From patchwork Mon Jan 16 15:55:49 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jan Kiszka X-Patchwork-Id: 136316 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [140.186.70.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id 7BFF81007D2 for ; Tue, 17 Jan 2012 03:52:58 +1100 (EST) Received: from localhost ([::1]:48633 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Rmovf-0002eo-KO for incoming@patchwork.ozlabs.org; Mon, 16 Jan 2012 10:57:03 -0500 Received: from eggs.gnu.org ([140.186.70.92]:54700) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Rmouu-0000X8-J3 for qemu-devel@nongnu.org; Mon, 16 Jan 2012 10:56:19 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Rmoui-0002nE-LT for qemu-devel@nongnu.org; Mon, 16 Jan 2012 10:56:16 -0500 Received: from thoth.sbs.de ([192.35.17.2]:21125) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Rmoui-0002mm-44 for qemu-devel@nongnu.org; Mon, 16 Jan 2012 10:56:04 -0500 Received: from mail1.siemens.de (localhost [127.0.0.1]) by thoth.sbs.de (8.13.6/8.13.6) with ESMTP id q0GFttHG007083; Mon, 16 Jan 2012 16:55:55 +0100 Received: from mchn199C.mchp.siemens.de ([139.25.109.49]) by mail1.siemens.de (8.13.6/8.13.6) with ESMTP id q0GFtql7023489; Mon, 16 Jan 2012 16:55:55 +0100 From: Jan Kiszka To: Avi Kivity , Marcelo Tosatti Date: Mon, 16 Jan 2012 16:55:49 +0100 Message-Id: <30001fdf32f57398b2a988865977f15b0abdcf14.1326729350.git.jan.kiszka@siemens.com> X-Mailer: git-send-email 1.7.3.4 In-Reply-To: References: In-Reply-To: References: X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6, seldom 2.4 (older, 4) X-Received-From: 192.35.17.2 Cc: Anthony Liguori , Lai Jiangshan , kvm@vger.kernel.org, "Michael S. Tsirkin" , qemu-devel , Blue Swirl Subject: [Qemu-devel] [PATCH v7 15/18] kvm: x86: Add user space part for in-kernel APIC 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 This introduces the alternative APIC device which makes use of KVM's in-kernel device model. External NMI injection via LINT1 is emulated by checking the current state of the in-kernel APIC, only injecting a NMI into the VCPU if LINT1 is unmasked and configured to DM_NMI. MSI is not yet supported, so we disable this when the in-kernel model is in use. CC: Lai Jiangshan Signed-off-by: Jan Kiszka --- Makefile.target | 2 +- hw/kvm/apic.c | 138 +++++++++++++++++++++++++++++++++++++++++++++++++++++ hw/pc.c | 15 ++++-- kvm.h | 4 ++ target-i386/kvm.c | 38 +++++++++++++++ 5 files changed, 191 insertions(+), 6 deletions(-) create mode 100644 hw/kvm/apic.c diff --git a/Makefile.target b/Makefile.target index 4fa91d3..5e5b5d1 100644 --- a/Makefile.target +++ b/Makefile.target @@ -228,7 +228,7 @@ obj-i386-y += vmport.o obj-i386-y += device-hotplug.o pci-hotplug.o smbios.o wdt_ib700.o obj-i386-y += debugcon.o multiboot.o obj-i386-y += pc_piix.o -obj-i386-$(CONFIG_KVM) += kvm/clock.o +obj-i386-$(CONFIG_KVM) += kvm/clock.o kvm/apic.o obj-i386-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o # shared objects diff --git a/hw/kvm/apic.c b/hw/kvm/apic.c new file mode 100644 index 0000000..6300695 --- /dev/null +++ b/hw/kvm/apic.c @@ -0,0 +1,138 @@ +/* + * KVM in-kernel APIC support + * + * Copyright (c) 2011 Siemens AG + * + * Authors: + * Jan Kiszka + * + * This work is licensed under the terms of the GNU GPL version 2. + * See the COPYING file in the top-level