Re: Do I need spin_lock before pgd/pmd/pte_offset?

[Ed L Cashin <ecashin@coraid.com>]

Timur Tabi <timur.tabi@ammasso.com> writes:

...
> with a spinlock?  That is, should I change the above to:
>
> 	spin_lock(&current->mm->page_table_lock);
>          pgd_t *pgd = pgd_offset(current->mm, address);
>          pmd_t *pmd = pmd_offset(pgd, address);
>          pte_t *pte = pte_offset_map(pmd, address);
>          pte_t _pte = *pte;
>          pte_unmap(pte);
> 	spin_unlock(&current->mm->page_table_lock);

The normal order of lock acquisition is first to get the mmap
semaphore (at which point you may sleep) and then to get the page
table lock.

A good reference for the proceedure you're implementing is follow_page
in mm/memory.c.  Note that it's called with the page_table_lock held.

> I'm guessing I only need to call a spinlock if the page isn't locked
> in memory.  Is that correct?

No, the page table lock allows you to see a consistent view of the
page tables while you hold it.  

-- 
  Ed L Cashin <ecashin@coraid.com>


--
Kernelnewbies: Help each other learn about the Linux kernel.
Archive:       http://mail.nl.linux.org/kernelnewbies/
FAQ:           http://kernelnewbies.org/faq/