From patchwork Tue Feb 25 10:05:21 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christian Borntraeger X-Patchwork-Id: 323907 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [IPv6:2001:4830:134:3::11]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 80C132C00AE for ; Tue, 25 Feb 2014 21:11:23 +1100 (EST) Received: from localhost ([::1]:34015 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WIEyu-00074W-Hs for incoming@patchwork.ozlabs.org; Tue, 25 Feb 2014 05:11:20 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:55012) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WIEtG-0007rS-HQ for qemu-devel@nongnu.org; Tue, 25 Feb 2014 05:05:39 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1WIEt5-0005BU-Er for qemu-devel@nongnu.org; Tue, 25 Feb 2014 05:05:30 -0500 Received: from e06smtp11.uk.ibm.com ([195.75.94.107]:45736) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WIEt5-0005Ad-5B for qemu-devel@nongnu.org; Tue, 25 Feb 2014 05:05:19 -0500 Received: from /spool/local by e06smtp11.uk.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Tue, 25 Feb 2014 10:05:17 -0000 Received: from d06dlp01.portsmouth.uk.ibm.com (9.149.20.13) by e06smtp11.uk.ibm.com (192.168.101.141) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Tue, 25 Feb 2014 10:05:15 -0000 Received: from b06cxnps4074.portsmouth.uk.ibm.com (d06relay11.portsmouth.uk.ibm.com [9.149.109.196]) by d06dlp01.portsmouth.uk.ibm.com (Postfix) with ESMTP id 5EEE817D806B for ; Tue, 25 Feb 2014 10:05:47 +0000 (GMT) Received: from d06av07.portsmouth.uk.ibm.com (d06av07.portsmouth.uk.ibm.com [9.149.37.248]) by b06cxnps4074.portsmouth.uk.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id s1PA52TX53411888 for ; Tue, 25 Feb 2014 10:05:02 GMT Received: from d06av07.portsmouth.uk.ibm.com (localhost [127.0.0.1]) by d06av07.portsmouth.uk.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id s1PA5DuT028020 for ; Tue, 25 Feb 2014 05:05:14 -0500 Received: from tuxmaker.boeblingen.de.ibm.com (tuxmaker.boeblingen.de.ibm.com [9.152.85.9]) by d06av07.portsmouth.uk.ibm.com (8.14.4/8.14.4/NCO v10.0 AVin) with ESMTP id s1PA5Dui028006; Tue, 25 Feb 2014 05:05:13 -0500 Received: by tuxmaker.boeblingen.de.ibm.com (Postfix, from userid 25651) id 45908122443E; Tue, 25 Feb 2014 11:05:13 +0100 (CET) From: Christian Borntraeger To: Anthony Liguori , Peter Maydell Date: Tue, 25 Feb 2014 11:05:21 +0100 Message-Id: <1393322735-31277-4-git-send-email-borntraeger@de.ibm.com> X-Mailer: git-send-email 1.8.4.2 In-Reply-To: <1393322735-31277-1-git-send-email-borntraeger@de.ibm.com> References: <1393322735-31277-1-git-send-email-borntraeger@de.ibm.com> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 14022510-5024-0000-0000-000008DDC817 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.4.x-2.6.x [generic] X-Received-From: 195.75.94.107 Cc: qemu-devel , Dominik Dingel , Alexander Graf , Christian Borntraeger , Jens Freimann , Cornelia Huck , Paolo Bonzini , Richard Henderson Subject: [Qemu-devel] [PATCH 03/17] s390x/async_pf: Check for apf extension and enable pfault X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org From: Dominik Dingel S390 can also use async page faults, to enhance guest scheduling. In case of live migration we want to disable the feature and let all pending request finish. Signed-off-by: Dominik Dingel Signed-off-by: Jens Freimann Signed-off-by: Christian Borntraeger --- hw/intc/s390_flic.c | 36 ++++++++++++++++++++++++++++++++++++ target-s390x/cpu.c | 6 ++++++ target-s390x/cpu.h | 4 ++++ target-s390x/kvm.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 94 insertions(+) diff --git a/hw/intc/s390_flic.c b/hw/intc/s390_flic.c index 1a7876d..b2ef3e3 100644 --- a/hw/intc/s390_flic.c +++ b/hw/intc/s390_flic.c @@ -63,6 +63,34 @@ static int flic_get_all_irqs(KVMS390FLICState *flic, return rc == -1 ? -errno : rc; } +static void flic_enable_pfault(KVMS390FLICState *flic) +{ + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_APF_ENABLE, + }; + int rc; + + rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + + if (rc) { + fprintf(stderr, "flic: couldn't enable pfault\n"); + } +} + +static void flic_disable_wait_pfault(KVMS390FLICState *flic) +{ + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, + }; + int