directory. + */ +#include "hw/apic_internal.h" +#include "kvm.h" + +static inline void kvm_apic_set_reg(struct kvm_lapic_state *kapic, + int reg_id, uint32_t val) +{ + *((uint32_t *)(kapic->regs + (reg_id << 4))) = val; +} + +static inline uint32_t kvm_apic_get_reg(struct kvm_lapic_state *kapic, + int reg_id) +{ + return *((uint32_t *)(kapic->regs + (reg_id << 4))); +} + +void kvm_put_apic_state(DeviceState *d, struct kvm_lapic_state *kapic) +{ + APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d); + int i; + + memset(kapic, 0, sizeof(kapic)); + kvm_apic_set_reg(kapic, 0x2, s->id << 24); + kvm_apic_set_reg(kapic, 0x8, s->tpr); + kvm_apic_set_reg(kapic, 0xd, s->log_dest << 24); + kvm_apic_set_reg(kapic, 0xe, s->dest_mode << 28 | 0x0fffffff); + kvm_apic_set_reg(kapic, 0xf, s->spurious_vec); + for (i = 0; i < 8; i++) { + kvm_apic_set_reg(kapic, 0x10 + i, s->isr[i]); + kvm_apic_set_reg(kapic, 0x18 + i, s->tmr[i]); + kvm_apic_set_reg(kapic, 0x20 + i, s->irr[i]); + } + kvm_apic_set_reg(kapic, 0x28, s->esr); + kvm_apic_set_reg(kapic, 0x30, s->icr[0]); + kvm_apic_set_reg(kapic, 0x31, s->icr[1]); + for (i = 0; i < APIC_LVT_NB; i++) { + kvm_apic_set_reg(kapic, 0x32 + i, s->lvt[i]); + } + kvm_apic_set_reg(kapic, 0x38, s->initial_count); + kvm_apic_set_reg(kapic, 0x3e, s->divide_conf); +} + +void kvm_get_apic_state(DeviceState *d, struct kvm_lapic_state *kapic) +{ + APICCommonState *s = DO_UPCAST(APICCommonState, busdev.qdev, d); + int i, v; + + s->id = kvm_apic_get_reg(kapic, 0x2) >> 24; + s->tpr = kvm_apic_get_reg(kapic, 0x8); + s->arb_id = kvm_apic_get_reg(kapic, 0x9); + s->log_dest = kvm_apic_get_reg(kapic, 0xd) >> 24; + s->dest_mode = kvm_apic_get_reg(kapic, 0xe) >> 28; + s->spurious_vec = kvm_apic_get_reg(kapic, 0xf); + for (i = 0; i < 8; i++) { + s->isr[i] = kvm_apic_get_reg(kapic, 0x10 + i); + s->tmr[i] = kvm_apic_get_reg(kapic, 0x18 + i); + s->irr[i] = kvm_apic_get_reg(kapic, 0x20 + i); + } + s->esr = kvm_apic_get_reg(kapic, 0x28); + s->icr[0] = kvm_apic_get_reg(kapic, 0x30); + s->icr[1] = kvm_apic_get_reg(kapic, 0x31); + for (i = 0; i < APIC_LVT_NB; i++) { + s->lvt[i] = kvm_apic_get_reg(kapic, 0x32 + i); + } + s->initial_count = kvm_apic_get_reg(kapic, 0x38); + s->divide_conf = kvm_apic_get_reg(kapic, 0x3e); + + v = (s->divide_conf & 3) | ((s->divide_conf >> 1) & 4); + s->count_shift = (v + 1) & 7; + + s->initial_count_load_time = qemu_get_clock_ns(vm_clock); + apic_next_timer(s, s->initial_count_load_time); +} + +static void kvm_apic_set_base(APICCommonState *s, uint64_t val) +{ + s->apicbase = val; +} + +static void kvm_apic_set_tpr(APICCommonState *s, uint8_t val) +{ + s->tpr = (val & 0x0f) << 4; +} + +static void do_inject_external_nmi(void *data) +{ + APICCommonState *s = data; + CPUState *env = s->cpu_env; + uint32_t lvt; + int ret; + + cpu_synchronize_state(env); + + lvt = s->lvt[APIC_LVT_LINT1]; + if (!