diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2008-01-31 09:30:10 +1100 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-01-31 09:30:10 +1100 |
commit | 2c57ee6f924c95e4dce61ed4776fb3f62e1b9f92 (patch) | |
tree | b9d92e52e8c0ee68a0f5012b470c6146a9f0b65a /arch/x86/kvm | |
parent | f389e9fcecdec4c4cb890ad28ea30a87a579ec3e (diff) | |
parent | 2f52d58c92d971bf421f461ad06eb93fb4f34981 (diff) |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (249 commits)
KVM: Move apic timer migration away from critical section
KVM: Put kvm_para.h include outside __KERNEL__
KVM: Fix unbounded preemption latency
KVM: Initialize the mmu caches only after verifying cpu support
KVM: MMU: Fix dirty page setting for pages removed from rmap
KVM: Portability: Move kvm_fpu to asm-x86/kvm.h
KVM: x86 emulator: Only allow VMCALL/VMMCALL trapped by #UD
KVM: MMU: Merge shadow level check in FNAME(fetch)
KVM: MMU: Move kvm_free_some_pages() into critical section
KVM: MMU: Switch to mmu spinlock
KVM: MMU: Avoid calling gfn_to_page() in mmu_set_spte()
KVM: Add kvm_read_guest_atomic()
KVM: MMU: Concurrent guest walkers
KVM: Disable vapic support on Intel machines with FlexPriority
KVM: Accelerated apic support
KVM: local APIC TPR access reporting facility
KVM: Print data for unimplemented wrmsr
KVM: MMU: Add cache miss statistic
KVM: MMU: Coalesce remote tlb flushes
KVM: Expose ioapic to ia64 save/restore APIs
...
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 57 | ||||
-rw-r--r-- | arch/x86/kvm/Makefile | 14 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 450 | ||||
-rw-r--r-- | arch/x86/kvm/irq.c | 78 | ||||
-rw-r--r-- | arch/x86/kvm/irq.h | 88 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_svm.h | 45 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 1154 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 50 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 1885 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 44 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 484 | ||||
-rw-r--r-- | arch/x86/kvm/segment_descriptor.h | 29 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 1731 | ||||
-rw-r--r-- | arch/x86/kvm/svm.h | 325 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 2679 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.h | 324 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 3287 | ||||
-rw-r--r-- | arch/x86/kvm/x86_emulate.c | 1912 |
18 files changed, 14636 insertions, 0 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig new file mode 100644 index 00000000000..c83e1c9b512 --- /dev/null +++ b/arch/x86/kvm/Kconfig @@ -0,0 +1,57 @@ +# +# KVM configuration +# +config HAVE_KVM + bool + +menuconfig VIRTUALIZATION + bool "Virtualization" + depends on HAVE_KVM || X86 + default y + ---help--- + Say Y here to get to see options for using your Linux host to run other + operating systems inside virtual machines (guests). + This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped and disabled. + +if VIRTUALIZATION + +config KVM + tristate "Kernel-based Virtual Machine (KVM) support" + depends on HAVE_KVM && EXPERIMENTAL + select PREEMPT_NOTIFIERS + select ANON_INODES + ---help--- + Support hosting fully virtualized guest machines using hardware + virtualization extensions. You will need a fairly recent + processor equipped with virtualization extensions. You will also + need to select one or more of the processor modules below. + + This module provides access to the hardware capabilities through + a character device node named /dev/kvm. + + To compile this as a module, choose M here: the module + will be called kvm. + + If unsure, say N. + +config KVM_INTEL + tristate "KVM for Intel processors support" + depends on KVM + ---help--- + Provides support for KVM on Intel processors equipped with the VT + extensions. + +config KVM_AMD + tristate "KVM for AMD processors support" + depends on KVM + ---help--- + Provides support for KVM on AMD processors equipped with the AMD-V + (SVM) extensions. + +# OK, it's a little counter-intuitive to do this, but it puts it neatly under +# the virtualization menu. +source drivers/lguest/Kconfig + +endif # VIRTUALIZATION diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile new file mode 100644 index 00000000000..ffdd0b31078 --- /dev/null +++ b/arch/x86/kvm/Makefile @@ -0,0 +1,14 @@ +# +# Makefile for Kernel-based Virtual Machine module +# + +common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o) + +EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm + +kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o +obj-$(CONFIG_KVM) += kvm.o +kvm-intel-objs = vmx.o +obj-$(CONFIG_KVM_INTEL) += kvm-intel.o +kvm-amd-objs = svm.o +obj-$(CONFIG_KVM_AMD) += kvm-amd.o diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c new file mode 100644 index 00000000000..ab29cf2def4 --- /dev/null +++ b/arch/x86/kvm/i8259.c @@ -0,0 +1,450 @@ +/* + * 8259 interrupt controller emulation + * + * Copyright (c) 2003-2004 Fabrice Bellard + * Copyright (c) 2007 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + * Authors: + * Yaozu (Eddie) Dong <Eddie.dong@intel.com> + * Port from Qemu. + */ +#include <linux/mm.h> +#include "irq.h" + +#include <linux/kvm_host.h> + +/* + * set irq level. If an edge is detected, then the IRR is set to 1 + */ +static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) +{ + int mask; + mask = 1 << irq; + if (s->elcr & mask) /* level triggered */ + if (level) { + s->irr |= mask; + s->last_irr |= mask; + } else { + s->irr &= ~mask; + s->last_irr &= ~mask; + } + else /* edge triggered */ + if (level) { + if ((s->last_irr & mask) == 0) + s->irr |= mask; + s->last_irr |= mask; + } else + s->last_irr &= ~mask; +} + +/* + * return the highest priority found in mask (highest = smallest + * number). Return 8 if no irq + */ +static inline int get_priority(struct kvm_kpic_state *s, int mask) +{ + int priority; + if (mask == 0) + return 8; + priority = 0; + while ((mask & (1 << ((priority + s->priority_add) & 7))) == 0) + priority++; + return priority; +} + +/* + * return the pic wanted interrupt. return -1 if none + */ +static int pic_get_irq(struct kvm_kpic_state *s) +{ + int mask, cur_priority, priority; + + mask = s->irr & ~s->imr; + priority = get_priority(s, mask); + if (priority == 8) + return -1; + /* + * compute current priority. If special fully nested mode on the + * master, the IRQ coming from the slave is not taken into account + * for the priority computation. + */ + mask = s->isr; + if (s->special_fully_nested_mode && s == &s->pics_state->pics[0]) + mask &= ~(1 << 2); + cur_priority = get_priority(s, mask); + if (priority < cur_priority) + /* + * higher priority found: an irq should be generated + */ + return (priority + s->priority_add) & 7; + else + return -1; +} + +/* + * raise irq to CPU if necessary. must be called every time the active + * irq may change + */ +static void pic_update_irq(struct kvm_pic *s) +{ + int irq2, irq; + + irq2 = pic_get_irq(&s->pics[1]); + if (irq2 >= 0) { + /* + * if irq request by slave pic, signal master PIC + */ + pic_set_irq1(&s->pics[0], 2, 1); + pic_set_irq1(&s->pics[0], 2, 0); + } + irq = pic_get_irq(&s->pics[0]); + if (irq >= 0) + s->irq_request(s->irq_request_opaque, 1); + else + s->irq_request(s->irq_request_opaque, 0); +} + +void kvm_pic_update_irq(struct kvm_pic *s) +{ + pic_update_irq(s); +} + +void kvm_pic_set_irq(void *opaque, int irq, int level) +{ + struct kvm_pic *s = opaque; + + pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); + pic_update_irq(s); +} + +/* + * acknowledge interrupt 'irq' + */ +static inline void pic_intack(struct kvm_kpic_state *s, int irq) +{ + if (s->auto_eoi) { + if (s->rotate_on_auto_eoi) + s->priority_add = (irq + 1) & 7; + } else + s->isr |= (1 << irq); + /* + * We don't clear a level sensitive interrupt here + */ + if (!(s->elcr & (1 << irq))) + s->irr &= ~(1 << irq); +} + +int kvm_pic_read_irq(struct kvm_pic *s) +{ + int irq, irq2, intno; + + irq = pic_get_irq(&s->pics[0]); + if (irq >= 0) { + pic_intack(&s->pics[0], irq); + if (irq == 2) { + irq2 = pic_get_irq(&s->pics[1]); + if (irq2 >= 0) + pic_intack(&s->pics[1], irq2); + else + /* + * spurious IRQ on slave controller + */ + irq2 = 7; + intno = s->pics[1].irq_base + irq2; + irq = irq2 + 8; + } else + intno = s->pics[0].irq_base + irq; + } else { + /* + * spurious IRQ on host controller + */ + irq = 7; + intno = s->pics[0].irq_base + irq; + } + pic_update_irq(s); + + return intno; +} + +void kvm_pic_reset(struct kvm_kpic_state *s) +{ + s->last_irr = 0; + s->irr = 0; + s->imr = 0; + s->isr = 0; + s->priority_add = 0; + s->irq_base = 0; + s->read_reg_select = 0; + s->poll = 0; + s->special_mask = 0; + s->init_state = 0; + s->auto_eoi = 0; + s->rotate_on_auto_eoi = 0; + s->special_fully_nested_mode = 0; + s->init4 = 0; +} + +static void pic_ioport_write(void *opaque, u32 addr, u32 val) +{ + struct kvm_kpic_state *s = opaque; + int priority, cmd, irq; + + addr &= 1; + if (addr == 0) { + if (val & 0x10) { + kvm_pic_reset(s); /* init */ + /* + * deassert a pending interrupt + */ + s->pics_state->irq_request(s->pics_state-> + irq_request_opaque, 0); + s->init_state = 1; + s->init4 = val & 1; + if (val & 0x02) + printk(KERN_ERR "single mode not supported"); + if (val & 0x08) + printk(KERN_ERR + "level sensitive irq not supported"); + } else if (val & 0x08) { + if (val & 0x04) + s->poll = 1; + if (val & 0x02) + s->read_reg_select = val & 1; + if (val & 0x40) + s->special_mask = (val >> 5) & 1; + } else { + cmd = val >> 5; + switch (cmd) { + case 0: + case 4: + s->rotate_on_auto_eoi = cmd >> 2; + break; + case 1: /* end of interrupt */ + case 5: + priority = get_priority(s, s->isr); + if (priority != 8) { + irq = (priority + s->priority_add) & 7; + s->isr &= ~(1 << irq); + if (cmd == 5) + s->priority_add = (irq + 1) & 7; + pic_update_irq(s->pics_state); + } + break; + case 3: + irq = val & 7; + s->isr &= ~(1 << irq); + pic_update_irq(s->pics_state); + break; + case 6: + s->priority_add = (val + 1) & 7; + pic_update_irq(s->pics_state); + break; + case 7: + irq = val & 7; + s->isr &= ~(1 << irq); + s->priority_add = (irq + 1) & 7; + pic_update_irq(s->pics_state); + break; + default: + break; /* no operation */ + } + } + } else + switch (s->init_state) { + case 0: /* normal mode */ + s->imr = val; + pic_update_irq(s->pics_state); + break; + case 1: + s->irq_base = val & 0xf8; + s->init_state = 2; + break; + case 2: + if (s->init4) + s->init_state = 3; + else + s->init_state = 0; + break; + case 3: + s->special_fully_nested_mode = (val >> 4) & 1; + s->auto_eoi = (val >> 1) & 1; + s->init_state = 0; + break; + } +} + +static u32 pic_poll_read(struct kvm_kpic_state *s, u32 addr1) +{ + int ret; + + ret = pic_get_irq(s); + if (ret >= 0) { + if (addr1 >> 7) { + s->pics_state->pics[0].isr &= ~(1 << 2); + s->pics_state->pics[0].irr &= ~(1 << 2); + } + s->irr &= ~(1 << ret); + s->isr &= ~(1 << ret); + if (addr1 >> 7 || ret != 2) + pic_update_irq(s->pics_state); + } else { + ret = 0x07; + pic_update_irq(s->pics_state); + } + + return ret; +} + +static u32 pic_ioport_read(void *opaque, u32 addr1) +{ + struct kvm_kpic_state *s = opaque; + unsigned int addr; + int ret; + + addr = addr1; + addr &= 1; + if (s->poll) { + ret = pic_poll_read(s, addr1); + s->poll = 0; + } else + if (addr == 0) + if (s->read_reg_select) + ret = s->isr; + else + ret = s->irr; + else + ret = s->imr; + return ret; +} + +static void elcr_ioport_write(void *opaque, u32 addr, u32 val) +{ + struct kvm_kpic_state *s = opaque; + s->elcr = val & s->elcr_mask; +} + +static u32 elcr_ioport_read(void *opaque, u32 addr1) +{ + struct kvm_kpic_state *s = opaque; + return s->elcr; +} + +static int picdev_in_range(struct kvm_io_device *this, gpa_t addr) +{ + switch (addr) { + case 0x20: + case 0x21: + case 0xa0: + case 0xa1: + case 0x4d0: + case 0x4d1: + return 1; + default: + return 0; + } +} + +static void picdev_write(struct kvm_io_device *this, + gpa_t addr, int len, const void *val) +{ + struct kvm_pic *s = this->private; + unsigned char data = *(unsigned char *)val; + + if (len != 1) { + if (printk_ratelimit()) + printk(KERN_ERR "PIC: non byte write\n"); + return; + } + switch (addr) { + case 0x20: + case 0x21: + case 0xa0: + case 0xa1: + pic_ioport_write(&s->pics[addr >> 7], addr, data); + break; + case 0x4d0: + case 0x4d1: + elcr_ioport_write(&s->pics[addr & 1], addr, data); + break; + } +} + +static void picdev_read(struct kvm_io_device *this, + gpa_t addr, int len, void *val) +{ + struct kvm_pic *s = this->private; + unsigned char data = 0; + + if (len != 1) { + if (printk_ratelimit()) + printk(KERN_ERR "PIC: non byte read\n"); + return; + } + switch (addr) { + case 0x20: + case 0x21: + case 0xa0: + case 0xa1: + data = pic_ioport_read(&s->pics[addr >> 7], addr); + break; + case 0x4d0: + case 0x4d1: + data = elcr_ioport_read(&s->pics[addr & 1], addr); + break; + } + *(unsigned char *)val = data; +} + +/* + * callback when PIC0 irq status changed + */ +static void pic_irq_request(void *opaque, int level) +{ + struct kvm *kvm = opaque; + struct kvm_vcpu *vcpu = kvm->vcpus[0]; + + pic_irqchip(kvm)->output = level; + if (vcpu) + kvm_vcpu_kick(vcpu); +} + +struct kvm_pic *kvm_create_pic(struct kvm *kvm) +{ + struct kvm_pic *s; + s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL); + if (!s) + return NULL; + s->pics[0].elcr_mask = 0xf8; + s->pics[1].elcr_mask = 0xde; + s->irq_request = pic_irq_request; + s->irq_request_opaque = kvm; + s->pics[0].pics_state = s; + s->pics[1].pics_state = s; + + /* + * Initialize PIO device + */ + s->dev.read = picdev_read; + s->dev.write = picdev_write; + s->dev.in_range = picdev_in_range; + s->dev.private = s; + kvm_io_bus_register_dev(&kvm->pio_bus, &s->dev); + return s; +} diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c new file mode 100644 index 00000000000..e5714759e97 --- /dev/null +++ b/arch/x86/kvm/irq.c @@ -0,0 +1,78 @@ +/* + * irq.c: API for in kernel interrupt controller + * Copyright (c) 2007, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * Authors: + * Yaozu (Eddie) Dong <Eddie.dong@intel.com> + * + */ + +#include <linux/module.h> +#include <linux/kvm_host.h> + +#include "irq.h" + +/* + * check if there is pending interrupt without + * intack. + */ +int kvm_cpu_has_interrupt(struct kvm_vcpu *v) +{ + struct kvm_pic *s; + + if (kvm_apic_has_interrupt(v) == -1) { /* LAPIC */ + if (kvm_apic_accept_pic_intr(v)) { + s = pic_irqchip(v->kvm); /* PIC */ + return s->output; + } else + return 0; + } + return 1; +} +EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); + +/* + * Read pending interrupt vector and intack. + */ +int kvm_cpu_get_interrupt(struct kvm_vcpu *v) +{ + struct kvm_pic *s; + int vector; + + vector = kvm_get_apic_interrupt(v); /* APIC */ + if (vector == -1) { + if (kvm_apic_accept_pic_intr(v)) { + s = pic_irqchip(v->kvm); + s->output = 0; /* PIC */ + vector = kvm_pic_read_irq(s); + } + } + return vector; +} +EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); + +void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) +{ + kvm_inject_apic_timer_irqs(vcpu); + /* TODO: PIT, RTC etc. */ +} +EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); + +void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec) +{ + kvm_apic_timer_intr_post(vcpu, vec); + /* TODO: PIT, RTC etc. */ +} +EXPORT_SYMBOL_GPL(kvm_timer_intr_post); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h new file mode 100644 index 00000000000..fa5ed5d59b5 --- /dev/null +++ b/arch/x86/kvm/irq.h @@ -0,0 +1,88 @@ +/* + * irq.h: in kernel interrupt controller related definitions + * Copyright (c) 2007, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * Authors: + * Yaozu (Eddie) Dong <Eddie.dong@intel.com> + * + */ + +#ifndef __IRQ_H +#define __IRQ_H + +#include <linux/mm_types.h> +#include <linux/hrtimer.h> +#include <linux/kvm_host.h> + +#include "iodev.h" +#include "ioapic.h" +#include "lapic.h" + +struct kvm; +struct kvm_vcpu; + +typedef void irq_request_func(void *opaque, int level); + +struct kvm_kpic_state { + u8 last_irr; /* edge detection */ + u8 irr; /* interrupt request register */ + u8 imr; /* interrupt mask register */ + u8 isr; /* interrupt service register */ + u8 priority_add; /* highest irq priority */ + u8 irq_base; + u8 read_reg_select; + u8 poll; + u8 special_mask; + u8 init_state; + u8 auto_eoi; + u8 rotate_on_auto_eoi; + u8 special_fully_nested_mode; + u8 init4; /* true if 4 byte init */ + u8 elcr; /* PIIX edge/trigger selection */ + u8 elcr_mask; + struct kvm_pic *pics_state; +}; + +struct kvm_pic { + struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */ + irq_request_func *irq_request; + void *irq_request_opaque; + int output; /* intr from master PIC */ + struct kvm_io_device dev; +}; + +struct kvm_pic *kvm_create_pic(struct kvm *kvm); +void kvm_pic_set_irq(void *opaque, int irq, int level); +int kvm_pic_read_irq(struct kvm_pic *s); +void kvm_pic_update_irq(struct kvm_pic *s); + +static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) +{ + return kvm->arch.vpic; +} + +static inline int irqchip_in_kernel(struct kvm *kvm) +{ + return pic_irqchip(kvm) != NULL; +} + +void kvm_pic_reset(struct kvm_kpic_state *s); + +void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec); +void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); +void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); +void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h new file mode 100644 index 00000000000..ecdfe97e463 --- /dev/null +++ b/arch/x86/kvm/kvm_svm.h @@ -0,0 +1,45 @@ +#ifndef __KVM_SVM_H +#define __KVM_SVM_H + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/kvm_host.h> +#include <asm/msr.h> + +#include "svm.h" + +static const u32 host_save_user_msrs[] = { +#ifdef CONFIG_X86_64 + MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, + MSR_FS_BASE, +#endif + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, +}; + +#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) +#define NUM_DB_REGS 4 + +struct kvm_vcpu; + +struct vcpu_svm { + struct kvm_vcpu vcpu; + struct vmcb *vmcb; + unsigned long vmcb_pa; + struct svm_cpu_data *svm_data; + uint64_t asid_generation; + + unsigned long db_regs[NUM_DB_REGS]; + + u64 next_rip; + + u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; + u64 host_gs_base; + unsigned long host_cr2; + unsigned long host_db_regs[NUM_DB_REGS]; + unsigned long host_dr6; + unsigned long host_dr7; +}; + +#endif + diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c new file mode 100644 index 00000000000..2cbee9479ce --- /dev/null +++ b/arch/x86/kvm/lapic.c @@ -0,0 +1,1154 @@ + +/* + * Local APIC virtualization + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2007 Novell + * Copyright (C) 2007 Intel + * + * Authors: + * Dor Laor <dor.laor@qumranet.com> + * Gregory Haskins <ghaskins@novell.com> + * Yaozu (Eddie) Dong <eddie.dong@intel.com> + * + * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/kvm_host.h> +#include <linux/kvm.h> +#include <linux/mm.h> +#include <linux/highmem.h> +#include <linux/smp.h> +#include <linux/hrtimer.h> +#include <linux/io.h> +#include <linux/module.h> +#include <asm/processor.h> +#include <asm/msr.h> +#include <asm/page.h> +#include <asm/current.h> +#include <asm/apicdef.h> +#include <asm/atomic.h> +#include <asm/div64.h> +#include "irq.h" + +#define PRId64 "d" +#define PRIx64 "llx" +#define PRIu64 "u" +#define PRIo64 "o" + +#define APIC_BUS_CYCLE_NS 1 + +/* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */ +#define apic_debug(fmt, arg...) + +#define APIC_LVT_NUM 6 +/* 14 is the version for Xeon and Pentium 8.4.8*/ +#define APIC_VERSION (0x14UL | ((APIC_LVT_NUM - 1) << 16)) +#define LAPIC_MMIO_LENGTH (1 << 12) +/* followed define is not in apicdef.h */ +#define APIC_SHORT_MASK 0xc0000 +#define APIC_DEST_NOSHORT 0x0 +#define APIC_DEST_MASK 0x800 +#define MAX_APIC_VECTOR 256 + +#define VEC_POS(v) ((v) & (32 - 1)) +#define REG_POS(v) (((v) >> 5) << 4) + +static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off) +{ + return *((u32 *) (apic->regs + reg_off)); +} + +static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) +{ + *((u32 *) (apic->regs + reg_off)) = val; +} + +static inline int apic_test_and_set_vector(int vec, void *bitmap) +{ + return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline int apic_test_and_clear_vector(int vec, void *bitmap) +{ + return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline void apic_set_vector(int vec, void *bitmap) +{ + set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline void apic_clear_vector(int vec, void *bitmap) +{ + clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline int apic_hw_enabled(struct kvm_lapic *apic) +{ + return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; +} + +static inline int apic_sw_enabled(struct kvm_lapic *apic) +{ + return apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED; +} + +static inline int apic_enabled(struct kvm_lapic *apic) +{ + return apic_sw_enabled(apic) && apic_hw_enabled(apic); +} + +#define LVT_MASK \ + (APIC_LVT_MASKED | APIC_SEND_PENDING | APIC_VECTOR_MASK) + +#define LINT_MASK \ + (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ + APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) + +static inline int kvm_apic_id(struct kvm_lapic *apic) +{ + return (apic_get_reg(apic, APIC_ID) >> 24) & 0xff; +} + +static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) +{ + return !(apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); +} + +static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) +{ + return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; +} + +static inline int apic_lvtt_period(struct kvm_lapic *apic) +{ + return apic_get_reg(apic, APIC_LVTT) & APIC_LVT_TIMER_PERIODIC; +} + +static unsigned int apic_lvt_mask[APIC_LVT_NUM] = { + LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */ + LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */ + LVT_MASK | APIC_MODE_MASK, /* LVTPC */ + LINT_MASK, LINT_MASK, /* LVT0-1 */ + LVT_MASK /* LVTERR */ +}; + +static int find_highest_vector(void *bitmap) +{ + u32 *word = bitmap; + int word_offset = MAX_APIC_VECTOR >> 5; + + while ((word_offset != 0) && (word[(--word_offset) << 2] == 0)) + continue; + + if (likely(!word_offset && !word[0])) + return -1; + else + return fls(word[word_offset << 2]) - 1 + (word_offset << 5); +} + +static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) +{ + return apic_test_and_set_vector(vec, apic->regs + APIC_IRR); +} + +static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) +{ + apic_clear_vector(vec, apic->regs + APIC_IRR); +} + +static inline int apic_find_highest_irr(struct kvm_lapic *apic) +{ + int result; + + result = find_highest_vector(apic->regs + APIC_IRR); + ASSERT(result == -1 || result >= 16); + + return result; +} + +int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + int highest_irr; + + if (!apic) + return 0; + highest_irr = apic_find_highest_irr(apic); + + return highest_irr; +} +EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr); + +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (!apic_test_and_set_irr(vec, apic)) { + /* a new pending irq is set in IRR */ + if (trig) + apic_set_vector(vec, apic->regs + APIC_TMR); + else + apic_clear_vector(vec, apic->regs + APIC_TMR); + kvm_vcpu_kick(apic->vcpu); + return 1; + } + return 0; +} + +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + + result = find_highest_vector(apic->regs + APIC_ISR); + ASSERT(result == -1 || result >= 16); + + return result; +} + +static void apic_update_ppr(struct kvm_lapic *apic) +{ + u32 tpr, isrv, ppr; + int isr; + + tpr = apic_get_reg(apic, APIC_TASKPRI); + isr = apic_find_highest_isr(apic); + isrv = (isr != -1) ? isr : 0; + + if ((tpr & 0xf0) >= (isrv & 0xf0)) + ppr = tpr & 0xff; + else + ppr = isrv & 0xf0; + + apic_debug("vlapic %p, ppr 0x%x, isr 0x%x, isrv 0x%x", + apic, ppr, isr, isrv); + + apic_set_reg(apic, APIC_PROCPRI, ppr); +} + +static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) +{ + apic_set_reg(apic, APIC_TASKPRI, tpr); + apic_update_ppr(apic); +} + +int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) +{ + return kvm_apic_id(apic) == dest; +} + +int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) +{ + int result = 0; + u8 logical_id; + + logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR)); + + switch (apic_get_reg(apic, APIC_DFR)) { + case APIC_DFR_FLAT: + if (logical_id & mda) + result = 1; + break; + case APIC_DFR_CLUSTER: + if (((logical_id >> 4) == (mda >> 0x4)) + && (logical_id & mda & 0xf)) + result = 1; + break; + default: + printk(KERN_WARNING "Bad DFR vcpu %d: %08x\n", + apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR)); + break; + } + + return result; +} + +static int apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, int dest, int dest_mode) +{ + int result = 0; + struct kvm_lapic *target = vcpu->arch.apic; + + apic_debug("target %p, source %p, dest 0x%x, " + "dest_mode 0x%x, short_hand 0x%x", + target, source, dest, dest_mode, short_hand); + + ASSERT(!target); + switch (short_hand) { + case APIC_DEST_NOSHORT: + if (dest_mode == 0) { + /* Physical mode. */ + if ((dest == 0xFF) || (dest == kvm_apic_id(target))) + result = 1; + } else + /* Logical mode. */ + result = kvm_apic_match_logical_addr(target, dest); + break; + case APIC_DEST_SELF: + if (target == source) + result = 1; + break; + case APIC_DEST_ALLINC: + result = 1; + break; + case APIC_DEST_ALLBUT: + if (target != source) + result = 1; + break; + default: + printk(KERN_WARNING "Bad dest shorthand value %x\n", + short_hand); + break; + } + + return result; +} + +/* + * Add a pending IRQ into lapic. + * Return 1 if successfully added and 0 if discarded. + */ +static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, + int vector, int level, int trig_mode) +{ + int orig_irr, result = 0; + struct kvm_vcpu *vcpu = apic->vcpu; + + switch (delivery_mode) { + case APIC_DM_FIXED: + case APIC_DM_LOWEST: + /* FIXME add logic for vcpu on reset */ + if (unlikely(!apic_enabled(apic))) + break; + + orig_irr = apic_test_and_set_irr(vector, apic); + if (orig_irr && trig_mode) { + apic_debug("level trig mode repeatedly for vector %d", + vector); + break; + } + + if (trig_mode) { + apic_debug("level trig mode for vector %d", vector); + apic_set_vector(vector, apic->regs + APIC_TMR); + } else + apic_clear_vector(vector, apic->regs + APIC_TMR); + + if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE) + kvm_vcpu_kick(vcpu); + else if (vcpu->arch.mp_state == VCPU_MP_STATE_HALTED) { + vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + if (waitqueue_active(&vcpu->wq)) + wake_up_interruptible(&vcpu->wq); + } + + result = (orig_irr == 0); + break; + + case APIC_DM_REMRD: + printk(KERN_DEBUG "Ignoring delivery mode 3\n"); + break; + + case APIC_DM_SMI: + printk(KERN_DEBUG "Ignoring guest SMI\n"); + break; + case APIC_DM_NMI: + printk(KERN_DEBUG "Ignoring guest NMI\n"); + break; + + case APIC_DM_INIT: + if (level) { + if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE) + printk(KERN_DEBUG + "INIT on a runnable vcpu %d\n", + vcpu->vcpu_id); + vcpu->arch.mp_state = VCPU_MP_STATE_INIT_RECEIVED; + kvm_vcpu_kick(vcpu); + } else { + printk(KERN_DEBUG + "Ignoring de-assert INIT to vcpu %d\n", + vcpu->vcpu_id); + } + + break; + + case APIC_DM_STARTUP: + printk(KERN_DEBUG "SIPI to vcpu %d vector 0x%02x\n", + vcpu->vcpu_id, vector); + if (vcpu->arch.mp_state == VCPU_MP_STATE_INIT_RECEIVED) { + vcpu->arch.sipi_vector = vector; + vcpu->arch.mp_state = VCPU_MP_STATE_SIPI_RECEIVED; + if (waitqueue_active(&vcpu->wq)) + wake_up_interruptible(&vcpu->wq); + } + break; + + default: + printk(KERN_ERR "TODO: unsupported delivery mode %x\n", + delivery_mode); + break; + } + return result; +} + +static struct kvm_lapic *kvm_apic_round_robin(struct kvm *kvm, u8 vector, + unsigned long bitmap) +{ + int last; + int next; + struct kvm_lapic *apic = NULL; + + last = kvm->arch.round_robin_prev_vcpu; + next = last; + + do { + if (++next == KVM_MAX_VCPUS) + next = 0; + if (kvm->vcpus[next] == NULL || !test_bit(next, &bitmap)) + continue; + apic = kvm->vcpus[next]->arch.apic; + if (apic && apic_enabled(apic)) + break; + apic = NULL; + } while (next != last); + kvm->arch.round_robin_prev_vcpu = next; + + if (!apic) + printk(KERN_DEBUG "vcpu not ready for apic_round_robin\n"); + + return apic; +} + +struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, + unsigned long bitmap) +{ + struct kvm_lapic *apic; + + apic = kvm_apic_round_robin(kvm, vector, bitmap); + if (apic) + return apic->vcpu; + return NULL; +} + +static void apic_set_eoi(struct kvm_lapic *apic) +{ + int vector = apic_find_highest_isr(apic); + + /* + * Not every write EOI will has corresponding ISR, + * one example is when Kernel check timer on setup_IO_APIC + */ + if (vector == -1) + return; + + apic_clear_vector(vector, apic->regs + APIC_ISR); + apic_update_ppr(apic); + + if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR)) + kvm_ioapic_update_eoi(apic->vcpu->kvm, vector); +} + +static void apic_send_ipi(struct kvm_lapic *apic) +{ + u32 icr_low = apic_get_reg(apic, APIC_ICR); + u32 icr_high = apic_get_reg(apic, APIC_ICR2); + + unsigned int dest = GET_APIC_DEST_FIELD(icr_high); + unsigned int short_hand = icr_low & APIC_SHORT_MASK; + unsigned int trig_mode = icr_low & APIC_INT_LEVELTRIG; + unsigned int level = icr_low & APIC_INT_ASSERT; + unsigned int dest_mode = icr_low & APIC_DEST_MASK; + unsigned int delivery_mode = icr_low & APIC_MODE_MASK; + unsigned int vector = icr_low & APIC_VECTOR_MASK; + + struct kvm_vcpu *target; + struct kvm_vcpu *vcpu; + unsigned long lpr_map = 0; + int i; + + apic_debug("icr_high 0x%x, icr_low 0x%x, " + "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " + "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", + icr_high, icr_low, short_hand, dest, + trig_mode, level, dest_mode, delivery_mode, vector); + + for (i = 0; i < KVM_MAX_VCPUS; i++) { + vcpu = apic->vcpu->kvm->vcpus[i]; + if (!vcpu) + continue; + + if (vcpu->arch.apic && + apic_match_dest(vcpu, apic, short_hand, dest, dest_mode)) { + if (delivery_mode == APIC_DM_LOWEST) + set_bit(vcpu->vcpu_id, &lpr_map); + else + __apic_accept_irq(vcpu->arch.apic, delivery_mode, + vector, level, trig_mode); + } + } + + if (delivery_mode == APIC_DM_LOWEST) { + target = kvm_get_lowest_prio_vcpu(vcpu->kvm, vector, lpr_map); + if (target != NULL) + __apic_accept_irq(target->arch.apic, delivery_mode, + vector, level, trig_mode); + } +} + +static u32 apic_get_tmcct(struct kvm_lapic *apic) +{ + u64 counter_passed; + ktime_t passed, now; + u32 tmcct; + + ASSERT(apic != NULL); + + now = apic->timer.dev.base->get_time(); + tmcct = apic_get_reg(apic, APIC_TMICT); + + /* if initial count is 0, current count should also be 0 */ + if (tmcct == 0) + return 0; + + if (unlikely(ktime_to_ns(now) <= + ktime_to_ns(apic->timer.last_update))) { + /* Wrap around */ + passed = ktime_add(( { + (ktime_t) { + .tv64 = KTIME_MAX - + (apic->timer.last_update).tv64}; } + ), now); + apic_debug("time elapsed\n"); + } else + passed = ktime_sub(now, apic->timer.last_update); + + counter_passed = div64_64(ktime_to_ns(passed), + (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); + + if (counter_passed > tmcct) { + if (unlikely(!apic_lvtt_period(apic))) { + /* one-shot timers stick at 0 until reset */ + tmcct = 0; + } else { + /* + * periodic timers reset to APIC_TMICT when they + * hit 0. The while loop simulates this happening N + * times. (counter_passed %= tmcct) would also work, + * but might be slower or not work on 32-bit?? + */ + while (counter_passed > tmcct) + counter_passed -= tmcct; + tmcct -= counter_passed; + } + } else { + tmcct -= counter_passed; + } + + return tmcct; +} + +static void __report_tpr_access(struct kvm_lapic *apic, bool write) +{ + struct kvm_vcpu *vcpu = apic->vcpu; + struct kvm_run *run = vcpu->run; + + set_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests); + kvm_x86_ops->cache_regs(vcpu); + run->tpr_access.rip = vcpu->arch.rip; + run->tpr_access.is_write = write; +} + +static inline void report_tpr_access(struct kvm_lapic *apic, bool write) +{ + if (apic->vcpu->arch.tpr_access_reporting) + __report_tpr_access(apic, write); +} + +static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) +{ + u32 val = 0; + + if (offset >= LAPIC_MMIO_LENGTH) + return 0; + + switch (offset) { + case APIC_ARBPRI: + printk(KERN_WARNING "Access APIC ARBPRI register " + "which is for P6\n"); + break; + + case APIC_TMCCT: /* Timer CCR */ + val = apic_get_tmcct(apic); + break; + + case APIC_TASKPRI: + report_tpr_access(apic, false); + /* fall thru */ + default: + apic_update_ppr(apic); + val = apic_get_reg(apic, offset); + break; + } + + return val; +} + +static void apic_mmio_read(struct kvm_io_device *this, + gpa_t address, int len, void *data) +{ + struct kvm_lapic *apic = (struct kvm_lapic *)this->private; + unsigned int offset = address - apic->base_address; + unsigned char alignment = offset & 0xf; + u32 result; + + if ((alignment + len) > 4) { + printk(KERN_ERR "KVM_APIC_READ: alignment error %lx %d", + (unsigned long)address, len); + return; + } + result = __apic_read(apic, offset & ~0xf); + + switch (len) { + case 1: + case 2: + case 4: + memcpy(data, (char *)&result + alignment, len); + break; + default: + printk(KERN_ERR "Local APIC read with len = %x, " + "should be 1,2, or 4 instead\n", len); + break; + } +} + +static void update_divide_count(struct kvm_lapic *apic) +{ + u32 tmp1, tmp2, tdcr; + + tdcr = apic_get_reg(apic, APIC_TDCR); + tmp1 = tdcr & 0xf; + tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1; + apic->timer.divide_count = 0x1 << (tmp2 & 0x7); + + apic_debug("timer divide count is 0x%x\n", + apic->timer.divide_count); +} + +static void start_apic_timer(struct kvm_lapic *apic) +{ + ktime_t now = apic->timer.dev.base->get_time(); + + apic->timer.last_update = now; + + apic->timer.period = apic_get_reg(apic, APIC_TMICT) * + APIC_BUS_CYCLE_NS * apic->timer.divide_count; + atomic_set(&apic->timer.pending, 0); + hrtimer_start(&apic->timer.dev, + ktime_add_ns(now, apic->timer.period), + HRTIMER_MODE_ABS); + + apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" + PRIx64 ", " + "timer initial count 0x%x, period %lldns, " + "expire @ 0x%016" PRIx64 ".\n", __FUNCTION__, + APIC_BUS_CYCLE_NS, ktime_to_ns(now), + apic_get_reg(apic, APIC_TMICT), + apic->timer.period, + ktime_to_ns(ktime_add_ns(now, + apic->timer.period))); +} + +static void apic_mmio_write(struct kvm_io_device *this, + gpa_t address, int len, const void *data) +{ + struct kvm_lapic *apic = (struct kvm_lapic *)this->private; + unsigned int offset = address - apic->base_address; + unsigned char alignment = offset & 0xf; + u32 val; + + /* + * APIC register must be aligned on 128-bits boundary. + * 32/64/128 bits registers must be accessed thru 32 bits. + * Refer SDM 8.4.1 + */ + if (len != 4 || alignment) { + if (printk_ratelimit()) + printk(KERN_ERR "apic write: bad size=%d %lx\n", + len, (long)address); + return; + } + + val = *(u32 *) data; + + /* too common printing */ + if (offset != APIC_EOI) + apic_debug("%s: offset 0x%x with length 0x%x, and value is " + "0x%x\n", __FUNCTION__, offset, len, val); + + offset &= 0xff0; + + switch (offset) { + case APIC_ID: /* Local APIC ID */ + apic_set_reg(apic, APIC_ID, val); + break; + + case APIC_TASKPRI: + report_tpr_access(apic, true); + apic_set_tpr(apic, val & 0xff); + break; + + case APIC_EOI: + apic_set_eoi(apic); + break; + + case APIC_LDR: + apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK); + break; + + case APIC_DFR: + apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); + break; + + case APIC_SPIV: + apic_set_reg(apic, APIC_SPIV, val & 0x3ff); + if (!(val & APIC_SPIV_APIC_ENABLED)) { + int i; + u32 lvt_val; + + for (i = 0; i < APIC_LVT_NUM; i++) { + lvt_val = apic_get_reg(apic, + APIC_LVTT + 0x10 * i); + apic_set_reg(apic, APIC_LVTT + 0x10 * i, + lvt_val | APIC_LVT_MASKED); + } + atomic_set(&apic->timer.pending, 0); + + } + break; + + case APIC_ICR: + /* No delay here, so we always clear the pending bit */ + apic_set_reg(apic, APIC_ICR, val & ~(1 << 12)); + apic_send_ipi(apic); + break; + + case APIC_ICR2: + apic_set_reg(apic, APIC_ICR2, val & 0xff000000); + break; + + case APIC_LVTT: + case APIC_LVTTHMR: + case APIC_LVTPC: + case APIC_LVT0: + case APIC_LVT1: + case APIC_LVTERR: + /* TODO: Check vector */ + if (!apic_sw_enabled(apic)) + val |= APIC_LVT_MASKED; + + val &= apic_lvt_mask[(offset - APIC_LVTT) >> 4]; + apic_set_reg(apic, offset, val); + + break; + + case APIC_TMICT: + hrtimer_cancel(&apic->timer.dev); + apic_set_reg(apic, APIC_TMICT, val); + start_apic_timer(apic); + return; + + case APIC_TDCR: + if (val & 4) + printk(KERN_ERR "KVM_WRITE:TDCR %x\n", val); + apic_set_reg(apic, APIC_TDCR, val); + update_divide_count(apic); + break; + + default: + apic_debug("Local APIC Write to read-only register %x\n", + offset); + break; + } + +} + +static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr) +{ + struct kvm_lapic *apic = (struct kvm_lapic *)this->private; + int ret = 0; + + + if (apic_hw_enabled(apic) && + (addr >= apic->base_address) && + (addr < (apic->base_address + LAPIC_MMIO_LENGTH))) + ret = 1; + + return ret; +} + +void kvm_free_lapic(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.apic) + return; + + hrtimer_cancel(&vcpu->arch.apic->timer.dev); + + if (vcpu->arch.apic->regs_page) + __free_page(vcpu->arch.apic->regs_page); + + kfree(vcpu->arch.apic); +} + +/* + *---------------------------------------------------------------------- + * LAPIC interface + *---------------------------------------------------------------------- + */ + +void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (!apic) + return; + apic_set_tpr(apic, ((cr8 & 0x0f) << 4) + | (apic_get_reg(apic, APIC_TASKPRI) & 4)); +} + +u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u64 tpr; + + if (!apic) + return 0; + tpr = (u64) apic_get_reg(apic, APIC_TASKPRI); + + return (tpr & 0xf0) >> 4; +} +EXPORT_SYMBOL_GPL(kvm_lapic_get_cr8); + +void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (!apic) { + value |= MSR_IA32_APICBASE_BSP; + vcpu->arch.apic_base = value; + return; + } + if (apic->vcpu->vcpu_id) + value &= ~MSR_IA32_APICBASE_BSP; + + vcpu->arch.apic_base = value; + apic->base_address = apic->vcpu->arch.apic_base & + MSR_IA32_APICBASE_BASE; + + /* with FSB delivery interrupt, we can restart APIC functionality */ + apic_debug("apic base msr is 0x%016" PRIx64 ", and base address is " + "0x%lx.\n", apic->vcpu->arch.apic_base, apic->base_address); + +} + +u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.apic_base; +} +EXPORT_SYMBOL_GPL(kvm_lapic_get_base); + +void kvm_lapic_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic; + int i; + + apic_debug("%s\n", __FUNCTION__); + + ASSERT(vcpu); + apic = vcpu->arch.apic; + ASSERT(apic != NULL); + + /* Stop the timer in case it's a reset to an active apic */ + hrtimer_cancel(&apic->timer.dev); + + apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24); + apic_set_reg(apic, APIC_LVR, APIC_VERSION); + + for (i = 0; i < APIC_LVT_NUM; i++) + apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); + apic_set_reg(apic, APIC_LVT0, + SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); + + apic_set_reg(apic, APIC_DFR, 0xffffffffU); + apic_set_reg(apic, APIC_SPIV, 0xff); + apic_set_reg(apic, APIC_TASKPRI, 0); + apic_set_reg(apic, APIC_LDR, 0); + apic_set_reg(apic, APIC_ESR, 0); + apic_set_reg(apic, APIC_ICR, 0); + apic_set_reg(apic, APIC_ICR2, 0); + apic_set_reg(apic, APIC_TDCR, 0); + apic_set_reg(apic, APIC_TMICT, 0); + for (i = 0; i < 8; i++) { + apic_set_reg(apic, APIC_IRR + 0x10 * i, 0); + apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); + apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); + } + update_divide_count(apic); + atomic_set(&apic->timer.pending, 0); + if (vcpu->vcpu_id == 0) + vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; + apic_update_ppr(apic); + + apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr=" + "0x%016" PRIx64 ", base_address=0x%0lx.