On Wed, Nov 23, 2011 at 8:57 AM, Pekka Enberg <penberg@xxxxxxxxxx> wrote: > On Wed, Nov 23, 2011 at 8:23 AM, Pekka Enberg <penberg@xxxxxxxxxx> wrote: >> On Tue, 22 Nov 2011, Gilad Ben-Yossef wrote: >>> >>> static void flush_all(struct kmem_cache *s) >>> { >>> - on_each_cpu(flush_cpu_slab, s, 1); >>> + cpumask_var_t cpus; >>> + struct kmem_cache_cpu *c; >>> + int cpu; >>> + >>> + if (likely(zalloc_cpumask_var(&cpus, GFP_ATOMIC))) { >> >> __GFP_NOWARN too maybe? >> Right, the allocation failure here is harmless. I should probably do the same for the page_alloc.c case as well. >>> + for_each_online_cpu(cpu) { >>> + c = per_cpu_ptr(s->cpu_slab, cpu); >>> + if (c->page) >>> + cpumask_set_cpu(cpu, cpus); >>> + } >>> + on_each_cpu_mask(cpus, flush_cpu_slab, s, 1); >>> + free_cpumask_var(cpus); >>> + } else >>> + on_each_cpu(flush_cpu_slab, s, 1); >>> } >> >> Acked-by: Pekka Enberg <penberg@xxxxxxxxxx> >> >> I can't take the patch because it depends on a new API introduced in the >> first patch. >> >> I'm CC'ing Andrew. Thanks! There's a git tree of these over at: git://github.com/gby/linux.git branch ipi_noise_v4 in case that helps. I will send v5 (and create a new git branch for it) with the above changes and the Arm patch description update once I get an Ack from Russel K. Cheers, Gilad > -- Gilad Ben-Yossef Chief Coffee Drinker gilad@xxxxxxxxxxxxx Israel Cell: +972-52-8260388 US Cell: +1-973-8260388 http://benyossef.com "Unfortunately, cache misses are an equal opportunity pain provider." -- Mike Galbraith, LKML -- 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