On 26/02/18 17:01, Pavel Tatashin wrote:
> Juergen Gross noticed that commit
> f7f99100d8d ("mm: stop zeroing memory during allocation in vmemmap")
> broke XEN PV domains when deferred struct page initialization is enabled.
>
> This is because the xen's PagePinned() flag is getting erased from struct
> pages when they are initialized later in boot.
>
> Juergen fixed this problem by disabling deferred pages on xen pv domains.
> It is desirable, however, to have this feature available as it reduces boot
> time. This fix re-enables the feature for pv-dmains, and fixes the problem
> the following way:
>
> The fix is to delay setting PagePinned flag until struct pages for all
> allocated memory are initialized, i.e. until after free_all_bootmem().
>
> A new x86_init.hyper op init_after_bootmem() is called to let xen know
> that boot allocator is done, and hence struct pages for all the allocated
> memory are now initialized. If deferred page initialization is enabled, the
> rest of struct pages are going to be initialized later in boot once
> page_alloc_init_late() is called.
>
> xen_after_bootmem() walks page table's pages and marks them pinned.
>
> Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Verified to work on a system where the original issue caused a crash.
Reviewed-by: Juergen Gross <jgross@xxxxxxxx>
Tested-by: Juergen Gross <jgross@xxxxxxxx>
Juergen
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