\n", __FUNCTION__, + vcpu, kvm_apic_id(apic), + vcpu->arch.apic_base, apic->base_address); +} +EXPORT_SYMBOL_GPL(kvm_lapic_reset); + +int kvm_lapic_enabled(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + int ret = 0; + + if (!apic) + return 0; + ret = apic_enabled(apic); + + return ret; +} +EXPORT_SYMBOL_GPL(kvm_lapic_enabled); + +/* + *---------------------------------------------------------------------- + * timer interface + *---------------------------------------------------------------------- + */ + +/* TODO: make sure __apic_timer_fn runs in current pCPU */ +static int __apic_timer_fn(struct kvm_lapic *apic) +{ + int result = 0; + wait_queue_head_t *q = &apic->vcpu->wq; + + atomic_inc(&apic->timer.pending); + if (waitqueue_active(q)) { + apic->vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + wake_up_interruptible(q); + } + if (apic_lvtt_period(apic)) { + result = 1; + apic->timer.dev.expires = ktime_add_ns( + apic->timer.dev.expires, + apic->timer.period); + } + return result; +} + +static int __inject_apic_timer_irq(struct kvm_lapic *apic) +{ + int vector; + + vector = apic_lvt_vector(apic, APIC_LVTT); + return __apic_accept_irq(apic, APIC_DM_FIXED, vector, 1, 0); +} + +static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) +{ + struct kvm_lapic *apic; + int restart_timer = 0; + + apic = container_of(data, struct kvm_lapic, timer.dev); + + restart_timer = __apic_timer_fn(apic); + + if (restart_timer) + return HRTIMER_RESTART; + else + return HRTIMER_NORESTART; +} + +int kvm_create_lapic(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic; + + ASSERT(vcpu != NULL); + apic_debug("apic_init %d\n", vcpu->vcpu_id); + + apic = kzalloc(sizeof(*apic), GFP_KERNEL); + if (!apic) + goto nomem; + + vcpu->arch.apic = apic; + + apic->regs_page = alloc_page(GFP_KERNEL); + if (apic->regs_page == NULL) { + printk(KERN_ERR "malloc apic regs error for vcpu %x\n", + vcpu->vcpu_id); + goto nomem_free_apic; + } + apic->regs = page_address(apic->regs_page); + memset(apic->regs, 0, PAGE_SIZE); + apic->vcpu = vcpu; + + hrtimer_init(&apic->timer.dev, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + apic->timer.dev.function = apic_timer_fn; + apic->base_address = APIC_DEFAULT_PHYS_BASE; + vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE; + + kvm_lapic_reset(vcpu); + apic->dev.read = apic_mmio_read; + apic->dev.write = apic_mmio_write; + apic->dev.in_range = apic_mmio_range; + apic->dev.private = apic; + + return 0; +nomem_free_apic: + kfree(apic); +nomem: + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(kvm_create_lapic); + +int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + int highest_irr; + + if (!apic || !apic_enabled(apic)) + return -1; + + apic_update_ppr(apic); + highest_irr = apic_find_highest_irr(apic); + if ((highest_irr == -1) || + ((highest_irr & 0xF0) <= apic_get_reg(apic, APIC_PROCPRI))) + return -1; + return highest_irr; +} + +int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) +{ + u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0); + int r = 0; + + if (vcpu->vcpu_id == 0) { + if (!apic_hw_enabled(vcpu->arch.apic)) + r = 1; + if ((lvt0 & APIC_LVT_MASKED) == 0 && + GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) + r = 1; + } + return r; +} + +void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (apic && apic_lvt_enabled(apic, APIC_LVTT) && + atomic_read(&apic->timer.pending) > 0) { + if (__inject_apic_timer_irq(apic)) + atomic_dec(&apic->timer.pending); + } +} + +void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (apic && apic_lvt_vector(apic, APIC_LVTT) == vec) + apic->timer.last_update = ktime_add_ns( + apic->timer.last_update, + apic->timer.period); +} + +int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) +{ + int vector = kvm_apic_has_interrupt(vcpu); + struct kvm_lapic *apic = vcpu->arch.apic; + + if (vector == -1) + return -1; + + apic_set_vector(vector, apic->regs + APIC_ISR); + apic_update_ppr(apic); + apic_clear_irr(vector, apic); + return vector; +} + +void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + apic->base_address = vcpu->arch.apic_base & + MSR_IA32_APICBASE_BASE; + apic_set_reg(apic, APIC_LVR, APIC_VERSION); + apic_update_ppr(apic); + hrtimer_cancel(&apic->timer.dev); + update_divide_count(apic); + start_apic_timer(apic); +} + +void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + struct hrtimer *timer; + + if (!apic) + return; + + timer = &apic->timer.dev; + if (hrtimer_cancel(timer)) + hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); +} + +void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) +{ + u32 data; + void *vapic; + + if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr) + return; + + vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0); + data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)); + kunmap_atomic(vapic, KM_USER0); + + apic_set_tpr(vcpu->arch.apic, data & 0xff); +} + +void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) +{ + u32 data, tpr; + int max_irr, max_isr; + struct kvm_lapic *apic; + void *vapic; + + if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr) + return; + + apic = vcpu->arch.apic; + tpr = apic_get_reg(apic, APIC_TASKPRI) & 0xff; + max_irr = apic_find_highest_irr(apic); + if (max_irr < 0) + max_irr = 0; + max_isr = apic_find_highest_isr(apic); + if (max_isr < 0) + max_isr = 0; + data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24); + + vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0); + *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data; + kunmap_atomic(vapic, KM_USER0); +} + +void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) +{ + if (!irqchip_in_kernel(vcpu->kvm)) + return; + + vcpu->arch.apic->vapic_addr = vapic_addr; +} diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h new file mode 100644 index 00000000000..676c396c9ce --- /dev/null +++ b/arch/x86/kvm/lapic.h @@ -0,0 +1,50 @@ +#ifndef __KVM_X86_LAPIC_H +#define __KVM_X86_LAPIC_H + +#include "iodev.h" + +#include <linux/kvm_host.h> + +struct kvm_lapic { + unsigned long base_address; + struct kvm_io_device dev; + struct { + atomic_t pending; + s64 period; /* unit: ns */ + u32 divide_count; + ktime_t last_update; + struct hrtimer dev; + } timer; + struct kvm_vcpu *vcpu; + struct page *regs_page; + void *regs; + gpa_t vapic_addr; + struct page *vapic_page; +}; +int kvm_create_lapic(struct kvm_vcpu *vcpu); +void kvm_free_lapic(struct kvm_vcpu *vcpu); + +int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); +int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); +void kvm_lapic_reset(struct kvm_vcpu *vcpu); +u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); +void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); +void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); + +int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); +int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig); + +u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); +void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); +void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu); +int kvm_lapic_enabled(struct kvm_vcpu *vcpu); +int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); +void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec); + +void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); +void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); +void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c new file mode 100644 index 00000000000..8efdcdbebb0 --- /dev/null +++ b/arch/x86/kvm/mmu.c @@ -0,0 +1,1885 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * This module enables machines with Intel VT-x extensions to run virtual + * machines without emulation or binary translation. + * + * MMU support + * + * Copyright (C) 2006 Qumranet, Inc. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "vmx.h" +#include "mmu.h" + +#include <linux/kvm_host.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/swap.h> + +#include <asm/page.h> +#include <asm/cmpxchg.h> +#include <asm/io.h> + +#undef MMU_DEBUG + +#undef AUDIT + +#ifdef AUDIT +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg); +#else +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {} +#endif + +#ifdef MMU_DEBUG + +#define pgprintk(x...) do { if (dbg) printk(x); } while (0) +#define rmap_printk(x...) do { if (dbg) printk(x); } while (0) + +#else + +#define pgprintk(x...) do { } while (0) +#define rmap_printk(x...) do { } while (0) + +#endif + +#if defined(MMU_DEBUG) || defined(AUDIT) +static int dbg = 1; +#endif + +#ifndef MMU_DEBUG +#define ASSERT(x) do { } while (0) +#else +#define ASSERT(x) \ + if (!(x)) { \ + printk(KERN_WARNING "assertion failed %s:%d: %s\n", \ + __FILE__, __LINE__, #x); \ + } +#endif + +#define PT64_PT_BITS 9 +#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS) +#define PT32_PT_BITS 10 +#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS) + +#define PT_WRITABLE_SHIFT 1 + +#define PT_PRESENT_MASK (1ULL << 0) +#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT) +#define PT_USER_MASK (1ULL << 2) +#define PT_PWT_MASK (1ULL << 3) +#define PT_PCD_MASK (1ULL << 4) +#define PT_ACCESSED_MASK (1ULL << 5) +#define PT_DIRTY_MASK (1ULL << 6) +#define PT_PAGE_SIZE_MASK (1ULL << 7) +#define PT_PAT_MASK (1ULL << 7) +#define PT_GLOBAL_MASK (1ULL << 8) +#define PT64_NX_SHIFT 63 +#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT) + +#define PT_PAT_SHIFT 7 +#define PT_DIR_PAT_SHIFT 12 +#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT) + +#define PT32_DIR_PSE36_SIZE 4 +#define PT32_DIR_PSE36_SHIFT 13 +#define PT32_DIR_PSE36_MASK \ + (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT) + + +#define PT_FIRST_AVAIL_BITS_SHIFT 9 +#define PT64_SECOND_AVAIL_BITS_SHIFT 52 + +#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) + +#define VALID_PAGE(x) ((x) != INVALID_PAGE) + +#define PT64_LEVEL_BITS 9 + +#define PT64_LEVEL_SHIFT(level) \ + (PAGE_SHIFT + (level - 1) * PT64_LEVEL_BITS) + +#define PT64_LEVEL_MASK(level) \ + (((1ULL << PT64_LEVEL_BITS) - 1) << PT64_LEVEL_SHIFT(level)) + +#define PT64_INDEX(address, level)\ + (((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1)) + + +#define PT32_LEVEL_BITS 10 + +#define PT32_LEVEL_SHIFT(level) \ + (PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS) + +#define PT32_LEVEL_MASK(level) \ + (((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level)) + +#define PT32_INDEX(address, level)\ + (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) + + +#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#define PT64_DIR_BASE_ADDR_MASK \ + (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) + +#define PT32_BASE_ADDR_MASK PAGE_MASK +#define PT32_DIR_BASE_ADDR_MASK \ + (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1)) + +#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \ + | PT64_NX_MASK) + +#define PFERR_PRESENT_MASK (1U << 0) +#define PFERR_WRITE_MASK (1U << 1) +#define PFERR_USER_MASK (1U << 2) +#define PFERR_FETCH_MASK (1U << 4) + +#define PT64_ROOT_LEVEL 4 +#define PT32_ROOT_LEVEL 2 +#define PT32E_ROOT_LEVEL 3 + +#define PT_DIRECTORY_LEVEL 2 +#define PT_PAGE_TABLE_LEVEL 1 + +#define RMAP_EXT 4 + +#define ACC_EXEC_MASK 1 +#define ACC_WRITE_MASK PT_WRITABLE_MASK +#define ACC_USER_MASK PT_USER_MASK +#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) + +struct kvm_rmap_desc { + u64 *shadow_ptes[RMAP_EXT]; + struct kvm_rmap_desc *more; +}; + +static struct kmem_cache *pte_chain_cache; +static struct kmem_cache *rmap_desc_cache; +static struct kmem_cache *mmu_page_header_cache; + +static u64 __read_mostly shadow_trap_nonpresent_pte; +static u64 __read_mostly shadow_notrap_nonpresent_pte; + +void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte) +{ + shadow_trap_nonpresent_pte = trap_pte; + shadow_notrap_nonpresent_pte = notrap_pte; +} +EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes); + +static int is_write_protection(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cr0 & X86_CR0_WP; +} + +static int is_cpuid_PSE36(void) +{ + return 1; +} + +static int is_nx(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.shadow_efer & EFER_NX; +} + +static int is_present_pte(unsigned long pte) +{ + return pte & PT_PRESENT_MASK; +} + +static int is_shadow_present_pte(u64 pte) +{ + pte &= ~PT_SHADOW_IO_MARK; + return pte != shadow_trap_nonpresent_pte + && pte != shadow_notrap_nonpresent_pte; +} + +static int is_writeble_pte(unsigned long pte) +{ + return pte & PT_WRITABLE_MASK; +} + +static int is_dirty_pte(unsigned long pte) +{ + return pte & PT_DIRTY_MASK; +} + +static int is_io_pte(unsigned long pte) +{ + return pte & PT_SHADOW_IO_MARK; +} + +static int is_rmap_pte(u64 pte) +{ + return pte != shadow_trap_nonpresent_pte + && pte != shadow_notrap_nonpresent_pte; +} + +static gfn_t pse36_gfn_delta(u32 gpte) +{ + int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT; + + return (gpte & PT32_DIR_PSE36_MASK) << shift; +} + +static void set_shadow_pte(u64 *sptep, u64 spte) +{ +#ifdef CONFIG_X86_64 + set_64bit((unsigned long *)sptep, spte); +#else + set_64bit((unsigned long long *)sptep, spte); +#endif +} + +static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, + struct kmem_cache *base_cache, int min) +{ + void *obj; + + if (cache->nobjs >= min) + return 0; + while (cache->nobjs < ARRAY_SIZE(cache->objects)) { + obj = kmem_cache_zalloc(base_cache, GFP_KERNEL); + if (!obj) + return -ENOMEM; + cache->objects[cache->nobjs++] = obj; + } + return 0; +} + +static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +{ + while (mc->nobjs) + kfree(mc->objects[--mc->nobjs]); +} + +static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, + int min) +{ + struct page *page; + + if (cache->nobjs >= min) + return 0; + while (cache->nobjs < ARRAY_SIZE(cache->objects)) { + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + set_page_private(page, 0); + cache->objects[cache->nobjs++] = page_address(page); + } + return 0; +} + +static void mmu_free_memory_cache_page(struct kvm_mmu_memory_cache *mc) +{ + while (mc->nobjs) + free_page((unsigned long)mc->objects[--mc->nobjs]); +} + +static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu) +{ + int r; + + r = mmu_topup_memory_cache(&vcpu->arch.mmu_pte_chain_cache, + pte_chain_cache, 4); + if (r) + goto out; + r = mmu_topup_memory_cache(&vcpu->arch.mmu_rmap_desc_cache, + rmap_desc_cache, 1); + if (r) + goto out; + r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8); + if (r) + goto out; + r = mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache, + mmu_page_header_cache, 4); +out: + return r; +} + +static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) +{ + mmu_free_memory_cache(&vcpu->arch.mmu_pte_chain_cache); + mmu_free_memory_cache(&vcpu->arch.mmu_rmap_desc_cache); + mmu_free_memory_cache_page(&vcpu->arch.mmu_page_cache); + mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); +} + +static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, + size_t size) +{ + void *p; + + BUG_ON(!mc->nobjs); + p = mc->objects[--mc->nobjs]; + memset(p, 0, size); + return p; +} + +static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu) +{ + return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_chain_cache, + sizeof(struct kvm_pte_chain)); +} + +static void mmu_free_pte_chain(struct kvm_pte_chain *pc) +{ + kfree(pc); +} + +static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu) +{ + return mmu_memory_cache_alloc(&vcpu->arch.mmu_rmap_desc_cache, + sizeof(struct kvm_rmap_desc)); +} + +static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) +{ + kfree(rd); +} + +/* + * Take gfn and return the reverse mapping to it. + * Note: gfn must be unaliased before this function get called + */ + +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + + slot = gfn_to_memslot(kvm, gfn); + return &slot->rmap[gfn - slot->base_gfn]; +} + +/* + * Reverse mapping data structures: + * + * If rmapp bit zero is zero, then rmapp point to the shadw page table entry + * that points to page_address(page). + * + * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc + * containing more mappings. + */ +static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) +{ + struct kvm_mmu_page *sp; + struct kvm_rmap_desc *desc; + unsigned long *rmapp; + int i; + + if (!is_rmap_pte(*spte)) + return; + gfn = unalias_gfn(vcpu->kvm, gfn); + sp = page_header(__pa(spte)); + sp->gfns[spte - sp->spt] = gfn; + rmapp = gfn_to_rmap(vcpu->kvm, gfn); + if (!*rmapp) { + rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte); + *rmapp = (unsigned long)spte; + } else if (!(*rmapp & 1)) { + rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte); + desc = mmu_alloc_rmap_desc(vcpu); + desc->shadow_ptes[0] = (u64 *)*rmapp; + desc->shadow_ptes[1] = spte; + *rmapp = (unsigned long)desc | 1; + } else { + rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte); + desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); + while (desc->shadow_ptes[RMAP_EXT-1] && desc->more) + desc = desc->more; + if (desc->shadow_ptes[RMAP_EXT-1]) { + desc->more = mmu_alloc_rmap_desc(vcpu); + desc = desc->more; + } + for (i = 0; desc->shadow_ptes[i]; ++i) + ; + desc->shadow_ptes[i] = spte; + } +} + +static void rmap_desc_remove_entry(unsigned long *rmapp, + struct kvm_rmap_desc *desc, + int i, + struct kvm_rmap_desc *prev_desc) +{ + int j; + + for (j = RMAP_EXT - 1; !desc->shadow_ptes[j] && j > i; --j) + ; + desc->shadow_ptes[i] = desc->shadow_ptes[j]; + desc->shadow_ptes[j] = NULL; + if (j != 0) + return; + if (!prev_desc && !desc->more) + *rmapp = (unsigned long)desc->shadow_ptes[0]; + else + if (prev_desc) + prev_desc->more = desc->more; + else + *rmapp = (unsigned long)desc->more | 1; + mmu_free_rmap_desc(desc); +} + +static void rmap_remove(struct kvm *kvm, u64 *spte) +{ + struct kvm_rmap_desc *desc; + struct kvm_rmap_desc *prev_desc; + struct kvm_mmu_page *sp; + struct page *page; + unsigned long *rmapp; + int i; + + if (!is_rmap_pte(*spte)) + return; + sp = page_header(__pa(spte)); + page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT); + mark_page_accessed(page); + if (is_writeble_pte(*spte)) + kvm_release_page_dirty(page); + else + kvm_release_page_clean(page); + rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt]); + if (!*rmapp) { + printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); + BUG(); + } else if (!(*rmapp & 1)) { + rmap_printk("rmap_remove: %p %llx 1->0\n", spte, *spte); + if ((u64 *)*rmapp != spte) { + printk(KERN_ERR "rmap_remove: %p %llx 1->BUG\n", + spte, *spte); + BUG(); + } + *rmapp = 0; + } else { + rmap_printk("rmap_remove: %p %llx many->many\n", spte, *spte); + desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); + prev_desc = NULL; + while (desc) { + for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i) + if (desc->shadow_ptes[i] == spte) { + rmap_desc_remove_entry(rmapp, + desc, i, + prev_desc); + return; + } + prev_desc = desc; + desc = desc->more; + } + BUG(); + } +} + +static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) +{ + struct kvm_rmap_desc *desc; + struct kvm_rmap_desc *prev_desc; + u64 *prev_spte; + int i; + + if (!*rmapp) + return NULL; + else if (!(*rmapp & 1)) { + if (!spte) + return (u64 *)*rmapp; + return NULL; + } + desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); + prev_desc = NULL; + prev_spte = NULL; + while (desc) { + for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i) { + if (prev_spte == spte) + return desc->shadow_ptes[i]; + prev_spte = desc->shadow_ptes[i]; + } + desc = desc->more; + } + return NULL; +} + +static void rmap_write_protect(struct kvm *kvm, u64 gfn) +{ + unsigned long *rmapp; + u64 *spte; + int write_protected = 0; + + gfn = unalias_gfn(kvm, gfn); + rmapp = gfn_to_rmap(kvm, gfn); + + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + BUG_ON(!spte); + BUG_ON(!(*spte & PT_PRESENT_MASK)); + rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); + if (is_writeble_pte(*spte)) { + set_shadow_pte(spte, *spte & ~PT_WRITABLE_MASK); + write_protected = 1; + } + spte = rmap_next(kvm, rmapp, spte); + } + if (write_protected) + kvm_flush_remote_tlbs(kvm); +} + +#ifdef MMU_DEBUG +static int is_empty_shadow_page(u64 *spt) +{ + u64 *pos; + u64 *end; + + for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) + if ((*pos & ~PT_SHADOW_IO_MARK) != shadow_trap_nonpresent_pte) { + printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__, + pos, *pos); + return 0; + } + return 1; +} +#endif + +static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + ASSERT(is_empty_shadow_page(sp->spt)); + list_del(&sp->link); + __free_page(virt_to_page(sp->spt)); + __free_page(virt_to_page(sp->gfns)); + kfree(sp); + ++kvm->arch.n_free_mmu_pages; +} + +static unsigned kvm_page_table_hashfn(gfn_t gfn) +{ + return gfn; +} + +static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, + u64 *parent_pte) +{ + struct kvm_mmu_page *sp; + + sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache, sizeof *sp); + sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); + sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); + set_page_private(virt_to_page(sp->spt), (unsigned long)sp); + list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); + ASSERT(is_empty_shadow_page(sp->spt)); + sp->slot_bitmap = 0; + sp->multimapped = 0; + sp->parent_pte = parent_pte; + --vcpu->kvm->arch.n_free_mmu_pages; + return sp; +} + +static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, u64 *parent_pte) +{ + struct kvm_pte_chain *pte_chain; + struct hlist_node *node; + int i; + + if (!parent_pte) + return; + if (!sp->multimapped) { + u64 *old = sp->parent_pte; + + if (!old) { + sp->parent_pte = parent_pte; + return; + } + sp->multimapped = 1; + pte_chain = mmu_alloc_pte_chain(vcpu); + INIT_HLIST_HEAD(&sp->parent_ptes); + hlist_add_head(&pte_chain->link, &sp->parent_ptes); + pte_chain->parent_ptes[0] = old; + } + hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link) { + if (pte_chain->parent_ptes[NR_PTE_CHAIN_ENTRIES-1]) + continue; + for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) + if (!pte_chain->parent_ptes[i]) { + pte_chain->parent_ptes[i] = parent_pte; + return; + } + } + pte_chain = mmu_alloc_pte_chain(vcpu); + BUG_ON(!pte_chain); + hlist_add_head(&pte_chain->link, &sp->parent_ptes); + pte_chain->parent_ptes[0] = parent_pte; +} + +static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp, + u64 *parent_pte) +{ + struct kvm_pte_chain *pte_chain; + struct hlist_node *node; + int i; + + if (!sp->multimapped) { + BUG_ON(sp->parent_pte != parent_pte); + sp->parent_pte = NULL; + return; + } + hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link) + for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) { + if (!pte_chain->parent_ptes[i]) + break; + if (pte_chain->parent_ptes[i] != parent_pte) + continue; + while (i + 1 < NR_PTE_CHAIN_ENTRIES + && pte_chain->parent_ptes[i + 1]) { + pte_chain->parent_ptes[i] + = pte_chain->parent_ptes[i + 1]; + ++i; + } + pte_chain->parent_ptes[i] = NULL; + if (i == 0) { + hlist_del(&pte_chain->link); + mmu_free_pte_chain(pte_chain); + if (hlist_empty(&sp->parent_ptes)) { + sp->multimapped = 0; + sp->parent_pte = NULL; + } + } + return; + } + BUG(); +} + +static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) +{ + unsigned index; + struct hlist_head *bucket; + struct kvm_mmu_page *sp; + struct hlist_node *node; + + pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); + index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + bucket = &kvm->arch.mmu_page_hash[index]; + hlist_for_each_entry(sp, node, bucket, hash_link) + if (sp->gfn == gfn && !sp->role.metaphysical) { + pgprintk("%s: found role %x\n", + __FUNCTION__, sp->role.word); + return sp; + } + return NULL; +} + +static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, + gfn_t gfn, + gva_t gaddr, + unsigned level, + int metaphysical, + unsigned access, + u64 *parent_pte, + bool *new_page) +{ + union kvm_mmu_page_role role; + unsigned index; + unsigned quadrant; + struct hlist_head *bucket; + struct kvm_mmu_page *sp; + struct hlist_node *node; + + role.word = 0; + role.glevels = vcpu->arch.mmu.root_level; + role.level = level; + role.metaphysical = metaphysical; + role.access = access; + if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { + quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); + quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; + role.quadrant = quadrant; + } + pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__, + gfn, role.word); + index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + bucket = &vcpu->kvm->arch.mmu_page_hash[index]; + hlist_for_each_entry(sp, node, bucket, hash_link) + if (sp->gfn == gfn && sp->role.word == role.word) { + mmu_page_add_parent_pte(vcpu, sp, parent_pte); + pgprintk("%s: found\n", __FUNCTION__); + return sp; + } + ++vcpu->kvm->stat.mmu_cache_miss; + sp = kvm_mmu_alloc_page(vcpu, parent_pte); + if (!sp) + return sp; + pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word); + sp->gfn = gfn; + sp->role = role; + hlist_add_head(&sp->hash_link, bucket); + vcpu->arch.mmu.prefetch_page(vcpu, sp); + if (!metaphysical) + rmap_write_protect(vcpu->kvm, gfn); + if (new_page) + *new_page = 1; + return sp; +} + +static void kvm_mmu_page_unlink_children(struct kvm *kvm, + struct kvm_mmu_page *sp) +{ + unsigned i; + u64 *pt; + u64 ent; + + pt = sp->spt; + + if (sp->role.level == PT_PAGE_TABLE_LEVEL) { + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { + if (is_shadow_present_pte(pt[i])) + rmap_remove(kvm, &pt[i]); + pt[i] = shadow_trap_nonpresent_pte; + } + kvm_flush_remote_tlbs(kvm); + return; + } + + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { + ent = pt[i]; + + pt[i] = shadow_trap_nonpresent_pte; + if (!is_shadow_present_pte(ent)) + continue; + ent &= PT64_BASE_ADDR_MASK; + mmu_page_remove_parent_pte(page_header(ent), &pt[i]); + } + kvm_flush_remote_tlbs(kvm); +} + +static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) +{ + mmu_page_remove_parent_pte(sp, parent_pte); +} + +static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm) +{ + int i; + + for (i = 0; i < KVM_MAX_VCPUS; ++i) + if (kvm->vcpus[i]) + kvm->vcpus[i]->arch.last_pte_updated = NULL; +} + +static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + u64 *parent_pte; + + ++kvm->stat.mmu_shadow_zapped; + while (sp->multimapped || sp->parent_pte) { + if (!sp->multimapped) + parent_pte = sp->parent_pte; + else { + struct kvm_pte_chain *chain; + + chain = container_of(sp->parent_ptes.first, + struct kvm_pte_chain, link); + parent_pte = chain->parent_ptes[0]; + } + BUG_ON(!parent_pte); + kvm_mmu_put_page(sp, parent_pte); + set_shadow_pte(parent_pte, shadow_trap_nonpresent_pte); + } + kvm_mmu_page_unlink_children(kvm, sp); + if (!sp->root_count) { + hlist_del(&sp->hash_link); + kvm_mmu_free_page(kvm, sp); + } else + list_move(&sp->link, &kvm->arch.active_mmu_pages); + kvm_mmu_reset_last_pte_updated(kvm); +} + +/* + * Changing the number of mmu pages allocated to the vm + * Note: if kvm_nr_mmu_pages is too small, you will get dead lock + */ +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages) +{ + /* + * If we set the number of mmu pages to be smaller be than the + * number of actived pages , we must to free some mmu pages before we + * change the value + */ + + if ((kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages) > + kvm_nr_mmu_pages) { + int n_used_mmu_pages = kvm->arch.n_alloc_mmu_pages + - kvm->arch.n_free_mmu_pages; + + while (n_used_mmu_pages > kvm_nr_mmu_pages) { + struct kvm_mmu_page *page; + + page = container_of(kvm->arch.active_mmu_pages.prev, + struct kvm_mmu_page, link); + kvm_mmu_zap_page(kvm, page); + n_used_mmu_pages--; + } + kvm->arch.n_free_mmu_pages = 0; + } + else + kvm->arch.n_free_mmu_pages += kvm_nr_mmu_pages + - kvm->arch.n_alloc_mmu_pages; + + kvm->arch.n_alloc_mmu_pages = kvm_nr_mmu_pages; +} + +static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +{ + unsigned index; + struct hlist_head *bucket; + struct kvm_mmu_page *sp; + struct hlist_node *node, *n; + int r; + + pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); + r = 0; + index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + bucket = &kvm->arch.mmu_page_hash[index]; + hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) + if (sp->gfn == gfn && !sp->role.metaphysical) { + pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn, + sp->role.word); + kvm_mmu_zap_page(kvm, sp); + r = 1; + } + return r; +} + +static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_mmu_page *sp; + + while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) { + pgprintk("%s: zap %lx %x\n", __FUNCTION__, gfn, sp->role.word); + kvm_mmu_zap_page(kvm, sp); + } +} + +static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) +{ + int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn)); + struct kvm_mmu_page *sp = page_header(__pa(pte)); + + __set_bit(slot, &sp->slot_bitmap); +} + +struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) +{ + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); + + if (gpa == UNMAPPED_GVA) + return NULL; + return gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); +} + +static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, + unsigned pt_access, unsigned pte_access, + int user_fault, int write_fault, int dirty, + int *ptwrite, gfn_t gfn, struct page *page) +{ + u64 spte; + int was_rmapped = is_rmap_pte(*shadow_pte); + int was_writeble = is_writeble_pte(*shadow_pte); + + pgprintk("%s: spte %llx access %x write_fault %d" + " user_fault %d gfn %lx\n", + __FUNCTION__, *shadow_pte, pt_access, + write_fault, user_fault, gfn); + + /* + * We don't set the accessed bit, since we sometimes want to see + * whether the guest actually used the pte (in order to detect + * demand paging). + */ + spte = PT_PRESENT_MASK | PT_DIRTY_MASK; + if (!dirty) + pte_access &= ~ACC_WRITE_MASK; + if (!(pte_access & ACC_EXEC_MASK)) + spte |= PT64_NX_MASK; + + spte |= PT_PRESENT_MASK; + if (pte_access & ACC_USER_MASK) + spte |= PT_USER_MASK; + + if (is_error_page(page)) { + set_shadow_pte(shadow_pte, + shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK); + kvm_release_page_clean(page); + return; + } + + spte |= page_to_phys(page); + + if ((pte_access & ACC_WRITE_MASK) + || (write_fault && !is_write_protection(vcpu) && !user_fault)) { + struct kvm_mmu_page *shadow; + + spte |= PT_WRITABLE_MASK; + if (user_fault) { + mmu_unshadow(vcpu->kvm, gfn); + goto unshadowed; + } + + shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn); + if (shadow) { + pgprintk("%s: found shadow page for %lx, marking ro\n", + __FUNCTION__, gfn); + pte_access &= ~ACC_WRITE_MASK; + if (is_writeble_pte(spte)) { + spte &= ~PT_WRITABLE_MASK; + kvm_x86_ops->tlb_flush(vcpu); + } + if (write_fault) + *ptwrite = 1; + } + } + +unshadowed: + + if (pte_access & ACC_WRITE_MASK) + mark_page_dirty(vcpu->kvm, gfn); + + pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte); + set_shadow_pte(shadow_pte, spte); + page_header_update_slot(vcpu->kvm, shadow_pte, gfn); + if (!was_rmapped) { + rmap_add(vcpu, shadow_pte, gfn); + if (!is_rmap_pte(*shadow_pte)) + kvm_release_page_clean(page); + } else { + if (was_writeble) + kvm_release_page_dirty(page); + else + kvm_release_page_clean(page); + } + if (!ptwrite || !*ptwrite) + vcpu->arch.last_pte_updated = shadow_pte; +} + +static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) +{ +} + +static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, + gfn_t gfn, struct page *page) +{ + int level = PT32E_ROOT_LEVEL; + hpa_t table_addr = vcpu->arch.mmu.root_hpa; + int pt_write = 0; + + for (; ; level--) { + u32 index = PT64_INDEX(v, level); + u64 *table; + + ASSERT(VALID_PAGE(table_addr)); + table = __va(table_addr); + + if (level == 1) { + mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL, + 0, write, 1, &pt_write, gfn, page); + return pt_write || is_io_pte(table[index]); + } + + if (table[index] == shadow_trap_nonpresent_pte) { + struct kvm_mmu_page *new_table; + gfn_t pseudo_gfn; + + pseudo_gfn = (v & PT64_DIR_BASE_ADDR_MASK) + >> PAGE_SHIFT; + new_table = kvm_mmu_get_page(vcpu, pseudo_gfn, + v, level - 1, + 1, ACC_ALL, &table[index], + NULL); + if (!new_table) { + pgprintk("nonpaging_map: ENOMEM\n"); + kvm_release_page_clean(page); + return -ENOMEM; + } + + table[index] = __pa(new_table->spt) | PT_PRESENT_MASK + | PT_WRITABLE_MASK | PT_USER_MASK; + } + table_addr = table[index] & PT64_BASE_ADDR_MASK; + } +} + +static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) +{ + int r; + + struct page *page; + + down_read(¤t->mm->mmap_sem); + page = gfn_to_page(vcpu->kvm, gfn); + + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + r = __nonpaging_map(vcpu, v, write, gfn, page); + spin_unlock(&vcpu->kvm->mmu_lock); + + up_read(¤t->mm->mmap_sem); + + return r; +} + + +static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp) +{ + int i; + + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) + sp->spt[i] = shadow_trap_nonpresent_pte; +} + +static void mmu_free_roots(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_mmu_page *sp; + + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return; + spin_lock(&vcpu->kvm->mmu_lock); +#ifdef CONFIG_X86_64 + if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { + hpa_t root = vcpu->arch.mmu.root_hpa; + + sp = page_header(root); + --sp->root_count; + vcpu->arch.mmu.root_hpa = INVALID_PAGE; + spin_unlock(&vcpu->kvm->mmu_lock); + return; + } +#endif + for (i = 0; i < 4; ++i) { + hpa_t root = vcpu->arch.mmu.pae_root[i]; + + if (root) { + root &= PT64_BASE_ADDR_MASK; + sp = page_header(root); + --sp->root_count; + } + vcpu->arch.mmu.pae_root[i] = INVALID_PAGE; + } + spin_unlock(&vcpu->kvm->mmu_lock); + vcpu->arch.mmu.root_hpa = INVALID_PAGE; +} + +static void mmu_alloc_roots(struct kvm_vcpu *vcpu) +{ + int i; + gfn_t root_gfn; + struct kvm_mmu_page *sp; + + root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; + +#ifdef CONFIG_X86_64 + if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { + hpa_t root = vcpu->arch.mmu.root_hpa; + + ASSERT(!VALID_PAGE(root)); + sp = kvm_mmu_get_page(vcpu, root_gfn, 0, + PT64_ROOT_LEVEL, 0, ACC_ALL, NULL, NULL); + root = __pa(sp->spt); + ++sp->root_count; + vcpu->arch.mmu.root_hpa = root; + return; + } +#endif + for (i = 0; i < 4; ++i) { + hpa_t root = vcpu->arch.mmu.pae_root[i]; + + ASSERT(!VALID_PAGE(root)); + if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { + if (!is_present_pte(vcpu->arch.pdptrs[i])) { + vcpu->arch.mmu.pae_root[i] = 0; + continue; + } + root_gfn = vcpu->arch.pdptrs[i] >> PAGE_SHIFT; + } else if (vcpu->arch.mmu.root_level == 0) + root_gfn = 0; + sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, + PT32_ROOT_LEVEL, !is_paging(vcpu), + ACC_ALL, NULL, NULL); + root = __pa(sp->spt); + ++sp->root_count; + vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK; + } + vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root); +} + +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr) +{ + return vaddr; +} + +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, + u32 error_code) +{ + gfn_t gfn; + int r; + + pgprintk("%s: gva %lx error %x\n", __FUNCTION__, gva, error_code); + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + ASSERT(vcpu); + ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + gfn = gva >> PAGE_SHIFT; + + return nonpaging_map(vcpu, gva & PAGE_MASK, + error_code & PFERR_WRITE_MASK, gfn); +} + +static void nonpaging_free(struct kvm_vcpu *vcpu) +{ + mmu_free_roots(vcpu); +} + +static int nonpaging_init_context(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu *context = &vcpu->arch.mmu; + + context->new_cr3 = nonpaging_new_cr3; + context->page_fault = nonpaging_page_fault; + context->gva_to_gpa = nonpaging_gva_to_gpa; + context->free = nonpaging_free; + context->prefetch_page = nonpaging_prefetch_page; + context->root_level = 0; + context->shadow_root_level = PT32E_ROOT_LEVEL; + context->root_hpa = INVALID_PAGE; + return 0; +} + +void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + kvm_x86_ops->tlb_flush(vcpu); +} + +static void paging_new_cr3(struct kvm_vcpu *vcpu) +{ + pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->cr3); + mmu_free_roots(vcpu); +} + +static void inject_page_fault(struct kvm_vcpu *vcpu, + u64 addr, + u32 err_code) +{ + kvm_inject_page_fault(vcpu, addr, err_code); +} + +static void paging_free(struct kvm_vcpu *vcpu) +{ + nonpaging_free(vcpu); +} + +#define PTTYPE 64 +#include "paging_tmpl.h" +#undef PTTYPE + +#define PTTYPE 32 +#include "paging_tmpl.h" +#undef PTTYPE + +static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level) +{ + struct kvm_mmu *context = &vcpu->arch.mmu; + + ASSERT(is_pae(vcpu)); + context->new_cr3 = paging_new_cr3; + context->page_fault = paging64_page_fault; + context->gva_to_gpa = paging64_gva_to_gpa; + context->prefetch_page = paging64_prefetch_page; + context->free = paging_free; + context->root_level = level; + context->shadow_root_level = level; + context->root_hpa = INVALID_PAGE; + return 0; +} + +static int paging64_init_context(struct kvm_vcpu *vcpu) +{ + return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL); +} + +static int paging32_init_context(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu *context = &vcpu->arch.mmu; + + context->new_cr3 = paging_new_cr3; + context->page_fault = paging32_page_fault; + context->gva_to_gpa = paging32_gva_to_gpa; + context->free = paging_free; + context->prefetch_page = paging32_prefetch_page; + context->root_level = PT32_ROOT_LEVEL; + context->shadow_root_level = PT32E_ROOT_LEVEL; + context->root_hpa = INVALID_PAGE; + return 0; +} + +static int paging32E_init_context(struct kvm_vcpu *vcpu) +{ + return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL); +} + +static int init_kvm_mmu(struct kvm_vcpu *vcpu) +{ + ASSERT(vcpu); + ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + if (!is_paging(vcpu)) + return nonpaging_init_context(vcpu); + else if (is_long_mode(vcpu)) + return paging64_init_context(vcpu); + else if (is_pae(vcpu)) + return paging32E_init_context(vcpu); + else + return paging32_init_context(vcpu); +} + +static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) +{ + ASSERT(vcpu); + if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) { + vcpu->arch.mmu.free(vcpu); + vcpu->arch.mmu.root_hpa = INVALID_PAGE; + } +} + +int kvm_mmu_reset_context(struct kvm_vcpu *vcpu) +{ + destroy_kvm_mmu(vcpu); + return init_kvm_mmu(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); + +int kvm_mmu_load(struct kvm_vcpu *vcpu) +{ + int r; + + r = mmu_topup_memory_caches(vcpu); + if (r) + goto out; + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + mmu_alloc_roots(vcpu); + spin_unlock(&vcpu->kvm->mmu_lock); + kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa); + kvm_mmu_flush_tlb(vcpu); +out: + return r; +} +EXPORT_SYMBOL_GPL(kvm_mmu_load); + +void kvm_mmu_unload(struct kvm_vcpu *vcpu) +{ + mmu_free_roots(vcpu); +} + +static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, + u64 *spte) +{ + u64 pte; + struct kvm_mmu_page *child; + + pte = *spte; + if (is_shadow_present_pte(pte)) { + if (sp->role.level == PT_PAGE_TABLE_LEVEL) + rmap_remove(vcpu->kvm, spte); + else { + child = page_header(pte & PT64_BASE_ADDR_MASK); + mmu_page_remove_parent_pte(child, spte); + } + } + set_shadow_pte(spte, shadow_trap_nonpresent_pte); +} + +static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, + u64 *spte, + const void *new, int bytes, + int offset_in_pte) +{ + if (sp->role.level != PT_PAGE_TABLE_LEVEL) { + ++vcpu->kvm->stat.mmu_pde_zapped; + return; + } + + ++vcpu->kvm->stat.mmu_pte_updated; + if (sp->role.glevels == PT32_ROOT_LEVEL) + paging32_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte); + else + paging64_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte); +} + +static bool need_remote_flush(u64 old, u64 new) +{ + if (!is_shadow_present_pte(old)) + return false; + if (!is_shadow_present_pte(new)) + return true; + if ((old ^ new) & PT64_BASE_ADDR_MASK) + return true; + old ^= PT64_NX_MASK; + new ^= PT64_NX_MASK; + return (old & ~new & PT64_PERM_MASK) != 0; +} + +static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, u64 old, u64 new) +{ + if (need_remote_flush(old, new)) + kvm_flush_remote_tlbs(vcpu->kvm); + else + kvm_mmu_flush_tlb(vcpu); +} + +static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) +{ + u64 *spte = vcpu->arch.last_pte_updated; + + return !!