On 9/27/2021 8:16 PM, David Hildenbrand wrote: > On 27.09.21 20:12, Matthew Wilcox wrote: >> >> But the thing we're allocating is at least PAGE_SIZE bytes in size. >> Why is "We should avoid storing anything in the free page itself" true? >> > > Immediately comes to mind: > * Free page reporting via virtio-balloon > * CMA on s390x (see arch_free_page()) > * Free page poisoning > * init_on_free I was thinking of debug_pagealloc (unmaps free pages from direct map) but yeah, the list is longer.
