On Tue, 22 Nov 2011, Markus Trippelsdorf wrote: > > Given slub is now lockless, validate_slab_slab() is probably very wrong > > these days. > > OK "slabinfo -v" is useless then. But that doesn't invalidate the BUGs > that I saw during boot. They happend before I could even run slabinfo > for the first time. Correct. Also the use of debugging disables the use of cmpxchg_double() but not this_cpu_cmpxchg() use. See cmpxchg_double_slab() and kmem_cache_open()s determination of the __CMPXCHG_DOUBLE flag. -- 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/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>