Ed L Cashin wrote:
pte_offset_map, if I recall correctly, can map a high-memory page table into the kernel address space. Later pte_unmap removes the mapping. pte_offset doesn't do that.
So you're saying that the page table itself is in high memory, outside the normal visibility of the kernel? Wouldn't that significantly impact performance?
Check the macro definitions in include/asm/pgtable.h, but I don't know what pte_offset_atomic does.
Neither does anyone else, apparently.
-- Timur Tabi Staff Software Engineer timur.tabi@xxxxxxxxxxx
-- Kernelnewbies: Help each other learn about the Linux kernel. Archive: http://mail.nl.linux.org/kernelnewbies/ FAQ: http://kernelnewbies.org/faq/
