On 2009-04-10, yihect <[email protected]> wrote: > > > > En, this is the method what I want to use. The question is all registers are > all accessed by > the only ioctl cmd. If one process want to do jobs that need to access a > series of registers, > the performance will affected internally due to frequent user-kernel-space > switch. > > So, if we use mutex/semaphore in ioctl level directly, is the performance > will become worse? > Is this true? Is there any better solutions for this? >
Another option is that you spin lock the access to the registers in kernel space. In this way, performance may be better than lock the entire ioctl. Jeffrey -- To unsubscribe from this list: send an email with "unsubscribe kernelnewbies" to [email protected] Please read the FAQ at http://kernelnewbies.org/FAQ