(spte && (*spte & PT_ACCESSED_MASK)); +} + +static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, + const u8 *new, int bytes) +{ + gfn_t gfn; + int r; + u64 gpte = 0; + + if (bytes != 4 && bytes != 8) + return; + + /* + * Assume that the pte write on a page table of the same type + * as the current vcpu paging mode. This is nearly always true + * (might be false while changing modes). Note it is verified later + * by update_pte(). + */ + if (is_pae(vcpu)) { + /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ + if ((bytes == 4) && (gpa % 4 == 0)) { + r = kvm_read_guest(vcpu->kvm, gpa & ~(u64)7, &gpte, 8); + if (r) + return; + memcpy((void *)&gpte + (gpa % 8), new, 4); + } else if ((bytes == 8) && (gpa % 8 == 0)) { + memcpy((void *)&gpte, new, 8); + } + } else { + if ((bytes == 4) && (gpa % 4 == 0)) + memcpy((void *)&gpte, new, 4); + } + if (!is_present_pte(gpte)) + return; + gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; + vcpu->arch.update_pte.gfn = gfn; + vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn); +} + +void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, + const u8 *new, int bytes) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + struct kvm_mmu_page *sp; + struct hlist_node *node, *n; + struct hlist_head *bucket; + unsigned index; + u64 entry; + u64 *spte; + unsigned offset = offset_in_page(gpa); + unsigned pte_size; + unsigned page_offset; + unsigned misaligned; + unsigned quadrant; + int level; + int flooded = 0; + int npte; + + pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes); + mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes); + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + ++vcpu->kvm->stat.mmu_pte_write; + kvm_mmu_audit(vcpu, "pre pte write"); + if (gfn == vcpu->arch.last_pt_write_gfn + && !last_updated_pte_accessed(vcpu)) { + ++vcpu->arch.last_pt_write_count; + if (vcpu->arch.last_pt_write_count >= 3) + flooded = 1; + } else { + vcpu->arch.last_pt_write_gfn = gfn; + vcpu->arch.last_pt_write_count = 1; + vcpu->arch.last_pte_updated = NULL; + } + index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + bucket = &vcpu->kvm->arch.mmu_page_hash[index]; + hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { + if (sp->gfn != gfn || sp->role.metaphysical) + continue; + pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; + misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); + misaligned |= bytes < 4; + if (misaligned || flooded) { + /* + * Misaligned accesses are too much trouble to fix + * up; also, they usually indicate a page is not used + * as a page table. + * + * If we're seeing too many writes to a page, + * it may no longer be a page table, or we may be + * forking, in which case it is better to unmap the + * page. + */ + pgprintk("misaligned: gpa %llx bytes %d role %x\n", + gpa, bytes, sp->role.word); + kvm_mmu_zap_page(vcpu->kvm, sp); + ++vcpu->kvm->stat.mmu_flooded; + continue; + } + page_offset = offset; + level = sp->role.level; + npte = 1; + if (sp->role.glevels == PT32_ROOT_LEVEL) { + page_offset <<= 1; /* 32->64 */ + /* + * A 32-bit pde maps 4MB while the shadow pdes map + * only 2MB. So we need to double the offset again + * and zap two pdes instead of one. + */ + if (level == PT32_ROOT_LEVEL) { + page_offset &= ~7; /* kill rounding error */ + page_offset <<= 1; + npte = 2; + } + quadrant = page_offset >> PAGE_SHIFT; + page_offset &= ~PAGE_MASK; + if (quadrant != sp->role.quadrant) + continue; + } + spte = &sp->spt[page_offset / sizeof(*spte)]; + while (npte--) { + entry = *spte; + mmu_pte_write_zap_pte(vcpu, sp, spte); + mmu_pte_write_new_pte(vcpu, sp, spte, new, bytes, + page_offset & (pte_size - 1)); + mmu_pte_write_flush_tlb(vcpu, entry, *spte); + ++spte; + } + } + kvm_mmu_audit(vcpu, "post pte write"); + spin_unlock(&vcpu->kvm->mmu_lock); + if (vcpu->arch.update_pte.page) { + kvm_release_page_clean(vcpu->arch.update_pte.page); + vcpu->arch.update_pte.page = NULL; + } +} + +int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) +{ + gpa_t gpa; + int r; + + down_read(¤t->mm->mmap_sem); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); + up_read(¤t->mm->mmap_sem); + + spin_lock(&vcpu->kvm->mmu_lock); + r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); + spin_unlock(&vcpu->kvm->mmu_lock); + return r; +} + +void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) +{ + while (vcpu->kvm->arch.n_free_mmu_pages < KVM_REFILL_PAGES) { + struct kvm_mmu_page *sp; + + sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev, + struct kvm_mmu_page, link); + kvm_mmu_zap_page(vcpu->kvm, sp); + ++vcpu->kvm->stat.mmu_recycled; + } +} + +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) +{ + int r; + enum emulation_result er; + + r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code); + if (r < 0) + goto out; + + if (!r) { + r = 1; + goto out; + } + + r = mmu_topup_memory_caches(vcpu); + if (r) + goto out; + + er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0); + + switch (er) { + case EMULATE_DONE: + return 1; + case EMULATE_DO_MMIO: + ++vcpu->stat.mmio_exits; + return 0; + case EMULATE_FAIL: + kvm_report_emulation_failure(vcpu, "pagetable"); + return 1; + default: + BUG(); + } +out: + return r; +} +EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); + +static void free_mmu_pages(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_page *sp; + + while (!list_empty(&vcpu->kvm->arch.active_mmu_pages)) { + sp = container_of(vcpu->kvm->arch.active_mmu_pages.next, + struct kvm_mmu_page, link); + kvm_mmu_zap_page(vcpu->kvm, sp); + } + free_page((unsigned long)vcpu->arch.mmu.pae_root); +} + +static int alloc_mmu_pages(struct kvm_vcpu *vcpu) +{ + struct page *page; + int i; + + ASSERT(vcpu); + + if (vcpu->kvm->arch.n_requested_mmu_pages) + vcpu->kvm->arch.n_free_mmu_pages = + vcpu->kvm->arch.n_requested_mmu_pages; + else + vcpu->kvm->arch.n_free_mmu_pages = + vcpu->kvm->arch.n_alloc_mmu_pages; + /* + * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64. + * Therefore we need to allocate shadow page tables in the first + * 4GB of memory, which happens to fit the DMA32 zone. + */ + page = alloc_page(GFP_KERNEL | __GFP_DMA32); + if (!page) + goto error_1; + vcpu->arch.mmu.pae_root = page_address(page); + for (i = 0; i < 4; ++i) + vcpu->arch.mmu.pae_root[i] = INVALID_PAGE; + + return 0; + +error_1: + free_mmu_pages(vcpu); + return -ENOMEM; +} + +int kvm_mmu_create(struct kvm_vcpu *vcpu) +{ + ASSERT(vcpu); + ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + return alloc_mmu_pages(vcpu); +} + +int kvm_mmu_setup(struct kvm_vcpu *vcpu) +{ + ASSERT(vcpu); + ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + return init_kvm_mmu(vcpu); +} + +void kvm_mmu_destroy(struct kvm_vcpu *vcpu) +{ + ASSERT(vcpu); + + destroy_kvm_mmu(vcpu); + free_mmu_pages(vcpu); + mmu_free_memory_caches(vcpu); +} + +void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) +{ + struct kvm_mmu_page *sp; + + list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) { + int i; + u64 *pt; + + if (!test_bit(slot, &sp->slot_bitmap)) + continue; + + pt = sp->spt; + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) + /* avoid RMW */ + if (pt[i] & PT_WRITABLE_MASK) + pt[i] &= ~PT_WRITABLE_MASK; + } +} + +void kvm_mmu_zap_all(struct kvm *kvm) +{ + struct kvm_mmu_page *sp, *node; + + spin_lock(&kvm->mmu_lock); + list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) + kvm_mmu_zap_page(kvm, sp); + spin_unlock(&kvm->mmu_lock); + + kvm_flush_remote_tlbs(kvm); +} + +void kvm_mmu_module_exit(void) +{ + if (pte_chain_cache) + kmem_cache_destroy(pte_chain_cache); + if (rmap_desc_cache) + kmem_cache_destroy(rmap_desc_cache); + if (mmu_page_header_cache) + kmem_cache_destroy(mmu_page_header_cache); +} + +int kvm_mmu_module_init(void) +{ + pte_chain_cache = kmem_cache_create("kvm_pte_chain", + sizeof(struct kvm_pte_chain), + 0, 0, NULL); + if (!pte_chain_cache) + goto nomem; + rmap_desc_cache = kmem_cache_create("kvm_rmap_desc", + sizeof(struct kvm_rmap_desc), + 0, 0, NULL); + if (!rmap_desc_cache) + goto nomem; + + mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header", + sizeof(struct kvm_mmu_page), + 0, 0, NULL); + if (!mmu_page_header_cache) + goto nomem; + + return 0; + +nomem: + kvm_mmu_module_exit(); + return -ENOMEM; +} + +/* + * Caculate mmu pages needed for kvm. + */ +unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) +{ + int i; + unsigned int nr_mmu_pages; + unsigned int nr_pages = 0; + + for (i = 0; i < kvm->nmemslots; i++) + nr_pages += kvm->memslots[i].npages; + + nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; + nr_mmu_pages = max(nr_mmu_pages, + (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + + return nr_mmu_pages; +} + +#ifdef AUDIT + +static const char *audit_msg; + +static gva_t canonicalize(gva_t gva) +{ +#ifdef CONFIG_X86_64 + gva = (long long)(gva << 16) >> 16; +#endif + return gva; +} + +static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, + gva_t va, int level) +{ + u64 *pt = __va(page_pte & PT64_BASE_ADDR_MASK); + int i; + gva_t va_delta = 1ul << (PAGE_SHIFT + 9 * (level - 1)); + + for (i = 0; i < PT64_ENT_PER_PAGE; ++i, va += va_delta) { + u64 ent = pt[i]; + + if (ent == shadow_trap_nonpresent_pte) + continue; + + va = canonicalize(va); + if (level > 1) { + if (ent == shadow_notrap_nonpresent_pte) + printk(KERN_ERR "audit: (%s) nontrapping pte" + " in nonleaf level: levels %d gva %lx" + " level %d pte %llx\n", audit_msg, + vcpu->arch.mmu.root_level, va, level, ent); + + audit_mappings_page(vcpu, ent, va, level - 1); + } else { + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va); + struct page *page = gpa_to_page(vcpu, gpa); + hpa_t hpa = page_to_phys(page); + + if (is_shadow_present_pte(ent) + && (ent & PT64_BASE_ADDR_MASK) != hpa) + printk(KERN_ERR "xx audit error: (%s) levels %d" + " gva %lx gpa %llx hpa %llx ent %llx %d\n", + audit_msg, vcpu->arch.mmu.root_level, + va, gpa, hpa, ent, + is_shadow_present_pte(ent)); + else if (ent == shadow_notrap_nonpresent_pte + && !is_error_hpa(hpa)) + printk(KERN_ERR "audit: (%s) notrap shadow," + " valid guest gva %lx\n", audit_msg, va); + kvm_release_page_clean(page); + + } + } +} + +static void audit_mappings(struct kvm_vcpu *vcpu) +{ + unsigned i; + + if (vcpu->arch.mmu.root_level == 4) + audit_mappings_page(vcpu, vcpu->arch.mmu.root_hpa, 0, 4); + else + for (i = 0; i < 4; ++i) + if (vcpu->arch.mmu.pae_root[i] & PT_PRESENT_MASK) + audit_mappings_page(vcpu, + vcpu->arch.mmu.pae_root[i], + i << 30, + 2); +} + +static int count_rmaps(struct kvm_vcpu *vcpu) +{ + int nmaps = 0; + int i, j, k; + + for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { + struct kvm_memory_slot *m = &vcpu->kvm->memslots[i]; + struct kvm_rmap_desc *d; + + for (j = 0; j < m->npages; ++j) { + unsigned long *rmapp = &m->rmap[j]; + + if (!*rmapp) + continue; + if (!(*rmapp & 1)) { + ++nmaps; + continue; + } + d = (struct kvm_rmap_desc *)(*rmapp & ~1ul); + while (d) { + for (k = 0; k < RMAP_EXT; ++k) + if (d->shadow_ptes[k]) + ++nmaps; + else + break; + d = d->more; + } + } + } + return nmaps; +} + +static int count_writable_mappings(struct kvm_vcpu *vcpu) +{ + int nmaps = 0; + struct kvm_mmu_page *sp; + int i; + + list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { + u64 *pt = sp->spt; + + if (sp->role.level != PT_PAGE_TABLE_LEVEL) + continue; + + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { + u64 ent = pt[i]; + + if (!(ent & PT_PRESENT_MASK)) + continue; + if (!(ent & PT_WRITABLE_MASK)) + continue; + ++nmaps; + } + } + return nmaps; +} + +static void audit_rmap(struct kvm_vcpu *vcpu) +{ + int n_rmap = count_rmaps(vcpu); + int n_actual = count_writable_mappings(vcpu); + + if (n_rmap != n_actual) + printk(KERN_ERR "%s: (%s) rmap %d actual %d\n", + __FUNCTION__, audit_msg, n_rmap, n_actual); +} + +static void audit_write_protection(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_page *sp; + struct kvm_memory_slot *slot; + unsigned long *rmapp; + gfn_t gfn; + + list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { + if (sp->role.metaphysical) + continue; + + slot = gfn_to_memslot(vcpu->kvm, sp->gfn); + gfn = unalias_gfn(vcpu->kvm, sp->gfn); + rmapp = &slot->rmap[gfn - slot->base_gfn]; + if (*rmapp) + printk(KERN_ERR "%s: (%s) shadow page has writable" + " mappings: gfn %lx role %x\n", + __FUNCTION__, audit_msg, sp->gfn, + sp->role.word); + } +} + +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) +{ + int olddbg = dbg; + + dbg = 0; + audit_msg = msg; + audit_rmap(vcpu); + audit_write_protection(vcpu); + audit_mappings(vcpu); + dbg = olddbg; +} + +#endif diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h new file mode 100644 index 00000000000..1fce19ec7a2 --- /dev/null +++ b/arch/x86/kvm/mmu.h @@ -0,0 +1,44 @@ +#ifndef __KVM_X86_MMU_H +#define __KVM_X86_MMU_H + +#include <linux/kvm_host.h> + +static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) +{ + if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES)) + __kvm_mmu_free_some_pages(vcpu); +} + +static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) +{ + if (likely(vcpu->arch.mmu.root_hpa != INVALID_PAGE)) + return 0; + + return kvm_mmu_load(vcpu); +} + +static inline int is_long_mode(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + return vcpu->arch.shadow_efer & EFER_LME; +#else + return 0; +#endif +} + +static inline int is_pae(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cr4 & X86_CR4_PAE; +} + +static inline int is_pse(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cr4 & X86_CR4_PSE; +} + +static inline int is_paging(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cr0 & X86_CR0_PG; +} + +#endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h new file mode 100644 index 00000000000..03ba8608fe0 --- /dev/null +++ b/arch/x86/kvm/paging_tmpl.h @@ -0,0 +1,484 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * This module enables machines with Intel VT-x extensions to run virtual + * machines without emulation or binary translation. + * + * MMU support + * + * Copyright (C) 2006 Qumranet, Inc. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +/* + * We need the mmu code to access both 32-bit and 64-bit guest ptes, + * so the code in this file is compiled twice, once per pte size. + */ + +#if PTTYPE == 64 + #define pt_element_t u64 + #define guest_walker guest_walker64 + #define FNAME(name) paging##64_##name + #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK + #define PT_INDEX(addr, level) PT64_INDEX(addr, level) + #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) + #define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level) + #define PT_LEVEL_BITS PT64_LEVEL_BITS + #ifdef CONFIG_X86_64 + #define PT_MAX_FULL_LEVELS 4 + #define CMPXCHG cmpxchg + #else + #define CMPXCHG cmpxchg64 + #define PT_MAX_FULL_LEVELS 2 + #endif +#elif PTTYPE == 32 + #define pt_element_t u32 + #define guest_walker guest_walker32 + #define FNAME(name) paging##32_##name + #define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK + #define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK + #define PT_INDEX(addr, level) PT32_INDEX(addr, level) + #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) + #define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level) + #define PT_LEVEL_BITS PT32_LEVEL_BITS + #define PT_MAX_FULL_LEVELS 2 + #define CMPXCHG cmpxchg +#else + #error Invalid PTTYPE value +#endif + +#define gpte_to_gfn FNAME(gpte_to_gfn) +#define gpte_to_gfn_pde FNAME(gpte_to_gfn_pde) + +/* + * The guest_walker structure emulates the behavior of the hardware page + * table walker. + */ +struct guest_walker { + int level; + gfn_t table_gfn[PT_MAX_FULL_LEVELS]; + pt_element_t ptes[PT_MAX_FULL_LEVELS]; + gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; + unsigned pt_access; + unsigned pte_access; + gfn_t gfn; + u32 error_code; +}; + +static gfn_t gpte_to_gfn(pt_element_t gpte) +{ + return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT; +} + +static gfn_t gpte_to_gfn_pde(pt_element_t gpte) +{ + return (gpte & PT_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; +} + +static bool FNAME(cmpxchg_gpte)(struct kvm *kvm, + gfn_t table_gfn, unsigned index, + pt_element_t orig_pte, pt_element_t new_pte) +{ + pt_element_t ret; + pt_element_t *table; + struct page *page; + + page = gfn_to_page(kvm, table_gfn); + table = kmap_atomic(page, KM_USER0); + + ret = CMPXCHG(&table[index], orig_pte, new_pte); + + kunmap_atomic(table, KM_USER0); + + kvm_release_page_dirty(page); + + return (ret != orig_pte); +} + +static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte) +{ + unsigned access; + + access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK; +#if PTTYPE == 64 + if (is_nx(vcpu)) + access &= ~(gpte >> PT64_NX_SHIFT); +#endif + return access; +} + +/* + * Fetch a guest pte for a guest virtual address + */ +static int FNAME(walk_addr)(struct guest_walker *walker, + struct kvm_vcpu *vcpu, gva_t addr, + int write_fault, int user_fault, int fetch_fault) +{ + pt_element_t pte; + gfn_t table_gfn; + unsigned index, pt_access, pte_access; + gpa_t pte_gpa; + + pgprintk("%s: addr %lx\n", __FUNCTION__, addr); +walk: + walker->level = vcpu->arch.mmu.root_level; + pte = vcpu->arch.cr3; +#if PTTYPE == 64 + if (!is_long_mode(vcpu)) { + pte = vcpu->arch.pdptrs[(addr >> 30) & 3]; + if (!is_present_pte(pte)) + goto not_present; + --walker->level; + } +#endif + ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) || + (vcpu->cr3 & CR3_NONPAE_RESERVED_BITS) == 0); + + pt_access = ACC_ALL; + + for (;;) { + index = PT_INDEX(addr, walker->level); + + table_gfn = gpte_to_gfn(pte); + pte_gpa = gfn_to_gpa(table_gfn); + pte_gpa += index * sizeof(pt_element_t); + walker->table_gfn[walker->level - 1] = table_gfn; + walker->pte_gpa[walker->level - 1] = pte_gpa; + pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__, + walker->level - 1, table_gfn); + + kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte)); + + if (!is_present_pte(pte)) + goto not_present; + + if (write_fault && !is_writeble_pte(pte)) + if (user_fault || is_write_protection(vcpu)) + goto access_error; + + if (user_fault && !(pte & PT_USER_MASK)) + goto access_error; + +#if PTTYPE == 64 + if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK)) + goto access_error; +#endif + + if (!(pte & PT_ACCESSED_MASK)) { + mark_page_dirty(vcpu->kvm, table_gfn); + if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, + index, pte, pte|PT_ACCESSED_MASK)) + goto walk; + pte |= PT_ACCESSED_MASK; + } + + pte_access = pt_access & FNAME(gpte_access)(vcpu, pte); + + walker->ptes[walker->level - 1] = pte; + + if (walker->level == PT_PAGE_TABLE_LEVEL) { + walker->gfn = gpte_to_gfn(pte); + break; + } + + if (walker->level == PT_DIRECTORY_LEVEL + && (pte & PT_PAGE_SIZE_MASK) + && (PTTYPE == 64 || is_pse(vcpu))) { + walker->gfn = gpte_to_gfn_pde(pte); + walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL); + if (PTTYPE == 32 && is_cpuid_PSE36()) + walker->gfn += pse36_gfn_delta(pte); + break; + } + + pt_access = pte_access; + --walker->level; + } + + if (write_fault && !is_dirty_pte(pte)) { + bool ret; + + mark_page_dirty(vcpu->kvm, table_gfn); + ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte, + pte|PT_DIRTY_MASK); + if (ret) + goto walk; + pte |= PT_DIRTY_MASK; + kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte)); + walker->ptes[walker->level - 1] = pte; + } + + walker->pt_access = pt_access; + walker->pte_access = pte_access; + pgprintk("%s: pte %llx pte_access %x pt_access %x\n", + __FUNCTION__, (u64)pte, pt_access, pte_access); + return 1; + +not_present: + walker->error_code = 0; + goto err; + +access_error: + walker->error_code = PFERR_PRESENT_MASK; + +err: + if (write_fault) + walker->error_code |= PFERR_WRITE_MASK; + if (user_fault) + walker->error_code |= PFERR_USER_MASK; + if (fetch_fault) + walker->error_code |= PFERR_FETCH_MASK; + return 0; +} + +static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, + u64 *spte, const void *pte, int bytes, + int offset_in_pte) +{ + pt_element_t gpte; + unsigned pte_access; + struct page *npage; + + gpte = *(const pt_element_t *)pte; + if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) { + if (!offset_in_pte && !is_present_pte(gpte)) + set_shadow_pte(spte, shadow_notrap_nonpresent_pte); + return; + } + if (bytes < sizeof(pt_element_t)) + return; + pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte); + pte_access = page->role.access & FNAME(gpte_access)(vcpu, gpte); + if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn) + return; + npage = vcpu->arch.update_pte.page; + if (!npage) + return; + get_page(npage); + mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0, + gpte & PT_DIRTY_MASK, NULL, gpte_to_gfn(gpte), npage); +} + +/* + * Fetch a shadow pte for a specific level in the paging hierarchy. + */ +static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, + struct guest_walker *walker, + int user_fault, int write_fault, int *ptwrite, + struct page *page) +{ + hpa_t shadow_addr; + int level; + u64 *shadow_ent; + unsigned access = walker->pt_access; + + if (!is_present_pte(walker->ptes[walker->level - 1])) + return NULL; + + shadow_addr = vcpu->arch.mmu.root_hpa; + level = vcpu->arch.mmu.shadow_root_level; + if (level == PT32E_ROOT_LEVEL) { + shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3]; + shadow_addr &= PT64_BASE_ADDR_MASK; + --level; + } + + for (; ; level--) { + u32 index = SHADOW_PT_INDEX(addr, level); + struct kvm_mmu_page *shadow_page; + u64 shadow_pte; + int metaphysical; + gfn_t table_gfn; + bool new_page = 0; + + shadow_ent = ((u64 *)__va(shadow_addr)) + index; + if (level == PT_PAGE_TABLE_LEVEL) + break; + if (is_shadow_present_pte(*shadow_ent)) { + shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK; + continue; + } + + if (level - 1 == PT_PAGE_TABLE_LEVEL + && walker->level == PT_DIRECTORY_LEVEL) { + metaphysical = 1; + if (!is_dirty_pte(walker->ptes[level - 1])) + access &= ~ACC_WRITE_MASK; + table_gfn = gpte_to_gfn(walker->ptes[level - 1]); + } else { + metaphysical = 0; + table_gfn = walker->table_gfn[level - 2]; + } + shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, + metaphysical, access, + shadow_ent, &new_page); + if (new_page && !metaphysical) { + int r; + pt_element_t curr_pte; + r = kvm_read_guest_atomic(vcpu->kvm, + walker->pte_gpa[level - 2], + &curr_pte, sizeof(curr_pte)); + if (r || curr_pte != walker->ptes[level - 2]) { + kvm_release_page_clean(page); + return NULL; + } + } + shadow_addr = __pa(shadow_page->spt); + shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK + | PT_WRITABLE_MASK | PT_USER_MASK; + *shadow_ent = shadow_pte; + } + + mmu_set_spte(vcpu, shadow_ent, access, walker->pte_access & access, + user_fault, write_fault, + walker->ptes[walker->level-1] & PT_DIRTY_MASK, + ptwrite, walker->gfn, page); + + return shadow_ent; +} + +/* + * Page fault handler. There are several causes for a page fault: + * - there is no shadow pte for the guest pte + * - write access through a shadow pte marked read only so that we can set + * the dirty bit + * - write access to a shadow pte marked read only so we can update the page + * dirty bitmap, when userspace requests it + * - mmio access; in this case we will never install a present shadow pte + * - normal guest page fault due to the guest pte marked not present, not + * writable, or not executable + * + * Returns: 1 if we need to emulate the instruction, 0 otherwise, or + * a negative value on error. + */ +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, + u32 error_code) +{ + int write_fault = error_code & PFERR_WRITE_MASK; + int user_fault = error_code & PFERR_USER_MASK; + int fetch_fault = error_code & PFERR_FETCH_MASK; + struct guest_walker walker; + u64 *shadow_pte; + int write_pt = 0; + int r; + struct page *page; + + pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code); + kvm_mmu_audit(vcpu, "pre page fault"); + + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + down_read(¤t->mm->mmap_sem); + /* + * Look up the shadow pte for the faulting address. + */ + r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault, + fetch_fault); + + /* + * The page is not mapped by the guest. Let the guest handle it. + */ + if (!r) { + pgprintk("%s: guest page fault\n", __FUNCTION__); + inject_page_fault(vcpu, addr, walker.error_code); + vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ + up_read(¤t->mm->mmap_sem); + return 0; + } + + page = gfn_to_page(vcpu->kvm, walker.gfn); + + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, + &write_pt, page); + pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__, + shadow_pte, *shadow_pte, write_pt); + + if (!write_pt) + vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ + + /* + * mmio: emulate if accessible, otherwise its a guest fault. + */ + if (shadow_pte && is_io_pte(*shadow_pte)) { + spin_unlock(&vcpu->kvm->mmu_lock); + up_read(¤t->mm->mmap_sem); + return 1; + } + + ++vcpu->stat.pf_fixed; + kvm_mmu_audit(vcpu, "post page fault (fixed)"); + spin_unlock(&vcpu->kvm->mmu_lock); + up_read(¤t->mm->mmap_sem); + + return write_pt; +} + +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr) +{ + struct guest_walker walker; + gpa_t gpa = UNMAPPED_GVA; + int r; + + r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0); + + if (r) { + gpa = gfn_to_gpa(walker.gfn); + gpa |= vaddr & ~PAGE_MASK; + } + + return gpa; +} + +static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp) +{ + int i, offset = 0, r = 0; + pt_element_t pt; + + if (sp->role.metaphysical + || (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) { + nonpaging_prefetch_page(vcpu, sp); + return; + } + + if (PTTYPE == 32) + offset = sp->role.quadrant << PT64_LEVEL_BITS; + + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { + gpa_t pte_gpa = gfn_to_gpa(sp->gfn); + pte_gpa += (i+offset) * sizeof(pt_element_t); + + r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &pt, + sizeof(pt_element_t)); + if (r || is_present_pte(pt)) + sp->spt[i] = shadow_trap_nonpresent_pte; + else + sp->spt[i] = shadow_notrap_nonpresent_pte; + } +} + +#undef pt_element_t +#undef guest_walker +#undef FNAME +#undef PT_BASE_ADDR_MASK +#undef PT_INDEX +#undef SHADOW_PT_INDEX +#undef PT_LEVEL_MASK +#undef PT_DIR_BASE_ADDR_MASK +#undef PT_LEVEL_BITS +#undef PT_MAX_FULL_LEVELS +#undef gpte_to_gfn +#undef gpte_to_gfn_pde +#undef CMPXCHG diff --git a/arch/x86/kvm/segment_descriptor.h b/arch/x86/kvm/segment_descriptor.h new file mode 100644 index 00000000000..56fc4c87338 --- /dev/null +++ b/arch/x86/kvm/segment_descriptor.h @@ -0,0 +1,29 @@ +#ifndef __SEGMENT_DESCRIPTOR_H +#define __SEGMENT_DESCRIPTOR_H + +struct segment_descriptor { + u16 limit_low; + u16 base_low; + u8 base_mid; + u8 type : 4; + u8 system : 1; + u8 dpl : 2; + u8 present : 1; + u8 limit_high : 4; + u8 avl : 1; + u8 long_mode : 1; + u8 default_op : 1; + u8 granularity : 1; + u8 base_high; +} __attribute__((packed)); + +#ifdef CONFIG_X86_64 +/* LDT or TSS descriptor in the GDT. 16 bytes. */ +struct segment_descriptor_64 { + struct segment_descriptor s; + u32 base_higher; + u32 pad_zero; +}; + +#endif +#endif diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c new file mode 100644 index 00000000000..de755cb1431 --- /dev/null +++ b/arch/x86/kvm/svm.c @@ -0,0 +1,1731 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#include <linux/kvm_host.h> + +#include "kvm_svm.h" +#include "irq.h" +#include "mmu.h" + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/vmalloc.h> +#include <linux/highmem.h> +#include <linux/sched.h> + +#include <asm/desc.h> + +MODULE_AUTHOR("Qumranet"); +MODULE_LICENSE("GPL"); + +#define IOPM_ALLOC_ORDER 2 +#define MSRPM_ALLOC_ORDER 1 + +#define DB_VECTOR 1 +#define UD_VECTOR 6 +#define GP_VECTOR 13 + +#define DR7_GD_MASK (1 << 13) +#define DR6_BD_MASK (1 << 13) + +#define SEG_TYPE_LDT 2 +#define SEG_TYPE_BUSY_TSS16 3 + +#define SVM_FEATURE_NPT (1 << 0) +#define SVM_FEATURE_LBRV (1 << 1) +#define SVM_DEATURE_SVML (1 << 2) + +static void kvm_reput_irq(struct vcpu_svm *svm); + +static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) +{ + return container_of(vcpu, struct vcpu_svm, vcpu); +} + +unsigned long iopm_base; +unsigned long msrpm_base; + +struct kvm_ldttss_desc { + u16 limit0; + u16 base0; + unsigned base1 : 8, type : 5, dpl : 2, p : 1; + unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; + u32 base3; + u32 zero1; +} __attribute__((packed)); + +struct svm_cpu_data { + int cpu; + + u64 asid_generation; + u32 max_asid; + u32 next_asid; + struct kvm_ldttss_desc *tss_desc; + + struct page *save_area; +}; + +static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); +static uint32_t svm_features; + +struct svm_init_data { + int cpu; + int r; +}; + +static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; + +#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges) +#define MSRS_RANGE_SIZE 2048 +#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) + +#define MAX_INST_SIZE 15 + +static inline u32 svm_has(u32 feat) +{ + return svm_features & feat; +} + +static inline u8 pop_irq(struct kvm_vcpu *vcpu) +{ + int word_index = __ffs(vcpu->arch.irq_summary); + int bit_index = __ffs(vcpu->arch.irq_pending[word_index]); + int irq = word_index * BITS_PER_LONG + bit_index; + + clear_bit(bit_index, &vcpu->arch.irq_pending[word_index]); + if (!vcpu->arch.irq_pending[word_index]) + clear_bit(word_index, &vcpu->arch.irq_summary); + return irq; +} + +static inline void push_irq(struct kvm_vcpu *vcpu, u8 irq) +{ + set_bit(irq, vcpu->arch.irq_pending); + set_bit(irq / BITS_PER_LONG, &vcpu->arch.irq_summary); +} + +static inline void clgi(void) +{ + asm volatile (SVM_CLGI); +} + +static inline void stgi(void) +{ + asm volatile (SVM_STGI); +} + +static inline void invlpga(unsigned long addr, u32 asid) +{ + asm volatile (SVM_INVLPGA :: "a"(addr), "c"(asid)); +} + +static inline unsigned long kvm_read_cr2(void) +{ + unsigned long cr2; + + asm volatile ("mov %%cr2, %0" : "=r" (cr2)); + return cr2; +} + +static inline void kvm_write_cr2(unsigned long val) +{ + asm volatile ("mov %0, %%cr2" :: "r" (val)); +} + +static inline unsigned long read_dr6(void) +{ + unsigned long dr6; + + asm volatile ("mov %%dr6, %0" : "=r" (dr6)); + return dr6; +} + +static inline void write_dr6(unsigned long val) +{ + asm volatile ("mov %0, %%dr6" :: "r" (val)); +} + +static inline unsigned long read_dr7(void) +{ + unsigned long dr7; + + asm volatile ("mov %%dr7, %0" : "=r" (dr7)); + return dr7; +} + +static inline void write_dr7(unsigned long val) +{ + asm volatile ("mov %0, %%dr7" :: "r" (val)); +} + +static inline void force_new_asid(struct kvm_vcpu *vcpu) +{ + to_svm(vcpu)->asid_generation--; +} + +static inline void flush_guest_tlb(struct kvm_vcpu *vcpu) +{ + force_new_asid(vcpu); +} + +static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + + to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK; + vcpu->arch.shadow_efer = efer; +} + +static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, + bool has_error_code, u32 error_code) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.event_inj = nr + | SVM_EVTINJ_VALID + | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) + | SVM_EVTINJ_TYPE_EXEPT; + svm->vmcb->control.event_inj_err = error_code; +} + +static bool svm_exception_injected(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return !(svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID); +} + +static int is_external_interrupt(u32 info) +{ + info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; + return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); +} + +static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!svm->next_rip) { + printk(KERN_DEBUG "%s: NOP\n", __FUNCTION__); + return; + } + if (svm->next_rip - svm->vmcb->save.rip > MAX_INST_SIZE) + printk(KERN_ERR "%s: ip 0x%llx next 0x%llx\n", + __FUNCTION__, + svm->vmcb->save.rip, + svm->next_rip); + + vcpu->arch.rip = svm->vmcb->save.rip = svm->next_rip; + svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; + + vcpu->arch.interrupt_window_open = 1; +} + +static int has_svm(void) +{ + uint32_t eax, ebx, ecx, edx; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + printk(KERN_INFO "has_svm: not amd\n"); + return 0; + } + + cpuid(0x80000000, &eax, &ebx, &ecx, &edx); + if (eax < SVM_CPUID_FUNC) { + printk(KERN_INFO "has_svm: can't execute cpuid_8000000a\n"); + return 0; + } + + cpuid(0x80000001, &eax, &ebx, &ecx, &edx); + if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) { + printk(KERN_DEBUG "has_svm: svm not available\n"); + return 0; + } + return 1; +} + +static void svm_hardware_disable(void *garbage) +{ + struct svm_cpu_data *svm_data + = per_cpu(svm_data, raw_smp_processor_id()); + + if (svm_data) { + uint64_t efer; + + wrmsrl(MSR_VM_HSAVE_PA, 0); + rdmsrl(MSR_EFER, efer); + wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK); + per_cpu(svm_data, raw_smp_processor_id()) = NULL; + __free_page(svm_data->save_area); + kfree(svm_data); + } +} + +static void svm_hardware_enable(void *garbage) +{ + + struct svm_cpu_data *svm_data; + uint64_t efer; +#ifdef CONFIG_X86_64 + struct desc_ptr gdt_descr; +#else + struct desc_ptr gdt_descr; +#endif + struct desc_struct *gdt; + int me = raw_smp_processor_id(); + + if (!has_svm()) { + printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); + return; + } + svm_data = per_cpu(svm_data, me); + + if (!svm_data) { + printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", + me); + return; + } + + svm_data->asid_generation = 1; + svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; + svm_data->next_asid = svm_data->max_asid + 1; + svm_features = cpuid_edx(SVM_CPUID_FUNC); + + asm volatile ("sgdt %0" : "=m"(gdt_descr)); + gdt = (struct desc_struct *)gdt_descr.address; + svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); + + rdmsrl(MSR_EFER, efer); + wrmsrl(MSR_EFER, efer | MSR_EFER_SVME_MASK); + + wrmsrl(MSR_VM_HSAVE_PA, + page_to_pfn(svm_data->save_area) << PAGE_SHIFT); +} + +static int svm_cpu_init(int cpu) +{ + struct svm_cpu_data *svm_data; + int r; + + svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); + if (!svm_data) + return -ENOMEM; + svm_data->cpu = cpu; + svm_data->save_area = alloc_page(GFP_KERNEL); + r = -ENOMEM; + if (!svm_data->save_area) + goto err_1; + + per_cpu(svm_data, cpu) = svm_data; + + return 0; + +err_1: + kfree(svm_data); + return r; + +} + +static void set_msr_interception(u32 *msrpm, unsigned msr, + int read, int write) +{ + int i; + + for (i = 0; i < NUM_MSR_MAPS; i++) { + if (msr >= msrpm_ranges[i] && + msr < msrpm_ranges[i] + MSRS_IN_RANGE) { + u32 msr_offset = (i * MSRS_IN_RANGE + msr - + msrpm_ranges[i]) * 2; + + u32 *base = msrpm + (msr_offset / 32); + u32 msr_shift = msr_offset % 32; + u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1); + *base = (*base & ~(0x3 << msr_shift)) | + (mask << msr_shift); + return; + } + } + BUG(); +} + +static __init int svm_hardware_setup(void) +{ + int cpu; + struct page *iopm_pages; + struct page *msrpm_pages; + void *iopm_va, *msrpm_va; + int r; + + iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER); + + if (!iopm_pages) + return -ENOMEM; + + iopm_va = page_address(iopm_pages); + memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); + clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */ + iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + + + msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + + r = -ENOMEM; + if (!msrpm_pages) + goto err_1; + + msrpm_va = page_address(msrpm_pages); + memset(msrpm_va, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + msrpm_base = page_to_pfn(msrpm_pages) << PAGE_SHIFT; + +#ifdef CONFIG_X86_64 + set_msr_interception(msrpm_va, MSR_GS_BASE, 1, 1); + set_msr_interception(msrpm_va, MSR_FS_BASE, 1, 1); + set_msr_interception(msrpm_va, MSR_KERNEL_GS_BASE, 1, 1); + set_msr_interception(msrpm_va, MSR_LSTAR, 1, 1); + set_msr_interception(msrpm_va, MSR_CSTAR, 1, 1); + set_msr_interception(msrpm_va, MSR_SYSCALL_MASK, 1, 1); +#endif + set_msr_interception(msrpm_va, MSR_K6_STAR, 1, 1); + set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_CS, 1, 1); + set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_ESP, 1, 1); + set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_EIP, 1, 1); + + for_each_online_cpu(cpu) { + r = svm_cpu_init(cpu); + if (r) + goto err_2; + } + return 0; + +err_2: + __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); + msrpm_base = 0; +err_1: + __free_pages(iopm_pages, IOPM_ALLOC_ORDER); + iopm_base = 0; + return r; +} + +static __exit void svm_hardware_unsetup(void) +{ + __free_pages(pfn_to_page(msrpm_base >> PAGE_SHIFT), MSRPM_ALLOC_ORDER); + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); + iopm_base = msrpm_base = 0; +} + +static void init_seg(struct vmcb_seg *seg) +{ + seg->selector = 0; + seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK | + SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ + seg->limit = 0xffff; + seg->base = 0; +} + +static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) +{ + seg->selector = 0; + seg->attrib = SVM_SELECTOR_P_MASK | type; + seg->limit = 0xffff; + seg->base = 0; +} + +static void init_vmcb(struct vmcb *vmcb) +{ + struct vmcb_control_area *control = &vmcb->control; + struct vmcb_save_area *save = &vmcb->save; + + control->intercept_cr_read = INTERCEPT_CR0_MASK | + INTERCEPT_CR3_MASK | + INTERCEPT_CR4_MASK | + INTERCEPT_CR8_MASK; + + control->intercept_cr_write = INTERCEPT_CR0_MASK | + INTERCEPT_CR3_MASK | + INTERCEPT_CR4_MASK | + INTERCEPT_CR8_MASK; + + control->intercept_dr_read = INTERCEPT_DR0_MASK | + INTERCEPT_DR1_MASK | + INTERCEPT_DR2_MASK | + INTERCEPT_DR3_MASK; + + control->intercept_dr_write = INTERCEPT_DR0_MASK | + INTERCEPT_DR1_MASK | + INTERCEPT_DR2_MASK | + INTERCEPT_DR3_MASK | + INTERCEPT_DR5_MASK | + INTERCEPT_DR7_MASK; + + control->intercept_exceptions = (1 << PF_VECTOR) | + (1 << UD_VECTOR); + + + control->intercept = (1ULL << INTERCEPT_INTR) | + (1ULL << INTERCEPT_NMI) | + (1ULL << INTERCEPT_SMI) | + /* + * selective cr0 intercept bug? + * 0: 0f 22 d8 mov %eax,%cr3 + * 3: 0f 20 c0 mov %cr0,%eax + * 6: 0d 00 00 00 80 or $0x80000000,%eax + * b: 0f 22 c0 mov %eax,%cr0 + * set cr3 ->interception + * get cr0 ->interception + * set cr0 -> no interception + */ + /* (1ULL << INTERCEPT_SELECTIVE_CR0) | */ + (1ULL << INTERCEPT_CPUID) | + (1ULL << INTERCEPT_INVD) | + (1ULL << INTERCEPT_HLT) | + (1ULL << INTERCEPT_INVLPGA) | + (1ULL << INTERCEPT_IOIO_PROT) | + (1ULL << INTERCEPT_MSR_PROT) | + (1ULL << INTERCEPT_TASK_SWITCH) | + (1ULL << INTERCEPT_SHUTDOWN) | + (1ULL << INTERCEPT_VMRUN) | + (1ULL << INTERCEPT_VMMCALL) | + (1ULL << INTERCEPT_VMLOAD) | + (1ULL << INTERCEPT_VMSAVE) | + (1ULL << INTERCEPT_STGI) | + (1ULL << INTERCEPT_CLGI) | + (1ULL << INTERCEPT_SKINIT) | + (1ULL << INTERCEPT_WBINVD) | + (1ULL << INTERCEPT_MONITOR) | + (1ULL << INTERCEPT_MWAIT); + + control->iopm_base_pa = iopm_base; + control->msrpm_base_pa = msrpm_base; + control->tsc_offset = 0; + control->int_ctl = V_INTR_MASKING_MASK; + + init_seg(&save->es); + init_seg(&save->ss); + init_seg(&save->ds); + init_seg(&save->fs); + init_seg(&save->gs); + + save->cs.selector = 0xf000; + /* Executable/Readable Code Segment */ + save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK | + SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK; + save->cs.limit = 0xffff; + /* + * cs.base should really be 0xffff0000, but vmx can't handle that, so + * be consistent with it. + * + * Replace when we have real mode working for vmx. + */ + save->cs.base = 0xf0000; + + save->gdtr.limit = 0xffff; + save->idtr.limit = 0xffff; + + init_sys_seg(&save->ldtr, SEG_TYPE_LDT); + init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); + + save->efer = MSR_EFER_SVME_MASK; + save->dr6 = 0xffff0ff0; + save->dr7 = 0x400; + save->rflags = 2; + save->rip = 0x0000fff0; + + /* + * cr0 val on cpu init should be 0x60000010, we enable cpu + * cache by default. the orderly way is to enable cache in bios. + */ + save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP; + save->cr4 = X86_CR4_PAE; + /* rdx = ?? */ +} + +static int svm_vcpu_reset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + init_vmcb(svm->vmcb); + + if (vcpu->vcpu_id != 0) { + svm->vmcb->save.rip = 0; + svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12; + svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8; + } + + return 0; +} + +static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) +{ + struct vcpu_svm *svm; + struct page *page; + int err; + + svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + if (!svm) { + err = -ENOMEM; + goto out; + } + + err = kvm_vcpu_init(&svm->vcpu, kvm, id); + if (err) + goto free_svm; + + page = alloc_page(GFP_KERNEL); + if (!page) { + err = -ENOMEM; + goto uninit; + } + + svm->vmcb = page_address(page); + clear_page(svm->vmcb); + svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; + svm->asid_generation = 0; + memset(svm->db_regs, 0, sizeof(svm->db_regs)); + init_vmcb(svm->vmcb); + + fx_init(&svm->vcpu); + svm->vcpu.fpu_active = 1; + svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; + if (svm->vcpu.vcpu_id == 0) + svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + + return &svm->vcpu; + +uninit: + kvm_vcpu_uninit(&svm->vcpu); +free_svm: + kmem_cache_free(kvm_vcpu_cache, svm); +out: + return ERR_PTR(err); +} + +static void svm_free_vcpu(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); + kvm_vcpu_uninit(vcpu); + kmem_cache_free(kvm_vcpu_cache, svm); +} + +static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int i; + + if (unlikely(cpu != vcpu->cpu)) { + u64 tsc_this, delta; + + /* + * Make sure that the guest sees a monotonically + * increasing TSC. + */ + rdtscll(tsc_this); + delta = vcpu->arch.host_tsc - tsc_this; + svm->vmcb->control.tsc_offset += delta; + vcpu->cpu = cpu; + kvm_migrate_apic_timer(vcpu); + } + + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); +} + +static void svm_vcpu_put(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int i; + + ++vcpu->stat.host_state_reload; + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + + rdtscll(vcpu->arch.host_tsc); +} + +static void svm_vcpu_decache(struct kvm_vcpu *vcpu) +{ +} + +static void svm_cache_regs(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; + vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; + vcpu->arch.rip = svm->vmcb->save.rip; +} + +static void svm_decache_regs(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.rip; +} + +static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) +{ + return to_svm(vcpu)->vmcb->save.rflags; +} + +static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + to_svm(vcpu)->vmcb->save.rflags = rflags; +} + +static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) +{ + struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; + + switch (seg) { + case VCPU_SREG_CS: return &save->cs; + case VCPU_SREG_DS: return &save->ds; + case VCPU_SREG_ES: return &save->es; + case VCPU_SREG_FS: return &save->fs; + case VCPU_SREG_GS: return &save->gs; + case VCPU_SREG_SS: return &save->ss; + case VCPU_SREG_TR: return &save->tr; + case VCPU_SREG_LDTR: return &save->ldtr; + } + BUG(); + return NULL; +} + +static u64 svm_get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + struct vmcb_seg *s = svm_seg(vcpu, seg); + + return s->base; +} + +static void svm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct vmcb_seg *s = svm_seg(vcpu, seg); + + var->base = s->base; + var->limit = s->limit; + var->selector = s->selector; + var->type = s->attrib & SVM_SELECTOR_TYPE_MASK; + var->s = (s->attrib >> SVM_SELECTOR_S_SHIFT) & 1; + var->dpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; + var->present = (s->attrib >> SVM_SELECTOR_P_SHIFT) & 1; + var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1; + var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1; + var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; + var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; + var->unusable = !var->present; +} + +static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + dt->limit = svm->vmcb->save.idtr.limit; + dt->base = svm->vmcb->save.idtr.base; +} + +static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.idtr.limit = dt->limit; + svm->vmcb->save.idtr.base = dt->base ; +} + +static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + dt->limit = svm->vmcb->save.gdtr.limit; + dt->base = svm->vmcb->save.gdtr.base; +} + +static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.gdtr.limit = dt->limit; + svm->vmcb->save.gdtr.base = dt->base ; +} + +static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) +{ +} + +static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + struct vcpu_svm *svm = to_svm(vcpu); + +#ifdef CONFIG_X86_64 + if (vcpu->arch.shadow_efer & EFER_LME) { + if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { + vcpu->arch.shadow_efer |= EFER_LMA; + svm->vmcb->save.efer |= EFER_LMA | EFER_LME; + } + + if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) { + vcpu->arch.shadow_efer &= ~EFER_LMA; + svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); + } + } +#endif + if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) { + svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + vcpu->fpu_active = 1; + } + + vcpu->arch.cr0 = cr0; + cr0 |= X86_CR0_PG | X86_CR0_WP; + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + svm->vmcb->save.cr0 = cr0; +} + +static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + vcpu->arch.cr4 = cr4; + to_svm(vcpu)->vmcb->save.cr4 = cr4 | X86_CR4_PAE; +} + +static void svm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_seg *s = svm_seg(vcpu, seg); + + s->base = var->base; + s->limit = var->limit; + s->selector = var->selector; + if (var->unusable) + s->attrib = 0; + else { + s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); + s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; + s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; + s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT; + s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; + s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; + s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; + s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; + } + if (seg == VCPU_SREG_CS) + svm->vmcb->save.cpl + = (svm->vmcb->save.cs.attrib + >> SVM_SELECTOR_DPL_SHIFT) & 3; + +} + +/* FIXME: + + svm(vcpu)->vmcb->control.int_ctl &= ~V_TPR_MASK; + svm(vcpu)->vmcb->control.int_ctl |= (sregs->cr8 & V_TPR_MASK); + +*/ + +static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +{ + return -EOPNOTSUPP; +} + +static int svm_get_irq(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 exit_int_info = svm->vmcb->control.exit_int_info; + + if (is_external_interrupt(exit_int_info)) + return exit_int_info & SVM_EVTINJ_VEC_MASK; + return -1; +} + +static void load_host_msrs(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); +#endif +} + +static void save_host_msrs(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); +#endif +} + +static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data) +{ + if (svm_data->next_asid > svm_data->max_asid) { + ++svm_data->asid_generation; + svm_data->next_asid = 1; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; + } + + svm->vcpu.cpu = svm_data->cpu; + svm->asid_generation = svm_data->asid_generation; + svm->vmcb->control.asid = svm_data->next_asid++; +} + +static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) +{ + return to_svm(vcpu)->db_regs[dr]; +} + +static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, + int *exception) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + *exception = 0; + + if (svm->vmcb->save.dr7 & DR7_GD_MASK) { + svm->vmcb->save.dr7 &= ~DR7_GD_MASK; + svm->vmcb->save.dr6 |= DR6_BD_MASK; + *exception = DB_VECTOR; + return; + } + + switch (dr) { + case 0 ... 