A question about tasklet's TASKLET_STATE_RUN state

[Simon <wei.guo.simon@xxxxxxxxx>]

Hi,

 

I read from ULK about the value of "TASKLET_STATE_RUN" for tasklet:

==

TASKLET_STATE_RUN

When set, this indicates that the tasklet is being executed; on a uniprocessor system this flag is not used because there is no need to check whether a specific tasklet is running.

In multiprocessor systems, checks the TASKLET_STATE_RUN flag of the tasklet.

• If it is set, a tasklet of the same type is already running on another CPU, so the function reinserts the task descriptor in the list pointed to by tasklet_vec[n] or tasklet_hi_vec[n] and activates the TASKLET_SOFTIRQ or HI_SOFTIRQ softirq again. In this way, execution of the tasklet is deferred until no other tasklets of the same type are running on other CPUs.

==

Each tasklet is defined as a tasklet_struct which is linked into perCPU list "tasklet_vec[NR_CPUS]". 

 

My question is:  One tasklet is “attached” to ONE CPU(since one tasklet is put into ONE perCPU tasklet_struct list). And looks tasklet_action() only handle tasklet_struct list of local CPU. So how could there be a chance for this tasklet to be executed at another CPU? ?

 

    299 struct tasklet_struct

    300 {

    301    struct tasklet_struct *next;

    302    unsigned long state;               // tasklet state sched/run

    303    atomic_t count;                     //lock

    304    void (*func)(unsigned long);

    305    unsigned long data;

    306 };

 

Puzzling,

Simon