From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ozlabs.org (ozlabs.org [103.22.144.67]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 147E71A1A1A for ; Fri, 18 Dec 2015 07:59:49 +1100 (AEDT) Received: from e36.co.us.ibm.com (e36.co.us.ibm.com [32.97.110.154]) (using TLSv1 with cipher CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 23812140BA8 for ; Fri, 18 Dec 2015 07:59:47 +1100 (AEDT) Received: from localhost by e36.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Thu, 17 Dec 2015 13:59:46 -0700 Received: from b03cxnp08025.gho.boulder.ibm.com (b03cxnp08025.gho.boulder.ibm.com [9.17.130.17]) by d03dlp01.boulder.ibm.com (Postfix) with ESMTP id D49AEC40004 for ; Thu, 17 Dec 2015 13:47:42 -0700 (MST) Received: from d03av02.boulder.ibm.com (d03av02.boulder.ibm.com [9.17.195.168]) by b03cxnp08025.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id tBHKxV2B25428028 for ; Thu, 17 Dec 2015 13:59:31 -0700 Received: from d03av02.boulder.ibm.com (localhost [127.0.0.1]) by d03av02.boulder.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id tBHKxUG3015150 for ; Thu, 17 Dec 2015 13:59:31 -0700 From: Suresh Warrier To: kvm@vger.kernel.org, linuxppc-dev@ozlabs.org Cc: warrier@linux.vnet.ibm.com, paulus@samba.org, agraf@suse.de, mpe@ellerman.id.au Subject: [PATCH v3 5/9] KVM: PPC: Book3S HV: Manage core host state Date: Thu, 17 Dec 2015 14:59:07 -0600 Message-Id: <1450385951-25128-6-git-send-email-warrier@linux.vnet.ibm.com> In-Reply-To: <1450385951-25128-1-git-send-email-warrier@linux.vnet.ibm.com> References: <1450385951-25128-1-git-send-email-warrier@linux.vnet.ibm.com> List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Update the core host state in kvmppc_host_rm_ops whenever the primary thread of the core enters the guest or returns back. Signed-off-by: Suresh Warrier --- arch/powerpc/kvm/book3s_hv.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 4042623..95a2ed3 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2261,6 +2261,46 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) } /* + * Clear core from the list of active host cores as we are about to + * enter the guest. Only do this if it is the primary thread of the + * core (not if a subcore) that is entering the guest. + */ +static inline void kvmppc_clear_host_core(int cpu) +{ + int core; + + if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu)) + return; + /* + * Memory barrier can be omitted here as we will do a smp_wmb() + * later in kvmppc_start_thread and we need ensure that state is + * visible to other CPUs only after we enter guest. + */ + core = cpu >> threads_shift; + kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0; +} + +/* + * Advertise this core as an active host core since we exited the guest + * Only need to do this if it is the primary thread of the core that is + * exiting. + */ +static inline void kvmppc_set_host_core(int cpu) +{ + int core; + + if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu)) + return; + + /* + * Memory barrier can be omitted here because we do a spin_unlock + * immediately after this which provides the memory barrier. + */ + core = cpu >> threads_shift; + kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1; +} + +/* * Run a set of guest threads on a physical core. * Called with vc->lock held. */ @@ -2372,6 +2412,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) } } + kvmppc_clear_host_core(pcpu); + /* Start all the threads */ active = 0; for (sub = 0; sub < core_info.n_subcores; ++sub) { @@ -2468,6 +2510,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_ipi_thread(pcpu + i); } + kvmppc_set_host_core(pcpu); + spin_unlock(&vc->lock); /* make sure updates to secondary vcpu structs are visible now */ -- 1.8.3.4