3: + svm->db_regs[dr] = value; + return; + case 4 ... 5: + if (vcpu->arch.cr4 & X86_CR4_DE) { + *exception = UD_VECTOR; + return; + } + case 7: { + if (value & ~((1ULL << 32) - 1)) { + *exception = GP_VECTOR; + return; + } + svm->vmcb->save.dr7 = value; + return; + } + default: + printk(KERN_DEBUG "%s: unexpected dr %u\n", + __FUNCTION__, dr); + *exception = UD_VECTOR; + return; + } +} + +static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 exit_int_info = svm->vmcb->control.exit_int_info; + struct kvm *kvm = svm->vcpu.kvm; + u64 fault_address; + u32 error_code; + + if (!irqchip_in_kernel(kvm) && + is_external_interrupt(exit_int_info)) + push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK); + + fault_address = svm->vmcb->control.exit_info_2; + error_code = svm->vmcb->control.exit_info_1; + return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); +} + +static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + int er; + + er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + if (er != EMULATE_DONE) + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + +static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + if (!(svm->vcpu.arch.cr0 & X86_CR0_TS)) + svm->vmcb->save.cr0 &= ~X86_CR0_TS; + svm->vcpu.fpu_active = 1; + + return 1; +} + +static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + /* + * VMCB is undefined after a SHUTDOWN intercept + * so reinitialize it. + */ + clear_page(svm->vmcb); + init_vmcb(svm->vmcb); + + kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + return 0; +} + +static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ + int size, down, in, string, rep; + unsigned port; + + ++svm->vcpu.stat.io_exits; + + svm->next_rip = svm->vmcb->control.exit_info_2; + + string = (io_info & SVM_IOIO_STR_MASK) != 0; + + if (string) { + if (emulate_instruction(&svm->vcpu, + kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + return 0; + return 1; + } + + in = (io_info & SVM_IOIO_TYPE_MASK) != 0; + port = io_info >> 16; + size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; + rep = (io_info & SVM_IOIO_REP_MASK) != 0; + down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0; + + return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); +} + +static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + return 1; +} + +static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->next_rip = svm->vmcb->save.rip + 1; + skip_emulated_instruction(&svm->vcpu); + return kvm_emulate_halt(&svm->vcpu); +} + +static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->next_rip = svm->vmcb->save.rip + 3; + skip_emulated_instruction(&svm->vcpu); + kvm_emulate_hypercall(&svm->vcpu); + return 1; +} + +static int invalid_op_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + +static int task_switch_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + pr_unimpl(&svm->vcpu, "%s: task switch is unsupported\n", __FUNCTION__); + kvm_run->exit_reason = KVM_EXIT_UNKNOWN; + return 0; +} + +static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->next_rip = svm->vmcb->save.rip + 2; + kvm_emulate_cpuid(&svm->vcpu); + return 1; +} + +static int emulate_on_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE) + pr_unimpl(&svm->vcpu, "%s: failed\n", __FUNCTION__); + return 1; +} + +static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + emulate_instruction(&svm->vcpu, NULL, 0, 0, 0); + if (irqchip_in_kernel(svm->vcpu.kvm)) + return 1; + kvm_run->exit_reason = KVM_EXIT_SET_TPR; + return 0; +} + +static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + switch (ecx) { + case MSR_IA32_TIME_STAMP_COUNTER: { + u64 tsc; + + rdtscll(tsc); + *data = svm->vmcb->control.tsc_offset + tsc; + break; + } + case MSR_K6_STAR: + *data = svm->vmcb->save.star; + break; +#ifdef CONFIG_X86_64 + case MSR_LSTAR: + *data = svm->vmcb->save.lstar; + break; + case MSR_CSTAR: + *data = svm->vmcb->save.cstar; + break; + case MSR_KERNEL_GS_BASE: + *data = svm->vmcb->save.kernel_gs_base; + break; + case MSR_SYSCALL_MASK: + *data = svm->vmcb->save.sfmask; + break; +#endif + case MSR_IA32_SYSENTER_CS: + *data = svm->vmcb->save.sysenter_cs; + break; + case MSR_IA32_SYSENTER_EIP: + *data = svm->vmcb->save.sysenter_eip; + break; + case MSR_IA32_SYSENTER_ESP: + *data = svm->vmcb->save.sysenter_esp; + break; + default: + return kvm_get_msr_common(vcpu, ecx, data); + } + return 0; +} + +static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u64 data; + + if (svm_get_msr(&svm->vcpu, ecx, &data)) + kvm_inject_gp(&svm->vcpu, 0); + else { + svm->vmcb->save.rax = data & 0xffffffff; + svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; + svm->next_rip = svm->vmcb->save.rip + 2; + skip_emulated_instruction(&svm->vcpu); + } + return 1; +} + +static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + switch (ecx) { + case MSR_IA32_TIME_STAMP_COUNTER: { + u64 tsc; + + rdtscll(tsc); + svm->vmcb->control.tsc_offset = data - tsc; + break; + } + case MSR_K6_STAR: + svm->vmcb->save.star = data; + break; +#ifdef CONFIG_X86_64 + case MSR_LSTAR: + svm->vmcb->save.lstar = data; + break; + case MSR_CSTAR: + svm->vmcb->save.cstar = data; + break; + case MSR_KERNEL_GS_BASE: + svm->vmcb->save.kernel_gs_base = data; + break; + case MSR_SYSCALL_MASK: + svm->vmcb->save.sfmask = data; + break; +#endif + case MSR_IA32_SYSENTER_CS: + svm->vmcb->save.sysenter_cs = data; + break; + case MSR_IA32_SYSENTER_EIP: + svm->vmcb->save.sysenter_eip = data; + break; + case MSR_IA32_SYSENTER_ESP: + svm->vmcb->save.sysenter_esp = data; + break; + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + /* + * only support writing 0 to the performance counters for now + * to make Windows happy. Should be replaced by a real + * performance counter emulation later. + */ + if (data != 0) + goto unhandled; + break; + default: + unhandled: + return kvm_set_msr_common(vcpu, ecx, data); + } + return 0; +} + +static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u64 data = (svm->vmcb->save.rax & -1u) + | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + svm->next_rip = svm->vmcb->save.rip + 2; + if (svm_set_msr(&svm->vcpu, ecx, data)) + kvm_inject_gp(&svm->vcpu, 0); + else + skip_emulated_instruction(&svm->vcpu); + return 1; +} + +static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (svm->vmcb->control.exit_info_1) + return wrmsr_interception(svm, kvm_run); + else + return rdmsr_interception(svm, kvm_run); +} + +static int interrupt_window_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + /* + * If the user space waits to inject interrupts, exit as soon as + * possible + */ + if (kvm_run->request_interrupt_window && + !svm->vcpu.arch.irq_summary) { + ++svm->vcpu.stat.irq_window_exits; + kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; + return 0; + } + + return 1; +} + +static int (*svm_exit_handlers[])(struct vcpu_svm *svm, + struct kvm_run *kvm_run) = { + [SVM_EXIT_READ_CR0] = emulate_on_interception, + [SVM_EXIT_READ_CR3] = emulate_on_interception, + [SVM_EXIT_READ_CR4] = emulate_on_interception, + [SVM_EXIT_READ_CR8] = emulate_on_interception, + /* for now: */ + [SVM_EXIT_WRITE_CR0] = emulate_on_interception, + [SVM_EXIT_WRITE_CR3] = emulate_on_interception, + [SVM_EXIT_WRITE_CR4] = emulate_on_interception, + [SVM_EXIT_WRITE_CR8] = cr8_write_interception, + [SVM_EXIT_READ_DR0] = emulate_on_interception, + [SVM_EXIT_READ_DR1] = emulate_on_interception, + [SVM_EXIT_READ_DR2] = emulate_on_interception, + [SVM_EXIT_READ_DR3] = emulate_on_interception, + [SVM_EXIT_WRITE_DR0] = emulate_on_interception, + [SVM_EXIT_WRITE_DR1] = emulate_on_interception, + [SVM_EXIT_WRITE_DR2] = emulate_on_interception, + [SVM_EXIT_WRITE_DR3] = emulate_on_interception, + [SVM_EXIT_WRITE_DR5] = emulate_on_interception, + [SVM_EXIT_WRITE_DR7] = emulate_on_interception, + [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, + [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, + [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, + [SVM_EXIT_INTR] = nop_on_interception, + [SVM_EXIT_NMI] = nop_on_interception, + [SVM_EXIT_SMI] = nop_on_interception, + [SVM_EXIT_INIT] = nop_on_interception, + [SVM_EXIT_VINTR] = interrupt_window_interception, + /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */ + [SVM_EXIT_CPUID] = cpuid_interception, + [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_HLT] = halt_interception, + [SVM_EXIT_INVLPG] = emulate_on_interception, + [SVM_EXIT_INVLPGA] = invalid_op_interception, + [SVM_EXIT_IOIO] = io_interception, + [SVM_EXIT_MSR] = msr_interception, + [SVM_EXIT_TASK_SWITCH] = task_switch_interception, + [SVM_EXIT_SHUTDOWN] = shutdown_interception, + [SVM_EXIT_VMRUN] = invalid_op_interception, + [SVM_EXIT_VMMCALL] = vmmcall_interception, + [SVM_EXIT_VMLOAD] = invalid_op_interception, + [SVM_EXIT_VMSAVE] = invalid_op_interception, + [SVM_EXIT_STGI] = invalid_op_interception, + [SVM_EXIT_CLGI] = invalid_op_interception, + [SVM_EXIT_SKINIT] = invalid_op_interception, + [SVM_EXIT_WBINVD] = emulate_on_interception, + [SVM_EXIT_MONITOR] = invalid_op_interception, + [SVM_EXIT_MWAIT] = invalid_op_interception, +}; + + +static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 exit_code = svm->vmcb->control.exit_code; + + kvm_reput_irq(svm); + + if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { + kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; + kvm_run->fail_entry.hardware_entry_failure_reason + = svm->vmcb->control.exit_code; + return 0; + } + + if (is_external_interrupt(svm->vmcb->control.exit_int_info) && + exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR) + printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x " + "exit_code 0x%x\n", + __FUNCTION__, svm->vmcb->control.exit_int_info, + exit_code); + + if (exit_code >= ARRAY_SIZE(svm_exit_handlers) + || !svm_exit_handlers[exit_code]) { + kvm_run->exit_reason = KVM_EXIT_UNKNOWN; + kvm_run->hw.hardware_exit_reason = exit_code; + return 0; + } + + return svm_exit_handlers[exit_code](svm, kvm_run); +} + +static void reload_tss(struct kvm_vcpu *vcpu) +{ + int cpu = raw_smp_processor_id(); + + struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu); + svm_data->tss_desc->type = 9; /* available 32/64-bit TSS */ + load_TR_desc(); +} + +static void pre_svm_run(struct vcpu_svm *svm) +{ + int cpu = raw_smp_processor_id(); + + struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu); + + svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; + if (svm->vcpu.cpu != cpu || + svm->asid_generation != svm_data->asid_generation) + new_asid(svm, svm_data); +} + + +static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) +{ + struct vmcb_control_area *control; + + control = &svm->vmcb->control; + control->int_vector = irq; + control->int_ctl &= ~V_INTR_PRIO_MASK; + control->int_ctl |= V_IRQ_MASK | + ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); +} + +static void svm_set_irq(struct kvm_vcpu *vcpu, int irq) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm_inject_irq(svm, irq); +} + +static void svm_intr_assist(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + int intr_vector = -1; + + if ((vmcb->control.exit_int_info & SVM_EVTINJ_VALID) && + ((vmcb->control.exit_int_info & SVM_EVTINJ_TYPE_MASK) == 0)) { + intr_vector = vmcb->control.exit_int_info & + SVM_EVTINJ_VEC_MASK; + vmcb->control.exit_int_info = 0; + svm_inject_irq(svm, intr_vector); + return; + } + + if (vmcb->control.int_ctl & V_IRQ_MASK) + return; + + if (!kvm_cpu_has_interrupt(vcpu)) + return; + + if (!(vmcb->save.rflags & X86_EFLAGS_IF) || + (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || + (vmcb->control.event_inj & SVM_EVTINJ_VALID)) { + /* unable to deliver irq, set pending irq */ + vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR); + svm_inject_irq(svm, 0x0); + return; + } + /* Okay, we can deliver the interrupt: grab it and update PIC state. */ + intr_vector = kvm_cpu_get_interrupt(vcpu); + svm_inject_irq(svm, intr_vector); + kvm_timer_intr_post(vcpu, intr_vector); +} + +static void kvm_reput_irq(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + + if ((control->int_ctl & V_IRQ_MASK) + && !irqchip_in_kernel(svm->vcpu.kvm)) { + control->int_ctl &= ~V_IRQ_MASK; + push_irq(&svm->vcpu, control->int_vector); + } + + svm->vcpu.arch.interrupt_window_open = + !(control->int_state & SVM_INTERRUPT_SHADOW_MASK); +} + +static void svm_do_inject_vector(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + int word_index = __ffs(vcpu->arch.irq_summary); + int bit_index = __ffs(vcpu->arch.irq_pending[word_index]); + int irq = word_index * BITS_PER_LONG + bit_index; + + clear_bit(bit_index, &vcpu->arch.irq_pending[word_index]); + if (!vcpu->arch.irq_pending[word_index]) + clear_bit(word_index, &vcpu->arch.irq_summary); + svm_inject_irq(svm, irq); +} + +static void do_interrupt_requests(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_control_area *control = &svm->vmcb->control; + + svm->vcpu.arch.interrupt_window_open = + (!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && + (svm->vmcb->save.rflags & X86_EFLAGS_IF)); + + if (svm->vcpu.arch.interrupt_window_open && svm->vcpu.arch.irq_summary) + /* + * If interrupts enabled, and not blocked by sti or mov ss. Good. + */ + svm_do_inject_vector(svm); + + /* + * Interrupts blocked. Wait for unblock. + */ + if (!svm->vcpu.arch.interrupt_window_open && + (svm->vcpu.arch.irq_summary || kvm_run->request_interrupt_window)) + control->intercept |= 1ULL << INTERCEPT_VINTR; + else + control->intercept &= ~(1ULL << INTERCEPT_VINTR); +} + +static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) +{ + return 0; +} + +static void save_db_regs(unsigned long *db_regs) +{ + asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0])); + asm volatile ("mov %%dr1, %0" : "=r"(db_regs[1])); + asm volatile ("mov %%dr2, %0" : "=r"(db_regs[2])); + asm volatile ("mov %%dr3, %0" : "=r"(db_regs[3])); +} + +static void load_db_regs(unsigned long *db_regs) +{ + asm volatile ("mov %0, %%dr0" : : "r"(db_regs[0])); + asm volatile ("mov %0, %%dr1" : : "r"(db_regs[1])); + asm volatile ("mov %0, %%dr2" : : "r"(db_regs[2])); + asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3])); +} + +static void svm_flush_tlb(struct kvm_vcpu *vcpu) +{ + force_new_asid(vcpu); +} + +static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) +{ +} + +static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u16 fs_selector; + u16 gs_selector; + u16 ldt_selector; + + pre_svm_run(svm); + + save_host_msrs(vcpu); + fs_selector = read_fs(); + gs_selector = read_gs(); + ldt_selector = read_ldt(); + svm->host_cr2 = kvm_read_cr2(); + svm->host_dr6 = read_dr6(); + svm->host_dr7 = read_dr7(); + svm->vmcb->save.cr2 = vcpu->arch.cr2; + + if (svm->vmcb->save.dr7 & 0xff) { + write_dr7(0); + save_db_regs(svm->host_db_regs); + load_db_regs(svm->db_regs); + } + + clgi(); + + local_irq_enable(); + + asm volatile ( +#ifdef CONFIG_X86_64 + "push %%rbp; \n\t" +#else + "push %%ebp; \n\t" +#endif + +#ifdef CONFIG_X86_64 + "mov %c[rbx](%[svm]), %%rbx \n\t" + "mov %c[rcx](%[svm]), %%rcx \n\t" + "mov %c[rdx](%[svm]), %%rdx \n\t" + "mov %c[rsi](%[svm]), %%rsi \n\t" + "mov %c[rdi](%[svm]), %%rdi \n\t" + "mov %c[rbp](%[svm]), %%rbp \n\t" + "mov %c[r8](%[svm]), %%r8 \n\t" + "mov %c[r9](%[svm]), %%r9 \n\t" + "mov %c[r10](%[svm]), %%r10 \n\t" + "mov %c[r11](%[svm]), %%r11 \n\t" + "mov %c[r12](%[svm]), %%r12 \n\t" + "mov %c[r13](%[svm]), %%r13 \n\t" + "mov %c[r14](%[svm]), %%r14 \n\t" + "mov %c[r15](%[svm]), %%r15 \n\t" +#else + "mov %c[rbx](%[svm]), %%ebx \n\t" + "mov %c[rcx](%[svm]), %%ecx \n\t" + "mov %c[rdx](%[svm]), %%edx \n\t" + "mov %c[rsi](%[svm]), %%esi \n\t" + "mov %c[rdi](%[svm]), %%edi \n\t" + "mov %c[rbp](%[svm]), %%ebp \n\t" +#endif + +#ifdef CONFIG_X86_64 + /* Enter guest mode */ + "push %%rax \n\t" + "mov %c[vmcb](%[svm]), %%rax \n\t" + SVM_VMLOAD "\n\t" + SVM_VMRUN "\n\t" + SVM_VMSAVE "\n\t" + "pop %%rax \n\t" +#else + /* Enter guest mode */ + "push %%eax \n\t" + "mov %c[vmcb](%[svm]), %%eax \n\t" + SVM_VMLOAD "\n\t" + SVM_VMRUN "\n\t" + SVM_VMSAVE "\n\t" + "pop %%eax \n\t" +#endif + + /* Save guest registers, load host registers */ +#ifdef CONFIG_X86_64 + "mov %%rbx, %c[rbx](%[svm]) \n\t" + "mov %%rcx, %c[rcx](%[svm]) \n\t" + "mov %%rdx, %c[rdx](%[svm]) \n\t" + "mov %%rsi, %c[rsi](%[svm]) \n\t" + "mov %%rdi, %c[rdi](%[svm]) \n\t" + "mov %%rbp, %c[rbp](%[svm]) \n\t" + "mov %%r8, %c[r8](%[svm]) \n\t" + "mov %%r9, %c[r9](%[svm]) \n\t" + "mov %%r10, %c[r10](%[svm]) \n\t" + "mov %%r11, %c[r11](%[svm]) \n\t" + "mov %%r12, %c[r12](%[svm]) \n\t" + "mov %%r13, %c[r13](%[svm]) \n\t" + "mov %%r14, %c[r14](%[svm]) \n\t" + "mov %%r15, %c[r15](%[svm]) \n\t" + + "pop %%rbp; \n\t" +#else + "mov %%ebx, %c[rbx](%[svm]) \n\t" + "mov %%ecx, %c[rcx](%[svm]) \n\t" + "mov %%edx, %c[rdx](%[svm]) \n\t" + "mov %%esi, %c[rsi](%[svm]) \n\t" + "mov %%edi, %c[rdi](%[svm]) \n\t" + "mov %%ebp, %c[rbp](%[svm]) \n\t" + + "pop %%ebp; \n\t" +#endif + : + : [svm]"a"(svm), + [vmcb]"i"(offsetof(struct vcpu_svm, vmcb_pa)), + [rbx]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RBX])), + [rcx]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RCX])), + [rdx]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RDX])), + [rsi]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RSI])), + [rdi]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RDI])), + [rbp]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RBP])) +#ifdef CONFIG_X86_64 + , [r8]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R8])), + [r9]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R9])), + [r10]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R10])), + [r11]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R11])), + [r12]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R12])), + [r13]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R13])), + [r14]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R14])), + [r15]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R15])) +#endif + : "cc", "memory" +#ifdef CONFIG_X86_64 + , "rbx", "rcx", "rdx", "rsi", "rdi" + , "r8", "r9", "r10", "r11" , "r12", "r13", "r14", "r15" +#else + , "ebx", "ecx", "edx" , "esi", "edi" +#endif + ); + + if ((svm->vmcb->save.dr7 & 0xff)) + load_db_regs(svm->host_db_regs); + + vcpu->arch.cr2 = svm->vmcb->save.cr2; + + write_dr6(svm->host_dr6); + write_dr7(svm->host_dr7); + kvm_write_cr2(svm->host_cr2); + + load_fs(fs_selector); + load_gs(gs_selector); + load_ldt(ldt_selector); + load_host_msrs(vcpu); + + reload_tss(vcpu); + + local_irq_disable(); + + stgi(); + + svm->next_rip = 0; +} + +static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.cr3 = root; + force_new_asid(vcpu); + + if (vcpu->fpu_active) { + svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); + svm->vmcb->save.cr0 |= X86_CR0_TS; + vcpu->fpu_active = 0; + } +} + +static int is_disabled(void) +{ + u64 vm_cr; + + rdmsrl(MSR_VM_CR, vm_cr); + if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) + return 1; + + return 0; +} + +static void +svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) +{ + /* + * Patch in the VMMCALL instruction: + */ + hypercall[0] = 0x0f; + hypercall[1] = 0x01; + hypercall[2] = 0xd9; +} + +static void svm_check_processor_compat(void *rtn) +{ + *(int *)rtn = 0; +} + +static bool svm_cpu_has_accelerated_tpr(void) +{ + return false; +} + +static struct kvm_x86_ops svm_x86_ops = { + .cpu_has_kvm_support = has_svm, + .disabled_by_bios = is_disabled, + .hardware_setup = svm_hardware_setup, + .hardware_unsetup = svm_hardware_unsetup, + .check_processor_compatibility = svm_check_processor_compat, + .hardware_enable = svm_hardware_enable, + .hardware_disable = svm_hardware_disable, + .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, + + .vcpu_create = svm_create_vcpu, + .vcpu_free = svm_free_vcpu, + .vcpu_reset = svm_vcpu_reset, + + .prepare_guest_switch = svm_prepare_guest_switch, + .vcpu_load = svm_vcpu_load, + .vcpu_put = svm_vcpu_put, + .vcpu_decache = svm_vcpu_decache, + + .set_guest_debug = svm_guest_debug, + .get_msr = svm_get_msr, + .set_msr = svm_set_msr, + .get_segment_base = svm_get_segment_base, + .get_segment = svm_get_segment, + .set_segment = svm_set_segment, + .get_cs_db_l_bits = kvm_get_cs_db_l_bits, + .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, + .set_cr0 = svm_set_cr0, + .set_cr3 = svm_set_cr3, + .set_cr4 = svm_set_cr4, + .set_efer = svm_set_efer, + .get_idt = svm_get_idt, + .set_idt = svm_set_idt, + .get_gdt = svm_get_gdt, + .set_gdt = svm_set_gdt, + .get_dr = svm_get_dr, + .set_dr = svm_set_dr, + .cache_regs = svm_cache_regs, + .decache_regs = svm_decache_regs, + .get_rflags = svm_get_rflags, + .set_rflags = svm_set_rflags, + + .tlb_flush = svm_flush_tlb, + + .run = svm_vcpu_run, + .handle_exit = handle_exit, + .skip_emulated_instruction = skip_emulated_instruction, + .patch_hypercall = svm_patch_hypercall, + .get_irq = svm_get_irq, + .set_irq = svm_set_irq, + .queue_exception = svm_queue_exception, + .exception_injected = svm_exception_injected, + .inject_pending_irq = svm_intr_assist, + .inject_pending_vectors = do_interrupt_requests, + + .set_tss_addr = svm_set_tss_addr, +}; + +static int __init svm_init(void) +{ + return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm), + THIS_MODULE); +} + +static void __exit svm_exit(void) +{ + kvm_exit(); +} + +module_init(svm_init) +module_exit(svm_exit) diff --git a/arch/x86/kvm/svm.h b/arch/x86/kvm/svm.h new file mode 100644 index 00000000000..5fd50491b55 --- /dev/null +++ b/arch/x86/kvm/svm.h @@ -0,0 +1,325 @@ +#ifndef __SVM_H +#define __SVM_H + +enum { + INTERCEPT_INTR, + INTERCEPT_NMI, + INTERCEPT_SMI, + INTERCEPT_INIT, + INTERCEPT_VINTR, + INTERCEPT_SELECTIVE_CR0, + INTERCEPT_STORE_IDTR, + INTERCEPT_STORE_GDTR, + INTERCEPT_STORE_LDTR, + INTERCEPT_STORE_TR, + INTERCEPT_LOAD_IDTR, + INTERCEPT_LOAD_GDTR, + INTERCEPT_LOAD_LDTR, + INTERCEPT_LOAD_TR, + INTERCEPT_RDTSC, + INTERCEPT_RDPMC, + INTERCEPT_PUSHF, + INTERCEPT_POPF, + INTERCEPT_CPUID, + INTERCEPT_RSM, + INTERCEPT_IRET, + INTERCEPT_INTn, + INTERCEPT_INVD, + INTERCEPT_PAUSE, + INTERCEPT_HLT, + INTERCEPT_INVLPG, + INTERCEPT_INVLPGA, + INTERCEPT_IOIO_PROT, + INTERCEPT_MSR_PROT, + INTERCEPT_TASK_SWITCH, + INTERCEPT_FERR_FREEZE, + INTERCEPT_SHUTDOWN, + INTERCEPT_VMRUN, + INTERCEPT_VMMCALL, + INTERCEPT_VMLOAD, + INTERCEPT_VMSAVE, + INTERCEPT_STGI, + INTERCEPT_CLGI, + INTERCEPT_SKINIT, + INTERCEPT_RDTSCP, + INTERCEPT_ICEBP, + INTERCEPT_WBINVD, + INTERCEPT_MONITOR, + INTERCEPT_MWAIT, + INTERCEPT_MWAIT_COND, +}; + + +struct __attribute__ ((__packed__)) vmcb_control_area { + u16 intercept_cr_read; + u16 intercept_cr_write; + u16 intercept_dr_read; + u16 intercept_dr_write; + u32 intercept_exceptions; + u64 intercept; + u8 reserved_1[44]; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u8 reserved_2[3]; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u8 reserved_3[4]; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u8 reserved_4[16]; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 lbr_ctl; + u8 reserved_5[832]; +}; + + +#define TLB_CONTROL_DO_NOTHING 0 +#define TLB_CONTROL_FLUSH_ALL_ASID 1 + +#define V_TPR_MASK 0x0f + +#define V_IRQ_SHIFT 8 +#define V_IRQ_MASK (1 << V_IRQ_SHIFT) + +#define V_INTR_PRIO_SHIFT 16 +#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT) + +#define V_IGN_TPR_SHIFT 20 +#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) + +#define V_INTR_MASKING_SHIFT 24 +#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) + +#define SVM_INTERRUPT_SHADOW_MASK 1 + +#define SVM_IOIO_STR_SHIFT 2 +#define SVM_IOIO_REP_SHIFT 3 +#define SVM_IOIO_SIZE_SHIFT 4 +#define SVM_IOIO_ASIZE_SHIFT 7 + +#define SVM_IOIO_TYPE_MASK 1 +#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT) +#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT) +#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) +#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) + +struct __attribute__ ((__packed__)) vmcb_seg { + u16 selector; + u16 attrib; + u32 limit; + u64 base; +}; + +struct __attribute__ ((__packed__)) vmcb_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u8 reserved_1[43]; + u8 cpl; + u8 reserved_2[4]; + u64 efer; + u8 reserved_3[112]; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u8 reserved_4[88]; + u64 rsp; + u8 reserved_5[24]; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_6[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; +}; + +struct __attribute__ ((__packed__)) vmcb { + struct vmcb_control_area control; + struct vmcb_save_area save; +}; + +#define SVM_CPUID_FEATURE_SHIFT 2 +#define SVM_CPUID_FUNC 0x8000000a + +#define MSR_EFER_SVME_MASK (1ULL << 12) +#define MSR_VM_CR 0xc0010114 +#define MSR_VM_HSAVE_PA 0xc0010117ULL + +#define SVM_VM_CR_SVM_DISABLE 4 + +#define SVM_SELECTOR_S_SHIFT 4 +#define SVM_SELECTOR_DPL_SHIFT 5 +#define SVM_SELECTOR_P_SHIFT 7 +#define SVM_SELECTOR_AVL_SHIFT 8 +#define SVM_SELECTOR_L_SHIFT 9 +#define SVM_SELECTOR_DB_SHIFT 10 +#define SVM_SELECTOR_G_SHIFT 11 + +#define SVM_SELECTOR_TYPE_MASK (0xf) +#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT) +#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT) +#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT) +#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT) +#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT) +#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT) +#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT) + +#define SVM_SELECTOR_WRITE_MASK (1 << 1) +#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK +#define SVM_SELECTOR_CODE_MASK (1 << 3) + +#define INTERCEPT_CR0_MASK 1 +#define INTERCEPT_CR3_MASK (1 << 3) +#define INTERCEPT_CR4_MASK (1 << 4) +#define INTERCEPT_CR8_MASK (1 << 8) + +#define INTERCEPT_DR0_MASK 1 +#define INTERCEPT_DR1_MASK (1 << 1) +#define INTERCEPT_DR2_MASK (1 << 2) +#define INTERCEPT_DR3_MASK (1 << 3) +#define INTERCEPT_DR4_MASK (1 << 4) +#define INTERCEPT_DR5_MASK (1 << 5) +#define INTERCEPT_DR6_MASK (1 << 6) +#define INTERCEPT_DR7_MASK (1 << 7) + +#define SVM_EVTINJ_VEC_MASK 0xff + +#define SVM_EVTINJ_TYPE_SHIFT 8 +#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_VALID (1 << 31) +#define SVM_EVTINJ_VALID_ERR (1 << 11) + +#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK + +#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR +#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI +#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT +#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT + +#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID +#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR + +#define SVM_EXIT_READ_CR0 0x000 +#define SVM_EXIT_READ_CR3 0x003 +#define SVM_EXIT_READ_CR4 0x004 +#define SVM_EXIT_READ_CR8 0x008 +#define SVM_EXIT_WRITE_CR0 0x010 +#define SVM_EXIT_WRITE_CR3 0x013 +#define SVM_EXIT_WRITE_CR4 0x014 +#define SVM_EXIT_WRITE_CR8 0x018 +#define SVM_EXIT_READ_DR0 0x020 +#define SVM_EXIT_READ_DR1 0x021 +#define SVM_EXIT_READ_DR2 0x022 +#define SVM_EXIT_READ_DR3 0x023 +#define SVM_EXIT_READ_DR4 0x024 +#define SVM_EXIT_READ_DR5 0x025 +#define SVM_EXIT_READ_DR6 0x026 +#define SVM_EXIT_READ_DR7 0x027 +#define SVM_EXIT_WRITE_DR0 0x030 +#define SVM_EXIT_WRITE_DR1 0x031 +#define SVM_EXIT_WRITE_DR2 0x032 +#define SVM_EXIT_WRITE_DR3 0x033 +#define SVM_EXIT_WRITE_DR4 0x034 +#define SVM_EXIT_WRITE_DR5 0x035 +#define SVM_EXIT_WRITE_DR6 0x036 +#define SVM_EXIT_WRITE_DR7 0x037 +#define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_INTR 0x060 +#define SVM_EXIT_NMI 0x061 +#define SVM_EXIT_SMI 0x062 +#define SVM_EXIT_INIT 0x063 +#define SVM_EXIT_VINTR 0x064 +#define SVM_EXIT_CR0_SEL_WRITE 0x065 +#define SVM_EXIT_IDTR_READ 0x066 +#define SVM_EXIT_GDTR_READ 0x067 +#define SVM_EXIT_LDTR_READ 0x068 +#define SVM_EXIT_TR_READ 0x069 +#define SVM_EXIT_IDTR_WRITE 0x06a +#define SVM_EXIT_GDTR_WRITE 0x06b +#define SVM_EXIT_LDTR_WRITE 0x06c +#define SVM_EXIT_TR_WRITE 0x06d +#define SVM_EXIT_RDTSC 0x06e +#define SVM_EXIT_RDPMC 0x06f +#define SVM_EXIT_PUSHF 0x070 +#define SVM_EXIT_POPF 0x071 +#define SVM_EXIT_CPUID 0x072 +#define SVM_EXIT_RSM 0x073 +#define SVM_EXIT_IRET 0x074 +#define SVM_EXIT_SWINT 0x075 +#define SVM_EXIT_INVD 0x076 +#define SVM_EXIT_PAUSE 0x077 +#define SVM_EXIT_HLT 0x078 +#define SVM_EXIT_INVLPG 0x079 +#define SVM_EXIT_INVLPGA 0x07a +#define SVM_EXIT_IOIO 0x07b +#define SVM_EXIT_MSR 0x07c +#define SVM_EXIT_TASK_SWITCH 0x07d +#define SVM_EXIT_FERR_FREEZE 0x07e +#define SVM_EXIT_SHUTDOWN 0x07f +#define SVM_EXIT_VMRUN 0x080 +#define SVM_EXIT_VMMCALL 0x081 +#define SVM_EXIT_VMLOAD 0x082 +#define SVM_EXIT_VMSAVE 0x083 +#define SVM_EXIT_STGI 0x084 +#define SVM_EXIT_CLGI 0x085 +#define SVM_EXIT_SKINIT 0x086 +#define SVM_EXIT_RDTSCP 0x087 +#define SVM_EXIT_ICEBP 0x088 +#define SVM_EXIT_WBINVD 0x089 +#define SVM_EXIT_MONITOR 0x08a +#define SVM_EXIT_MWAIT 0x08b +#define SVM_EXIT_MWAIT_COND 0x08c +#define SVM_EXIT_NPF 0x400 + +#define SVM_EXIT_ERR -1 + +#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */ + +#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda" +#define SVM_VMRUN ".byte 0x0f, 0x01, 0xd8" +#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb" +#define SVM_CLGI ".byte 0x0f, 0x01, 0xdd" +#define SVM_STGI ".byte 0x0f, 0x01, 0xdc" +#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf" + +#endif + diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c new file mode 100644 index 00000000000..ad36447e696 --- /dev/null +++ b/arch/x86/kvm/vmx.c @@ -0,0 +1,2679 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * This module enables machines with Intel VT-x extensions to run virtual + * machines without emulation or binary translation. + * + * Copyright (C) 2006 Qumranet, Inc. + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "irq.h" +#include "vmx.h" +#include "segment_descriptor.h" +#include "mmu.h" + +#include <linux/kvm_host.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/highmem.h> +#include <linux/sched.h> +#include <linux/moduleparam.h> + +#include <asm/io.h> +#include <asm/desc.h> + +MODULE_AUTHOR("Qumranet"); +MODULE_LICENSE("GPL"); + +static int bypass_guest_pf = 1; +module_param(bypass_guest_pf, bool, 0); + +struct vmcs { + u32 revision_id; + u32 abort; + char data[0]; +}; + +struct vcpu_vmx { + struct kvm_vcpu vcpu; + int launched; + u8 fail; + u32 idt_vectoring_info; + struct kvm_msr_entry *guest_msrs; + struct kvm_msr_entry *host_msrs; + int nmsrs; + int save_nmsrs; + int msr_offset_efer; +#ifdef CONFIG_X86_64 + int msr_offset_kernel_gs_base; +#endif + struct vmcs *vmcs; + struct { + int loaded; + u16 fs_sel, gs_sel, ldt_sel; + int gs_ldt_reload_needed; + int fs_reload_needed; + int guest_efer_loaded; + } host_state; + struct { + struct { + bool pending; + u8 vector; + unsigned rip; + } irq; + } rmode; +}; + +static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) +{ + return container_of(vcpu, struct vcpu_vmx, vcpu); +} + +static int init_rmode_tss(struct kvm *kvm); + +static DEFINE_PER_CPU(struct vmcs *, vmxarea); +static DEFINE_PER_CPU(struct vmcs *, current_vmcs); + +static struct page *vmx_io_bitmap_a; +static struct page *vmx_io_bitmap_b; + +static struct vmcs_config { + int size; + int order; + u32 revision_id; + u32 pin_based_exec_ctrl; + u32 cpu_based_exec_ctrl; + u32 cpu_based_2nd_exec_ctrl; + u32 vmexit_ctrl; + u32 vmentry_ctrl; +} vmcs_config; + +#define VMX_SEGMENT_FIELD(seg) \ + [VCPU_SREG_##seg] = { \ + .selector = GUEST_##seg##_SELECTOR, \ + .base = GUEST_##seg##_BASE, \ + .limit = GUEST_##seg##_LIMIT, \ + .ar_bytes = GUEST_##seg##_AR_BYTES, \ + } + +static struct kvm_vmx_segment_field { + unsigned selector; + unsigned base; + unsigned limit; + unsigned ar_bytes; +} kvm_vmx_segment_fields[] = { + VMX_SEGMENT_FIELD(CS), + VMX_SEGMENT_FIELD(DS), + VMX_SEGMENT_FIELD(ES), + VMX_SEGMENT_FIELD(FS), + VMX_SEGMENT_FIELD(GS), + VMX_SEGMENT_FIELD(SS), + VMX_SEGMENT_FIELD(TR), + VMX_SEGMENT_FIELD(LDTR), +}; + +/* + * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it + * away by decrementing the array size. + */ +static const u32 vmx_msr_index[] = { +#ifdef CONFIG_X86_64 + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE, +#endif + MSR_EFER, MSR_K6_STAR, +}; +#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) + +static void load_msrs(struct kvm_msr_entry *e, int n) +{ + int i; + + for (i = 0; i < n; ++i) + wrmsrl(e[i].index, e[i].data); +} + +static void save_msrs(struct kvm_msr_entry *e, int n) +{ + int i; + + for (i = 0; i < n; ++i) + rdmsrl(e[i].index, e[i].data); +} + +static inline int is_page_fault(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | + INTR_INFO_VALID_MASK)) == + (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); +} + +static inline int is_no_device(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | + INTR_INFO_VALID_MASK)) == + (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); +} + +static inline int is_invalid_opcode(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | + INTR_INFO_VALID_MASK)) == + (INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); +} + +static inline int is_external_interrupt(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) + == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); +} + +static inline int cpu_has_vmx_tpr_shadow(void) +{ + return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW); +} + +static inline int vm_need_tpr_shadow(struct kvm *kvm) +{ + return ((cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm))); +} + +static inline int cpu_has_secondary_exec_ctrls(void) +{ + return (vmcs_config.cpu_based_exec_ctrl & + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS); +} + +static inline bool cpu_has_vmx_virtualize_apic_accesses(void) +{ + return (vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); +} + +static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) +{ + return ((cpu_has_vmx_virtualize_apic_accesses()) && + (irqchip_in_kernel(kvm))); +} + +static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) +{ + int i; + + for (i = 0; i < vmx->nmsrs; ++i) + if (vmx->guest_msrs[i].index == msr) + return i; + return -1; +} + +static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) +{ + int i; + + i = __find_msr_index(vmx, msr); + if (i >= 0) + return &vmx->guest_msrs[i]; + return NULL; +} + +static void vmcs_clear(struct vmcs *vmcs) +{ + u64 phys_addr = __pa(vmcs); + u8 error; + + asm volatile (ASM_VMX_VMCLEAR_RAX "; setna %0" + : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) + : "cc", "memory"); + if (error) + printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n", + vmcs, phys_addr); +} + +static void __vcpu_clear(void *arg) +{ + struct vcpu_vmx *vmx = arg; + int cpu = raw_smp_processor_id(); + + if (vmx->vcpu.cpu == cpu) + vmcs_clear(vmx->vmcs); + if (per_cpu(current_vmcs, cpu) == vmx->vmcs) + per_cpu(current_vmcs, cpu) = NULL; + rdtscll(vmx->vcpu.arch.host_tsc); +} + +static void vcpu_clear(struct vcpu_vmx *vmx) +{ + if (vmx->vcpu.cpu == -1) + return; + smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 0, 1); + vmx->launched = 0; +} + +static unsigned long vmcs_readl(unsigned long field) +{ + unsigned long value; + + asm volatile (ASM_VMX_VMREAD_RDX_RAX + : "=a"(value) : "d"(field) : "cc"); + return value; +} + +static u16 vmcs_read16(unsigned long field) +{ + return vmcs_readl(field); +} + +static u32 vmcs_read32(unsigned long field) +{ + return vmcs_readl(field); +} + +static u64 vmcs_read64(unsigned long field) +{ +#ifdef CONFIG_X86_64 + return vmcs_readl(field); +#else + return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32); +#endif +} + +static noinline void vmwrite_error(unsigned long field, unsigned long value) +{ + printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", + field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); + dump_stack(); +} + +static void vmcs_writel(unsigned long field, unsigned long value) +{ + u8 error; + + asm volatile (ASM_VMX_VMWRITE_RAX_RDX "; setna %0" + : "=q"(error) : "a"(value), "d"(field) : "cc"); + if (unlikely(error)) + vmwrite_error(field, value); +} + +static void vmcs_write16(unsigned long field, u16 value) +{ + vmcs_writel(field, value); +} + +static void vmcs_write32(unsigned long field, u32 value) +{ + vmcs_writel(field, value); +} + +static void vmcs_write64(unsigned long field, u64 value) +{ +#ifdef CONFIG_X86_64 + vmcs_writel(field, value); +#else + vmcs_writel(field, value); + asm volatile (""); + vmcs_writel(field+1, value >> 32); +#endif +} + +static void vmcs_clear_bits(unsigned long field, u32 mask) +{ + vmcs_writel(field, vmcs_readl(field) & ~mask); +} + +static void vmcs_set_bits(unsigned long field, u32 mask) +{ + vmcs_writel(field, vmcs_readl(field) | mask); +} + +static void update_exception_bitmap(struct kvm_vcpu *vcpu) +{ + u32 eb; + + eb = (1u << PF_VECTOR) | (1u << UD_VECTOR); + if (!vcpu->fpu_active) + eb |= 1u << NM_VECTOR; + if (vcpu->guest_debug.enabled) + eb |= 1u << 1; + if (vcpu->arch.rmode.active) + eb = ~0; + vmcs_write32(EXCEPTION_BITMAP, eb); +} + +static void reload_tss(void) +{ +#ifndef CONFIG_X86_64 + + /* + * VT restores TR but not its size. Useless. + */ + struct descriptor_table gdt; + struct segment_descriptor *descs; + + get_gdt(&gdt); + descs = (void *)gdt.base; + descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ + load_TR_desc(); +#endif +} + +static void load_transition_efer(struct vcpu_vmx *vmx) +{ + int efer_offset = vmx->msr_offset_efer; + u64 host_efer = vmx->host_msrs[efer_offset].data; + u64 guest_efer = vmx->guest_msrs[efer_offset].data; + u64 ignore_bits; + + if (efer_offset < 0) + return; + /* + * NX is emulated; LMA and LME handled by hardware; SCE meaninless + * outside long mode + */ + ignore_bits = EFER_NX | EFER_SCE; +#ifdef CONFIG_X86_64 + ignore_bits |= EFER_LMA | EFER_LME; + /* SCE is meaningful only in long mode on Intel */ + if (guest_efer & EFER_LMA) + ignore_bits &= ~(u64)EFER_SCE; +#endif + if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits)) + return; + + vmx->host_state.guest_efer_loaded = 1; + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; + wrmsrl(MSR_EFER, guest_efer); + vmx->vcpu.stat.efer_reload++; +} + +static void reload_host_efer(struct vcpu_vmx *vmx) +{ + if (vmx->host_state.guest_efer_loaded) { + vmx->host_state.guest_efer_loaded = 0; + load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1); + } +} + +static void vmx_save_host_state(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (vmx->host_state.loaded) + return; + + vmx->host_state.loaded = 1; + /* + * Set host fs and gs selectors. Unfortunately, 22.2.3 does not + * allow segment selectors with cpl > 0 or ti == 1. + */ + vmx->host_state.ldt_sel = read_ldt(); + vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; + vmx->host_state.fs_sel = read_fs(); + if (!(vmx->host_state.fs_sel & 7)) { + vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); + vmx->host_state.fs_reload_needed = 0; + } else { + vmcs_write16(HOST_FS_SELECTOR, 0); + vmx->host_state.fs_reload_needed = 1; + } + vmx->host_state.gs_sel = read_gs(); + if (!(vmx->host_state.gs_sel & 7)) + vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel); + else { + vmcs_write16(HOST_GS_SELECTOR, 0); + vmx->host_state.gs_ldt_reload_needed = 1; + } + +#ifdef CONFIG_X86_64 + vmcs_writel(HOST_FS_BASE, read_msr(MSR_FS_BASE)); + vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE)); +#else + vmcs_writel(HOST_FS_BASE, segment_base(vmx->host_state.fs_sel)); + vmcs_writel(HOST_GS_BASE, segment_base(vmx->host_state.gs_sel)); +#endif + +#ifdef CONFIG_X86_64 + if (is_long_mode(&vmx->vcpu)) + save_msrs(vmx->host_msrs + + vmx->msr_offset_kernel_gs_base, 1); + +#endif + load_msrs(vmx->guest_msrs, vmx->save_nmsrs); + load_transition_efer(vmx); +} + +static void vmx_load_host_state(struct vcpu_vmx *vmx) +{ + unsigned long flags; + + if (!vmx->host_state.loaded) + return; + + ++vmx->vcpu.stat.host_state_reload; + vmx->host_state.loaded = 0; + if (vmx->host_state.fs_reload_needed) + load_fs(vmx->host_state.fs_sel); + if (vmx->host_state.gs_ldt_reload_needed) { + load_ldt(vmx->host_state.ldt_sel); + /* + * If we have to reload gs, we must take care to + * preserve our gs base. + */ + local_irq_save(flags); + load_gs(vmx->host_state.gs_sel); +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE)); +#endif + local_irq_restore(flags); + } + reload_tss(); + save_msrs(vmx->guest_msrs, vmx->save_nmsrs); + load_msrs(vmx->host_msrs, vmx->save_nmsrs); + reload_host_efer(vmx); +} + +/* + * Switches to specified vcpu, until a matching vcpu_put(), but assumes + * vcpu mutex is already taken. + */ +static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 phys_addr = __pa(vmx->vmcs); + u64 tsc_this, delta; + + if (vcpu->cpu != cpu) { + vcpu_clear(vmx); + kvm_migrate_apic_timer(vcpu); + } + + if (per_cpu(current_vmcs, cpu) != vmx->vmcs) { + u8 error; + + per_cpu(current_vmcs, cpu) = vmx->vmcs; + asm volatile (ASM_VMX_VMPTRLD_RAX "; setna %0" + : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) + : "cc"); + if (error) + printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n", + vmx->vmcs, phys_addr); + } + + if (vcpu->cpu != cpu) { + struct descriptor_table dt; + unsigned long sysenter_esp; + + vcpu->cpu = cpu; + /* + * Linux uses per-cpu TSS and GDT, so set these when switching + * processors. + */ + vmcs_writel(HOST_TR_BASE, read_tr_base()); /* 22.2.4 */ + get_gdt(&dt); + vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */ + + rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); + vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + + /* + * Make sure the time stamp counter is monotonous. + */ + rdtscll(tsc_this); + delta = vcpu->arch.host_tsc - tsc_this; + vmcs_write64(TSC_OFFSET, vmcs_read64(TSC_OFFSET) + delta); + } +} + +static void vmx_vcpu_put(struct kvm_vcpu *vcpu) +{ + vmx_load_host_state(to_vmx(vcpu)); +} + +static void vmx_fpu_activate(struct kvm_vcpu *vcpu) +{ + if (vcpu->fpu_active) + return; + vcpu->fpu_active = 1; + vmcs_clear_bits(GUEST_CR0, X86_CR0_TS); + if (vcpu->arch.cr0 & X86_CR0_TS) + vmcs_set_bits(GUEST_CR0, X86_CR0_TS); + update_exception_bitmap(vcpu); +} + +static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) +{ + if (!vcpu->fpu_active) + return; + vcpu->fpu_active = 0; + vmcs_set_bits(GUEST_CR0, X86_CR0_TS); + update_exception_bitmap(vcpu); +} + +static void vmx_vcpu_decache(struct kvm_vcpu *vcpu) +{ + vcpu_clear(to_vmx(vcpu)); +} + +static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) +{ + return vmcs_readl(GUEST_RFLAGS); +} + +static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->arch.rmode.active) + rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; + vmcs_writel(GUEST_RFLAGS, rflags); +} + +static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + unsigned long rip; + u32 interruptibility; + + rip = vmcs_readl(GUEST_RIP); + rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + vmcs_writel(GUEST_RIP, rip); + + /* + * We emulated an instruction, so temporary interrupt blocking + * should be removed, if set. + */ + interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); + if (interruptibility & 3) + vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, + interruptibility & ~3); + vcpu->arch.interrupt_window_open = 1; +} + +static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, + bool has_error_code, u32 error_code) +{ + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, + nr | INTR_TYPE_EXCEPTION + | (has_error_code ? INTR_INFO_DELIEVER_CODE_MASK : 0) + | INTR_INFO_VALID_MASK); + if (has_error_code) + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); +} + +static bool vmx_exception_injected(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + return !(vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); +} + +/* + * Swap MSR entry in host/guest MSR entry array. + */ +#ifdef CONFIG_X86_64 +static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) +{ + struct kvm_msr_entry tmp; + + tmp = vmx->guest_msrs[to]; + vmx->guest_msrs[to] = vmx->guest_msrs[from]; + vmx->guest_msrs[from] = tmp; + tmp = vmx->host_msrs[to]; + vmx->host_msrs[to] = vmx->host_msrs[from]; + vmx->host_msrs[from] = tmp; +} +#endif + +/* + * Set up the vmcs to automatically save and restore system + * msrs. Don't touch the 64-bit msrs if the guest is in legacy + * mode, as fiddling with msrs is very expensive. + */ +static void setup_msrs(struct vcpu_vmx *vmx) +{ + int save_nmsrs; + + save_nmsrs = 0; +#ifdef CONFIG_X86_64 + if (is_long_mode(&vmx->vcpu)) { + int index; + + index = __find_msr_index(vmx, MSR_SYSCALL_MASK); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_LSTAR); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_CSTAR); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_KERNEL_GS_BASE); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); + /* + * MSR_K6_STAR is only needed on long mode guests, and only + * if efer.sce is enabled. + */ + index = __find_msr_index(vmx, MSR_K6_STAR); + if ((index >= 0) && (vmx->vcpu.arch.shadow_efer & EFER_SCE)) + move_msr_up(vmx, index, save_nmsrs++); + } +#endif + vmx->save_nmsrs = save_nmsrs; + +#ifdef CONFIG_X86_64 + vmx->msr_offset_kernel_gs_base = + __find_msr_index(vmx, MSR_KERNEL_GS_BASE); +#endif + vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER); +} + +/* + * reads and returns guest's timestamp counter "register" + * guest_tsc = host_tsc + tsc_offset -- 21.3 + */ +static u64 guest_read_tsc(void) +{ + u64 host_tsc, tsc_offset; + + rdtscll(host_tsc); + tsc_offset = vmcs_read64(TSC_OFFSET); + return host_tsc + tsc_offset; +} + +/* + * writes 'guest_tsc' into guest's timestamp counter "register" + * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc + */ +static void guest_write_tsc(u64 guest_tsc) +{ + u64 host_tsc; + + rdtscll(host_tsc); + vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); +} + +/* + * Reads an msr value (of 'msr_index') into 'pdata'. + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. + */ +static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +{ + u64 data; + struct kvm_msr_entry *msr; + + if (!pdata) { + printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); + return -EINVAL; + } + + switch (msr_index) { +#ifdef CONFIG_X86_64 + case MSR_FS_BASE: + data = vmcs_readl(GUEST_FS_BASE); + break; + case MSR_GS_BASE: + data = vmcs_readl(GUEST_GS_BASE); + break; + case MSR_EFER: + return kvm_get_msr_common(vcpu, msr_index, pdata); +#endif + case MSR_IA32_TIME_STAMP_COUNTER: + data = guest_read_tsc(); + break; + case MSR_IA32_SYSENTER_CS: + data = vmcs_read32(GUEST_SYSENTER_CS); + break; + case MSR_IA32_SYSENTER_EIP: + data = vmcs_readl(GUEST_SYSENTER_EIP); + break; + case MSR_IA32_SYSENTER_ESP: + data = vmcs_readl(GUEST_SYSENTER_ESP); + break; + default: + msr = find_msr_entry(to_vmx(vcpu), msr_index); + if (msr) { + data = msr->data; + break; + } + return kvm_get_msr_common(vcpu, msr_index, pdata); + } + + *pdata = data; + return 0; +} + +/* + * Writes msr value into into the appropriate "register". + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. + */ +static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_msr_entry *msr; + int ret = 0; + + switch (msr_index) { +#ifdef CONFIG_X86_64 + case MSR_EFER: + ret = kvm_set_msr_common(vcpu, msr_index, data); + if (vmx->host_state.loaded) { + reload_host_efer(vmx); + load_transition_efer(vmx); + } + break; + case MSR_FS_BASE: + vmcs_writel(GUEST_FS_BASE, data); + break; + case MSR_GS_BASE: + vmcs_writel(GUEST_GS_BASE, data); + break; +#endif + case MSR_IA32_SYSENTER_CS: + vmcs_write32(GUEST_SYSENTER_CS, data); + break; + case MSR_IA32_SYSENTER_EIP: + vmcs_writel(GUEST_SYSENTER_EIP, data); + break; + case MSR_IA32_SYSENTER_ESP: + vmcs_writel(GUEST_SYSENTER_ESP, data); + break; + case MSR_IA32_TIME_STAMP_COUNTER: + guest_write_tsc(data); + break; + default: + msr = find_msr_entry(vmx, msr_index); + if (msr) { + msr->data = data; + if (vmx->host_state.loaded) + load_msrs(vmx->guest_msrs, vmx->save_nmsrs); + break; + } + ret = kvm_set_msr_common(vcpu, msr_index, data); + } + + return ret; +} + +/* + * Sync the rsp and rip registers into the vcpu structure. This allows + * registers to be accessed by indexing vcpu->arch.regs. + */ +static void vcpu_load_rsp_rip(struct kvm_vcpu *vcpu) +{ + vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); + vcpu->arch.rip = vmcs_readl(GUEST_RIP); +} + +/* + * Syncs rsp and rip back into the vmcs. Should be called after possible + * modification. + */ +static void vcpu_put_rsp_rip(struct kvm_vcpu *vcpu) +{ + vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); + vmcs_writel(GUEST_RIP, vcpu->arch.rip); +} + +static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +{ + unsigned long dr7 = 0x400; + int old_singlestep; + + old_singlestep = vcpu->guest_debug.singlestep; + + vcpu->guest_debug.enabled = dbg->enabled; + if (vcpu->guest_debug.enabled) { + int i; + + dr7 |= 0x200; /* exact */ + for (i = 0; i < 4; ++i) { + if (!dbg->breakpoints[i].enabled) + continue; + vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address; + dr7 |= 2 << (i*2); /* global enable */ + dr7 |= 0 << (i*4+16); /* execution breakpoint */ + } + + vcpu->guest_debug.singlestep = dbg->singlestep; + } else + vcpu->guest_debug.singlestep = 0; + + if (old_singlestep && !vcpu->guest_debug.singlestep) { + unsigned long flags; + + flags = vmcs_readl(GUEST_RFLAGS); + flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + vmcs_writel(GUEST_RFLAGS, flags); + } + + update_exception_bitmap(vcpu); + vmcs_writel(GUEST_DR7, dr7); + + return 0; +} + +static int vmx_get_irq(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 idtv_info_field; + + idtv_info_field = vmx->idt_vectoring_info; + if (idtv_info_field & INTR_INFO_VALID_MASK) { + if (is_external_interrupt(idtv_info_field)) + return idtv_info_field & VECTORING_INFO_VECTOR_MASK; + else + printk(KERN_DEBUG "pending exception: not handled yet\n"); + } + return -1; +} + +static __init int cpu_has_kvm_support(void) +{ + unsigned long ecx = cpuid_ecx(1); + return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */ +} + +static __init int vmx_disabled_by_bios(void) +{ + u64 msr; + + rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); + return (msr & (MSR_IA32_FEATURE_CONTROL_LOCKED | + MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) + == MSR_IA32_FEATURE_CONTROL_LOCKED; + /* locked but not enabled */ +} + +static void hardware_enable(void *garbage) +{ + int cpu = raw_smp_processor_id(); + u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + u64 old; + + rdmsrl(MSR_IA32_FEATURE_CONTROL, old); + if ((old & (MSR_IA32_FEATURE_CONTROL_LOCKED | + MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) + != (MSR_IA32_FEATURE_CONTROL_LOCKED | + MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) + /* enable and lock */ + wrmsrl(MSR_IA32_FEATURE_CONTROL, old | + MSR_IA32_FEATURE_CONTROL_LOCKED | + MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED); + write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */ + asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) + : "memory", "cc"); +} + +static void hardware_disable(void *garbage) +{ + asm volatile (ASM_VMX_VMXOFF : : : "cc"); +} + +static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, + u32 msr, u32 *result) +{ + u32 vmx_msr_low, vmx_msr_high; + u32 ctl = ctl_min | ctl_opt; + + rdmsr(msr, vmx_msr_low, vmx_msr_high); + + ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */ + ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */ + + /* Ensure minimum (required) set of control bits are supported. */ + if (ctl_min & ~ctl) + return -EIO; + + *result = ctl; + return 0; +} + +static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) +{ + u32 vmx_msr_low, vmx_msr_high; + u32 min, opt; + u32 _pin_based_exec_control = 0; + u32 _cpu_based_exec_control = 0; + u32 _cpu_based_2nd_exec_control = 0; + u32 _vmexit_control = 0; + u32 _vmentry_control = 0; + + min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; + opt = 0; + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, + &_pin_based_exec_control) < 0) + return -EIO; + + min = CPU_BASED_HLT_EXITING | +#ifdef CONFIG_X86_64 + CPU_BASED_CR8_LOAD_EXITING | + CPU_BASED_CR8_STORE_EXITING | +#endif + CPU_BASED_USE_IO_BITMAPS | + CPU_BASED_MOV_DR_EXITING | + CPU_BASED_USE_TSC_OFFSETING; + opt = CPU_BASED_TPR_SHADOW | + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, + &_cpu_based_exec_control) < 0) + return -EIO; +#ifdef CONFIG_X86_64 + if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) + _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & + ~CPU_BASED_CR8_STORE_EXITING; +#endif + if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { + min = 0; + opt = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_WBINVD_EXITING; + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS2, + &_cpu_based_2nd_exec_control) < 0) + return -EIO; + } +#ifndef CONFIG_X86_64 + if (!(_cpu_based_2nd_exec_control & + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) + _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; +#endif + + min = 0; +#ifdef CONFIG_X86_64 + min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; +#endif + opt = 0; + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, + &_vmexit_control) < 0) + return -EIO; + + min = opt = 0; + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, + &_vmentry_control) < 0) + return -EIO; + + rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); + + /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ + if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) + return -EIO; + +#ifdef CONFIG_X86_64 + /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ + if (vmx_msr_high & (1u<<16)) + return -EIO; +#endif + + /* Require Write-Back (WB) memory type for VMCS accesses. */ + if (((vmx_msr_high >> 18) & 15) != 6) + return -EIO; + + vmcs_conf->size = vmx_msr_high & 0x1fff; + vmcs_conf->order = get_order(vmcs_config.size); + vmcs_conf->revision_id = vmx_msr_low; + + vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; + vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; + vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; + vmcs_conf->vmexit_ctrl = _vmexit_control; + vmcs_conf->vmentry_ctrl = _vmentry_control; + + return 0; +} + +static struct vmcs *alloc_vmcs_cpu(int cpu) +{ + int node = cpu_to_node(cpu); + struct page *pages; + struct vmcs *vmcs; + + pages = alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); + if (!pages) + return NULL; + vmcs = page_address(pages); + memset(vmcs, 0, vmcs_config.size); + vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */ + return vmcs; +} + +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static void free_vmcs(struct vmcs *vmcs) +{ + free_pages((unsigned long)vmcs, vmcs_config.order); +} + +static void free_kvm_area(void) +{ + int cpu; + + for_each_online_cpu(cpu) + free_vmcs(per_cpu(vmxarea, cpu)); +} + +static __init int alloc_kvm_area(void) +{ + int cpu; + + for_each_online_cpu(cpu) { + struct vmcs *vmcs; + + vmcs = alloc_vmcs_cpu(cpu); + if (!vmcs) { + free_kvm_area(); + return -ENOMEM; + } + + per_cpu(vmxarea, cpu) = vmcs; + } + return 0; +} + +static __init int hardware_setup(void) +{ + if (setup_vmcs_config(&vmcs_config) < 0) + return -EIO; + return alloc_kvm_area(); +} + +static __exit void hardware_unsetup(void) +{ + free_kvm_area(); +} + +static void fix_pmode_dataseg(int seg, struct kvm_save_segment *save) +{ + struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + + if (vmcs_readl(sf->base) == save->base && (save->base & AR_S_MASK)) { + vmcs_write16(sf->selector, save->selector); + vmcs_writel(sf->base, save->base); + vmcs_write32(sf->limit, save->limit); + vmcs_write32(sf->ar_bytes, save->ar); + } else { + u32 dpl = (vmcs_read16(sf->selector) & SELECTOR_RPL_MASK) + << AR_DPL_SHIFT; + vmcs_write32(sf->ar_bytes, 0x93 | dpl); + } +} + +static void enter_pmode(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + + vcpu->arch.rmode.active = 0; + + vmcs_writel(GUEST_TR_BASE, vcpu->arch.rmode.tr.base); + vmcs_write32(GUEST_TR_LIMIT, vcpu->arch.rmode.tr.limit); + vmcs_write32(GUEST_TR_AR_BYTES, vcpu->arch.rmode.tr.ar); + + flags = vmcs_readl(GUEST_RFLAGS); + flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM); + flags |= (vcpu->arch.rmode.save_iopl << IOPL_SHIFT); + vmcs_writel(GUEST_RFLAGS, flags); + + vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | + (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); + + update_exception_bitmap(vcpu); + + fix_pmode_dataseg(VCPU_SREG_ES, &vcpu->arch.rmode.es); + fix_pmode_dataseg(VCPU_SREG_DS, &vcpu->arch.rmode.ds); + fix_pmode_dataseg(VCPU_SREG_GS, &vcpu->arch.rmode.gs); + fix_pmode_dataseg(VCPU_SREG_FS, &vcpu->arch.rmode.fs); + + vmcs_write16(GUEST_SS_SELECTOR, 0); + vmcs_write32(GUEST_SS_AR_BYTES, 0x93); + + vmcs_write16(GUEST_CS_SELECTOR, + vmcs_read16(GUEST_CS_SELECTOR) & ~SELECTOR_RPL_MASK); + vmcs_write32(GUEST_CS_AR_BYTES, 0x9b); +} + +static gva_t rmode_tss_base(struct kvm *kvm) +{ + if (!kvm->arch.tss_addr) { + gfn_t base_gfn = kvm->memslots[0].base_gfn + + kvm->memslots[0].npages - 3; + return base_gfn << PAGE_SHIFT; + } + return kvm->arch.tss_addr; +} + +static void fix_rmode_seg(int seg, struct kvm_save_segment *save) +{ + struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + + save->selector = vmcs_read16(sf->selector); + save->base = vmcs_readl(sf->base); + save->limit = vmcs_read32(sf->limit); + save->ar = vmcs_read32(sf->ar_bytes); + vmcs_write16(sf->selector, save->base >> 4); + vmcs_write32(sf->base, save->base & 0xfffff); + vmcs_write32(sf->limit, 0xffff); + vmcs_write32(sf->ar_bytes, 0xf3); +} + +static void enter_rmode(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + + vcpu->arch.rmode.active = 1; + + vcpu->arch.rmode.tr.base = vmcs_readl(GUEST_TR_BASE); + vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); + + vcpu->arch.rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT); + vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); + + vcpu->arch.rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES); + vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); + + flags = vmcs_readl(GUEST_RFLAGS); + vcpu->arch.rmode.save_iopl + = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + + flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; + + vmcs_writel(GUEST_RFLAGS, flags); + vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); + update_exception_bitmap(vcpu); + + vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4); + vmcs_write32(GUEST_SS_LIMIT, 0xffff); + vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); + + vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); + vmcs_write32(GUEST_CS_LIMIT, 0xffff); + if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) + vmcs_writel(GUEST_CS_BASE, 0xf0000); + vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); + + fix_rmode_seg(VCPU_SREG_ES, &vcpu->arch.rmode.es); + fix_rmode_seg(VCPU_SREG_DS, &vcpu->arch.rmode.ds); + fix_rmode_seg(VCPU_SREG_GS, &vcpu->arch.rmode.gs); + fix_rmode_seg(VCPU_SREG_FS, &vcpu->arch.rmode.fs); + + kvm_mmu_reset_context(vcpu); + init_rmode_tss(vcpu->kvm); +} + +#ifdef CONFIG_X86_64 + +static void enter_lmode(struct kvm_vcpu *vcpu) +{ + u32 guest_tr_ar; + + guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); + if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { + printk(KERN_DEBUG "%s: tss fixup for long mode. \n", + __FUNCTION__); + vmcs_write32(GUEST_TR_AR_BYTES, + (guest_tr_ar & ~AR_TYPE_MASK) + | AR_TYPE_BUSY_64_TSS); + } + + vcpu->arch.shadow_efer |= EFER_LMA; + + find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME; + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) + | VM_ENTRY_IA32E_MODE); +} + +static void exit_lmode(struct kvm_vcpu *vcpu) +{ + vcpu->arch.shadow_efer &= ~EFER_LMA; + + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) + & ~VM_ENTRY_IA32E_MODE); +} + +#endif + +static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) +{ + vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK; + vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK; +} + +static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + vmx_fpu_deactivate(vcpu); + + if (vcpu->arch.rmode.active && (cr0 & X86_CR0_PE)) + enter_pmode(vcpu); + + if (!vcpu->arch.rmode.active && !(cr0 & X86_CR0_PE)) + enter_rmode(vcpu); + +#ifdef CONFIG_X86_64 + if (vcpu->arch.shadow_efer & EFER_LME) { + if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) + enter_lmode(vcpu); + if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) + exit_lmode(vcpu); + } +#endif + + vmcs_writel(CR0_READ_SHADOW, cr0); + vmcs_writel(GUEST_CR0, + (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON); + vcpu->arch.cr0 = cr0; + + if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE)) + vmx_fpu_activate(vcpu); +} + +static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + vmcs_writel(GUEST_CR3, cr3); + if (vcpu->arch.cr0 & X86_CR0_PE) + vmx_fpu_deactivate(vcpu); +} + +static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + vmcs_writel(CR4_READ_SHADOW, cr4); + vmcs_writel(GUEST_CR4, cr4 | (vcpu->arch.rmode.active ? + KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON)); + vcpu->arch.cr4 = cr4; +} + +#ifdef CONFIG_X86_64 + +static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + + vcpu->arch.shadow_efer = efer; + if (efer & EFER_LMA) { + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) | + VM_ENTRY_IA32E_MODE); + msr->data = efer; + + } else { + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) & + ~VM_ENTRY_IA32E_MODE); + + msr->data = efer & ~EFER_LME; + } + setup_msrs(vmx); +} + +#endif + +static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + + return vmcs_readl(sf->base); +} + +static void vmx_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + u32 ar; + + var->base = vmcs_readl(sf->base); + var->limit = vmcs_read32(sf->limit); + var->selector = vmcs_read16(sf->selector); + ar = vmcs_read32(sf->ar_bytes); + if (ar & AR_UNUSABLE_MASK) + ar = 0; + var->type = ar & 15; + var->s = (ar >> 4) & 1; + var->dpl = (ar >> 5) & 3; + var->present = (ar >> 7) & 1; + var->avl = (ar >> 12) & 1; + var->l = (ar >> 13) & 1; + var->db = (ar >> 14) & 1; + var->g = (ar >> 15) & 1; + var->unusable = (ar >> 16) & 1; +} + +static u32 vmx_segment_access_rights(struct kvm_segment *var) +{ + u32 ar; + + if (var->unusable) + ar = 1 << 16; + else { + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + } + if (ar == 0) /* a 0 value means unusable */ + ar = AR_UNUSABLE_MASK; + + return ar; +} + +static void vmx_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + u32 ar; + + if (vcpu->arch.rmode.active && seg == VCPU_SREG_TR) { + vcpu->arch.rmode.tr.selector = var->selector; + vcpu->arch.rmode.tr.base = var->base; + vcpu->arch.rmode.tr.limit = var->limit; + vcpu->arch.rmode.tr.ar = vmx_segment_access_rights(var); + return; + } + vmcs_writel(sf->base, var->base); + vmcs_write32(sf->limit, var->limit); + vmcs_write16(sf->selector, var->selector); + if (vcpu->arch.rmode.active && var->s) { + /* + * Hack real-mode segments into vm86 compatibility. + */ + if (var->base == 0xffff0000 && var->selector == 0xf000) + vmcs_writel(sf->base, 0xf0000); + ar = 0xf3; + } else + ar = vmx_segment_access_rights(var); + vmcs_write32(sf->ar_bytes, ar); +} + +static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +{ + u32 ar = vmcs_read32(GUEST_CS_AR_BYTES); + + *db = (ar >> 14) & 1; + *l = (ar >> 13) & 1; +} + +static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + dt->limit = vmcs_read32(GUEST_IDTR_LIMIT); + dt->base = vmcs_readl(GUEST_IDTR_BASE); +} + +static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + vmcs_write32(GUEST_IDTR_LIMIT, dt->limit); + vmcs_writel(GUEST_IDTR_BASE, dt->base); +} + +static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + dt->limit = vmcs_read32(GUEST_GDTR_LIMIT); + dt->base = vmcs_readl(GUEST_GDTR_BASE); +} + +static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + vmcs_write32(GUEST_GDTR_LIMIT, dt->limit); + vmcs_writel(GUEST_GDTR_BASE, dt->base); +} + +static int init_rmode_tss(struct kvm *kvm) +{ + gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT; + u16 data = 0; + int ret = 0; + int r; + + down_read(¤t->mm->mmap_sem); + r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); + if (r < 0) + goto out; + data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; + r = kvm_write_guest_page(kvm, fn++, &data, 0x66, sizeof(u16)); + if (r < 0) + goto out; + r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE); + if (r < 0) + goto out; + r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); + if (r < 0) + goto out; + data = ~0; + r = kvm_write_guest_page(kvm, fn, &data, + RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1, + sizeof(u8)); + if (r < 0) + goto out; + + ret = 1; +out: + up_read(¤t->mm->mmap_sem); + return ret; +} + +static void seg_setup(int seg) +{ + struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + + vmcs_write16(sf->selector, 0); + vmcs_writel(sf->base, 0); + vmcs_write32(sf->limit, 0xffff); + vmcs_write32(sf->ar_bytes, 0x93); +} + +static int alloc_apic_access_page(struct kvm *kvm) +{ + struct kvm_userspace_memory_region kvm_userspace_mem; + int r = 0; + + down_write(¤t->mm->mmap_sem); + if (kvm->arch.apic_access_page) + goto out; + kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; + kvm_userspace_mem.flags = 0; + kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL; + kvm_userspace_mem.memory_size = PAGE_SIZE; + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); + if (r) + goto out; + kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); +out: + up_write(¤t->mm->mmap_sem); + return r; +} + +/* + * Sets up the vmcs for emulated real mode. + */ +static int vmx_vcpu_setup(struct vcpu_vmx *vmx) +{ + u32 host_sysenter_cs; + u32 junk; + unsigned long a; + struct descriptor_table dt; + int i; + unsigned long kvm_vmx_return; + u32 exec_control; + + /* I/O */ + vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a)); + vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b)); + + vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ + + /* Control */ + vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, + vmcs_config.pin_based_exec_ctrl); + + exec_control = vmcs_config.cpu_based_exec_ctrl; + if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) { + exec_control &= ~CPU_BASED_TPR_SHADOW; +#ifdef CONFIG_X86_64 + exec_control |= CPU_BASED_CR8_STORE_EXITING | + CPU_BASED_CR8_LOAD_EXITING; +#endif + } + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control); + + if (cpu_has_secondary_exec_ctrls()) { + exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; + if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) + exec_control &= + ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + } + + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf); + vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ + + vmcs_writel(HOST_CR0, read_cr0()); /* 22.2.3 */ + vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ + vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + + vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ + vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ + vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ + vmcs_write16(HOST_FS_SELECTOR, read_fs()); /* 22.2.4 */ + vmcs_write16(HOST_GS_SELECTOR, read_gs()); /* 22.2.4 */ + vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ +#ifdef CONFIG_X86_64 + rdmsrl(MSR_FS_BASE, a); + vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */ + rdmsrl(MSR_GS_BASE, a); + vmcs_writel(HOST_GS_BASE, a); /* 22.2.4 */ +#else + vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ + vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ +#endif + + vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ + + get_idt(&dt); + vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */ + + asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return)); + vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */ + vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); + + rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk); + vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs); + rdmsrl(MSR_IA32_SYSENTER_ESP, a); + vmcs_writel(HOST_IA32_SYSENTER_ESP, a); /* 22.2.3 */ + rdmsrl(MSR_IA32_SYSENTER_EIP, a); + vmcs_writel(HOST_IA32_SYSENTER_EIP, a); /* 22.2.3 */ + + for (i = 0; i < NR_VMX_MSR; ++i) { + u32 index = vmx_msr_index[i]; + u32 data_low, data_high; + u64 data; + int j = vmx->nmsrs; + + if (rdmsr_safe(index, &data_low, &data_high) < 0) + continue; + if (wrmsr_safe(index, data_low, data_high) < 0) + continue; + data = data_low | ((u64)data_high << 32); + vmx->host_msrs[j].index = index; + vmx->host_msrs[j].reserved = 0; + vmx->host_msrs[j].data = data; + vmx->guest_msrs[j] = vmx->host_msrs[j]; + ++vmx->nmsrs; + } + + vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); + + /* 22.2.1, 20.8.1 */ + vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl); + + vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); + vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); + + if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) + if (alloc_apic_access_page(vmx->vcpu.kvm) != 0) + return -ENOMEM; + + return 0; +} + +static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 msr; + int ret; + + if (!init_rmode_tss(vmx->vcpu.kvm)) { + ret = -ENOMEM; + goto out; + } + + vmx->vcpu.arch.rmode.active = 0; + + vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); + set_cr8(&vmx->vcpu, 0); + msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; + if (vmx->vcpu.vcpu_id == 0) + msr |= MSR_IA32_APICBASE_BSP; + kvm_set_apic_base(&vmx->vcpu, msr); + + fx_init(&vmx->vcpu); + + /* + * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode + * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh. + */ + if (vmx->vcpu.vcpu_id == 0) { + vmcs_write16(GUEST_CS_SELECTOR, 0xf000); + vmcs_writel(GUEST_CS_BASE, 0x000f0000); + } else { + vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8); + vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12); + } + vmcs_write32(GUEST_CS_LIMIT, 0xffff); + vmcs_write32(GUEST_CS_AR_BYTES, 0x9b); + + seg_setup(VCPU_SREG_DS); + seg_setup(VCPU_SREG_ES); + seg_setup(VCPU_SREG_FS); + seg_setup(VCPU_SREG_GS); + seg_setup(VCPU_SREG_SS); + + vmcs_write16(GUEST_TR_SELECTOR, 0); + vmcs_writel(GUEST_TR_BASE, 0); + vmcs_write32(GUEST_TR_LIMIT, 0xffff); + vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); + + vmcs_write16(GUEST_LDTR_SELECTOR, 0); + vmcs_writel(GUEST_LDTR_BASE, 0); + vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); + vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); + + vmcs_write32(GUEST_SYSENTER_CS, 0); + vmcs_writel(GUEST_SYSENTER_ESP, 0); + vmcs_writel(GUEST_SYSENTER_EIP, 0); + + vmcs_writel(GUEST_RFLAGS, 0x02); + if (vmx->vcpu.vcpu_id == 0) + vmcs_writel(GUEST_RIP, 0xfff0); + else + vmcs_writel(GUEST_RIP, 0); + vmcs_writel(GUEST_RSP, 0); + + /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */ + vmcs_writel(GUEST_DR7, 0x400); + + vmcs_writel(GUEST_GDTR_BASE, 0); + vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); + + vmcs_writel(GUEST_IDTR_BASE, 0); + vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); + + vmcs_write32(GUEST_ACTIVITY_STATE, 0); + vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); + vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); + + guest_write_tsc(0); + + /* Special registers */ + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + setup_msrs(vmx); + + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ + + if (cpu_has_vmx_tpr_shadow()) { + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); + if (vm_need_tpr_shadow(vmx->vcpu.kvm)) + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, + page_to_phys(vmx->vcpu.arch.apic->regs_page)); + vmcs_write32(TPR_THRESHOLD, 0); + } + + if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) + vmcs_write64(APIC_ACCESS_ADDR, + page_to_phys(vmx->vcpu.kvm->arch.apic_access_page)); + + vmx->vcpu.arch.cr0 = 0x60000010; + vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */ + vmx_set_cr4(&vmx->vcpu, 0); +#ifdef CONFIG_X86_64 + vmx_set_efer(&vmx->vcpu, 0); +#endif + vmx_fpu_activate(&vmx->vcpu); + update_exception_bitmap(&vmx->vcpu); + + return 0; + +out: + return ret; +} + +static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (vcpu->arch.rmode.active) { + vmx->rmode.irq.pending = true; + vmx->rmode.irq.vector = irq; + vmx->rmode.irq.rip = vmcs_readl(GUEST_RIP); + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, + irq | INTR_TYPE_SOFT_INTR | INTR_INFO_VALID_MASK); + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); + vmcs_writel(GUEST_RIP, vmx->rmode.irq.rip - 1); + return; + } + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, + irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); +} + +static void kvm_do_inject_irq(struct kvm_vcpu *vcpu) +{ + int word_index = __ffs(vcpu->arch.irq_summary); + int bit_index = __ffs(vcpu->arch.irq_pending[word_index]); + int irq = word_index * BITS_PER_LONG + bit_index; + + clear_bit(bit_index, &vcpu->arch.irq_pending[word_index]); + if (!vcpu->arch.irq_pending[word_index]) + clear_bit(word_index, &vcpu->arch.irq_summary); + vmx_inject_irq(vcpu, irq); +} + + +static void do_interrupt_requests(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) +{ + u32 cpu_based_vm_exec_control; + + vcpu->arch.interrupt_window_open = + ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0); + + if (vcpu->arch.interrupt_window_open && + vcpu->arch.irq_summary && + !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK)) + /* + * If interrupts enabled, and not blocked by sti or mov ss. Good. + */ + kvm_do_inject_irq(vcpu); + + cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + if (!vcpu->arch.interrupt_window_open && + (vcpu->arch.irq_summary || kvm_run->request_interrupt_window)) + /* + * Interrupts blocked. Wait for unblock. + */ + cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; + else + cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); +} + +static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) +{ + int ret; + struct kvm_userspace_memory_region tss_mem = { + .slot = 8, + .guest_phys_addr = addr, + .memory_size = PAGE_SIZE * 3, + .flags = 0, + }; + + ret = kvm_set_memory_region(kvm, &tss_mem, 0); + if (ret) + return ret; + kvm->arch.tss_addr = addr; + return 0; +} + +static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu) +{ + struct kvm_guest_debug *dbg = &vcpu->guest_debug; + + set_debugreg(dbg->bp[0], 0); + set_debugreg(dbg->bp[1], 1); + set_debugreg(dbg->bp[2], 2); + set_debugreg(dbg->bp[3], 3); + + if (dbg->singlestep) { + unsigned long flags; + + flags = vmcs_readl(GUEST_RFLAGS); + flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + vmcs_writel(GUEST_RFLAGS, flags); + } +} + +static int handle_rmode_exception(struct kvm_vcpu *vcpu, + int vec, u32 err_code) +{ + if (!vcpu->arch.rmode.active) + return 0; + + /* + * Instruction with address size override prefix opcode 0x67 + * Cause the #SS fault with 0 error code in VM86 mode. + */ + if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) + if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE) + return 1; + return 0; +} + +static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 intr_info, error_code; + unsigned long cr2, rip; + u32 vect_info; + enum emulation_result er; + + vect_info = vmx->idt_vectoring_info; + intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + if ((vect_info & VECTORING_INFO_VALID_MASK) && + !is_page_fault(intr_info)) + printk(KERN_ERR "%s: unexpected, vectoring info 0x%x " + "intr info 0x%x\n", __FUNCTION__, vect_info, intr_info); + + if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) { + int irq = vect_info & VECTORING_INFO_VECTOR_MASK; + set_bit(irq, vcpu->arch.irq_pending); + set_bit(irq / BITS_PER_LONG, &vcpu->arch.irq_summary); + } + + if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */ + return 1; /* already handled by vmx_vcpu_run() */ + + if (is_no_device(intr_info)) { + vmx_fpu_activate(vcpu); + return 1; + } + + if (is_invalid_opcode(intr_info)) { + er = emulate_instruction(vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + if (er != EMULATE_DONE) + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + error_code = 0; + rip = vmcs_readl(GUEST_RIP); + if (intr_info & INTR_INFO_DELIEVER_CODE_MASK) + error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + if (is_page_fault(intr_info)) { + cr2 = vmcs_readl(EXIT_QUALIFICATION); + return kvm_mmu_page_fault(vcpu, cr2, error_code); + } + + if (vcpu->arch.rmode.active && + handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK, + error_code)) { + if (vcpu->arch.halt_request) { + vcpu->arch.halt_request = 0; + return kvm_emulate_halt(vcpu); + } + return 1; + } + + if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == + (INTR_TYPE_EXCEPTION | 1)) { + kvm_run->exit_reason = KVM_EXIT_DEBUG; + return 0; + } + kvm_run->exit_reason = KVM_EXIT_EXCEPTION; + kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK; + kvm_run->ex.error_code = error_code; + return 0; +} + +static int handle_external_interrupt(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) +{ + ++vcpu->stat.irq_exits; + return 1; +} + +static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + return 0; +} + +static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + unsigned long exit_qualification; + int size, down, in, string, rep; + unsigned port; + + ++vcpu->stat.io_exits; + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + string = (exit_qualification & 16) != 0; + + if (string) { + if (emulate_instruction(vcpu, + kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + return 0; + return 1; + } + + size = (exit_qualification & 7) + 1; + in = (exit_qualification & 8) != 0; + down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0; + rep = (exit_qualification & 32) != 0; + port = exit_qualification >> 16; + + return kvm_emulate_pio(vcpu, kvm_run, in, size, port); +} + +static void +vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) +{ + /* + * Patch in the VMCALL instruction: + */ + hypercall[0] = 0x0f; + hypercall[1] = 0x01; + hypercall[2] = 0xc1; +} + +static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + unsigned long exit_qualification; + int cr; + int reg; + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + cr = exit_qualification & 15; + reg = (exit_qualification >> 8) & 15; + switch ((exit_qualification >> 4) & 3) { + case 0: /* mov to cr */ + switch (cr) { + case 0: + vcpu_load_rsp_rip(vcpu); + set_cr0(vcpu, vcpu->arch.regs[reg]); + skip_emulated_instruction(vcpu); + return 1; + case 3: + vcpu_load_rsp_rip(vcpu); + set_cr3(vcpu, vcpu->arch.regs[reg]); + skip_emulated_instruction(vcpu); + return 1; + case 4: + vcpu_load_rsp_rip(vcpu); + set_cr4(vcpu, vcpu->arch.regs[reg]); + skip_emulated_instruction(vcpu); + return 1; + case 8: + vcpu_load_rsp_rip(vcpu); + set_cr8(vcpu, vcpu->arch.regs[reg]); + skip_emulated_instruction(vcpu); + if (irqchip_in_kernel(vcpu->kvm)) + return 1; + kvm_run->exit_reason = KVM_EXIT_SET_TPR; + return 0; + }; + break; + case 2: /* clts */ + vcpu_load_rsp_rip(vcpu); + vmx_fpu_deactivate(vcpu); + vcpu->arch.cr0 &= ~X86_CR0_TS; + vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); + vmx_fpu_activate(vcpu); + skip_emulated_instruction(vcpu); + return 1; + case 1: /*mov from cr*/ + switch (cr) { + case 3: + vcpu_load_rsp_rip(vcpu); + vcpu->arch.regs[reg] = vcpu->arch.cr3; + vcpu_put_rsp_rip(vcpu); + skip_emulated_instruction(vcpu); + return 1; + case 8: + vcpu_load_rsp_rip(vcpu); + vcpu->arch.regs[reg] = get_cr8(vcpu); + vcpu_put_rsp_rip(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + break; + case 3: /* lmsw */ + lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f); + + skip_emulated_instruction(vcpu); + return 1; + default: + break; + } + kvm_run->exit_reason = 0; + pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", + (int)(exit_qualification >> 4) & 3, cr); + return 0; +} + +static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + unsigned long exit_qualification; + unsigned long val; + int dr, reg; + + /* + * FIXME: this code assumes the host is debugging the guest. + * need to deal with guest debugging itself too. + */ + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + dr = exit_qualification & 7; + reg = (exit_qualification >> 8) & 15; + vcpu_load_rsp_rip(vcpu); + if (exit_qualification & 16) { + /* mov from dr */ + switch (dr) { + case 6: + val = 0xffff0ff0; + break; + case 7: + val = 0x400; + break; + default: + val = 0; + } + vcpu->arch.regs[reg] = val; + } else { + /* mov to dr */ + } + vcpu_put_rsp_rip(vcpu); + skip_emulated_instruction(vcpu); + return 1; +} + +static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + kvm_emulate_cpuid(vcpu); + return 1; +} + +static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; + u64 data; + + if (vmx_get_msr(vcpu, ecx, &data)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + /* FIXME: handling of bits 32:63 of rax, rdx */ + vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u; + vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u; + skip_emulated_instruction(vcpu); + return 1; +} + +static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; + u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) + | ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32); + + if (vmx_set_msr(vcpu, ecx, data) != 0) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + skip_emulated_instruction(vcpu); + return 1; +} + +static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) +{ + return 1; +} + +static int handle_interrupt_window(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) +{ + u32 cpu_based_vm_exec_control; + + /* clear pending irq */ + cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + /* + * If the user space waits to inject interrupts, exit as soon as + * possible + */ + if (kvm_run->request_interrupt_window && + !vcpu->arch.irq_summary) { + kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; + ++vcpu->stat.irq_window_exits; + return 0; + } + return 1; +} + +static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + skip_emulated_instruction(vcpu); + return kvm_emulate_halt(vcpu); +} + +static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + skip_emulated_instruction(vcpu); + kvm_emulate_hypercall(vcpu); + return 1; +} + +static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + skip_emulated_instruction(vcpu); + /* TODO: Add support for VT-d/pass-through device */ + return 1; +} + +static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + u64 exit_qualification; + enum emulation_result er; + unsigned long offset; + + exit_qualification = vmcs_read64(EXIT_QUALIFICATION); + offset = exit_qualification & 0xffful; + + er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + + if (er != EMULATE_DONE) { + printk(KERN_ERR + "Fail to handle apic access vmexit! Offset is 0x%lx\n", + offset); + return -ENOTSUPP; + } + return 1; +} + +/* + * The exit handlers return 1 if the exit was handled fully and guest execution + * may resume. Otherwise they set the kvm_run parameter to indicate what needs + * to be done to userspace and return 0. + */ +static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) = { + [EXIT_REASON_EXCEPTION_NMI] = handle_exception, + [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, + [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, + [EXIT_REASON_IO_INSTRUCTION] = handle_io, + [EXIT_REASON_CR_ACCESS] = handle_cr, + [EXIT_REASON_DR_ACCESS] = handle_dr, + [EXIT_REASON_CPUID] = handle_cpuid, + [EXIT_REASON_MSR_READ] = handle_rdmsr, + [EXIT_REASON_MSR_WRITE] = handle_wrmsr, + [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, + [EXIT_REASON_HLT] = handle_halt, + [EXIT_REASON_VMCALL] = handle_vmcall, + [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, + [EXIT_REASON_APIC_ACCESS] = handle_apic_access, + [EXIT_REASON_WBINVD] = handle_wbinvd, +}; + +static const int kvm_vmx_max_exit_handlers = + ARRAY_SIZE(kvm_vmx_exit_handlers); + +/* + * The guest has