From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932418AbdBKJ45 (ORCPT ); Sat, 11 Feb 2017 04:56:57 -0500 Received: from mail-pg0-f68.google.com ([74.125.83.68]:34855 "EHLO mail-pg0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932104AbdBKJ4y (ORCPT ); Sat, 11 Feb 2017 04:56:54 -0500 Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (1.0) Subject: Re: [PATCH v4] fork: free vmapped stacks in cache when cpus are offline From: Hoeun Ryu X-Mailer: iPhone Mail (14C92) In-Reply-To: Date: Sat, 11 Feb 2017 18:56:41 +0900 Cc: Andrew Morton , Michal Hocko , Ingo Molnar , Andy Lutomirski , "Eric W. Biederman" , Oleg Nesterov , Mateusz Guzik , linux-kernel@vger.kernel.org, kernel-hardening@lists.openwall.com Message-Id: References: <1486770080-25007-1-git-send-email-hoeun.ryu@gmail.com> To: Thomas Gleixner Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from quoted-printable to 8bit by mail.home.local id v1B9vC9t004706 > On Feb 11, 2017, at 5:31 PM, Thomas Gleixner wrote: > >> On Sat, 11 Feb 2017, Hoeun Ryu wrote: >> #define NR_CACHED_STACKS 2 >> static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); >> + >> +static int free_vm_stack_cache(unsigned int cpu) >> +{ >> + struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); >> + int i; >> + >> + for (i = 0; i < NR_CACHED_STACKS; i++) { >> + struct vm_struct *vm_stack = cached_vm_stacks[i]; >> + >> + if (!vm_stack) >> + continue; >> + >> + vfree(vm_stack->addr); >> + cached_vm_stacks[i] = NULL; >> + } >> + >> + return 0; >> +} >> #endif >> >> static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) >> @@ -456,6 +474,11 @@ void __init fork_init(void) >> for (i = 0; i < UCOUNT_COUNTS; i++) { >> init_user_ns.ucount_max[i] = max_threads/2; >> } >> + >> +#ifdef CONFIG_VMAP_STACK >> + cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vmstack_cache", >> + NULL, free_vm_stack_cache); >> +#endif > > If you wrap that in vm_stack_cache_init() and have a stub for !VMAP_STACK > (add an #else to the #ifdef VMAP_STACK section above) then you spare the > ugly ifdef in fork_init() OK. I will. > Thanks, > > tglx