> Perhaps there are some better ideas?
Yes. Dave, could we create a new interface to avoid the spin_lock?
modify write_seqlock(set_lock *s) to write_seqlock(seq_lock *s, int lock), it will modify all calling routines.
write a new interface write_seqlock_percpu(), which gets rid of the spin_lock, we can call by a different name, since there is no lock.
IBM Linux Technology Center
15300 SW Koll Parkway
Beaverton, OR 97006-6063
Phone: (503) 578-7638
FAX: (503) 578-3228