rc; + + rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + + if (rc) { + fprintf(stderr, "flic: couldn't disable pfault\n"); + } +} + /** flic_enqueue_irqs - returns 0 on success * @buf: pointer to buffer which is passed to kernel * @len: length of buffer @@ -136,6 +164,8 @@ static void kvm_flic_save(QEMUFile *f, void *opaque) void *buf; int count; + flic_disable_wait_pfault((struct KVMS390FLICState *) opaque); + buf = g_try_malloc0(len); if (!buf) { /* Storing FLIC_FAILED into the count field here will cause the @@ -184,6 +214,8 @@ static int kvm_flic_load(QEMUFile *f, void *opaque, int version_id) goto out; } + flic_enable_pfault((struct KVMS390FLICState *) opaque); + count = qemu_get_be64(f); len = count * sizeof(struct kvm_s390_irq); if (count == FLIC_FAILED) { @@ -256,10 +288,14 @@ static void kvm_s390_flic_reset(DeviceState *dev) return; } + flic_disable_wait_pfault(flic); + rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); if (rc) { trace_flic_reset_failed(errno); } + + flic_enable_pfault(flic); } static void kvm_s390_flic_class_init(ObjectClass *oc, void *data) diff --git a/target-s390x/cpu.c b/target-s390x/cpu.c index ff57b80..f1319e5 100644 --- a/target-s390x/cpu.c +++ b/target-s390x/cpu.c @@ -83,6 +83,7 @@ static void s390_cpu_reset(CPUState *s) S390CPUClass *scc = S390_CPU_GET_CLASS(cpu); CPUS390XState *env = &cpu->env; + env->pfault_token = -1UL; s390_del_running_cpu(cpu); scc->parent_reset(s); #if !defined(CONFIG_USER_ONLY) @@ -105,6 +106,8 @@ static void s390_cpu_initial_reset(CPUState *s) /* architectured initial values for CR 0 and 14 */ env->cregs[0] = CR0_RESET; env->cregs[14] = CR14_RESET; + + env->pfault_token = -1UL; } /* CPUClass:reset() */ @@ -123,6 +126,9 @@ static void s390_cpu_full_reset(CPUState *s) /* architectured initial values for CR 0 and 14 */ env->cregs[0] = CR0_RESET; env->cregs[14] = CR14_RESET; + + env->pfault_token = -1UL; + /* set halted to 1 to make sure we can add the cpu in * s390_ipl_cpu code, where CPUState::halted is set back to 0 * after incrementing the cpu counter */ diff --git a/target-s390x/cpu.h b/target-s390x/cpu.h index 96c2b4a..b09ff92 100644 --- a/target-s390x/cpu.h +++ b/target-s390x/cpu.h @@ -121,6 +121,10 @@ typedef struct CPUS390XState { uint64_t cputm; uint32_t todpr; + uint64_t pfault_token; + uint64_t pfault_compare; + uint64_t pfault_select; + CPU_COMMON /* reset does memset(0) up to here */ diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c index f60ccdc..9430a35 100644 --- a/target-s390x/kvm.c +++ b/target-s390x/kvm.c @@ -87,12 +87,14 @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = { }; static int cap_sync_regs; +static int cap_async_pf; static void *legacy_s390_alloc(size_t size); int kvm_arch_init(KVMState *s) { cap_sync_regs = kvm_check_extension(s, KVM_CAP_SYNC_REGS); + cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF); if (!kvm_check_extension(s, KVM_CAP_S390_GMAP) || !kvm_check_extension(s, KVM_CAP_S390_COW)) { phys_mem_set_alloc(legacy_s390_alloc); @@ -178,6 +180,29 @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } + if (cap_async_pf) { + reg.id = KVM_REG_S390_PFTOKEN; + reg.addr = (__u64)&(env->pfault_token); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + if (ret < 0) { + return ret; + } + + reg.id = KVM_REG_S390_PFCOMPARE; + reg.addr = (__u64)&(env->pfault_compare); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + if (ret < 0) { + return ret; + } + + reg.id = KVM_REG_S390_PFSELECT; + reg.addr = (__u64)&(env->pfault_select); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + if (ret < 0) { + return ret; + } + } + if (cap_sync_regs && cs->kvm_run->kvm_valid_regs & KVM_SYNC_ACRS && cs->kvm_run->kvm_valid_regs & KVM_SYNC_CRS) { @@ -282,6 +307,29 @@ int kvm_arch_get_registers(CPUState *cs) return r; } + if (cap_async_pf) { + reg.id = KVM_REG_S390_PFTOKEN; + reg.addr = (__u64)&(env->pfault_token); + r = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + if (r < 0) { + return r; + } + + reg.id = KVM_REG_S390_PFCOMPARE; + reg.addr = (__u64)&(env->pfault_compare); + r = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + if (r < 0) { + return r; + } + + reg.id = KVM_REG_S390_PFSELECT; + reg.addr = (__u64)&(env->pfault_select); + r = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + if (r < 0) { + return r; + } + } + return 0; }