Re: [PATCH v3 2/5] pid: split cyclic id allocation cursor from idr

[Ian Kent <ikent@redhat.com>]

On 3/12/22 01:16, Brian Foster wrote:
> As a next step in separating pid allocation from the idr, split off
> the cyclic pid allocation cursor from the idr. Lift the cursor value
> into the struct pid_namespace. Note that this involves temporarily
> open-coding the cursor increment on allocation, but this is cleaned
> up in the subsequent patch.
>
> Signed-off-by: Matthew Wilcox <willy@infradead.org>
> Signed-off-by: Brian Foster <bfoster@redhat.com>


Reviewed-by: Ian Kent <raven@themaw.net>

> ---
>   arch/powerpc/platforms/cell/spufs/sched.c | 2 +-
>   fs/proc/loadavg.c                         | 2 +-
>   include/linux/pid_namespace.h             | 1 +
>   kernel/pid.c                              | 6 ++++--
>   kernel/pid_namespace.c                    | 4 ++--
>   5 files changed, 9 insertions(+), 6 deletions(-)
>
> diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
> index 99bd027a7f7c..a2ed928d7658 100644
> --- a/arch/powerpc/platforms/cell/spufs/sched.c
> +++ b/arch/powerpc/platforms/cell/spufs/sched.c
> @@ -1072,7 +1072,7 @@ static int show_spu_loadavg(struct seq_file *s, void *private)
>   		LOAD_INT(c), LOAD_FRAC(c),
>   		count_active_contexts(),
>   		atomic_read(&nr_spu_contexts),
> -		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
> +		READ_ONCE(task_active_pid_ns(current)->pid_next) - 1);
>   	return 0;
>   }
>   #endif
> diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
> index 817981e57223..2740b31b6461 100644
> --- a/fs/proc/loadavg.c
> +++ b/fs/proc/loadavg.c
> @@ -22,7 +22,7 @@ static int loadavg_proc_show(struct seq_file *m, void *v)
>   		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
>   		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
>   		nr_running(), nr_threads,
> -		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
> +		READ_ONCE(task_active_pid_ns(current)->pid_next) - 1);
>   	return 0;
>   }
>   
> diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
> index 07481bb87d4e..82c72482019d 100644
> --- a/include/linux/pid_namespace.h
> +++ b/include/linux/pid_namespace.h
> @@ -18,6 +18,7 @@ struct fs_pin;
>   
>   struct pid_namespace {
>   	struct idr idr;
> +	unsigned int pid_next;
>   	struct rcu_head rcu;
>   	unsigned int pid_allocated;
>   	struct task_struct *child_reaper;
> diff --git a/kernel/pid.c b/kernel/pid.c
> index 3622f8b13143..2e2d33273c8e 100644
> --- a/kernel/pid.c
> +++ b/kernel/pid.c
> @@ -75,6 +75,7 @@ int pid_max_max = PID_MAX_LIMIT;
>   struct pid_namespace init_pid_ns = {
>   	.ns.count = REFCOUNT_INIT(2),
>   	.idr = IDR_INIT(init_pid_ns.idr),
> +	.pid_next = 0,
>   	.pid_allocated = PIDNS_ADDING,
>   	.level = 0,
>   	.child_reaper = &init_task,
> @@ -208,7 +209,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
>   			 * init really needs pid 1, but after reaching the
>   			 * maximum wrap back to RESERVED_PIDS
>   			 */
> -			if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
> +			if (tmp->pid_next > RESERVED_PIDS)
>   				pid_min = RESERVED_PIDS;
>   
>   			/*
> @@ -217,6 +218,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
>   			 */
>   			nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
>   					      pid_max, GFP_ATOMIC);
> +			tmp->pid_next = nr + 1;
>   		}
>   		xa_unlock_irq(&tmp->idr.idr_rt);
>   		idr_preload_end();
> @@ -278,7 +280,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
>   
>   		/* On failure to allocate the first pid, reset the state */
>   		if (tmp == ns && tmp->pid_allocated == PIDNS_ADDING)
> -			idr_set_cursor(&ns->idr, 0);
> +			ns->pid_next = 0;
>   
>   		idr_remove(&tmp->idr, upid->nr);
>   		xa_unlock_irq(&tmp->idr.idr_rt);
> diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
> index f4f8cb0435b4..a53d20c5c85e 100644
> --- a/kernel/pid_namespace.c
> +++ b/kernel/pid_namespace.c
> @@ -272,12 +272,12 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
>   	 * it should synchronize its usage with external means.
>   	 */
>   
> -	next = idr_get_cursor(&pid_ns->idr) - 1;
> +	next = READ_ONCE(pid_ns->pid_next) - 1;
>   
>   	tmp.data = &next;
>   	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
>   	if (!ret && write)
> -		idr_set_cursor(&pid_ns->idr, next + 1);
> +		WRITE_ONCE(pid_ns->pid_next, next + 1);
>   
>   	return ret;
>   }