From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-8.3 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS, URIBL_BLOCKED,USER_AGENT_SANE_1 autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8DC44C4CEC9 for ; Tue, 17 Sep 2019 23:25:05 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 63D3421852 for ; Tue, 17 Sep 2019 23:25:05 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726073AbfIQXZF (ORCPT ); Tue, 17 Sep 2019 19:25:05 -0400 Received: from mga12.intel.com ([192.55.52.136]:39603 "EHLO mga12.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726054AbfIQXZF (ORCPT ); Tue, 17 Sep 2019 19:25:05 -0400 X-Amp-Result: UNKNOWN X-Amp-Original-Verdict: FILE UNKNOWN X-Amp-File-Uploaded: False Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 17 Sep 2019 16:25:04 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,518,1559545200"; d="scan'208";a="180940510" Received: from sjchrist-coffee.jf.intel.com (HELO linux.intel.com) ([10.54.74.41]) by orsmga008.jf.intel.com with ESMTP; 17 Sep 2019 16:25:04 -0700 Date: Tue, 17 Sep 2019 16:25:04 -0700 From: Sean Christopherson To: Jarkko Sakkinen Cc: linux-sgx@vger.kernel.org, Shay Katz-zamir , Serge Ayoun Subject: Re: [PATCH v3 13/17] x86/sgx: Introduce sgx_can_reclaim() Message-ID: <20190917232504.GH10319@linux.intel.com> References: <20190916101803.30726-1-jarkko.sakkinen@linux.intel.com> <20190916101803.30726-14-jarkko.sakkinen@linux.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20190916101803.30726-14-jarkko.sakkinen@linux.intel.com> User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-sgx-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-sgx@vger.kernel.org On Mon, Sep 16, 2019 at 01:17:59PM +0300, Jarkko Sakkinen wrote: > Make sgx_reclaim_evict() idempotennt and rename it to sgx_can_reclaim() and > set SGX_ENCL_PAGE_RECLAIMED in the call site. > > Cc: Sean Christopherson > Cc: Shay Katz-zamir > Cc: Serge Ayoun > Signed-off-by: Jarkko Sakkinen > --- > arch/x86/kernel/cpu/sgx/reclaim.c | 32 +++++++++++++++++-------------- > 1 file changed, 18 insertions(+), 14 deletions(-) > > diff --git a/arch/x86/kernel/cpu/sgx/reclaim.c b/arch/x86/kernel/cpu/sgx/reclaim.c > index 5a4d44dd02d7..cc3155b61513 100644 > --- a/arch/x86/kernel/cpu/sgx/reclaim.c > +++ b/arch/x86/kernel/cpu/sgx/reclaim.c > @@ -121,7 +121,19 @@ void sgx_mark_page_reclaimable(struct sgx_epc_page *page) > spin_unlock(&sgx_active_page_list_lock); > } > > -static bool sgx_reclaimer_evict(struct sgx_epc_page *epc_page) > +/** > + * sgx_can_reclaim() - Filter out the pages that should not be reclaimed > + * @epc_page: a candidate EPC page > + * > + * Do not reclaim this page if it has been recently accessed by any mm_struct > + * *and* if the enclave is still alive. No need to take the enclave's lock, > + * worst case scenario reclaiming pages from a dead enclave is delayed slightly. > + * A live enclave with a recently accessed page is more common and avoiding lock > + * contention in that case is a boon to performance. > + * > + * Return: true if the page should be reclaimed > + */ > +static bool sgx_can_reclaim(struct sgx_epc_page *epc_page) > { > struct sgx_encl_page *page = epc_page->owner; > struct sgx_encl *encl = page->encl; > @@ -147,21 +159,9 @@ static bool sgx_reclaimer_evict(struct sgx_epc_page *epc_page) > > srcu_read_unlock(&encl->srcu, idx); > > - /* > - * Do not reclaim this page if it has been recently accessed by any > - * mm_struct *and* if the enclave is still alive. No need to take > - * the enclave's lock, worst case scenario reclaiming pages from a > - * dead enclave is delayed slightly. A live enclave with a recently > - * accessed page is more common and avoiding lock contention in that > - * case is a boon to performance. > - */ > if (!ret && !(atomic_read(&encl->flags) & SGX_ENCL_DEAD)) > return false; > > - mutex_lock(&encl->lock); > - page->desc |= SGX_ENCL_PAGE_RECLAIMED; > - mutex_unlock(&encl->lock); > - > return true; > } > > @@ -405,8 +405,12 @@ void sgx_reclaim_pages(void) > epc_page = chunk[i]; > encl_page = epc_page->owner; > > - if (sgx_reclaimer_evict(epc_page)) > + if (sgx_can_reclaim(epc_page)) { > + mutex_lock(&encl_page->encl->lock); > + encl_page->desc |= SGX_ENCL_PAGE_RECLAIMED; If we move setting SGX_ENCL_PAGE_RECLAIMED here, then we should also move the clearing (currently in sgx_encl_ewb()) into the loop that calls sgx_reclaimer_write(). That would also fix the issue of SGX_ENCL_PAGE_RECLAIMED being left set when the enclave is dead. > + mutex_unlock(&encl_page->encl->lock); > continue; > + } > > kref_put(&encl_page->encl->refcount, sgx_encl_release); > > -- > 2.20.1 >