Messages in this thread | | | Date | Wed, 15 Oct 2008 16:24:29 +0100 | From | "Jan Beulich" <> | Subject | Re: [Xen-devel] [PATCH]: Fix Xen domU boot with batched mprotect |
| |
>>> Chris Lalancette <clalance@redhat.com> 15.10.08 13:03 >>> >The right thing to do is to use arbitrary_virt_to_machine, so that we can be >sure we are modifying the right pfn. This unfortunately introduces a >performance penalty because of a full page-table-walk, but we can avoid that >penalty for pages in the p2m list by checking if virt_addr_valid is true, and if >so, just doing the lookup in the p2m table.
Could you explain how virt_addr_valid() can validly be used here? Looking at its implementation
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
a kaddr in kmap space (i.e. above high_memory) would return a bogus physical address, and hence pfn_valid() on the resulting pfn is meaningless.
I'd instead simply compare the address in question against high_memory, and perhaps instead of in arbitrary_virt_to_machine() in ptep_modify_prot_commit() under an #ifdef CONFIG_HIGHPTE. But performance-wise, CONFIG_HIGHPTE sucks under Xen anyway, so you'd better not turn this on in the first place. We may want/need to provide a means to disable this at run time so the same kernel when run natively could still make use of it, but without impacting performance under Xen.
Jan
| |