On Wed, Apr 14, 2010 at 11:24 PM, Steven Whitehouse <steve@xxxxxxxxxxx> wrote: > Hi, > > Also, what lock should be protecting this code: > > va->flags |= VM_LAZY_FREE; > atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, > &vmap_lazy_nr); > > in free_unmap_vmap_area_noflush() ? It seem that if > __purge_vmap_area_lazy runs between the two statements above that the > number of pages contained in vmap_lazy_nr will be incorrect. Maybe the > two statements should just be reversed? I can't see any reason that the > flag assignment would be atomic either. In recent tests, including the > patch below, the following has been reported to me: It was already fixed. https://patchwork.kernel.org/patch/89783/ Thanks. -- Kind regards, Minchan Kim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href