exited. See if we can fix it or if we need userspace + * assistance. + */ +static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +{ + u32 exit_reason = vmcs_read32(VM_EXIT_REASON); + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 vectoring_info = vmx->idt_vectoring_info; + + if (unlikely(vmx->fail)) { + kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; + kvm_run->fail_entry.hardware_entry_failure_reason + = vmcs_read32(VM_INSTRUCTION_ERROR); + return 0; + } + + if ((vectoring_info & VECTORING_INFO_VALID_MASK) && + exit_reason != EXIT_REASON_EXCEPTION_NMI) + printk(KERN_WARNING "%s: unexpected, valid vectoring info and " + "exit reason is 0x%x\n", __FUNCTION__, exit_reason); + if (exit_reason < kvm_vmx_max_exit_handlers + && kvm_vmx_exit_handlers[exit_reason]) + return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); + else { + kvm_run->exit_reason = KVM_EXIT_UNKNOWN; + kvm_run->hw.hardware_exit_reason = exit_reason; + } + return 0; +} + +static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +{ +} + +static void update_tpr_threshold(struct kvm_vcpu *vcpu) +{ + int max_irr, tpr; + + if (!vm_need_tpr_shadow(vcpu->kvm)) + return; + + if (!kvm_lapic_enabled(vcpu) || + ((max_irr = kvm_lapic_find_highest_irr(vcpu)) == -1)) { + vmcs_write32(TPR_THRESHOLD, 0); + return; + } + + tpr = (kvm_lapic_get_cr8(vcpu) & 0x0f) << 4; + vmcs_write32(TPR_THRESHOLD, (max_irr > tpr) ? tpr >> 4 : max_irr >> 4); +} + +static void enable_irq_window(struct kvm_vcpu *vcpu) +{ + u32 cpu_based_vm_exec_control; + + cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); +} + +static void vmx_intr_assist(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 idtv_info_field, intr_info_field; + int has_ext_irq, interrupt_window_open; + int vector; + + update_tpr_threshold(vcpu); + + has_ext_irq = kvm_cpu_has_interrupt(vcpu); + intr_info_field = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); + idtv_info_field = vmx->idt_vectoring_info; + if (intr_info_field & INTR_INFO_VALID_MASK) { + if (idtv_info_field & INTR_INFO_VALID_MASK) { + /* TODO: fault when IDT_Vectoring */ + if (printk_ratelimit()) + printk(KERN_ERR "Fault when IDT_Vectoring\n"); + } + if (has_ext_irq) + enable_irq_window(vcpu); + return; + } + if (unlikely(idtv_info_field & INTR_INFO_VALID_MASK)) { + if ((idtv_info_field & VECTORING_INFO_TYPE_MASK) + == INTR_TYPE_EXT_INTR + && vcpu->arch.rmode.active) { + u8 vect = idtv_info_field & VECTORING_INFO_VECTOR_MASK; + + vmx_inject_irq(vcpu, vect); + if (unlikely(has_ext_irq)) + enable_irq_window(vcpu); + return; + } + + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field); + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, + vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); + + if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK)) + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, + vmcs_read32(IDT_VECTORING_ERROR_CODE)); + if (unlikely(has_ext_irq)) + enable_irq_window(vcpu); + return; + } + if (!has_ext_irq) + return; + interrupt_window_open = + ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0); + if (interrupt_window_open) { + vector = kvm_cpu_get_interrupt(vcpu); + vmx_inject_irq(vcpu, vector); + kvm_timer_intr_post(vcpu, vector); + } else + enable_irq_window(vcpu); +} + +/* + * Failure to inject an interrupt should give us the information + * in IDT_VECTORING_INFO_FIELD. However, if the failure occurs + * when fetching the interrupt redirection bitmap in the real-mode + * tss, this doesn't happen. So we do it ourselves. + */ +static void fixup_rmode_irq(struct vcpu_vmx *vmx) +{ + vmx->rmode.irq.pending = 0; + if (vmcs_readl(GUEST_RIP) + 1 != vmx->rmode.irq.rip) + return; + vmcs_writel(GUEST_RIP, vmx->rmode.irq.rip); + if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) { + vmx->idt_vectoring_info &= ~VECTORING_INFO_TYPE_MASK; + vmx->idt_vectoring_info |= INTR_TYPE_EXT_INTR; + return; + } + vmx->idt_vectoring_info = + VECTORING_INFO_VALID_MASK + | INTR_TYPE_EXT_INTR + | vmx->rmode.irq.vector; +} + +static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 intr_info; + + /* + * Loading guest fpu may have cleared host cr0.ts + */ + vmcs_writel(HOST_CR0, read_cr0()); + + asm( + /* Store host registers */ +#ifdef CONFIG_X86_64 + "push %%rdx; push %%rbp;" + "push %%rcx \n\t" +#else + "push %%edx; push %%ebp;" + "push %%ecx \n\t" +#endif + ASM_VMX_VMWRITE_RSP_RDX "\n\t" + /* Check if vmlaunch of vmresume is needed */ + "cmpl $0, %c[launched](%0) \n\t" + /* Load guest registers. Don't clobber flags. */ +#ifdef CONFIG_X86_64 + "mov %c[cr2](%0), %%rax \n\t" + "mov %%rax, %%cr2 \n\t" + "mov %c[rax](%0), %%rax \n\t" + "mov %c[rbx](%0), %%rbx \n\t" + "mov %c[rdx](%0), %%rdx \n\t" + "mov %c[rsi](%0), %%rsi \n\t" + "mov %c[rdi](%0), %%rdi \n\t" + "mov %c[rbp](%0), %%rbp \n\t" + "mov %c[r8](%0), %%r8 \n\t" + "mov %c[r9](%0), %%r9 \n\t" + "mov %c[r10](%0), %%r10 \n\t" + "mov %c[r11](%0), %%r11 \n\t" + "mov %c[r12](%0), %%r12 \n\t" + "mov %c[r13](%0), %%r13 \n\t" + "mov %c[r14](%0), %%r14 \n\t" + "mov %c[r15](%0), %%r15 \n\t" + "mov %c[rcx](%0), %%rcx \n\t" /* kills %0 (rcx) */ +#else + "mov %c[cr2](%0), %%eax \n\t" + "mov %%eax, %%cr2 \n\t" + "mov %c[rax](%0), %%eax \n\t" + "mov %c[rbx](%0), %%ebx \n\t" + "mov %c[rdx](%0), %%edx \n\t" + "mov %c[rsi](%0), %%esi \n\t" + "mov %c[rdi](%0), %%edi \n\t" + "mov %c[rbp](%0), %%ebp \n\t" + "mov %c[rcx](%0), %%ecx \n\t" /* kills %0 (ecx) */ +#endif + /* Enter guest mode */ + "jne .Llaunched \n\t" + ASM_VMX_VMLAUNCH "\n\t" + "jmp .Lkvm_vmx_return \n\t" + ".Llaunched: " ASM_VMX_VMRESUME "\n\t" + ".Lkvm_vmx_return: " + /* Save guest registers, load host registers, keep flags */ +#ifdef CONFIG_X86_64 + "xchg %0, (%%rsp) \n\t" + "mov %%rax, %c[rax](%0) \n\t" + "mov %%rbx, %c[rbx](%0) \n\t" + "pushq (%%rsp); popq %c[rcx](%0) \n\t" + "mov %%rdx, %c[rdx](%0) \n\t" + "mov %%rsi, %c[rsi](%0) \n\t" + "mov %%rdi, %c[rdi](%0) \n\t" + "mov %%rbp, %c[rbp](%0) \n\t" + "mov %%r8, %c[r8](%0) \n\t" + "mov %%r9, %c[r9](%0) \n\t" + "mov %%r10, %c[r10](%0) \n\t" + "mov %%r11, %c[r11](%0) \n\t" + "mov %%r12, %c[r12](%0) \n\t" + "mov %%r13, %c[r13](%0) \n\t" + "mov %%r14, %c[r14](%0) \n\t" + "mov %%r15, %c[r15](%0) \n\t" + "mov %%cr2, %%rax \n\t" + "mov %%rax, %c[cr2](%0) \n\t" + + "pop %%rbp; pop %%rbp; pop %%rdx \n\t" +#else + "xchg %0, (%%esp) \n\t" + "mov %%eax, %c[rax](%0) \n\t" + "mov %%ebx, %c[rbx](%0) \n\t" + "pushl (%%esp); popl %c[rcx](%0) \n\t" + "mov %%edx, %c[rdx](%0) \n\t" + "mov %%esi, %c[rsi](%0) \n\t" + "mov %%edi, %c[rdi](%0) \n\t" + "mov %%ebp, %c[rbp](%0) \n\t" + "mov %%cr2, %%eax \n\t" + "mov %%eax, %c[cr2](%0) \n\t" + + "pop %%ebp; pop %%ebp; pop %%edx \n\t" +#endif + "setbe %c[fail](%0) \n\t" + : : "c"(vmx), "d"((unsigned long)HOST_RSP), + [launched]"i"(offsetof(struct vcpu_vmx, launched)), + [fail]"i"(offsetof(struct vcpu_vmx, fail)), + [rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])), + [rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])), + [rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])), + [rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])), + [rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])), + [rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])), + [rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])), +#ifdef CONFIG_X86_64 + [r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])), + [r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])), + [r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])), + [r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])), + [r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])), + [r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])), + [r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])), + [r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])), +#endif + [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)) + : "cc", "memory" +#ifdef CONFIG_X86_64 + , "rbx", "rdi", "rsi" + , "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15" +#else + , "ebx", "edi", "rsi" +#endif + ); + + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); + if (vmx->rmode.irq.pending) + fixup_rmode_irq(vmx); + + vcpu->arch.interrupt_window_open = + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0; + + asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS)); + vmx->launched = 1; + + intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + /* We need to handle NMIs before interrupts are enabled */ + if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */ + asm("int $2"); +} + +static void vmx_free_vmcs(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (vmx->vmcs) { + on_each_cpu(__vcpu_clear, vmx, 0, 1); + free_vmcs(vmx->vmcs); + vmx->vmcs = NULL; + } +} + +static void vmx_free_vcpu(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + vmx_free_vmcs(vcpu); + kfree(vmx->host_msrs); + kfree(vmx->guest_msrs); + kvm_vcpu_uninit(vcpu); + kmem_cache_free(kvm_vcpu_cache, vmx); +} + +static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) +{ + int err; + struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + int cpu; + + if (!vmx) + return ERR_PTR(-ENOMEM); + + err = kvm_vcpu_init(&vmx->vcpu, kvm, id); + if (err) + goto free_vcpu; + + vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!vmx->guest_msrs) { + err = -ENOMEM; + goto uninit_vcpu; + } + + vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!vmx->host_msrs) + goto free_guest_msrs; + + vmx->vmcs = alloc_vmcs(); + if (!vmx->vmcs) + goto free_msrs; + + vmcs_clear(vmx->vmcs); + + cpu = get_cpu(); + vmx_vcpu_load(&vmx->vcpu, cpu); + err = vmx_vcpu_setup(vmx); + vmx_vcpu_put(&vmx->vcpu); + put_cpu(); + if (err) + goto free_vmcs; + + return &vmx->vcpu; + +free_vmcs: + free_vmcs(vmx->vmcs); +free_msrs: + kfree(vmx->host_msrs); +free_guest_msrs: + kfree(vmx->guest_msrs); +uninit_vcpu: + kvm_vcpu_uninit(&vmx->vcpu); +free_vcpu: + kmem_cache_free(kvm_vcpu_cache, vmx); + return ERR_PTR(err); +} + +static void __init vmx_check_processor_compat(void *rtn) +{ + struct vmcs_config vmcs_conf; + + *(int *)rtn = 0; + if (setup_vmcs_config(&vmcs_conf) < 0) + *(int *)rtn = -EIO; + if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { + printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", + smp_processor_id()); + *(int *)rtn = -EIO; + } +} + +static struct kvm_x86_ops vmx_x86_ops = { + .cpu_has_kvm_support = cpu_has_kvm_support, + .disabled_by_bios = vmx_disabled_by_bios, + .hardware_setup = hardware_setup, + .hardware_unsetup = hardware_unsetup, + .check_processor_compatibility = vmx_check_processor_compat, + .hardware_enable = hardware_enable, + .hardware_disable = hardware_disable, + .cpu_has_accelerated_tpr = cpu_has_vmx_virtualize_apic_accesses, + + .vcpu_create = vmx_create_vcpu, + .vcpu_free = vmx_free_vcpu, + .vcpu_reset = vmx_vcpu_reset, + + .prepare_guest_switch = vmx_save_host_state, + .vcpu_load = vmx_vcpu_load, + .vcpu_put = vmx_vcpu_put, + .vcpu_decache = vmx_vcpu_decache, + + .set_guest_debug = set_guest_debug, + .guest_debug_pre = kvm_guest_debug_pre, + .get_msr = vmx_get_msr, + .set_msr = vmx_set_msr, + .get_segment_base = vmx_get_segment_base, + .get_segment = vmx_get_segment, + .set_segment = vmx_set_segment, + .get_cs_db_l_bits = vmx_get_cs_db_l_bits, + .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, + .set_cr0 = vmx_set_cr0, + .set_cr3 = vmx_set_cr3, + .set_cr4 = vmx_set_cr4, +#ifdef CONFIG_X86_64 + .set_efer = vmx_set_efer, +#endif + .get_idt = vmx_get_idt, + .set_idt = vmx_set_idt, + .get_gdt = vmx_get_gdt, + .set_gdt = vmx_set_gdt, + .cache_regs = vcpu_load_rsp_rip, + .decache_regs = vcpu_put_rsp_rip, + .get_rflags = vmx_get_rflags, + .set_rflags = vmx_set_rflags, + + .tlb_flush = vmx_flush_tlb, + + .run = vmx_vcpu_run, + .handle_exit = kvm_handle_exit, + .skip_emulated_instruction = skip_emulated_instruction, + .patch_hypercall = vmx_patch_hypercall, + .get_irq = vmx_get_irq, + .set_irq = vmx_inject_irq, + .queue_exception = vmx_queue_exception, + .exception_injected = vmx_exception_injected, + .inject_pending_irq = vmx_intr_assist, + .inject_pending_vectors = do_interrupt_requests, + + .set_tss_addr = vmx_set_tss_addr, +}; + +static int __init vmx_init(void) +{ + void *iova; + int r; + + vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); + if (!vmx_io_bitmap_a) + return -ENOMEM; + + vmx_io_bitmap_b = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); + if (!vmx_io_bitmap_b) { + r = -ENOMEM; + goto out; + } + + /* + * Allow direct access to the PC debug port (it is often used for I/O + * delays, but the vmexits simply slow things down). + */ + iova = kmap(vmx_io_bitmap_a); + memset(iova, 0xff, PAGE_SIZE); + clear_bit(0x80, iova); + kunmap(vmx_io_bitmap_a); + + iova = kmap(vmx_io_bitmap_b); + memset(iova, 0xff, PAGE_SIZE); + kunmap(vmx_io_bitmap_b); + + r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE); + if (r) + goto out1; + + if (bypass_guest_pf) + kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); + + return 0; + +out1: + __free_page(vmx_io_bitmap_b); +out: + __free_page(vmx_io_bitmap_a); + return r; +} + +static void __exit vmx_exit(void) +{ + __free_page(vmx_io_bitmap_b); + __free_page(vmx_io_bitmap_a); + + kvm_exit(); +} + +module_init(vmx_init) +module_exit(vmx_exit) diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h new file mode 100644 index 00000000000..d52ae8d7303 --- /dev/null +++ b/arch/x86/kvm/vmx.h @@ -0,0 +1,324 @@ +#ifndef VMX_H +#define VMX_H + +/* + * vmx.h: VMX Architecture related definitions + * Copyright (c) 2004, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + * A few random additions are: + * Copyright (C) 2006 Qumranet + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * + */ + +/* + * Definitions of Primary Processor-Based VM-Execution Controls. + */ +#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004 +#define CPU_BASED_USE_TSC_OFFSETING 0x00000008 +#define CPU_BASED_HLT_EXITING 0x00000080 +#define CPU_BASED_INVLPG_EXITING 0x00000200 +#define CPU_BASED_MWAIT_EXITING 0x00000400 +#define CPU_BASED_RDPMC_EXITING 0x00000800 +#define CPU_BASED_RDTSC_EXITING 0x00001000 +#define CPU_BASED_CR8_LOAD_EXITING 0x00080000 +#define CPU_BASED_CR8_STORE_EXITING 0x00100000 +#define CPU_BASED_TPR_SHADOW 0x00200000 +#define CPU_BASED_MOV_DR_EXITING 0x00800000 +#define CPU_BASED_UNCOND_IO_EXITING 0x01000000 +#define CPU_BASED_USE_IO_BITMAPS 0x02000000 +#define CPU_BASED_USE_MSR_BITMAPS 0x10000000 +#define CPU_BASED_MONITOR_EXITING 0x20000000 +#define CPU_BASED_PAUSE_EXITING 0x40000000 +#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000 +/* + * Definitions of Secondary Processor-Based VM-Execution Controls. + */ +#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001 +#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 + + +#define PIN_BASED_EXT_INTR_MASK 0x00000001 +#define PIN_BASED_NMI_EXITING 0x00000008 +#define PIN_BASED_VIRTUAL_NMIS 0x00000020 + +#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200 +#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000 + +#define VM_ENTRY_IA32E_MODE 0x00000200 +#define VM_ENTRY_SMM 0x00000400 +#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800 + +/* VMCS Encodings */ +enum vmcs_field { + GUEST_ES_SELECTOR = 0x00000800, + GUEST_CS_SELECTOR = 0x00000802, + GUEST_SS_SELECTOR = 0x00000804, + GUEST_DS_SELECTOR = 0x00000806, + GUEST_FS_SELECTOR = 0x00000808, + GUEST_GS_SELECTOR = 0x0000080a, + GUEST_LDTR_SELECTOR = 0x0000080c, + GUEST_TR_SELECTOR = 0x0000080e, + HOST_ES_SELECTOR = 0x00000c00, + HOST_CS_SELECTOR = 0x00000c02, + HOST_SS_SELECTOR = 0x00000c04, + HOST_DS_SELECTOR = 0x00000c06, + HOST_FS_SELECTOR = 0x00000c08, + HOST_GS_SELECTOR = 0x00000c0a, + HOST_TR_SELECTOR = 0x00000c0c, + IO_BITMAP_A = 0x00002000, + IO_BITMAP_A_HIGH = 0x00002001, + IO_BITMAP_B = 0x00002002, + IO_BITMAP_B_HIGH = 0x00002003, + MSR_BITMAP = 0x00002004, + MSR_BITMAP_HIGH = 0x00002005, + VM_EXIT_MSR_STORE_ADDR = 0x00002006, + VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007, + VM_EXIT_MSR_LOAD_ADDR = 0x00002008, + VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009, + VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a, + VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b, + TSC_OFFSET = 0x00002010, + TSC_OFFSET_HIGH = 0x00002011, + VIRTUAL_APIC_PAGE_ADDR = 0x00002012, + VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013, + APIC_ACCESS_ADDR = 0x00002014, + APIC_ACCESS_ADDR_HIGH = 0x00002015, + VMCS_LINK_POINTER = 0x00002800, + VMCS_LINK_POINTER_HIGH = 0x00002801, + GUEST_IA32_DEBUGCTL = 0x00002802, + GUEST_IA32_DEBUGCTL_HIGH = 0x00002803, + PIN_BASED_VM_EXEC_CONTROL = 0x00004000, + CPU_BASED_VM_EXEC_CONTROL = 0x00004002, + EXCEPTION_BITMAP = 0x00004004, + PAGE_FAULT_ERROR_CODE_MASK = 0x00004006, + PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008, + CR3_TARGET_COUNT = 0x0000400a, + VM_EXIT_CONTROLS = 0x0000400c, + VM_EXIT_MSR_STORE_COUNT = 0x0000400e, + VM_EXIT_MSR_LOAD_COUNT = 0x00004010, + VM_ENTRY_CONTROLS = 0x00004012, + VM_ENTRY_MSR_LOAD_COUNT = 0x00004014, + VM_ENTRY_INTR_INFO_FIELD = 0x00004016, + VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018, + VM_ENTRY_INSTRUCTION_LEN = 0x0000401a, + TPR_THRESHOLD = 0x0000401c, + SECONDARY_VM_EXEC_CONTROL = 0x0000401e, + VM_INSTRUCTION_ERROR = 0x00004400, + VM_EXIT_REASON = 0x00004402, + VM_EXIT_INTR_INFO = 0x00004404, + VM_EXIT_INTR_ERROR_CODE = 0x00004406, + IDT_VECTORING_INFO_FIELD = 0x00004408, + IDT_VECTORING_ERROR_CODE = 0x0000440a, + VM_EXIT_INSTRUCTION_LEN = 0x0000440c, + VMX_INSTRUCTION_INFO = 0x0000440e, + GUEST_ES_LIMIT = 0x00004800, + GUEST_CS_LIMIT = 0x00004802, + GUEST_SS_LIMIT = 0x00004804, + GUEST_DS_LIMIT = 0x00004806, + GUEST_FS_LIMIT = 0x00004808, + GUEST_GS_LIMIT = 0x0000480a, + GUEST_LDTR_LIMIT = 0x0000480c, + GUEST_TR_LIMIT = 0x0000480e, + GUEST_GDTR_LIMIT = 0x00004810, + GUEST_IDTR_LIMIT = 0x00004812, + GUEST_ES_AR_BYTES = 0x00004814, + GUEST_CS_AR_BYTES = 0x00004816, + GUEST_SS_AR_BYTES = 0x00004818, + GUEST_DS_AR_BYTES = 0x0000481a, + GUEST_FS_AR_BYTES = 0x0000481c, + GUEST_GS_AR_BYTES = 0x0000481e, + GUEST_LDTR_AR_BYTES = 0x00004820, + GUEST_TR_AR_BYTES = 0x00004822, + GUEST_INTERRUPTIBILITY_INFO = 0x00004824, + GUEST_ACTIVITY_STATE = 0X00004826, + GUEST_SYSENTER_CS = 0x0000482A, + HOST_IA32_SYSENTER_CS = 0x00004c00, + CR0_GUEST_HOST_MASK = 0x00006000, + CR4_GUEST_HOST_MASK = 0x00006002, + CR0_READ_SHADOW = 0x00006004, + CR4_READ_SHADOW = 0x00006006, + CR3_TARGET_VALUE0 = 0x00006008, + CR3_TARGET_VALUE1 = 0x0000600a, + CR3_TARGET_VALUE2 = 0x0000600c, + CR3_TARGET_VALUE3 = 0x0000600e, + EXIT_QUALIFICATION = 0x00006400, + GUEST_LINEAR_ADDRESS = 0x0000640a, + GUEST_CR0 = 0x00006800, + GUEST_CR3 = 0x00006802, + GUEST_CR4 = 0x00006804, + GUEST_ES_BASE = 0x00006806, + GUEST_CS_BASE = 0x00006808, + GUEST_SS_BASE = 0x0000680a, + GUEST_DS_BASE = 0x0000680c, + GUEST_FS_BASE = 0x0000680e, + GUEST_GS_BASE = 0x00006810, + GUEST_LDTR_BASE = 0x00006812, + GUEST_TR_BASE = 0x00006814, + GUEST_GDTR_BASE = 0x00006816, + GUEST_IDTR_BASE = 0x00006818, + GUEST_DR7 = 0x0000681a, + GUEST_RSP = 0x0000681c, + GUEST_RIP = 0x0000681e, + GUEST_RFLAGS = 0x00006820, + GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822, + GUEST_SYSENTER_ESP = 0x00006824, + GUEST_SYSENTER_EIP = 0x00006826, + HOST_CR0 = 0x00006c00, + HOST_CR3 = 0x00006c02, + HOST_CR4 = 0x00006c04, + HOST_FS_BASE = 0x00006c06, + HOST_GS_BASE = 0x00006c08, + HOST_TR_BASE = 0x00006c0a, + HOST_GDTR_BASE = 0x00006c0c, + HOST_IDTR_BASE = 0x00006c0e, + HOST_IA32_SYSENTER_ESP = 0x00006c10, + HOST_IA32_SYSENTER_EIP = 0x00006c12, + HOST_RSP = 0x00006c14, + HOST_RIP = 0x00006c16, +}; + +#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 + +#define EXIT_REASON_EXCEPTION_NMI 0 +#define EXIT_REASON_EXTERNAL_INTERRUPT 1 +#define EXIT_REASON_TRIPLE_FAULT 2 + +#define EXIT_REASON_PENDING_INTERRUPT 7 + +#define EXIT_REASON_TASK_SWITCH 9 +#define EXIT_REASON_CPUID 10 +#define EXIT_REASON_HLT 12 +#define EXIT_REASON_INVLPG 14 +#define EXIT_REASON_RDPMC 15 +#define EXIT_REASON_RDTSC 16 +#define EXIT_REASON_VMCALL 18 +#define EXIT_REASON_VMCLEAR 19 +#define EXIT_REASON_VMLAUNCH 20 +#define EXIT_REASON_VMPTRLD 21 +#define EXIT_REASON_VMPTRST 22 +#define EXIT_REASON_VMREAD 23 +#define EXIT_REASON_VMRESUME 24 +#define EXIT_REASON_VMWRITE 25 +#define EXIT_REASON_VMOFF 26 +#define EXIT_REASON_VMON 27 +#define EXIT_REASON_CR_ACCESS 28 +#define EXIT_REASON_DR_ACCESS 29 +#define EXIT_REASON_IO_INSTRUCTION 30 +#define EXIT_REASON_MSR_READ 31 +#define EXIT_REASON_MSR_WRITE 32 +#define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 +#define EXIT_REASON_APIC_ACCESS 44 +#define EXIT_REASON_WBINVD 54 + +/* + * Interruption-information format + */ +#define INTR_INFO_VECTOR_MASK 0xff /* 7:0 */ +#define INTR_INFO_INTR_TYPE_MASK 0x700 /* 10:8 */ +#define INTR_INFO_DELIEVER_CODE_MASK 0x800 /* 11 */ +#define INTR_INFO_VALID_MASK 0x80000000 /* 31 */ + +#define VECTORING_INFO_VECTOR_MASK INTR_INFO_VECTOR_MASK +#define VECTORING_INFO_TYPE_MASK INTR_INFO_INTR_TYPE_MASK +#define VECTORING_INFO_DELIEVER_CODE_MASK INTR_INFO_DELIEVER_CODE_MASK +#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK + +#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ +#define INTR_TYPE_EXCEPTION (3 << 8) /* processor exception */ +#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ + +/* + * Exit Qualifications for MOV for Control Register Access + */ +#define CONTROL_REG_ACCESS_NUM 0x7 /* 2:0, number of control reg.*/ +#define CONTROL_REG_ACCESS_TYPE 0x30 /* 5:4, access type */ +#define CONTROL_REG_ACCESS_REG 0xf00 /* 10:8, general purpose reg. */ +#define LMSW_SOURCE_DATA_SHIFT 16 +#define LMSW_SOURCE_DATA (0xFFFF << LMSW_SOURCE_DATA_SHIFT) /* 16:31 lmsw source */ +#define REG_EAX (0 << 8) +#define REG_ECX (1 << 8) +#define REG_EDX (2 << 8) +#define REG_EBX (3 << 8) +#define REG_ESP (4 << 8) +#define REG_EBP (5 << 8) +#define REG_ESI (6 << 8) +#define REG_EDI (7 << 8) +#define REG_R8 (8 << 8) +#define REG_R9 (9 << 8) +#define REG_R10 (10 << 8) +#define REG_R11 (11 << 8) +#define REG_R12 (12 << 8) +#define REG_R13 (13 << 8) +#define REG_R14 (14 << 8) +#define REG_R15 (15 << 8) + +/* + * Exit Qualifications for MOV for Debug Register Access + */ +#define DEBUG_REG_ACCESS_NUM 0x7 /* 2:0, number of debug reg. */ +#define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */ +#define TYPE_MOV_TO_DR (0 << 4) +#define TYPE_MOV_FROM_DR (1 << 4) +#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose reg. */ + + +/* segment AR */ +#define SEGMENT_AR_L_MASK (1 << 13) + +#define AR_TYPE_ACCESSES_MASK 1 +#define AR_TYPE_READABLE_MASK (1 << 1) +#define AR_TYPE_WRITEABLE_MASK (1 << 2) +#define AR_TYPE_CODE_MASK (1 << 3) +#define AR_TYPE_MASK 0x0f +#define AR_TYPE_BUSY_64_TSS 11 +#define AR_TYPE_BUSY_32_TSS 11 +#define AR_TYPE_BUSY_16_TSS 3 +#define AR_TYPE_LDT 2 + +#define AR_UNUSABLE_MASK (1 << 16) +#define AR_S_MASK (1 << 4) +#define AR_P_MASK (1 << 7) +#define AR_L_MASK (1 << 13) +#define AR_DB_MASK (1 << 14) +#define AR_G_MASK (1 << 15) +#define AR_DPL_SHIFT 5 +#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3) + +#define AR_RESERVD_MASK 0xfffe0f00 + +#define MSR_IA32_VMX_BASIC 0x480 +#define MSR_IA32_VMX_PINBASED_CTLS 0x481 +#define MSR_IA32_VMX_PROCBASED_CTLS 0x482 +#define MSR_IA32_VMX_EXIT_CTLS 0x483 +#define MSR_IA32_VMX_ENTRY_CTLS 0x484 +#define MSR_IA32_VMX_MISC 0x485 +#define MSR_IA32_VMX_CR0_FIXED0 0x486 +#define MSR_IA32_VMX_CR0_FIXED1 0x487 +#define MSR_IA32_VMX_CR4_FIXED0 0x488 +#define MSR_IA32_VMX_CR4_FIXED1 0x489 +#define MSR_IA32_VMX_VMCS_ENUM 0x48a +#define MSR_IA32_VMX_PROCBASED_CTLS2 0x48b + +#define MSR_IA32_FEATURE_CONTROL 0x3a +#define MSR_IA32_FEATURE_CONTROL_LOCKED 0x1 +#define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED 0x4 + +#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT 9 + +#endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c new file mode 100644 index 00000000000..8f94a0b89df --- /dev/null +++ b/arch/x86/kvm/x86.c @@ -0,0 +1,3287 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * derived from drivers/kvm/kvm_main.c + * + * Copyright (C) 2006 Qumranet, Inc. + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include <linux/kvm_host.h> +#include "segment_descriptor.h" +#include "irq.h" +#include "mmu.h" + +#include <linux/kvm.h> +#include <linux/fs.h> +#include <linux/vmalloc.h> +#include <linux/module.h> +#include <linux/mman.h> +#include <linux/highmem.h> + +#include <asm/uaccess.h> +#include <asm/msr.h> + +#define MAX_IO_MSRS 256 +#define CR0_RESERVED_BITS \ + (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ + | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ + | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) +#define CR4_RESERVED_BITS \ + (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ + | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ + | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ + | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) + +#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) +#define EFER_RESERVED_BITS 0xfffffffffffff2fe + +#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM +#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU + +struct kvm_x86_ops *kvm_x86_ops; + +struct kvm_stats_debugfs_item debugfs_entries[] = { + { "pf_fixed", VCPU_STAT(pf_fixed) }, + { "pf_guest", VCPU_STAT(pf_guest) }, + { "tlb_flush", VCPU_STAT(tlb_flush) }, + { "invlpg", VCPU_STAT(invlpg) }, + { "exits", VCPU_STAT(exits) }, + { "io_exits", VCPU_STAT(io_exits) }, + { "mmio_exits", VCPU_STAT(mmio_exits) }, + { "signal_exits", VCPU_STAT(signal_exits) }, + { "irq_window", VCPU_STAT(irq_window_exits) }, + { "halt_exits", VCPU_STAT(halt_exits) }, + { "halt_wakeup", VCPU_STAT(halt_wakeup) }, + { "request_irq", VCPU_STAT(request_irq_exits) }, + { "irq_exits", VCPU_STAT(irq_exits) }, + { "host_state_reload", VCPU_STAT(host_state_reload) }, + { "efer_reload", VCPU_STAT(efer_reload) }, + { "fpu_reload", VCPU_STAT(fpu_reload) }, + { "insn_emulation", VCPU_STAT(insn_emulation) }, + { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, + { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, + { "mmu_pte_write", VM_STAT(mmu_pte_write) }, + { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, + { "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) }, + { "mmu_flooded", VM_STAT(mmu_flooded) }, + { "mmu_recycled", VM_STAT(mmu_recycled) }, + { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, + { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, + { NULL } +}; + + +unsigned long segment_base(u16 selector) +{ + struct descriptor_table gdt; + struct segment_descriptor *d; + unsigned long table_base; + unsigned long v; + + if (selector == 0) + return 0; + + asm("sgdt %0" : "=m"(gdt)); + table_base = gdt.base; + + if (selector & 4) { /* from ldt */ + u16 ldt_selector; + + asm("sldt %0" : "=g"(ldt_selector)); + table_base = segment_base(ldt_selector); + } + d = (struct segment_descriptor *)(table_base + (selector & ~7)); + v = d->base_low | ((unsigned long)d->base_mid << 16) | + ((unsigned long)d->base_high << 24); +#ifdef CONFIG_X86_64 + if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) + v |= ((unsigned long) \ + ((struct segment_descriptor_64 *)d)->base_higher) << 32; +#endif + return v; +} +EXPORT_SYMBOL_GPL(segment_base); + +u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) +{ + if (irqchip_in_kernel(vcpu->kvm)) + return vcpu->arch.apic_base; + else + return vcpu->arch.apic_base; +} +EXPORT_SYMBOL_GPL(kvm_get_apic_base); + +void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data) +{ + /* TODO: reserve bits check */ + if (irqchip_in_kernel(vcpu->kvm)) + kvm_lapic_set_base(vcpu, data); + else + vcpu->arch.apic_base = data; +} +EXPORT_SYMBOL_GPL(kvm_set_apic_base); + +void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) +{ + WARN_ON(vcpu->arch.exception.pending); + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = false; + vcpu->arch.exception.nr = nr; +} +EXPORT_SYMBOL_GPL(kvm_queue_exception); + +void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, + u32 error_code) +{ + ++vcpu->stat.pf_guest; + if (vcpu->arch.exception.pending && vcpu->arch.exception.nr == PF_VECTOR) { + printk(KERN_DEBUG "kvm: inject_page_fault:" + " double fault 0x%lx\n", addr); + vcpu->arch.exception.nr = DF_VECTOR; + vcpu->arch.exception.error_code = 0; + return; + } + vcpu->arch.cr2 = addr; + kvm_queue_exception_e(vcpu, PF_VECTOR, error_code); +} + +void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) +{ + WARN_ON(vcpu->arch.exception.pending); + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = true; + vcpu->arch.exception.nr = nr; + vcpu->arch.exception.error_code = error_code; +} +EXPORT_SYMBOL_GPL(kvm_queue_exception_e); + +static void __queue_exception(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code); +} + +/* + * Load the pae pdptrs. Return true is they are all valid. + */ +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; + unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2; + int i; + int ret; + u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)]; + + down_read(¤t->mm->mmap_sem); + ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte, + offset * sizeof(u64), sizeof(pdpte)); + if (ret < 0) { + ret = 0; + goto out; + } + for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { + if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) { + ret = 0; + goto out; + } + } + ret = 1; + + memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs)); +out: + up_read(¤t->mm->mmap_sem); + + return ret; +} + +static bool pdptrs_changed(struct kvm_vcpu *vcpu) +{ + u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)]; + bool changed = true; + int r; + + if (is_long_mode(vcpu) || !is_pae(vcpu)) + return false; + + down_read(¤t->mm->mmap_sem); + r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte)); + if (r < 0) + goto out; + changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0; +out: + up_read(¤t->mm->mmap_sem); + + return changed; +} + +void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + if (cr0 & CR0_RESERVED_BITS) { + printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", + cr0, vcpu->arch.cr0); + kvm_inject_gp(vcpu, 0); + return; + } + + if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) { + printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n"); + kvm_inject_gp(vcpu, 0); + return; + } + + if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) { + printk(KERN_DEBUG "set_cr0: #GP, set PG flag " + "and a clear PE flag\n"); + kvm_inject_gp(vcpu, 0); + return; + } + + if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { +#ifdef CONFIG_X86_64 + if ((vcpu->arch.shadow_efer & EFER_LME)) { + int cs_db, cs_l; + + if (!is_pae(vcpu)) { + printk(KERN_DEBUG "set_cr0: #GP, start paging " + "in long mode while PAE is disabled\n"); + kvm_inject_gp(vcpu, 0); + return; + } + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + if (cs_l) { + printk(KERN_DEBUG "set_cr0: #GP, start paging " + "in long mode while CS.L == 1\n"); + kvm_inject_gp(vcpu, 0); + return; + + } + } else +#endif + if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { + printk(KERN_DEBUG "set_cr0: #GP, pdptrs " + "reserved bits\n"); + kvm_inject_gp(vcpu, 0); + return; + } + + } + + kvm_x86_ops->set_cr0(vcpu, cr0); + vcpu->arch.cr0 = cr0; + + kvm_mmu_reset_context(vcpu); + return; +} +EXPORT_SYMBOL_GPL(set_cr0); + +void lmsw(struct kvm_vcpu *vcpu, unsigned long msw) +{ + set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)); +} +EXPORT_SYMBOL_GPL(lmsw); + +void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + if (cr4 & CR4_RESERVED_BITS) { + printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); + kvm_inject_gp(vcpu, 0); + return; + } + + if (is_long_mode(vcpu)) { + if (!(cr4 & X86_CR4_PAE)) { + printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while " + "in long mode\n"); + kvm_inject_gp(vcpu, 0); + return; + } + } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE) + && !load_pdptrs(vcpu, vcpu->arch.cr3)) { + printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); + kvm_inject_gp(vcpu, 0); + return; + } + + if (cr4 & X86_CR4_VMXE) { + printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n"); + kvm_inject_gp(vcpu, 0); + return; + } + kvm_x86_ops->set_cr4(vcpu, cr4); + vcpu->arch.cr4 = cr4; + kvm_mmu_reset_context(vcpu); +} +EXPORT_SYMBOL_GPL(set_cr4); + +void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) { + kvm_mmu_flush_tlb(vcpu); + return; + } + + if (is_long_mode(vcpu)) { + if (cr3 & CR3_L_MODE_RESERVED_BITS) { + printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n"); + kvm_inject_gp(vcpu, 0); + return; + } + } else { + if (is_pae(vcpu)) { + if (cr3 & CR3_PAE_RESERVED_BITS) { + printk(KERN_DEBUG + "set_cr3: #GP, reserved bits\n"); + kvm_inject_gp(vcpu, 0); + return; + } + if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) { + printk(KERN_DEBUG "set_cr3: #GP, pdptrs " + "reserved bits\n"); + kvm_inject_gp(vcpu, 0); + return; + } + } + /* + * We don't check reserved bits in nonpae mode, because + * this isn't enforced, and VMware depends on this. + */ + } + + down_read(¤t->mm->mmap_sem); + /* + * Does the new cr3 value map to physical memory? (Note, we + * catch an invalid cr3 even in real-mode, because it would + * cause trouble later on when we turn on paging anyway.) + * + * A real CPU would silently accept an invalid cr3 and would + * attempt to use it - with largely undefined (and often hard + * to debug) behavior on the guest side. + */ + if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT))) + kvm_inject_gp(vcpu, 0); + else { + vcpu->arch.cr3 = cr3; + vcpu->arch.mmu.new_cr3(vcpu); + } + up_read(¤t->mm->mmap_sem); +} +EXPORT_SYMBOL_GPL(set_cr3); + +void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) +{ + if (cr8 & CR8_RESERVED_BITS) { + printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8); + kvm_inject_gp(vcpu, 0); + return; + } + if (irqchip_in_kernel(vcpu->kvm)) + kvm_lapic_set_tpr(vcpu, cr8); + else + vcpu->arch.cr8 = cr8; +} +EXPORT_SYMBOL_GPL(set_cr8); + +unsigned long get_cr8(struct kvm_vcpu *vcpu) +{ + if (irqchip_in_kernel(vcpu->kvm)) + return kvm_lapic_get_cr8(vcpu); + else + return vcpu->arch.cr8; +} +EXPORT_SYMBOL_GPL(get_cr8); + +/* + * List of msr numbers which we expose to userspace through KVM_GET_MSRS + * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. + * + * This list is modified at module load time to reflect the + * capabilities of the host cpu. + */ +static u32 msrs_to_save[] = { + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_K6_STAR, +#ifdef CONFIG_X86_64 + MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, +#endif + MSR_IA32_TIME_STAMP_COUNTER, +}; + +static unsigned num_msrs_to_save; + +static u32 emulated_msrs[] = { + MSR_IA32_MISC_ENABLE, +}; + +#ifdef CONFIG_X86_64 + +static void set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + if (efer & EFER_RESERVED_BITS) { + printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n", + efer); + kvm_inject_gp(vcpu, 0); + return; + } + + if (is_paging(vcpu) + && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) { + printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n"); + kvm_inject_gp(vcpu, 0); + return; + } + + kvm_x86_ops->set_efer(vcpu, efer); + + efer &= ~EFER_LMA; + efer |= vcpu->arch.shadow_efer & EFER_LMA; + + vcpu->arch.shadow_efer = efer; +} + +#endif + +/* + * Writes msr value into into the appropriate "register". + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. + */ +int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) +{ + return kvm_x86_ops->set_msr(vcpu, msr_index, data); +} + +/* + * Adapt set_msr() to msr_io()'s calling convention + */ +static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + return kvm_set_msr(vcpu, index, *data); +} + + +int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + switch (msr) { +#ifdef CONFIG_X86_64 + case MSR_EFER: + set_efer(vcpu, data); + break; +#endif + case MSR_IA32_MC0_STATUS: + pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n", + __FUNCTION__, data); + break; + case MSR_IA32_MCG_STATUS: + pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", + __FUNCTION__, data); + break; + case MSR_IA32_UCODE_REV: + case MSR_IA32_UCODE_WRITE: + case 0x200 ... 0x2ff: /* MTRRs */ + break; + case MSR_IA32_APICBASE: + kvm_set_apic_base(vcpu, data); + break; + case MSR_IA32_MISC_ENABLE: + vcpu->arch.ia32_misc_enable_msr = data; + break; + default: + pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_msr_common); + + +/* + * Reads an msr value (of 'msr_index') into 'pdata'. + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. + */ +int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +{ + return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); +} + +int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data; + + switch (msr) { + case 0xc0010010: /* SYSCFG */ + case 0xc0010015: /* HWCR */ + case MSR_IA32_PLATFORM_ID: + case MSR_IA32_P5_MC_ADDR: + case MSR_IA32_P5_MC_TYPE: + case MSR_IA32_MC0_CTL: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MCG_CAP: + case MSR_IA32_MC0_MISC: + case MSR_IA32_MC0_MISC+4: + case MSR_IA32_MC0_MISC+8: + case MSR_IA32_MC0_MISC+12: + case MSR_IA32_MC0_MISC+16: + case MSR_IA32_UCODE_REV: + case MSR_IA32_PERF_STATUS: + case MSR_IA32_EBL_CR_POWERON: + /* MTRR registers */ + case 0xfe: + case 0x200 ... 0x2ff: + data = 0; + break; + case 0xcd: /* fsb frequency */ + data = 3; + break; + case MSR_IA32_APICBASE: + data = kvm_get_apic_base(vcpu); + break; + case MSR_IA32_MISC_ENABLE: + data = vcpu->arch.ia32_misc_enable_msr; + break; +#ifdef CONFIG_X86_64 + case MSR_EFER: + data = vcpu->arch.shadow_efer; + break; +#endif + default: + pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_msr_common); + +/* + * Read or write a bunch of msrs. All parameters are kernel addresses. + * + * @return number of msrs set successfully. + */ +static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, + struct kvm_msr_entry *entries, + int (*do_msr)(struct kvm_vcpu *vcpu, + unsigned index, u64 *data)) +{ + int i; + + vcpu_load(vcpu); + + for (i = 0; i < msrs->nmsrs; ++i) + if (do_msr(vcpu, entries[i].index, &entries[i].data)) + break; + + vcpu_put(vcpu); + + return i; +} + +/* + * Read or write a bunch of msrs. Parameters are user addresses. + * + * @return number of msrs set successfully. + */ +static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, + int (*do_msr)(struct kvm_vcpu *vcpu, + unsigned index, u64 *data), + int writeback) +{ + struct kvm_msrs msrs; + struct kvm_msr_entry *entries; + int r, n; + unsigned size; + + r = -EFAULT; + if (copy_from_user(&msrs, user_msrs, sizeof msrs)) + goto out; + + r = -E2BIG; + if (msrs.nmsrs >= MAX_IO_MSRS) + goto out; + + r = -ENOMEM; + size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; + entries = vmalloc(size); + if (!entries) + goto out; + + r = -EFAULT; + if (copy_from_user(entries, user_msrs->entries, size)) + goto out_free; + + r = n = __msr_io(vcpu, &msrs, entries, do_msr); + if (r < 0) + goto out_free; + + r = -EFAULT; + if (writeback && copy_to_user(user_msrs->entries, entries, size)) + goto out_free; + + r = n; + +out_free: + vfree(entries); +out: + return r; +} + +/* + * Make sure that a cpu that is being hot-unplugged does not have any vcpus + * cached on it. + */ +void decache_vcpus_on_cpu(int cpu) +{ + struct kvm *vm; + struct kvm_vcpu *vcpu; + int i; + + spin_lock(&kvm_lock); + list_for_each_entry(vm, &vm_list, vm_list) + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + vcpu = vm->vcpus[i]; + if (!vcpu) + continue; + /* + * If the vcpu is locked, then it is running on some + * other cpu and therefore it is not cached on the + * cpu in question. + * + * If it's not locked, check the last cpu it executed + * on. + */ + if (mutex_trylock(&vcpu->mutex)) { + if (vcpu->cpu == cpu) { + kvm_x86_ops->vcpu_decache(vcpu); + vcpu->cpu = -1; + } + mutex_unlock(&vcpu->mutex); + } + } + spin_unlock(&kvm_lock); +} + +int kvm_dev_ioctl_check_extension(long ext) +{ + int r; + + switch (ext) { + case KVM_CAP_IRQCHIP: + case KVM_CAP_HLT: + case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: + case KVM_CAP_USER_MEMORY: + case KVM_CAP_SET_TSS_ADDR: + case KVM_CAP_EXT_CPUID: + r = 1; + break; + case KVM_CAP_VAPIC: + r = !kvm_x86_ops->cpu_has_accelerated_tpr(); + break; + default: + r = 0; + break; + } + return r; + +} + +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + long r; + + switch (ioctl) { + case KVM_GET_MSR_INDEX_LIST: { + struct kvm_msr_list __user *user_msr_list = argp; + struct kvm_msr_list msr_list; + unsigned n; + + r = -EFAULT; + if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list)) + goto out; + n = msr_list.nmsrs; + msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs); + if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) + goto out; + r = -E2BIG; + if (n < num_msrs_to_save) + goto out; + r = -EFAULT; + if (copy_to_user(user_msr_list->indices, &msrs_to_save, + num_msrs_to_save * sizeof(u32))) + goto out; + if (copy_to_user(user_msr_list->indices + + num_msrs_to_save * sizeof(u32), + &emulated_msrs, + ARRAY_SIZE(emulated_msrs) * sizeof(u32))) + goto out; + r = 0; + break; + } + default: + r = -EINVAL; + } +out: + return r; +} + +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + kvm_x86_ops->vcpu_load(vcpu, cpu); +} + +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->vcpu_put(vcpu); + kvm_put_guest_fpu(vcpu); +} + +static int is_efer_nx(void) +{ + u64 efer; + + rdmsrl(MSR_EFER, efer); + return efer & EFER_NX; +} + +static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_cpuid_entry2 *e, *entry; + + entry = NULL; + for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + e = &vcpu->arch.cpuid_entries[i]; + if (e->function == 0x80000001) { + entry = e; + break; + } + } + if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) { + entry->edx &= ~(1 << 20); + printk(KERN_INFO "kvm: guest NX capability removed\n"); + } +} + +/* when an old userspace process fills a new kernel module */ +static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid *cpuid, + struct kvm_cpuid_entry __user *entries) +{ + int r, i; + struct kvm_cpuid_entry *cpuid_entries; + + r = -E2BIG; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + goto out; + r = -ENOMEM; + cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent); + if (!cpuid_entries) + goto out; + r = -EFAULT; + if (copy_from_user(cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry))) + goto out_free; + for (i = 0; i < cpuid->nent; i++) { + vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; + vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; + vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx; + vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx; + vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx; + vcpu->arch.cpuid_entries[i].index = 0; + vcpu->arch.cpuid_entries[i].flags = 0; + vcpu->arch.cpuid_entries[i].padding[0] = 0; + vcpu->arch.cpuid_entries[i].padding[1] = 0; + vcpu->arch.cpuid_entries[i].padding[2] = 0; + } + vcpu->arch.cpuid_nent = cpuid->nent; + cpuid_fix_nx_cap(vcpu); + r = 0; + +out_free: + vfree(cpuid_entries); +out: + return r; +} + +static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + int r; + + r = -E2BIG; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + goto out; + r = -EFAULT; + if (copy_from_user(&vcpu->arch.cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry2))) + goto out; + vcpu->arch.cpuid_nent = cpuid->nent; + return 0; + +out: + return r; +} + +static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + int r; + + r = -E2BIG; + if (cpuid->nent < vcpu->arch.cpuid_nent) + goto out; + r = -EFAULT; + if (copy_to_user(entries, &vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) + goto out; + return 0; + +out: + cpuid->nent = vcpu->arch.cpuid_nent; + return r; +} + +static inline u32 bit(int bitno) +{ + return 1 << (bitno & 31); +} + +static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index) +{ + entry->function = function; + entry->index = index; + cpuid_count(entry->function, entry->index, + &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); + entry->flags = 0; +} + +static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index, int *nent, int maxnent) +{ + const u32 kvm_supported_word0_x86_features = bit(X86_FEATURE_FPU) | + bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) | + bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) | + bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) | + bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) | + bit(X86_FEATURE_SEP) | bit(X86_FEATURE_PGE) | + bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) | + bit(X86_FEATURE_CLFLSH) | bit(X86_FEATURE_MMX) | + bit(X86_FEATURE_FXSR) | bit(X86_FEATURE_XMM) | + bit(X86_FEATURE_XMM2) | bit(X86_FEATURE_SELFSNOOP); + const u32 kvm_supported_word1_x86_features = bit(X86_FEATURE_FPU) | + bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) | + bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) | + bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) | + bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) | + bit(X86_FEATURE_PGE) | + bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) | + bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) | + bit(X86_FEATURE_SYSCALL) | + (bit(X86_FEATURE_NX) && is_efer_nx()) | +#ifdef CONFIG_X86_64 + bit(X86_FEATURE_LM) | +#endif + bit(X86_FEATURE_MMXEXT) | + bit(X86_FEATURE_3DNOWEXT) | + bit(X86_FEATURE_3DNOW); + const u32 kvm_supported_word3_x86_features = + bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16); + const u32 kvm_supported_word6_x86_features = + bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY); + + /* all func 2 cpuid_count() should be called on the same cpu */ + get_cpu(); + do_cpuid_1_ent(entry, function, index); + ++*nent; + + switch (function) { + case 0: + entry->eax = min(entry->eax, (u32)0xb); + break; + case 1: + entry->edx &= kvm_supported_word0_x86_features; + entry->ecx &= kvm_supported_word3_x86_features; + break; + /* function 2 entries are STATEFUL. That is, repeated cpuid commands + * may return different values. This forces us to get_cpu() before + * issuing the first command, and also to emulate this annoying behavior + * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ + case 2: { + int t, times = entry->eax & 0xff; + + entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + for (t = 1; t < times && *nent < maxnent; ++t) { + do_cpuid_1_ent(&entry[t], function, 0); + entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + ++*nent; + } + break; + } + /* function 4 and 0xb have additional index. */ + case 4: { + int index, cache_type; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* read more entries until cache_type is zero */ + for (index = 1; *nent < maxnent; ++index) { + cache_type = entry[index - 1].eax & 0x1f; + if (!cache_type) + break; + do_cpuid_1_ent(&entry[index], function, index); + entry[index].