(lvt & APIC_LVT_MASKED) && ((lvt >> 8) & 7) == APIC_DM_NMI) { + ret = kvm_vcpu_ioctl(env, KVM_NMI); + if (ret < 0) { + fprintf(stderr, "KVM: injection failed, NMI lost (%s)\n", + strerror(-ret)); + } + } +} + +static void kvm_apic_external_nmi(APICCommonState *s) +{ + run_on_cpu(s->cpu_env, do_inject_external_nmi, s); +} + +static void kvm_apic_init(APICCommonState *s) +{ + memory_region_init_reservation(&s->io_memory, "kvm-apic-msi", + MSI_SPACE_SIZE); +} + +static APICCommonInfo kvm_apic_info = { + .busdev.qdev.name = "kvm-apic", + .init = kvm_apic_init, + .set_base = kvm_apic_set_base, + .set_tpr = kvm_apic_set_tpr, + .external_nmi = kvm_apic_external_nmi, +}; + +static void kvm_apic_register_device(void) +{ + apic_qdev_register(&kvm_apic_info); +} + +device_init(kvm_apic_register_device) diff --git a/hw/pc.c b/hw/pc.c index 9519079..5f6ac8a 100644 --- a/hw/pc.c +++ b/hw/pc.c @@ -879,25 +879,30 @@ DeviceState *cpu_get_current_apic(void) static DeviceState *apic_init(void *env, uint8_t apic_id) { DeviceState *dev; - SysBusDevice *d; static int apic_mapped; - dev = qdev_create(NULL, "apic"); + if (kvm_enabled() && kvm_irqchip_in_kernel()) { + dev = qdev_create(NULL, "kvm-apic"); + } else { + dev = qdev_create(NULL, "apic"); + } qdev_prop_set_uint8(dev, "id", apic_id); qdev_prop_set_ptr(dev, "cpu_env", env); qdev_init_nofail(dev); - d = sysbus_from_qdev(dev); /* XXX: mapping more APICs at the same memory location */ if (apic_mapped == 0) { /* NOTE: the APIC is directly connected to the CPU - it is not on the global memory bus. */ /* XXX: what if the base changes? */ - sysbus_mmio_map(d, 0, MSI_ADDR_BASE); + sysbus_mmio_map(sysbus_from_qdev(dev), 0, MSI_ADDR_BASE); apic_mapped = 1; } - msi_supported = true; + /* KVM does not support MSI yet. */ + if (!kvm_enabled() || !kvm_irqchip_in_kernel()) { + msi_supported = true; + } return dev; } diff --git a/kvm.h b/kvm.h index a3c87af..f866296 100644 --- a/kvm.h +++ b/kvm.h @@ -31,6 +31,7 @@ extern int kvm_allowed; #endif struct kvm_run; +struct kvm_lapic_state; typedef struct KVMCapabilityInfo { const char *name; @@ -134,6 +135,9 @@ int kvm_irqchip_set_irq(KVMState *s, int irq, int level); void kvm_irqchip_add_route(KVMState *s, int gsi, int irqchip, int pin); int kvm_irqchip_commit_routes(KVMState *s); +void kvm_put_apic_state(DeviceState *d, struct kvm_lapic_state *kapic); +void kvm_get_apic_state(DeviceState *d, struct kvm_lapic_state *kapic); + struct kvm_guest_debug; struct kvm_debug_exit_arch; diff --git a/target-i386/kvm.c b/target-i386/kvm.c index 9d1191f..274b3cb 100644 --- a/target-i386/kvm.c +++ b/target-i386/kvm.c @@ -1277,6 +1277,36 @@ static int kvm_get_mp_state(CPUState *env) return 0; } +static int kvm_get_apic(CPUState *env) +{ + DeviceState *apic = env->apic_state; + struct kvm_lapic_state kapic; + int ret; + + if (apic && kvm_enabled() && kvm_irqchip_in_kernel()) { + ret = kvm_vcpu_ioctl(env, KVM_GET_LAPIC, &kapic); + if (ret < 0) { + return ret; + } + + kvm_get_apic_state(apic, &kapic); + } + return 0; +} + +static int kvm_put_apic(CPUState *env) +{ + DeviceState *apic = env->apic_state; + struct kvm_lapic_state kapic; + + if (apic && kvm_enabled() && kvm_irqchip_in_kernel()) { + kvm_put_apic_state(apic, &kapic); + + return kvm_vcpu_ioctl(env, KVM_SET_LAPIC, &kapic); + } + return 0; +} + static int kvm_put_vcpu_events(CPUState *env, int level) { struct kvm_vcpu_events events; @@ -1450,6 +1480,10 @@ int kvm_arch_put_registers(CPUState *env, int level) if (ret < 0) { return ret; } + ret = kvm_put_apic(env); + if (ret < 0) { + return ret; + } } ret = kvm_put_vcpu_events(env, level); if (ret < 0) { @@ -1497,6 +1531,10 @@ int kvm_arch_get_registers(CPUState *env) if (ret < 0) { return ret; } + ret = kvm_get_apic(env); + if (ret < 0) { + return ret; + } ret = kvm_get_vcpu_events(env); if (ret < 0) { return ret;