tid[2] = 31496; set_tid_size = 3; If only the PIDs of the two innermost nested PID namespaces should be defined it would look like this: set_tid[0] = 1; set_tid[1] = 42; set_tid_size = 2; The PID of the newly created process would then be the next available free PID in the PID namespace level 0 (host) and 42 in the PID namespace at level 1 and the PID of the process in the innermost PID namespace would be 1. The set_tid array is used to specify the PID of a process starting from the innermost nested PID namespaces up to set_tid_size PID namespaces. set_tid_size cannot be larger then the current PID namespace level. Signed-off-by: Adrian Reber Reviewed-by: Christian Brauner Reviewed-by: Oleg Nesterov Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com> Acked-by: Andrei Vagin Link: https://lore.kernel.org/r/20191115123621.142252-1-areber@redhat.com Signed-off-by: Christian Brauner --- include/linux/pid.h | 3 ++- include/linux/pid_namespace.h | 2 ++ include/linux/sched/task.h | 3 +++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 034e3cd60dc0..998ae7d24450 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -124,7 +124,8 @@ extern struct pid *find_vpid(int nr); extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); -extern struct pid *alloc_pid(struct pid_namespace *ns); +extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, + size_t set_tid_size); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 49538b172483..2ed6af88794b 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -12,6 +12,8 @@ #include #include +/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ +#define MAX_PID_NS_LEVEL 32 struct fs_pin; diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4b1c3b664f51..f1879884238e 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -26,6 +26,9 @@ struct kernel_clone_args { unsigned long stack; unsigned long stack_size; unsigned long tls; + pid_t *set_tid; + /* Number of elements in *set_tid */ + size_t set_tid_size; }; /* -- cgit v1.2.3