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + } + break; + } + case 0xb: { + int index, level_type; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* read more entries until level_type is zero */ + for (index = 1; *nent < maxnent; ++index) { + level_type = entry[index - 1].ecx & 0xff; + if (!level_type) + break; + do_cpuid_1_ent(&entry[index], function, index); + entry[index].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + } + break; + } + case 0x80000000: + entry->eax = min(entry->eax, 0x8000001a); + break; + case 0x80000001: + entry->edx &= kvm_supported_word1_x86_features; + entry->ecx &= kvm_supported_word6_x86_features; + break; + } + put_cpu(); +} + +static int kvm_vm_ioctl_get_supported_cpuid(struct kvm *kvm, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + struct kvm_cpuid_entry2 *cpuid_entries; + int limit, nent = 0, r = -E2BIG; + u32 func; + + if (cpuid->nent < 1) + goto out; + r = -ENOMEM; + cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); + if (!cpuid_entries) + goto out; + + do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent); + limit = cpuid_entries[0].eax; + for (func = 1; func <= limit && nent < cpuid->nent; ++func) + do_cpuid_ent(&cpuid_entries[nent], func, 0, + &nent, cpuid->nent); + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent); + limit = cpuid_entries[nent - 1].eax; + for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) + do_cpuid_ent(&cpuid_entries[nent], func, 0, + &nent, cpuid->nent); + r = -EFAULT; + if (copy_to_user(entries, cpuid_entries, + nent * sizeof(struct kvm_cpuid_entry2))) + goto out_free; + cpuid->nent = nent; + r = 0; + +out_free: + vfree(cpuid_entries); +out: + return r; +} + +static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s) +{ + vcpu_load(vcpu); + memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); + vcpu_put(vcpu); + + return 0; +} + +static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s) +{ + vcpu_load(vcpu); + memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s); + kvm_apic_post_state_restore(vcpu); + vcpu_put(vcpu); + + return 0; +} + +static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq) +{ + if (irq->irq < 0 || irq->irq >= 256) + return -EINVAL; + if (irqchip_in_kernel(vcpu->kvm)) + return -ENXIO; + vcpu_load(vcpu); + + set_bit(irq->irq, vcpu->arch.irq_pending); + set_bit(irq->irq / BITS_PER_LONG, &vcpu->arch.irq_summary); + + vcpu_put(vcpu); + + return 0; +} + +static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, + struct kvm_tpr_access_ctl *tac) +{ + if (tac->flags) + return -EINVAL; + vcpu->arch.tpr_access_reporting = !!tac->enabled; + return 0; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + int r; + + switch (ioctl) { + case KVM_GET_LAPIC: { + struct kvm_lapic_state lapic; + + memset(&lapic, 0, sizeof lapic); + r = kvm_vcpu_ioctl_get_lapic(vcpu, &lapic); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &lapic, sizeof lapic)) + goto out; + r = 0; + break; + } + case KVM_SET_LAPIC: { + struct kvm_lapic_state lapic; + + r = -EFAULT; + if (copy_from_user(&lapic, argp, sizeof lapic)) + goto out; + r = kvm_vcpu_ioctl_set_lapic(vcpu, &lapic);; + if (r) + goto out; + r = 0; + break; + } + case KVM_INTERRUPT: { + struct kvm_interrupt irq; + + r = -EFAULT; + if (copy_from_user(&irq, argp, sizeof irq)) + goto out; + r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); + if (r) + goto out; + r = 0; + break; + } + case KVM_SET_CPUID: { + struct kvm_cpuid __user *cpuid_arg = argp; + struct kvm_cpuid cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); + if (r) + goto out; + break; + } + case KVM_SET_CPUID2: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, + cpuid_arg->entries); + if (r) + goto out; + break; + } + case KVM_GET_CPUID2: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid, + cpuid_arg->entries); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) + goto out; + r = 0; + break; + } + case KVM_GET_MSRS: + r = msr_io(vcpu, argp, kvm_get_msr, 1); + break; + case KVM_SET_MSRS: + r = msr_io(vcpu, argp, do_set_msr, 0); + break; + case KVM_TPR_ACCESS_REPORTING: { + struct kvm_tpr_access_ctl tac; + + r = -EFAULT; + if (copy_from_user(&tac, argp, sizeof tac)) + goto out; + r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &tac, sizeof tac)) + goto out; + r = 0; + break; + }; + case KVM_SET_VAPIC_ADDR: { + struct kvm_vapic_addr va; + + r = -EINVAL; + if (!irqchip_in_kernel(vcpu->kvm)) + goto out; + r = -EFAULT; + if (copy_from_user(&va, argp, sizeof va)) + goto out; + r = 0; + kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); + break; + } + default: + r = -EINVAL; + } +out: + return r; +} + +static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) +{ + int ret; + + if (addr > (unsigned int)(-3 * PAGE_SIZE)) + return -1; + ret = kvm_x86_ops->set_tss_addr(kvm, addr); + return ret; +} + +static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, + u32 kvm_nr_mmu_pages) +{ + if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) + return -EINVAL; + + down_write(¤t->mm->mmap_sem); + + kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); + kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; + + up_write(¤t->mm->mmap_sem); + return 0; +} + +static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +{ + return kvm->arch.n_alloc_mmu_pages; +} + +gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) +{ + int i; + struct kvm_mem_alias *alias; + + for (i = 0; i < kvm->arch.naliases; ++i) { + alias = &kvm->arch.aliases[i]; + if (gfn >= alias->base_gfn + && gfn < alias->base_gfn + alias->npages) + return alias->target_gfn + gfn - alias->base_gfn; + } + return gfn; +} + +/* + * Set a new alias region. Aliases map a portion of physical memory into + * another portion. This is useful for memory windows, for example the PC + * VGA region. + */ +static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, + struct kvm_memory_alias *alias) +{ + int r, n; + struct kvm_mem_alias *p; + + r = -EINVAL; + /* General sanity checks */ + if (alias->memory_size & (PAGE_SIZE - 1)) + goto out; + if (alias->guest_phys_addr & (PAGE_SIZE - 1)) + goto out; + if (alias->slot >= KVM_ALIAS_SLOTS) + goto out; + if (alias->guest_phys_addr + alias->memory_size + < alias->guest_phys_addr) + goto out; + if (alias->target_phys_addr + alias->memory_size + < alias->target_phys_addr) + goto out; + + down_write(¤t->mm->mmap_sem); + + p = &kvm->arch.aliases[alias->slot]; + p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; + p->npages = alias->memory_size >> PAGE_SHIFT; + p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT; + + for (n = KVM_ALIAS_SLOTS; n > 0; --n) + if (kvm->arch.aliases[n - 1].npages) + break; + kvm->arch.naliases = n; + + kvm_mmu_zap_all(kvm); + + up_write(¤t->mm->mmap_sem); + + return 0; + +out: + return r; +} + +static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +{ + int r; + + r = 0; + switch (chip->chip_id) { + case KVM_IRQCHIP_PIC_MASTER: + memcpy(&chip->chip.pic, + &pic_irqchip(kvm)->pics[0], + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_PIC_SLAVE: + memcpy(&chip->chip.pic, + &pic_irqchip(kvm)->pics[1], + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_IOAPIC: + memcpy(&chip->chip.ioapic, + ioapic_irqchip(kvm), + sizeof(struct kvm_ioapic_state)); + break; + default: + r = -EINVAL; + break; + } + return r; +} + +static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +{ + int r; + + r = 0; + switch (chip->chip_id) { + case KVM_IRQCHIP_PIC_MASTER: + memcpy(&pic_irqchip(kvm)->pics[0], + &chip->chip.pic, + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_PIC_SLAVE: + memcpy(&pic_irqchip(kvm)->pics[1], + &chip->chip.pic, + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_IOAPIC: + memcpy(ioapic_irqchip(kvm), + &chip->chip.ioapic, + sizeof(struct kvm_ioapic_state)); + break; + default: + r = -EINVAL; + break; + } + kvm_pic_update_irq(pic_irqchip(kvm)); + return r; +} + +/* + * Get (and clear) the dirty memory log for a memory slot. + */ +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log) +{ + int r; + int n; + struct kvm_memory_slot *memslot; + int is_dirty = 0; + + down_write(¤t->mm->mmap_sem); + + r = kvm_get_dirty_log(kvm, log, &is_dirty); + if (r) + goto out; + + /* If nothing is dirty, don't bother messing with page tables. */ + if (is_dirty) { + kvm_mmu_slot_remove_write_access(kvm, log->slot); + kvm_flush_remote_tlbs(kvm); + memslot = &kvm->memslots[log->slot]; + n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + memset(memslot->dirty_bitmap, 0, n); + } + r = 0; +out: + up_write(¤t->mm->mmap_sem); + return r; +} + +long kvm_arch_vm_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + void __user *argp = (void __user *)arg; + int r = -EINVAL; + + switch (ioctl) { + case KVM_SET_TSS_ADDR: + r = kvm_vm_ioctl_set_tss_addr(kvm, arg); + if (r < 0) + goto out; + break; + case KVM_SET_MEMORY_REGION: { + struct kvm_memory_region kvm_mem; + struct kvm_userspace_memory_region kvm_userspace_mem; + + r = -EFAULT; + if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem)) + goto out; + kvm_userspace_mem.slot = kvm_mem.slot; + kvm_userspace_mem.flags = kvm_mem.flags; + kvm_userspace_mem.guest_phys_addr = kvm_mem.guest_phys_addr; + kvm_userspace_mem.memory_size = kvm_mem.memory_size; + r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 0); + if (r) + goto out; + break; + } + case KVM_SET_NR_MMU_PAGES: + r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); + if (r) + goto out; + break; + case KVM_GET_NR_MMU_PAGES: + r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); + break; + case KVM_SET_MEMORY_ALIAS: { + struct kvm_memory_alias alias; + + r = -EFAULT; + if (copy_from_user(&alias, argp, sizeof alias)) + goto out; + r = kvm_vm_ioctl_set_memory_alias(kvm, &alias); + if (r) + goto out; + break; + } + case KVM_CREATE_IRQCHIP: + r = -ENOMEM; + kvm->arch.vpic = kvm_create_pic(kvm); + if (kvm->arch.vpic) { + r = kvm_ioapic_init(kvm); + if (r) { + kfree(kvm->arch.vpic); + kvm->arch.vpic = NULL; + goto out; + } + } else + goto out; + break; + case KVM_IRQ_LINE: { + struct kvm_irq_level irq_event; + + r = -EFAULT; + if (copy_from_user(&irq_event, argp, sizeof irq_event)) + goto out; + if (irqchip_in_kernel(kvm)) { + mutex_lock(&kvm->lock); + if (irq_event.irq < 16) + kvm_pic_set_irq(pic_irqchip(kvm), + irq_event.irq, + irq_event.level); + kvm_ioapic_set_irq(kvm->arch.vioapic, + irq_event.irq, + irq_event.level); + mutex_unlock(&kvm->lock); + r = 0; + } + break; + } + case KVM_GET_IRQCHIP: { + /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ + struct kvm_irqchip chip; + + r = -EFAULT; + if (copy_from_user(&chip, argp, sizeof chip)) + goto out; + r = -ENXIO; + if (!irqchip_in_kernel(kvm)) + goto out; + r = kvm_vm_ioctl_get_irqchip(kvm, &chip); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &chip, sizeof chip)) + goto out; + r = 0; + break; + } + case KVM_SET_IRQCHIP: { + /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ + struct kvm_irqchip chip; + + r = -EFAULT; + if (copy_from_user(&chip, argp, sizeof chip)) + goto out; + r = -ENXIO; + if (!irqchip_in_kernel(kvm)) + goto out; + r = kvm_vm_ioctl_set_irqchip(kvm, &chip); + if (r) + goto out; + r = 0; + break; + } + case KVM_GET_SUPPORTED_CPUID: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_vm_ioctl_get_supported_cpuid(kvm, &cpuid, + cpuid_arg->entries); + if (r) + goto out; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) + goto out; + r = 0; + break; + } + default: + ; + } +out: + return r; +} + +static void kvm_init_msr_list(void) +{ + u32 dummy[2]; + unsigned i, j; + + for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { + if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) + continue; + if (j < i) + msrs_to_save[j] = msrs_to_save[i]; + j++; + } + num_msrs_to_save = j; +} + +/* + * Only apic need an MMIO device hook, so shortcut now.. + */ +static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu, + gpa_t addr) +{ + struct kvm_io_device *dev; + + if (vcpu->arch.apic) { + dev = &vcpu->arch.apic->dev; + if (dev->in_range(dev, addr)) + return dev; + } + return NULL; +} + + +static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, + gpa_t addr) +{ + struct kvm_io_device *dev; + + dev = vcpu_find_pervcpu_dev(vcpu, addr); + if (dev == NULL) + dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr); + return dev; +} + +int emulator_read_std(unsigned long addr, + void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + void *data = val; + int r = X86EMUL_CONTINUE; + + down_read(¤t->mm->mmap_sem); + while (bytes) { + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + unsigned offset = addr & (PAGE_SIZE-1); + unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); + int ret; + + if (gpa == UNMAPPED_GVA) { + r = X86EMUL_PROPAGATE_FAULT; + goto out; + } + ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy); + if (ret < 0) { + r = X86EMUL_UNHANDLEABLE; + goto out; + } + + bytes -= tocopy; + data += tocopy; + addr += tocopy; + } +out: + up_read(¤t->mm->mmap_sem); + return r; +} +EXPORT_SYMBOL_GPL(emulator_read_std); + +static int emulator_read_emulated(unsigned long addr, + void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + struct kvm_io_device *mmio_dev; + gpa_t gpa; + + if (vcpu->mmio_read_completed) { + memcpy(val, vcpu->mmio_data, bytes); + vcpu->mmio_read_completed = 0; + return X86EMUL_CONTINUE; + } + + down_read(¤t->mm->mmap_sem); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + up_read(¤t->mm->mmap_sem); + + /* For APIC access vmexit */ + if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto mmio; + + if (emulator_read_std(addr, val, bytes, vcpu) + == X86EMUL_CONTINUE) + return X86EMUL_CONTINUE; + if (gpa == UNMAPPED_GVA) + return X86EMUL_PROPAGATE_FAULT; + +mmio: + /* + * Is this MMIO handled locally? + */ + mutex_lock(&vcpu->kvm->lock); + mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); + if (mmio_dev) { + kvm_iodevice_read(mmio_dev, gpa, bytes, val); + mutex_unlock(&vcpu->kvm->lock); + return X86EMUL_CONTINUE; + } + mutex_unlock(&vcpu->kvm->lock); + + vcpu->mmio_needed = 1; + vcpu->mmio_phys_addr = gpa; + vcpu->mmio_size = bytes; + vcpu->mmio_is_write = 0; + + return X86EMUL_UNHANDLEABLE; +} + +static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes) +{ + int ret; + + down_read(¤t->mm->mmap_sem); + ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); + if (ret < 0) { + up_read(¤t->mm->mmap_sem); + return 0; + } + kvm_mmu_pte_write(vcpu, gpa, val, bytes); + up_read(¤t->mm->mmap_sem); + return 1; +} + +static int emulator_write_emulated_onepage(unsigned long addr, + const void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + struct kvm_io_device *mmio_dev; + gpa_t gpa; + + down_read(¤t->mm->mmap_sem); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + up_read(¤t->mm->mmap_sem); + + if (gpa == UNMAPPED_GVA) { + kvm_inject_page_fault(vcpu, addr, 2); + return X86EMUL_PROPAGATE_FAULT; + } + + /* For APIC access vmexit */ + if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto mmio; + + if (emulator_write_phys(vcpu, gpa, val, bytes)) + return X86EMUL_CONTINUE; + +mmio: + /* + * Is this MMIO handled locally? + */ + mutex_lock(&vcpu->kvm->lock); + mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); + if (mmio_dev) { + kvm_iodevice_write(mmio_dev, gpa, bytes, val); + mutex_unlock(&vcpu->kvm->lock); + return X86EMUL_CONTINUE; + } + mutex_unlock(&vcpu->kvm->lock); + + vcpu->mmio_needed = 1; + vcpu->mmio_phys_addr = gpa; + vcpu->mmio_size = bytes; + vcpu->mmio_is_write = 1; + memcpy(vcpu->mmio_data, val, bytes); + + return X86EMUL_CONTINUE; +} + +int emulator_write_emulated(unsigned long addr, + const void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + /* Crossing a page boundary? */ + if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { + int rc, now; + + now = -addr & ~PAGE_MASK; + rc = emulator_write_emulated_onepage(addr, val, now, vcpu); + if (rc != X86EMUL_CONTINUE) + return rc; + addr += now; + val += now; + bytes -= now; + } + return emulator_write_emulated_onepage(addr, val, bytes, vcpu); +} +EXPORT_SYMBOL_GPL(emulator_write_emulated); + +static int emulator_cmpxchg_emulated(unsigned long addr, + const void *old, + const void *new, + unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + static int reported; + + if (!reported) { + reported = 1; + printk(KERN_WARNING "kvm: emulating exchange as write\n"); + } +#ifndef CONFIG_X86_64 + /* guests cmpxchg8b have to be emulated atomically */ + if (bytes == 8) { + gpa_t gpa; + struct page *page; + char *addr; + u64 val; + + down_read(¤t->mm->mmap_sem); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + + if (gpa == UNMAPPED_GVA || + (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto emul_write; + + if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + goto emul_write; + + val = *(u64 *)new; + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + addr = kmap_atomic(page, KM_USER0); + set_64bit((u64 *)(addr + offset_in_page(gpa)), val); + kunmap_atomic(addr, KM_USER0); + kvm_release_page_dirty(page); + emul_write: + up_read(¤t->mm->mmap_sem); + } +#endif + + return emulator_write_emulated(addr, new, bytes, vcpu); +} + +static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + return kvm_x86_ops->get_segment_base(vcpu, seg); +} + +int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) +{ + return X86EMUL_CONTINUE; +} + +int emulate_clts(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS); + return X86EMUL_CONTINUE; +} + +int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + + switch (dr) { + case 0 ... 3: + *dest = kvm_x86_ops->get_dr(vcpu, dr); + return X86EMUL_CONTINUE; + default: + pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr); + return X86EMUL_UNHANDLEABLE; + } +} + +int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +{ + unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; + int exception; + + kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception); + if (exception) { + /* FIXME: better handling */ + return X86EMUL_UNHANDLEABLE; + } + return X86EMUL_CONTINUE; +} + +void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) +{ + static int reported; + u8 opcodes[4]; + unsigned long rip = vcpu->arch.rip; + unsigned long rip_linear; + + rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); + + if (reported) + return; + + emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu); + + printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", + context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); + reported = 1; +} +EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); + +struct x86_emulate_ops emulate_ops = { + .read_std = emulator_read_std, + .read_emulated = emulator_read_emulated, + .write_emulated = emulator_write_emulated, + .cmpxchg_emulated = emulator_cmpxchg_emulated, +}; + +int emulate_instruction(struct kvm_vcpu *vcpu, + struct kvm_run *run, + unsigned long cr2, + u16 error_code, + int emulation_type) +{ + int r; + struct decode_cache *c; + + vcpu->arch.mmio_fault_cr2 = cr2; + kvm_x86_ops->cache_regs(vcpu); + + vcpu->mmio_is_write = 0; + vcpu->arch.pio.string = 0; + + if (!(emulation_type & EMULTYPE_NO_DECODE)) { + int cs_db, cs_l; + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + + vcpu->arch.emulate_ctxt.vcpu = vcpu; + vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.mode = + (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) + ? X86EMUL_MODE_REAL : cs_l + ? X86EMUL_MODE_PROT64 : cs_db + ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + + if (vcpu->arch.emulate_ctxt.mode == X86EMUL_MODE_PROT64) { + vcpu->arch.emulate_ctxt.cs_base = 0; + vcpu->arch.emulate_ctxt.ds_base = 0; + vcpu->arch.emulate_ctxt.es_base = 0; + vcpu->arch.emulate_ctxt.ss_base = 0; + } else { + vcpu->arch.emulate_ctxt.cs_base = + get_segment_base(vcpu, VCPU_SREG_CS); + vcpu->arch.emulate_ctxt.ds_base = + get_segment_base(vcpu, VCPU_SREG_DS); + vcpu->arch.emulate_ctxt.es_base = + get_segment_base(vcpu, VCPU_SREG_ES); + vcpu->arch.emulate_ctxt.ss_base = + get_segment_base(vcpu, VCPU_SREG_SS); + } + + vcpu->arch.emulate_ctxt.gs_base = + get_segment_base(vcpu, VCPU_SREG_GS); + vcpu->arch.emulate_ctxt.fs_base = + get_segment_base(vcpu, VCPU_SREG_FS); + + r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); + + /* Reject the instructions other than VMCALL/VMMCALL when + * try to emulate invalid opcode */ + c = &vcpu->arch.emulate_ctxt.decode; + if ((emulation_type & EMULTYPE_TRAP_UD) && + (!(c->twobyte && c->b == 0x01 && + (c->modrm_reg == 0 || c->modrm_reg == 3) && + c->modrm_mod == 3 && c->modrm_rm == 1))) + return EMULATE_FAIL; + + ++vcpu->stat.insn_emulation; + if (r) { + ++vcpu->stat.insn_emulation_fail; + if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) + return EMULATE_DONE; + return EMULATE_FAIL; + } + } + + r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); + + if (vcpu->arch.pio.string) + return EMULATE_DO_MMIO; + + if ((r || vcpu->mmio_is_write) && run) { + run->exit_reason = KVM_EXIT_MMIO; + run->mmio.phys_addr = vcpu->mmio_phys_addr; + memcpy(run->mmio.data, vcpu->mmio_data, 8); + run->mmio.len = vcpu->mmio_size; + run->mmio.is_write = vcpu->mmio_is_write; + } + + if (r) { + if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) + return EMULATE_DONE; + if (!vcpu->mmio_needed) { + kvm_report_emulation_failure(vcpu, "mmio"); + return EMULATE_FAIL; + } + return EMULATE_DO_MMIO; + } + + kvm_x86_ops->decache_regs(vcpu); + kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + + if (vcpu->mmio_is_write) { + vcpu->mmio_needed = 0; + return EMULATE_DO_MMIO; + } + + return EMULATE_DONE; +} +EXPORT_SYMBOL_GPL(emulate_instruction); + +static void free_pio_guest_pages(struct kvm_vcpu *vcpu) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(vcpu->arch.pio.guest_pages); ++i) + if (vcpu->arch.pio.guest_pages[i]) { + kvm_release_page_dirty(vcpu->arch.pio.guest_pages[i]); + vcpu->arch.pio.guest_pages[i] = NULL; + } +} + +static int pio_copy_data(struct kvm_vcpu *vcpu) +{ + void *p = vcpu->arch.pio_data; + void *q; + unsigned bytes; + int nr_pages = vcpu->arch.pio.guest_pages[1] ? 2 : 1; + + q = vmap(vcpu->arch.pio.guest_pages, nr_pages, VM_READ|VM_WRITE, + PAGE_KERNEL); + if (!q) { + free_pio_guest_pages(vcpu); + return -ENOMEM; + } + q += vcpu->arch.pio.guest_page_offset; + bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; + if (vcpu->arch.pio.in) + memcpy(q, p, bytes); + else + memcpy(p, q, bytes); + q -= vcpu->arch.pio.guest_page_offset; + vunmap(q); + free_pio_guest_pages(vcpu); + return 0; +} + +int complete_pio(struct kvm_vcpu *vcpu) +{ + struct kvm_pio_request *io = &vcpu->arch.pio; + long delta; + int r; + + kvm_x86_ops->cache_regs(vcpu); + + if (!io->string) { + if (io->in) + memcpy(&vcpu->arch.regs[VCPU_REGS_RAX], vcpu->arch.pio_data, + io->size); + } else { + if (io->in) { + r = pio_copy_data(vcpu); + if (r) { + kvm_x86_ops->cache_regs(vcpu); + return r; + } + } + + delta = 1; + if (io->rep) { + delta *= io->cur_count; + /* + * The size of the register should really depend on + * current address size. + */ + vcpu->arch.regs[VCPU_REGS_RCX] -= delta; + } + if (io->down) + delta = -delta; + delta *= io->size; + if (io->in) + vcpu->arch.regs[VCPU_REGS_RDI] += delta; + else + vcpu->arch.regs[VCPU_REGS_RSI] += delta; + } + + kvm_x86_ops->decache_regs(vcpu); + + io->count -= io->cur_count; + io->cur_count = 0; + + return 0; +} + +static void kernel_pio(struct kvm_io_device *pio_dev, + struct kvm_vcpu *vcpu, + void *pd) +{ + /* TODO: String I/O for in kernel device */ + + mutex_lock(&vcpu->kvm->lock); + if (vcpu->arch.pio.in) + kvm_iodevice_read(pio_dev, vcpu->arch.pio.port, + vcpu->arch.pio.size, + pd); + else + kvm_iodevice_write(pio_dev, vcpu->arch.pio.port, + vcpu->arch.pio.size, + pd); + mutex_unlock(&vcpu->kvm->lock); +} + +static void pio_string_write(struct kvm_io_device *pio_dev, + struct kvm_vcpu *vcpu) +{ + struct kvm_pio_request *io = &vcpu->arch.pio; + void *pd = vcpu->arch.pio_data; + int i; + + mutex_lock(&vcpu->kvm->lock); + for (i = 0; i < io->cur_count; i++) { + kvm_iodevice_write(pio_dev, io->port, + io->size, + pd); + pd += io->size; + } + mutex_unlock(&vcpu->kvm->lock); +} + +static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu, + gpa_t addr) +{ + return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr); +} + +int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, + int size, unsigned port) +{ + struct kvm_io_device *pio_dev; + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; + vcpu->run->io.size = vcpu->arch.pio.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1; + vcpu->run->io.port = vcpu->arch.pio.port = port; + vcpu->arch.pio.in = in; + vcpu->arch.pio.string = 0; + vcpu->arch.pio.down = 0; + vcpu->arch.pio.guest_page_offset = 0; + vcpu->arch.pio.rep = 0; + + kvm_x86_ops->cache_regs(vcpu); + memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4); + kvm_x86_ops->decache_regs(vcpu); + + kvm_x86_ops->skip_emulated_instruction(vcpu); + + pio_dev = vcpu_find_pio_dev(vcpu, port); + if (pio_dev) { + kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data); + complete_pio(vcpu); + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_emulate_pio); + +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, + int size, unsigned long count, int down, + gva_t address, int rep, unsigned port) +{ + unsigned now, in_page; + int i, ret = 0; + int nr_pages = 1; + struct page *page; + struct kvm_io_device *pio_dev; + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; + vcpu->run->io.size = vcpu->arch.pio.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count; + vcpu->run->io.port = vcpu->arch.pio.port = port; + vcpu->arch.pio.in = in; + vcpu->arch.pio.string = 1; + vcpu->arch.pio.down = down; + vcpu->arch.pio.guest_page_offset = offset_in_page(address); + vcpu->arch.pio.rep = rep; + + if (!count) { + kvm_x86_ops->skip_emulated_instruction(vcpu); + return 1; + } + + if (!down) + in_page = PAGE_SIZE - offset_in_page(address); + else + in_page = offset_in_page(address) + size; + now = min(count, (unsigned long)in_page / size); + if (!now) { + /* + * String I/O straddles page boundary. Pin two guest pages + * so that we satisfy atomicity constraints. Do just one + * transaction to avoid complexity. + */ + nr_pages = 2; + now = 1; + } + if (down) { + /* + * String I/O in reverse. Yuck. Kill the guest, fix later. + */ + pr_unimpl(vcpu, "guest string pio down\n"); + kvm_inject_gp(vcpu, 0); + return 1; + } + vcpu->run->io.count = now; + vcpu->arch.pio.cur_count = now; + + if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count) + kvm_x86_ops->skip_emulated_instruction(vcpu); + + for (i = 0; i < nr_pages; ++i) { + down_read(¤t->mm->mmap_sem); + page = gva_to_page(vcpu, address + i * PAGE_SIZE); + vcpu->arch.pio.guest_pages[i] = page; + up_read(¤t->mm->mmap_sem); + if (!page) { + kvm_inject_gp(vcpu, 0); + free_pio_guest_pages(vcpu); + return 1; + } + } + + pio_dev = vcpu_find_pio_dev(vcpu, port); + if (!vcpu->arch.pio.in) { + /* string PIO write */ + ret = pio_copy_data(vcpu); + if (ret >= 0 && pio_dev) { + pio_string_write(pio_dev, vcpu); + complete_pio(vcpu); + if (vcpu->arch.pio.count == 0) + ret = 1; + } + } else if (pio_dev) + pr_unimpl(vcpu, "no string pio read support yet, " + "port %x size %d count %ld\n", + port, size, count); + + return ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); + +int kvm_arch_init(void *opaque) +{ + int r; + struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; + + if (kvm_x86_ops) { + printk(KERN_ERR "kvm: already loaded the other module\n"); + r = -EEXIST; + goto out; + } + + if (!ops->cpu_has_kvm_support()) { + printk(KERN_ERR "kvm: no hardware support\n"); + r = -EOPNOTSUPP; + goto out; + } + if (ops->disabled_by_bios()) { + printk(KERN_ERR "kvm: disabled by bios\n"); + r = -EOPNOTSUPP; + goto out; + } + + r = kvm_mmu_module_init(); + if (r) + goto out; + + kvm_init_msr_list(); + + kvm_x86_ops = ops; + kvm_mmu_set_nonpresent_ptes(0ull, 0ull); + return 0; + +out: + return r; +} + +void kvm_arch_exit(void) +{ + kvm_x86_ops = NULL; + kvm_mmu_module_exit(); +} + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.halt_exits; + if (irqchip_in_kernel(vcpu->kvm)) { + vcpu->arch.mp_state = VCPU_MP_STATE_HALTED; + kvm_vcpu_block(vcpu); + if (vcpu->arch.mp_state != VCPU_MP_STATE_RUNNABLE) + return -EINTR; + return 1; + } else { + vcpu->run->exit_reason = KVM_EXIT_HLT; + return 0; + } +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt); + +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +{ + unsigned long nr, a0, a1, a2, a3, ret; + + kvm_x86_ops->cache_regs(vcpu); + + nr = vcpu->arch.regs[VCPU_REGS_RAX]; + a0 = vcpu->arch.regs[VCPU_REGS_RBX]; + a1 = vcpu->arch.regs[VCPU_REGS_RCX]; + a2 = vcpu->arch.regs[VCPU_REGS_RDX]; + a3 = vcpu->arch.regs[VCPU_REGS_RSI]; + + if (!is_long_mode(vcpu)) { + nr &= 0xFFFFFFFF; + a0 &= 0xFFFFFFFF; + a1 &= 0xFFFFFFFF; + a2 &= 0xFFFFFFFF; + a3 &= 0xFFFFFFFF; + } + + switch (nr) { + case KVM_HC_VAPIC_POLL_IRQ: + ret = 0; + break; + default: + ret = -KVM_ENOSYS; + break; + } + vcpu->arch.regs[VCPU_REGS_RAX] = ret; + kvm_x86_ops->decache_regs(vcpu); + return 0; +} +EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); + +int kvm_fix_hypercall(struct kvm_vcpu *vcpu) +{ + char instruction[3]; + int ret = 0; + + + /* + * Blow out the MMU to ensure that no other VCPU has an active mapping + * to ensure that the updated hypercall appears atomically across all + * VCPUs. + */ + kvm_mmu_zap_all(vcpu->kvm); + + kvm_x86_ops->cache_regs(vcpu); + kvm_x86_ops->patch_hypercall(vcpu, instruction); + if (emulator_write_emulated(vcpu->arch.rip, instruction, 3, vcpu) + != X86EMUL_CONTINUE) + ret = -EFAULT; + + return ret; +} + +static u64 mk_cr_64(u64 curr_cr, u32 new_val) +{ + return (curr_cr & ~((1ULL << 32) - 1)) | new_val; +} + +void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) +{ + struct descriptor_table dt = { limit, base }; + + kvm_x86_ops->set_gdt(vcpu, &dt); +} + +void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) +{ + struct descriptor_table dt = { limit, base }; + + kvm_x86_ops->set_idt(vcpu, &dt); +} + +void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, + unsigned long *rflags) +{ + lmsw(vcpu, msw); + *rflags = kvm_x86_ops->get_rflags(vcpu); +} + +unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) +{ + kvm_x86_ops->decache_cr4_guest_bits(vcpu); + switch (cr) { + case 0: + return vcpu->arch.cr0; + case 2: + return vcpu->arch.cr2; + case 3: + return vcpu->arch.cr3; + case 4: + return vcpu->arch.cr4; + case 8: + return get_cr8(vcpu); + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); + return 0; + } +} + +void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, + unsigned long *rflags) +{ + switch (cr) { + case 0: + set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); + *rflags = kvm_x86_ops->get_rflags(vcpu); + break; + case 2: + vcpu->arch.cr2 = val; + break; + case 3: + set_cr3(vcpu, val); + break; + case 4: + set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val)); + break; + case 8: + set_cr8(vcpu, val & 0xfUL); + break; + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); + } +} + +static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) +{ + struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; + int j, nent = vcpu->arch.cpuid_nent; + + e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; + /* when no next entry is found, the current entry[i] is reselected */ + for (j = i + 1; j == i; j = (j + 1) % nent) { + struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; + if (ej->function == e->function) { + ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + return j; + } + } + return 0; /* silence gcc, even though control never reaches here */ +} + +/* find an entry with matching function, matching index (if needed), and that + * should be read next (if it's stateful) */ +static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, + u32 function, u32 index) +{ + if (e->function != function) + return 0; + if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) + return 0; + if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && + !