> On Mar 21, 2024, at 18:20, Oscar Salvador <osalvador@xxxxxxx> wrote: > > On Thu, Mar 21, 2024 at 05:49:49PM +0800, Muchun Song wrote: >> There are some more page dumping information from console: >> >> [ 61.367144][ T42] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff888028132880 pfn:0x28130 >> [ 61.371430][ T42] flags: 0xfff80000000000(node=0|zone=1|lastcpupid=0xfff) >> [ 61.374455][ T42] page_type: 0xffffffff() >> [ 61.376096][ T42] raw: 00fff80000000000 ffff888015ecd540 dead000000000100 0000000000000000 >> [ 61.379994][ T42] raw: ffff888028132880 0000000000190000 00000000ffffffff 0000000000000000 >> >> Alright, the page is freed (with a refcount of 0). > > Yes, basically the page changed betwen folio_test_large() (returned true > for PG_Head) and the call to const_folio_flags() (which now returned > false for PG_Head). > > As David pointed out, Willy is working on making PageHutelb more > robust [1]. > > > [1] https://lore.kernel.org/linux-mm/20240314012506.1600378-1-willy@xxxxxxxxxxxxx/ Sorry, I am not on the CC list, so I didn't know this. But thank you and David for this information, I think it could fix this problem. Muchun, Thanks.