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) + return 0; + return 1; +} + +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + int i; + u32 function, index; + struct kvm_cpuid_entry2 *e, *best; + + kvm_x86_ops->cache_regs(vcpu); + function = vcpu->arch.regs[VCPU_REGS_RAX]; + index = vcpu->arch.regs[VCPU_REGS_RCX]; + vcpu->arch.regs[VCPU_REGS_RAX] = 0; + vcpu->arch.regs[VCPU_REGS_RBX] = 0; + vcpu->arch.regs[VCPU_REGS_RCX] = 0; + vcpu->arch.regs[VCPU_REGS_RDX] = 0; + best = NULL; + for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + e = &vcpu->arch.cpuid_entries[i]; + if (is_matching_cpuid_entry(e, function, index)) { + if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) + move_to_next_stateful_cpuid_entry(vcpu, i); + best = e; + break; + } + /* + * Both basic or both extended? + */ + if (((e->function ^ function) & 0x80000000) == 0) + if (!best || e->function > best->function) + best = e; + } + if (best) { + vcpu->arch.regs[VCPU_REGS_RAX] = best->eax; + vcpu->arch.regs[VCPU_REGS_RBX] = best->ebx; + vcpu->arch.regs[VCPU_REGS_RCX] = best->ecx; + vcpu->arch.regs[VCPU_REGS_RDX] = best->edx; + } + kvm_x86_ops->decache_regs(vcpu); + kvm_x86_ops->skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); + +/* + * Check if userspace requested an interrupt window, and that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) +{ + return (!vcpu->arch.irq_summary && + kvm_run->request_interrupt_window && + vcpu->arch.interrupt_window_open && + (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF)); +} + +static void post_kvm_run_save(struct kvm_vcpu *vcpu, + struct kvm_run *kvm_run) +{ + kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->cr8 = get_cr8(vcpu); + kvm_run->apic_base = kvm_get_apic_base(vcpu); + if (irqchip_in_kernel(vcpu->kvm)) + kvm_run->ready_for_interrupt_injection = 1; + else + kvm_run->ready_for_interrupt_injection = + (vcpu->arch.interrupt_window_open && + vcpu->arch.irq_summary == 0); +} + +static void vapic_enter(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + struct page *page; + + if (!apic || !apic->vapic_addr) + return; + + down_read(¤t->mm->mmap_sem); + page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); + vcpu->arch.apic->vapic_page = page; + up_read(¤t->mm->mmap_sem); +} + +static void vapic_exit(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (!apic || !apic->vapic_addr) + return; + + kvm_release_page_dirty(apic->vapic_page); + mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); +} + +static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + int r; + + if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) { + pr_debug("vcpu %d received sipi with vector # %x\n", + vcpu->vcpu_id, vcpu->arch.sipi_vector); + kvm_lapic_reset(vcpu); + r = kvm_x86_ops->vcpu_reset(vcpu); + if (r) + return r; + vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + } + + vapic_enter(vcpu); + +preempted: + if (vcpu->guest_debug.enabled) + kvm_x86_ops->guest_debug_pre(vcpu); + +again: + r = kvm_mmu_reload(vcpu); + if (unlikely(r)) + goto out; + + if (vcpu->requests) { + if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) + __kvm_migrate_apic_timer(vcpu); + if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, + &vcpu->requests)) { + kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; + r = 0; + goto out; + } + } + + kvm_inject_pending_timer_irqs(vcpu); + + preempt_disable(); + + kvm_x86_ops->prepare_guest_switch(vcpu); + kvm_load_guest_fpu(vcpu); + + local_irq_disable(); + + if (need_resched()) { + local_irq_enable(); + preempt_enable(); + r = 1; + goto out; + } + + if (signal_pending(current)) { + local_irq_enable(); + preempt_enable(); + r = -EINTR; + kvm_run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.signal_exits; + goto out; + } + + if (vcpu->arch.exception.pending) + __queue_exception(vcpu); + else if (irqchip_in_kernel(vcpu->kvm)) + kvm_x86_ops->inject_pending_irq(vcpu); + else + kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run); + + kvm_lapic_sync_to_vapic(vcpu); + + vcpu->guest_mode = 1; + kvm_guest_enter(); + + if (vcpu->requests) + if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) + kvm_x86_ops->tlb_flush(vcpu); + + kvm_x86_ops->run(vcpu, kvm_run); + + vcpu->guest_mode = 0; + local_irq_enable(); + + ++vcpu->stat.exits; + + /* + * We must have an instruction between local_irq_enable() and + * kvm_guest_exit(), so the timer interrupt isn't delayed by + * the interrupt shadow. The stat.exits increment will do nicely. + * But we need to prevent reordering, hence this barrier(): + */ + barrier(); + + kvm_guest_exit(); + + preempt_enable(); + + /* + * Profile KVM exit RIPs: + */ + if (unlikely(prof_on == KVM_PROFILING)) { + kvm_x86_ops->cache_regs(vcpu); + profile_hit(KVM_PROFILING, (void *)vcpu->arch.rip); + } + + if (vcpu->arch.exception.pending && kvm_x86_ops->exception_injected(vcpu)) + vcpu->arch.exception.pending = false; + + kvm_lapic_sync_from_vapic(vcpu); + + r = kvm_x86_ops->handle_exit(kvm_run, vcpu); + + if (r > 0) { + if (dm_request_for_irq_injection(vcpu, kvm_run)) { + r = -EINTR; + kvm_run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.request_irq_exits; + goto out; + } + if (!need_resched()) + goto again; + } + +out: + if (r > 0) { + kvm_resched(vcpu); + goto preempted; + } + + post_kvm_run_save(vcpu, kvm_run); + + vapic_exit(vcpu); + + return r; +} + +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + int r; + sigset_t sigsaved; + + vcpu_load(vcpu); + + if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_UNINITIALIZED)) { + kvm_vcpu_block(vcpu); + vcpu_put(vcpu); + return -EAGAIN; + } + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); + + /* re-sync apic's tpr */ + if (!irqchip_in_kernel(vcpu->kvm)) + set_cr8(vcpu, kvm_run->cr8); + + if (vcpu->arch.pio.cur_count) { + r = complete_pio(vcpu); + if (r) + goto out; + } +#if CONFIG_HAS_IOMEM + if (vcpu->mmio_needed) { + memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); + vcpu->mmio_read_completed = 1; + vcpu->mmio_needed = 0; + r = emulate_instruction(vcpu, kvm_run, + vcpu->arch.mmio_fault_cr2, 0, + EMULTYPE_NO_DECODE); + if (r == EMULATE_DO_MMIO) { + /* + * Read-modify-write. Back to userspace. + */ + r = 0; + goto out; + } + } +#endif + if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) { + kvm_x86_ops->cache_regs(vcpu); + vcpu->arch.regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret; + kvm_x86_ops->decache_regs(vcpu); + } + + r = __vcpu_run(vcpu, kvm_run); + +out: + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + vcpu_put(vcpu); + return r; +} + +int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_load(vcpu); + + kvm_x86_ops->cache_regs(vcpu); + + regs->rax = vcpu->arch.regs[VCPU_REGS_RAX]; + regs->rbx = vcpu->arch.regs[VCPU_REGS_RBX]; + regs->rcx = vcpu->arch.regs[VCPU_REGS_RCX]; + regs->rdx = vcpu->arch.regs[VCPU_REGS_RDX]; + regs->rsi = vcpu->arch.regs[VCPU_REGS_RSI]; + regs->rdi = vcpu->arch.regs[VCPU_REGS_RDI]; + regs->rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + regs->rbp = vcpu->arch.regs[VCPU_REGS_RBP]; +#ifdef CONFIG_X86_64 + regs->r8 = vcpu->arch.regs[VCPU_REGS_R8]; + regs->r9 = vcpu->arch.regs[VCPU_REGS_R9]; + regs->r10 = vcpu->arch.regs[VCPU_REGS_R10]; + regs->r11 = vcpu->arch.regs[VCPU_REGS_R11]; + regs->r12 = vcpu->arch.regs[VCPU_REGS_R12]; + regs->r13 = vcpu->arch.regs[VCPU_REGS_R13]; + regs->r14 = vcpu->arch.regs[VCPU_REGS_R14]; + regs->r15 = vcpu->arch.regs[VCPU_REGS_R15]; +#endif + + regs->rip = vcpu->arch.rip; + regs->rflags = kvm_x86_ops->get_rflags(vcpu); + + /* + * Don't leak debug flags in case they were set for guest debugging + */ + if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) + regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + + vcpu_put(vcpu); + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_load(vcpu); + + vcpu->arch.regs[VCPU_REGS_RAX] = regs->rax; + vcpu->arch.regs[VCPU_REGS_RBX] = regs->rbx; + vcpu->arch.regs[VCPU_REGS_RCX] = regs->rcx; + vcpu->arch.regs[VCPU_REGS_RDX] = regs->rdx; + vcpu->arch.regs[VCPU_REGS_RSI] = regs->rsi; + vcpu->arch.regs[VCPU_REGS_RDI] = regs->rdi; + vcpu->arch.regs[VCPU_REGS_RSP] = regs->rsp; + vcpu->arch.regs[VCPU_REGS_RBP] = regs->rbp; +#ifdef CONFIG_X86_64 + vcpu->arch.regs[VCPU_REGS_R8] = regs->r8; + vcpu->arch.regs[VCPU_REGS_R9] = regs->r9; + vcpu->arch.regs[VCPU_REGS_R10] = regs->r10; + vcpu->arch.regs[VCPU_REGS_R11] = regs->r11; + vcpu->arch.regs[VCPU_REGS_R12] = regs->r12; + vcpu->arch.regs[VCPU_REGS_R13] = regs->r13; + vcpu->arch.regs[VCPU_REGS_R14] = regs->r14; + vcpu->arch.regs[VCPU_REGS_R15] = regs->r15; +#endif + + vcpu->arch.rip = regs->rip; + kvm_x86_ops->set_rflags(vcpu, regs->rflags); + + kvm_x86_ops->decache_regs(vcpu); + + vcpu_put(vcpu); + + return 0; +} + +static void get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + return kvm_x86_ops->get_segment(vcpu, var, seg); +} + +void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +{ + struct kvm_segment cs; + + get_segment(vcpu, &cs, VCPU_SREG_CS); + *db = cs.db; + *l = cs.l; +} +EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + struct descriptor_table dt; + int pending_vec; + + vcpu_load(vcpu); + + get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); + get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); + get_segment(vcpu, &sregs->es, VCPU_SREG_ES); + get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); + get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); + get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); + + get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); + get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + + kvm_x86_ops->get_idt(vcpu, &dt); + sregs->idt.limit = dt.limit; + sregs->idt.base = dt.base; + kvm_x86_ops->get_gdt(vcpu, &dt); + sregs->gdt.limit = dt.limit; + sregs->gdt.base = dt.base; + + kvm_x86_ops->decache_cr4_guest_bits(vcpu); + sregs->cr0 = vcpu->arch.cr0; + sregs->cr2 = vcpu->arch.cr2; + sregs->cr3 = vcpu->arch.cr3; + sregs->cr4 = vcpu->arch.cr4; + sregs->cr8 = get_cr8(vcpu); + sregs->efer = vcpu->arch.shadow_efer; + sregs->apic_base = kvm_get_apic_base(vcpu); + + if (irqchip_in_kernel(vcpu->kvm)) { + memset(sregs->interrupt_bitmap, 0, + sizeof sregs->interrupt_bitmap); + pending_vec = kvm_x86_ops->get_irq(vcpu); + if (pending_vec >= 0) + set_bit(pending_vec, + (unsigned long *)sregs->interrupt_bitmap); + } else + memcpy(sregs->interrupt_bitmap, vcpu->arch.irq_pending, + sizeof sregs->interrupt_bitmap); + + vcpu_put(vcpu); + + return 0; +} + +static void set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + return kvm_x86_ops->set_segment(vcpu, var, seg); +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + int mmu_reset_needed = 0; + int i, pending_vec, max_bits; + struct descriptor_table dt; + + vcpu_load(vcpu); + + dt.limit = sregs->idt.limit; + dt.base = sregs->idt.base; + kvm_x86_ops->set_idt(vcpu, &dt); + dt.limit = sregs->gdt.limit; + dt.base = sregs->gdt.base; + kvm_x86_ops->set_gdt(vcpu, &dt); + + vcpu->arch.cr2 = sregs->cr2; + mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3; + vcpu->arch.cr3 = sregs->cr3; + + set_cr8(vcpu, sregs->cr8); + + mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer; +#ifdef CONFIG_X86_64 + kvm_x86_ops->set_efer(vcpu, sregs->efer); +#endif + kvm_set_apic_base(vcpu, sregs->apic_base); + + kvm_x86_ops->decache_cr4_guest_bits(vcpu); + + mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0; + vcpu->arch.cr0 = sregs->cr0; + kvm_x86_ops->set_cr0(vcpu, sregs->cr0); + + mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; + kvm_x86_ops->set_cr4(vcpu, sregs->cr4); + if (!is_long_mode(vcpu) && is_pae(vcpu)) + load_pdptrs(vcpu, vcpu->arch.cr3); + + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + + if (!irqchip_in_kernel(vcpu->kvm)) { + memcpy(vcpu->arch.irq_pending, sregs->interrupt_bitmap, + sizeof vcpu->arch.irq_pending); + vcpu->arch.irq_summary = 0; + for (i = 0; i < ARRAY_SIZE(vcpu->arch.irq_pending); ++i) + if (vcpu->arch.irq_pending[i]) + __set_bit(i, &vcpu->arch.irq_summary); + } else { + max_bits = (sizeof sregs->interrupt_bitmap) << 3; + pending_vec = find_first_bit( + (const unsigned long *)sregs->interrupt_bitmap, + max_bits); + /* Only pending external irq is handled here */ + if (pending_vec < max_bits) { + kvm_x86_ops->set_irq(vcpu, pending_vec); + pr_debug("Set back pending irq %d\n", + pending_vec); + } + } + + set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); + set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); + set_segment(vcpu, &sregs->es, VCPU_SREG_ES); + set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); + set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); + set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); + + set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); + set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + + vcpu_put(vcpu); + + return 0; +} + +int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, + struct kvm_debug_guest *dbg) +{ + int r; + + vcpu_load(vcpu); + + r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + + vcpu_put(vcpu); + + return r; +} + +/* + * fxsave fpu state. Taken from x86_64/processor.h. To be killed when + * we have asm/x86/processor.h + */ +struct fxsave { + u16 cwd; + u16 swd; + u16 twd; + u16 fop; + u64 rip; + u64 rdp; + u32 mxcsr; + u32 mxcsr_mask; + u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ +#ifdef CONFIG_X86_64 + u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */ +#else + u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ +#endif +}; + +/* + * Translate a guest virtual address to a guest physical address. + */ +int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, + struct kvm_translation *tr) +{ + unsigned long vaddr = tr->linear_address; + gpa_t gpa; + + vcpu_load(vcpu); + down_read(¤t->mm->mmap_sem); + gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr); + up_read(¤t->mm->mmap_sem); + tr->physical_address = gpa; + tr->valid = gpa != UNMAPPED_GVA; + tr->writeable = 1; + tr->usermode = 0; + vcpu_put(vcpu); + + return 0; +} + +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image; + + vcpu_load(vcpu); + + memcpy(fpu->fpr, fxsave->st_space, 128); + fpu->fcw = fxsave->cwd; + fpu->fsw = fxsave->swd; + fpu->ftwx = fxsave->twd; + fpu->last_opcode = fxsave->fop; + fpu->last_ip = fxsave->rip; + fpu->last_dp = fxsave->rdp; + memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); + + vcpu_put(vcpu); + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image; + + vcpu_load(vcpu); + + memcpy(fxsave->st_space, fpu->fpr, 128); + fxsave->cwd = fpu->fcw; + fxsave->swd = fpu->fsw; + fxsave->twd = fpu->ftwx; + fxsave->fop = fpu->last_opcode; + fxsave->rip = fpu->last_ip; + fxsave->rdp = fpu->last_dp; + memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); + + vcpu_put(vcpu); + + return 0; +} + +void fx_init(struct kvm_vcpu *vcpu) +{ + unsigned after_mxcsr_mask; + + /* Initialize guest FPU by resetting ours and saving into guest's */ + preempt_disable(); + fx_save(&vcpu->arch.host_fx_image); + fpu_init(); + fx_save(&vcpu->arch.guest_fx_image); + fx_restore(&vcpu->arch.host_fx_image); + preempt_enable(); + + vcpu->arch.cr0 |= X86_CR0_ET; + after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space); + vcpu->arch.guest_fx_image.mxcsr = 0x1f80; + memset((void *)&vcpu->arch.guest_fx_image + after_mxcsr_mask, + 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask); +} +EXPORT_SYMBOL_GPL(fx_init); + +void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) +{ + if (!vcpu->fpu_active || vcpu->guest_fpu_loaded) + return; + + vcpu->guest_fpu_loaded = 1; + fx_save(&vcpu->arch.host_fx_image); + fx_restore(&vcpu->arch.guest_fx_image); +} +EXPORT_SYMBOL_GPL(kvm_load_guest_fpu); + +void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) +{ + if (!vcpu->guest_fpu_loaded) + return; + + vcpu->guest_fpu_loaded = 0; + fx_save(&vcpu->arch.guest_fx_image); + fx_restore(&vcpu->arch.host_fx_image); + ++vcpu->stat.fpu_reload; +} +EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); + +void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->vcpu_free(vcpu); +} + +struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, + unsigned int id) +{ + return kvm_x86_ops->vcpu_create(kvm, id); +} + +int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +{ + int r; + + /* We do fxsave: this must be aligned. */ + BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF); + + vcpu_load(vcpu); + r = kvm_arch_vcpu_reset(vcpu); + if (r == 0) + r = kvm_mmu_setup(vcpu); + vcpu_put(vcpu); + if (r < 0) + goto free_vcpu; + + return 0; +free_vcpu: + kvm_x86_ops->vcpu_free(vcpu); + return r; +} + +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + vcpu_load(vcpu); + kvm_mmu_unload(vcpu); + vcpu_put(vcpu); + + kvm_x86_ops->vcpu_free(vcpu); +} + +int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) +{ + return kvm_x86_ops->vcpu_reset(vcpu); +} + +void kvm_arch_hardware_enable(void *garbage) +{ + kvm_x86_ops->hardware_enable(garbage); +} + +void kvm_arch_hardware_disable(void *garbage) +{ + kvm_x86_ops->hardware_disable(garbage); +} + +int kvm_arch_hardware_setup(void) +{ + return kvm_x86_ops->hardware_setup(); +} + +void kvm_arch_hardware_unsetup(void) +{ + kvm_x86_ops->hardware_unsetup(); +} + +void kvm_arch_check_processor_compat(void *rtn) +{ + kvm_x86_ops->check_processor_compatibility(rtn); +} + +int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct page *page; + struct kvm *kvm; + int r; + + BUG_ON(vcpu->kvm == NULL); + kvm = vcpu->kvm; + + vcpu->arch.mmu.root_hpa = INVALID_PAGE; + if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0) + vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + else + vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED; + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) { + r = -ENOMEM; + goto fail; + } + vcpu->arch.pio_data = page_address(page); + + r = kvm_mmu_create(vcpu); + if (r < 0) + goto fail_free_pio_data; + + if (irqchip_in_kernel(kvm)) { + r = kvm_create_lapic(vcpu); + if (r < 0) + goto fail_mmu_destroy; + } + + return 0; + +fail_mmu_destroy: + kvm_mmu_destroy(vcpu); +fail_free_pio_data: + free_page((unsigned long)vcpu->arch.pio_data); +fail: + return r; +} + +void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + kvm_free_lapic(vcpu); + kvm_mmu_destroy(vcpu); + free_page((unsigned long)vcpu->arch.pio_data); +} + +struct kvm *kvm_arch_create_vm(void) +{ + struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + + if (!kvm) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + + return kvm; +} + +static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) +{ + vcpu_load(vcpu); + kvm_mmu_unload(vcpu); + vcpu_put(vcpu); +} + +static void kvm_free_vcpus(struct kvm *kvm) +{ + unsigned int i; + + /* + * Unpin any mmu pages first. + */ + for (i = 0; i < KVM_MAX_VCPUS; ++i) + if (kvm->vcpus[i]) + kvm_unload_vcpu_mmu(kvm->vcpus[i]); + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + if (kvm->vcpus[i]) { + kvm_arch_vcpu_free(kvm->vcpus[i]); + kvm->vcpus[i] = NULL; + } + } + +} + +void kvm_arch_destroy_vm(struct kvm *kvm) +{ + kfree(kvm->arch.vpic); + kfree(kvm->arch.vioapic); + kvm_free_vcpus(kvm); + kvm_free_physmem(kvm); + kfree(kvm); +} + +int kvm_arch_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + int npages = mem->memory_size >> PAGE_SHIFT; + struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot]; + + /*To keep backward compatibility with older userspace, + *x86 needs to hanlde !user_alloc case. + */ + if (!user_alloc) { + if (npages && !old.rmap) { + memslot->userspace_addr = do_mmap(NULL, 0, + npages * PAGE_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, + 0); + + if (IS_ERR((void *)memslot->userspace_addr)) + return PTR_ERR((void *)memslot->userspace_addr); + } else { + if (!old.user_alloc && old.rmap) { + int ret; + + ret = do_munmap(current->mm, old.userspace_addr, + old.npages * PAGE_SIZE); + if (ret < 0) + printk(KERN_WARNING + "kvm_vm_ioctl_set_memory_region: " + "failed to munmap memory\n"); + } + } + } + + if (!kvm->arch.n_requested_mmu_pages) { + unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + } + + kvm_mmu_slot_remove_write_access(kvm, mem->slot); + kvm_flush_remote_tlbs(kvm); + + return 0; +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE + || vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED; +} + +static void vcpu_kick_intr(void *info) +{ +#ifdef DEBUG + struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info; + printk(KERN_DEBUG "vcpu_kick_intr %p \n", vcpu); +#endif +} + +void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +{ + int ipi_pcpu = vcpu->cpu; + + if (waitqueue_active(&vcpu->wq)) { + wake_up_interruptible(&vcpu->wq); + ++vcpu->stat.halt_wakeup; + } + if (vcpu->guest_mode) + smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0); +} diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c new file mode 100644 index 00000000000..79586003397 --- /dev/null +++ b/arch/x86/kvm/x86_emulate.c @@ -0,0 +1,1912 @@ +/****************************************************************************** + * x86_emulate.c + * + * Generic x86 (32-bit and 64-bit) instruction decoder and emulator. + * + * Copyright (c) 2005 Keir Fraser + * + * Linux coding style, mod r/m decoder, segment base fixes, real-mode + * privileged instructions: + * + * Copyright (C) 2006 Qumranet + * + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 + */ + +#ifndef __KERNEL__ +#include <stdio.h> +#include <stdint.h> +#include <public/xen.h> +#define DPRINTF(_f, _a ...) printf(_f , ## _a) +#else +#include <linux/kvm_host.h> +#define DPRINTF(x...) do {} while (0) +#endif +#include <linux/module.h> +#include <asm/kvm_x86_emulate.h> + +/* + * Opcode effective-address decode tables. + * Note that we only emulate instructions that have at least one memory + * operand (excluding implicit stack references). We assume that stack + * references and instruction fetches will never occur in special memory + * areas that require emulation. So, for example, 'mov <imm>,<reg>' need + * not be handled. + */ + +/* Operand sizes: 8-bit operands or specified/overridden size. */ +#define ByteOp (1<<0) /* 8-bit operands. */ +/* Destination operand type. */ +#define ImplicitOps (1<<1) /* Implicit in opcode. No generic decode. */ +#define DstReg (2<<1) /* Register operand. */ +#define DstMem (3<<1) /* Memory operand. */ +#define DstMask (3<<1) +/* Source operand type. */ +#define SrcNone (0<<3) /* No source operand. */ +#define SrcImplicit (0<<3) /* Source operand is implicit in the opcode. */ +#define SrcReg (1<<3) /* Register operand. */ +#define SrcMem (2<<3) /* Memory operand. */ +#define SrcMem16 (3<<3) /* Memory operand (16-bit). */ +#define SrcMem32 (4<<3) /* Memory operand (32-bit). */ +#define SrcImm (5<<3) /* Immediate operand. */ +#define SrcImmByte (6<<3) /* 8-bit sign-extended immediate operand. */ +#define SrcMask (7<<3) +/* Generic ModRM decode. */ +#define ModRM (1<<6) +/* Destination is only written; never read. */ +#define Mov (1<<7) +#define BitOp (1<<8) +#define MemAbs (1<<9) /* Memory operand is absolute displacement */ +#define String (1<<10) /* String instruction (rep capable) */ +#define Stack (1<<11) /* Stack instruction (push/pop) */ + +static u16 opcode_table[256] = { + /* 0x00 - 0x07 */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + 0, 0, 0, 0, + /* 0x08 - 0x0F */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + 0, 0, 0, 0, + /* 0x10 - 0x17 */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + 0, 0, 0, 0, + /* 0x18 - 0x1F */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + 0, 0, 0, 0, + /* 0x20 - 0x27 */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + SrcImmByte, SrcImm, 0, 0, + /* 0x28 - 0x2F */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + 0, 0, 0, 0, + /* 0x30 - 0x37 */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + 0, 0, 0, 0, + /* 0x38 - 0x3F */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, + 0, 0, 0, 0, + /* 0x40 - 0x47 */ + DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, + /* 0x48 - 0x4F */ + DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, + /* 0x50 - 0x57 */ + SrcReg | Stack, SrcReg | Stack, SrcReg | Stack, SrcReg | Stack, + SrcReg | Stack, SrcReg | Stack, SrcReg | Stack, SrcReg | Stack, + /* 0x58 - 0x5F */ + DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, + DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, + /* 0x60 - 0x67 */ + 0, 0, 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , + 0, 0, 0, 0, + /* 0x68 - 0x6F */ + 0, 0, ImplicitOps | Mov | Stack, 0, + SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* insb, insw/insd */ + SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* outsb, outsw/outsd */ + /* 0x70 - 0x77 */ + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + /* 0x78 - 0x7F */ + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + /* 0x80 - 0x87 */ + ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, + ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM, + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, + /* 0x88 - 0x8F */ + ByteOp | DstMem | SrcReg | ModRM | Mov, DstMem | SrcReg | ModRM | Mov, + ByteOp | DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + 0, ModRM | DstReg, 0, DstMem | SrcNone | ModRM | Mov | Stack, + /* 0x90 - 0x9F */ + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0, + /* 0xA0 - 0xA7 */ + ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs, + ByteOp | DstMem | SrcReg | Mov | MemAbs, DstMem | SrcReg | Mov | MemAbs, + ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, + ByteOp | ImplicitOps | String, ImplicitOps | String, + /* 0xA8 - 0xAF */ + 0, 0, ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, + ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, + ByteOp | ImplicitOps | String, ImplicitOps | String, + /* 0xB0 - 0xBF */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xC0 - 0xC7 */ + ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM, + 0, ImplicitOps | Stack, 0, 0, + ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov, + /* 0xC8 - 0xCF */ + 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xD0 - 0xD7 */ + ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, + ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, + 0, 0, 0, 0, + /* 0xD8 - 0xDF */ + 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xE0 - 0xE7 */ + 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xE8 - 0xEF */ + ImplicitOps | Stack, SrcImm|ImplicitOps, 0, SrcImmByte|ImplicitOps, + 0, 0, 0, 0, + /* 0xF0 - 0xF7 */ + 0, 0, 0, 0, + ImplicitOps, ImplicitOps, + ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, + /* 0xF8 - 0xFF */ + ImplicitOps, 0, ImplicitOps, ImplicitOps, + 0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM +}; + +static u16 twobyte_table[256] = { + /* 0x00 - 0x0F */ + 0, SrcMem | ModRM | DstReg, 0, 0, 0, 0, ImplicitOps, 0, + ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0, + /* 0x10 - 0x1F */ + 0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0, + /* 0x20 - 0x2F */ + ModRM | ImplicitOps, ModRM, ModRM | ImplicitOps, ModRM, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + /* 0x30 - 0x3F */ + ImplicitOps, 0, ImplicitOps, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0x40 - 0x47 */ + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + /* 0x48 - 0x4F */ + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, + /* 0x50 - 0x5F */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0x60 - 0x6F */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0x70 - 0x7F */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0x80 - 0x8F */ + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, + /* 0x90 - 0x9F */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xA0 - 0xA7 */ + 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0, + /* 0xA8 - 0xAF */ + 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0, + /* 0xB0 - 0xB7 */ + ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, 0, + DstMem | SrcReg | ModRM | BitOp, + 0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem16 | ModRM | Mov, + /* 0xB8 - 0xBF */ + 0, 0, DstMem | SrcImmByte | ModRM, DstMem | SrcReg | ModRM | BitOp, + 0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov, + DstReg | SrcMem16 | ModRM | Mov, + /* 0xC0 - 0xCF */ + 0, 0, 0, DstMem | SrcReg | ModRM | Mov, 0, 0, 0, ImplicitOps | ModRM, + 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xD0 - 0xDF */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xE0 - 0xEF */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + /* 0xF0 - 0xFF */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 +}; + +/* EFLAGS bit definitions. */ +#define EFLG_OF (1<<11) +#define EFLG_DF (1<<10) +#define EFLG_SF (1<<7) +#define EFLG_ZF (1<<6) +#define EFLG_AF (1<<4) +#define EFLG_PF (1<<2) +#define EFLG_CF (1<<0) + +/* + * Instruction emulation: + * Most instructions are emulated directly via a fragment of inline assembly + * code. This allows us to save/restore EFLAGS and thus very easily pick up + * any modified flags. + */ + +#if defined(CONFIG_X86_64) +#define _LO32 "k" /* force 32-bit operand */ +#define _STK "%%rsp" /* stack pointer */ +#elif defined(__i386__) +#define _LO32 "" /* force 32-bit operand */ +#define _STK "%%esp" /* stack pointer */ +#endif + +/* + * These EFLAGS bits are restored from saved value during emulation, and + * any changes are written back to the saved value after emulation. + */ +#define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF) + +/* Before executing instruction: restore necessary bits in EFLAGS. */ +#define _PRE_EFLAGS(_sav, _msk, _tmp) \ + /* EFLAGS = (_sav & _msk) | (EFLAGS & ~_msk); _sav &= ~_msk; */ \ + "movl %"_sav",%"_LO32 _tmp"; " \ + "push %"_tmp"; " \ + "push %"_tmp"; " \ + "movl %"_msk",%"_LO32 _tmp"; " \ + "andl %"_LO32 _tmp",("_STK"); " \ + "pushf; " \ + "notl %"_LO32 _tmp"; " \ + "andl %"_LO32 _tmp",("_STK"); " \ + "andl %"_LO32 _tmp","__stringify(BITS_PER_LONG/4)"("_STK"); " \ + "pop %"_tmp"; " \ + "orl %"_LO32 _tmp",("_STK"); " \ + "popf; " \ + "pop %"_sav"; " + +/* After executing instruction: write-back necessary bits in EFLAGS. */ +#define _POST_EFLAGS(_sav, _msk, _tmp) \ + /* _sav |= EFLAGS & _msk; */ \ + "pushf; " \ + "pop %"_tmp"; " \ + "andl %"_msk",%"_LO32 _tmp"; " \ + "orl %"_LO32 _tmp",%"_sav"; " + +/* Raw emulation: instruction has two explicit operands. */ +#define __emulate_2op_nobyte(_op,_src,_dst,_eflags,_wx,_wy,_lx,_ly,_qx,_qy) \ + do { \ + unsigned long _tmp; \ + \ + switch ((_dst).bytes) { \ + case 2: \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "4", "2") \ + _op"w %"_wx"3,%1; " \ + _POST_EFLAGS("0", "4", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), \ + "=&r" (_tmp) \ + : _wy ((_src).val), "i" (EFLAGS_MASK)); \ + break; \ + case 4: \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "4", "2") \ + _op"l %"_lx"3,%1; " \ + _POST_EFLAGS("0", "4", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), \ + "=&r" (_tmp) \ + : _ly ((_src).val), "i" (EFLAGS_MASK)); \ + break; \ + case 8: \ + __emulate_2op_8byte(_op, _src, _dst, \ + _eflags, _qx, _qy); \ + break; \ + } \ + } while (0) + +#define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ + do { \ + unsigned long _tmp; \ + switch ((_dst).bytes) { \ + case 1: \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "4", "2") \ + _op"b %"_bx"3,%1; " \ + _POST_EFLAGS("0", "4", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), \ + "=&r" (_tmp) \ + : _by ((_src).val), "i" (EFLAGS_MASK)); \ + break; \ + default: \ + __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ + _wx, _wy, _lx, _ly, _qx, _qy); \ + break; \ + } \ + } while (0) + +/* Source operand is byte-sized and may be restricted to just %cl. */ +#define emulate_2op_SrcB(_op, _src, _dst, _eflags) \ + __emulate_2op(_op, _src, _dst, _eflags, \ + "b", "c", "b", "c", "b", "c", "b", "c") + +/* Source operand is byte, word, long or quad sized. */ +#define emulate_2op_SrcV(_op, _src, _dst, _eflags) \ + __emulate_2op(_op, _src, _dst, _eflags, \ + "b", "q", "w", "r", _LO32, "r", "", "r") + +/* Source operand is word, long or quad sized. */ +#define emulate_2op_SrcV_nobyte(_op, _src, _dst, _eflags) \ + __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ + "w", "r", _LO32, "r", "", "r") + +/* Instruction has only one explicit operand (no source operand). */ +#define emulate_1op(_op, _dst, _eflags) \ + do { \ + unsigned long _tmp; \ + \ + switch ((_dst).bytes) { \ + case 1: \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "3", "2") \ + _op"b %1; " \ + _POST_EFLAGS("0", "3", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), \ + "=&r" (_tmp) \ + : "i" (EFLAGS_MASK)); \ + break; \ + case 2: \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "3", "2") \ + _op"w %1; " \ + _POST_EFLAGS("0", "3", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), \ + "=&r" (_tmp) \ + : "i" (EFLAGS_MASK)); \ + break; \ + case 4: \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "3", "2") \ + _op"l %1; " \ + _POST_EFLAGS("0", "3", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), \ + "=&r" (_tmp) \ + : "i" (EFLAGS_MASK)); \ + break; \ + case 8: \ + __emulate_1op_8byte(_op, _dst, _eflags); \ + break; \ + } \ + } while (0) + +/* Emulate an instruction with quadword operands (x86/64 only). */ +#if defined(CONFIG_X86_64) +#define __emulate_2op_8byte(_op, _src, _dst, _eflags, _qx, _qy) \ + do { \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "4", "2") \ + _op"q %"_qx"3,%1; " \ + _POST_EFLAGS("0", "4", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), "=&r" (_tmp) \ + : _qy ((_src).val), "i" (EFLAGS_MASK)); \ + } while (0) + +#define __emulate_1op_8byte(_op, _dst, _eflags) \ + do { \ + __asm__ __volatile__ ( \ + _PRE_EFLAGS("0", "3", "2") \ + _op"q %1; " \ + _POST_EFLAGS("0", "3", "2") \ + : "=m" (_eflags), "=m" ((_dst).val), "=&r" (_tmp) \ + : "i" (EFLAGS_MASK)); \ + } while (0) + +#elif defined(__i386__) +#define __emulate_2op_8byte(_op, _src, _dst, _eflags, _qx, _qy) +#define __emulate_1op_8byte(_op, _dst, _eflags) +#endif /* __i386__ */ + +/* Fetch next part of the instruction being emulated. */ +#define insn_fetch(_type, _size, _eip) \ +({ unsigned long _x; \ + rc = do_insn_fetch(ctxt, ops, (_eip), &_x, (_size)); \ + if (rc != 0) \ + goto done; \ + (_eip) += (_size); \ + (_type)_x; \ +}) + +/* Access/update address held in a register, based on addressing mode. */ +#define address_mask(reg) \ + ((c->ad_bytes == sizeof(unsigned long)) ? \ + (reg) : ((reg) & ((1UL << (c->ad_bytes << 3)) - 1))) +#define register_address(base, reg) \ + ((base) + address_mask(reg)) +#define register_address_increment(reg, inc) \ + do { \ + /* signed type ensures sign extension to long */ \ + int _inc = (inc); \ + if (c->ad_bytes == sizeof(unsigned long)) \ + (reg) += _inc; \ + else \ + (reg) = ((reg) & \ + ~((1UL << (c->ad_bytes << 3)) - 1)) | \ + (((reg) + _inc) & \ + ((1UL << (c->ad_bytes << 3)) - 1)); \ + } while (0) + +#define JMP_REL(rel) \ + do { \ + register_address_increment(c->eip, rel); \ + } while (0) + +static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + unsigned long linear, u8 *dest) +{ + struct fetch_cache *fc = &ctxt->decode.fetch; + int rc; + int size; + + if (linear < fc->start || linear >= fc->end) { + size = min(15UL, PAGE_SIZE - offset_in_page(linear)); + rc = ops->read_std(linear, fc->data, size, ctxt->vcpu); + if (rc) + return rc; + fc->start = linear; + fc->end = linear + size; + } + *dest = fc->data[linear - fc->start]; + return 0; +} + +static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + unsigned long eip, void *dest, unsigned size) +{ + int rc = 0; + + eip += ctxt->cs_base; + while (size--) { + rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++); + if (rc) + return rc; + } + return 0; +} + +/* + * Given the 'reg' portion of a ModRM byte, and a register block, return a + * pointer into the block that addresses the relevant register. + * @highbyte_regs specifies whether to decode AH,CH,DH,BH. + */ +static void *decode_register(u8 modrm_reg, unsigned long *regs, + int highbyte_regs) +{ + void *p; + + p = ®s[modrm_reg]; + if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8) + p = (unsigned char *)®s[modrm_reg & 3] + 1; + return p; +} + +static int read_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + void *ptr, + u16 *size, unsigned long *address, int op_bytes) +{ + int rc; + + if (op_bytes == 2) + op_bytes = 3; + *address = 0; + rc = ops->read_std((unsigned long)ptr, (unsigned long *)size, 2, + ctxt->vcpu); + if (rc) + return rc; + rc = ops->read_std((unsigned long)ptr + 2, address, op_bytes, + ctxt->vcpu); + return rc; +} + +static int test_cc(unsigned int condition, unsigned int flags) +{ + int rc = 0; + + switch ((condition & 15) >> 1) { + case 0: /* o */ + rc |= (flags & EFLG_OF); + break; + case 1: /* b/c/nae */ + rc |= (flags & EFLG_CF); + break; + case 2: /* z/e */ + rc |= (flags & EFLG_ZF); + break; + case 3: /* be/na */ + rc |= (flags & (EFLG_CF|EFLG_ZF)); + break; + case 4: /* s */ + rc |= (flags & EFLG_SF); + break; + case 5: /* p/pe */ + rc |= (flags & EFLG_PF); + break; + case 7: /* le/ng */ + rc |= (flags & EFLG_ZF); + /* fall through */ + case 6: /* l/nge */ + rc |= (!(flags & EFLG_SF) != !(flags & EFLG_OF)); + break; + } + + /* Odd condition identifiers (lsb == 1) have inverted sense. */ + return (!!rc ^ (condition & 1)); +} + +static void decode_register_operand(struct operand *op, + struct decode_cache *c, + int inhibit_bytereg) +{ + unsigned reg = c->modrm_reg; + int highbyte_regs = c->rex_prefix == 0; + + if (!(c->d & ModRM)) + reg = (c->b & 7) | ((c->rex_prefix & 1) << 3); + op->type = OP_REG; + if ((c->d & ByteOp) && !inhibit_bytereg) { + op->ptr = decode_register(reg, c->regs, highbyte_regs); + op->val = *(u8 *)op->ptr; + op->bytes = 1; + } else { + op->ptr = decode_register(reg, c->regs, 0); + op->bytes = c->op_bytes; + switch (op->bytes) { + case 2: + op->val = *(u16 *)op->ptr; + break; + case 4: + op->val = *(u32 *)op->ptr; + break; + case 8: + op->val = *(u64 *) op->ptr; + break; + } + } + op->orig_val = op->val; +} + +static int decode_modrm(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + u8 sib; + int index_reg = 0, base_reg = 0, scale, rip_relative = 0; + int rc = 0; + + if (c->rex_prefix) { + c->modrm_reg = (c->rex_prefix & 4) << 1; /* REX.R */ + index_reg = (c->rex_prefix & 2) << 2; /* REX.X */ + c->modrm_rm = base_reg = (c->rex_prefix & 1) << 3; /* REG.B */ + } + + c->modrm = insn_fetch(u8, 1, c->eip); + c->modrm_mod |= (c->modrm & 0xc0) >> 6; + c->modrm_reg |= (c->modrm & 0x38) >> 3; + c->modrm_rm |= (c->modrm & 0x07); + c->modrm_ea = 0; + c->use_modrm_ea = 1; + + if (c->modrm_mod == 3) { + c->modrm_val = *(unsigned long *) + decode_register(c->modrm_rm, c->regs, c->d & ByteOp); + return rc; + } + + if (c->ad_bytes == 2) { + unsigned bx = c->regs[VCPU_REGS_RBX]; + unsigned bp = c->regs[VCPU_REGS_RBP]; + unsigned si = c->regs[VCPU_REGS_RSI]; + unsigned di = c->regs[VCPU_REGS_RDI]; + + /* 16-bit ModR/M decode. */ + switch (c->modrm_mod) { + case 0: + if (c->modrm_rm == 6) + c->modrm_ea += insn_fetch(u16, 2, c->eip); + break; + case 1: + c->modrm_ea += insn_fetch(s8, 1, c->eip); + break; + case 2: + c->modrm_ea += insn_fetch(u16, 2, c->eip); + break; + } + switch (c->modrm_rm) { + case 0: + c->modrm_ea += bx + si; + break; + case 1: + c->modrm_ea += bx + di; + break; + case 2: + c->modrm_ea += bp + si; + break; + case 3: + c->modrm_ea += bp + di; + break; + case 4: + c->modrm_ea += si; + break; + case 5: + c->modrm_ea += di; + break; + case 6: + if (c->modrm_mod != 0) + c->modrm_ea += bp; + break; + case 7: + c->modrm_ea += bx; + break; + } + if (c->modrm_rm == 2 || c->modrm_rm == 3 || + (c->modrm_rm == 6 && c->modrm_mod != 0)) + if (!c->override_base) + c->override_base = &ctxt->ss_base; + c->modrm_ea = (u16)c->modrm_ea; + } else { + /* 32/64-bit ModR/M decode. */ + switch (c->modrm_rm) { + case 4: + case 12: + sib = insn_fetch(u8, 1, c->eip); + index_reg |= (sib >> 3) & 7; + base_reg |= sib & 7; + scale = sib >> 6; + + switch (base_reg) { + case 5: + if (c->modrm_mod != 0) + c->modrm_ea += c->regs[base_reg]; + else + c->modrm_ea += + insn_fetch(s32, 4, c->eip); + break; + default: + c->modrm_ea += c->regs[base_reg]; + } + switch (index_reg) { + case 4: + break; + default: + c->modrm_ea += c->regs[index_reg] << scale; + } + break; + case 5: + if (c->modrm_mod != 0) + c->modrm_ea += c->regs[c->modrm_rm]; + else if (ctxt->mode == X86EMUL_MODE_PROT64) + rip_relative = 1; + break; + default: + c->modrm_ea += c->regs[c->modrm_rm]; + break; + } + switch (c->modrm_mod) { + case 0: + if (c->modrm_rm == 5) + c->modrm_ea += insn_fetch(s32, 4, c->eip); + break; + case 1: + c->modrm_ea += insn_fetch(s8, 1, c->eip); + break; + case 2: + c->modrm_ea += insn_fetch(s32, 4, c->eip); + break; + } + } + if (rip_relative) { + c->modrm_ea += c->eip; + switch (c->d & SrcMask) { + case SrcImmByte: + c->modrm_ea += 1; + break; + case SrcImm: + if (c->d & ByteOp) + c->modrm_ea += 1; + else + if (c->op_bytes == 8) + c->modrm_ea += 4; + else + c->modrm_ea += c->op_bytes; + } + } +done: + return rc; +} + +static int decode_abs(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc = 0; + + switch (c->ad_bytes) { + case 2: + c->modrm_ea = insn_fetch(u16, 2, c->eip); + break; + case 4: + c->modrm_ea = insn_fetch(u32, 4, c->eip); + break; + case 8: + c->modrm_ea = insn_fetch(u64, 8, c->eip); + break; + } +done: + return rc; +} + +int +x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc = 0; + int mode = ctxt->mode; + int def_op_bytes, def_ad_bytes; + + /* Shadow copy of register state. Committed on successful emulation. */ + + memset(c, 0, sizeof(struct decode_cache)); + c->eip = ctxt->vcpu->arch.rip; + memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); + + switch (mode) { + case X86EMUL_MODE_REAL: + case X86EMUL_MODE_PROT16: + def_op_bytes = def_ad_bytes = 2; + break; + case X86EMUL_MODE_PROT32: + def_op_bytes = def_ad_bytes = 4; + break; +#ifdef CONFIG_X86_64 + case X86EMUL_MODE_PROT64: + def_op_bytes = 4; + def_ad_bytes = 8; + break; +#endif + default: + return -1; + } + + c->op_bytes = def_op_bytes; + c->ad_bytes = def_ad_bytes; + + /* Legacy prefixes. */ + for (;;) { + switch (c->b = insn_fetch(u8, 1, c->eip)) { + case 0x66: /* operand-size override */ + /* switch between 2/4 bytes */ + c->op_bytes = def_op_bytes ^ 6; + break; + case 0x67: /* address-size override */ + if (mode == X86EMUL_MODE_PROT64) + /* switch between 4/8 bytes */ + c->ad_bytes = def_ad_bytes ^ 12; + else + /* switch between 2/4 bytes */ + c->ad_bytes = def_ad_bytes ^ 6; + break; + case 0x2e: /* CS override */ + c->override_base = &ctxt->cs_base; + break; + case 0x3e: /* DS override */ + c->override_base = &ctxt->ds_base; + break; + case 0x26: /* ES override */ + c->override_base = &ctxt->es_base; + break; + case 0x64: /* FS override */ + c->override_base = &ctxt->fs_base; + break; + case 0x65: /* GS override */ + c->override_base = &ctxt->gs_base; + break; + case 0x36: /* SS override */ + c->override_base = &ctxt->ss_base; + break; + case 0x40 ... 0x4f: /* REX */ + if (mode != X86EMUL_MODE_PROT64) + goto done_prefixes; + c->rex_prefix = c->b; + continue; + case 0xf0: /* LOCK */ + c->lock_prefix = 1; + break; + case 0xf2: /* REPNE/REPNZ */ + c->rep_prefix = REPNE_PREFIX; + break; + case 0xf3: /* REP/REPE/REPZ */ + c->rep_prefix = REPE_PREFIX; + break; + default: + goto done_prefixes; + } + + /* Any legacy prefix after a REX prefix nullifies its effect. */ + + c->rex_prefix = 0; + } + +done_prefixes: + + /* REX prefix. */ + if (c->rex_prefix) + if (c->rex_prefix & 8) + c->op_bytes = 8; /* REX.W */ + + /* Opcode byte(s). */ + c->d = opcode_table[c->b]; + if (c->d == 0) { + /* Two-byte opcode? */ + if (c->b == 0x0f) { + c->twobyte = 1; + c->b = insn_fetch(u8, 1, c->eip); + c->d = twobyte_table[c->b]; + } + + /* Unrecognised? */ + if (c->d == 0) { + DPRINTF("Cannot emulate %02x\n", c->b); + return -1; + } + } + + if (mode == X86EMUL_MODE_PROT64 && (c->d & Stack)) + c->op_bytes = 8; + + /* ModRM and SIB bytes. */ + if (c->d & ModRM) + rc = decode_modrm(ctxt, ops); + else if (c->d & MemAbs) + rc = decode_abs(ctxt, ops); + if (rc) + goto done; + + if (!c->override_base) + c->override_base = &ctxt->ds_base; + if (mode == X86EMUL_MODE_PROT64 && + c->override_base != &ctxt->fs_base && + c->override_base != &ctxt->gs_base) + c->override_base = NULL; + + if (c->override_base) + c->modrm_ea += *c->override_base; + + if (c->ad_bytes != 8) + c->modrm_ea = (u32)c->modrm_ea; + /* + * Decode and fetch the source operand: register, memory + * or immediate. + */ + switch (c->d & SrcMask) { + case SrcNone: + break; + case SrcReg: + decode_register_operand(&c->src, c, 0); + break; + case SrcMem16: + c->src.bytes = 2; + goto srcmem_common; + case SrcMem32: + c->src.bytes = 4; + goto srcmem_common; + case SrcMem: + c->src.bytes = (c->d & ByteOp) ? 1 : + c->op_bytes; + /* Don't fetch the address for invlpg: it could be unmapped. */ + if (c->twobyte && c->b == 0x01 && c->modrm_reg == 7) + break; + srcmem_common: + /* + * For instructions with a ModR/M byte, switch to register + * access if Mod = 3. + */ + if ((c->d & ModRM) && c->modrm_mod == 3) { + c->src.type = OP_REG; + break; + } + c->src.type = OP_MEM; + break; + case SrcImm: + c->src.type = OP_IMM; + c->src.ptr = (unsigned long *)c->eip; + c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + if (c->src.bytes == 8) + c->src.bytes = 4; + /* NB. Immediates are sign-extended as necessary. */ + switch (c->src.bytes) { + case 1: + c->src.val = insn_fetch(s8, 1, c->eip); + break; + case 2: + c->src.val = insn_fetch(s16, 2, c->eip); + break; + case 4: + c->src.val = insn_fetch(s32, 4, c->eip); + break; + } + break; + case SrcImmByte: + c->src.type = OP_IMM; + c->src.ptr = (unsigned long *)c->eip; + c->src.bytes = 1; + c->src.val = insn_fetch(s8, 1, c->eip); + break; + } + + /* Decode and fetch the destination operand: register or memory. */ + switch (c->d & DstMask) { + case ImplicitOps: + /* Special instructions do their own operand decoding. */ + return 0; + case DstReg: + decode_register_operand(&c->dst, c, + c->twobyte && (c->b == 0xb6 || c->b == 0xb7)); + break; + case DstMem: + if ((c->d & ModRM) && c->modrm_mod == 3) { + c->dst.type = OP_REG; + break; + } + c->dst.type = OP_MEM; + break; + } + +done: + return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; +} + +static inline void emulate_push(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + + c->dst.type = OP_MEM; + c->dst.bytes = c->op_bytes; + c->dst.val = c->src.val; + register_address_increment(c->regs[VCPU_REGS_RSP], -c->op_bytes); + c->dst.ptr = (void *) register_address(ctxt->ss_base, + c->regs[VCPU_REGS_RSP]); +} + +static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + + rc = ops->read_std(register_address(ctxt->ss_base, + c->regs[VCPU_REGS_RSP]), + &c->dst.val, c->dst.bytes, ctxt->vcpu); + if (rc != 0) + return rc; + + register_address_increment(c->regs[VCPU_REGS_RSP], c->dst.bytes); + + return 0; +} + +static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + switch (c->modrm_reg) { + case 0: /* rol */ + emulate_2op_SrcB("rol", c->src, c->dst, ctxt->eflags); + break; + case 1: /* ror */ + emulate_2op_SrcB("ror", c->src, c->dst, ctxt->eflags); + break; + case 2: /* rcl */ + emulate_2op_SrcB("rcl", c->src, c->dst, ctxt->eflags); + break; + case 3: /* rcr */ + emulate_2op_SrcB("rcr", c->src, c->dst, ctxt->eflags); + break; + case 4: /* sal/shl */ + case 6: /* sal/shl */ + emulate_2op_SrcB("sal", c->src, c->dst, ctxt->eflags); + break; + case 5: /* shr */ + emulate_2op_SrcB("shr", c->src, c->dst, ctxt->eflags); + break; + case 7: /* sar */ + emulate_2op_SrcB("sar", c->src, c->dst, ctxt->eflags); + break; + } +} + +static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc = 0; + + switch (c->modrm_reg) { + case 0 ... 1: /* test */ + /* + * Special case in Grp3: test has an immediate + * source operand. + */ + c->src.type = OP_IMM; + c->src.ptr = (unsigned long *)c->eip; + c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + if (c->src.bytes == 8) + c->src.bytes = 4; + switch (c->src.bytes) { + case 1: + c->src.val = insn_fetch(s8, 1, c->eip); + break; + case 2: + c->src.val = insn_fetch(s16, 2, c->eip); + break; + case 4: + c->src.val = insn_fetch(s32, 4, c->eip); + break; + } + emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags); + break; + case 2: /* not */ + c->dst.val = ~c->dst.val; + break; + case 3: /* neg */ + emulate_1op("neg", c->dst, ctxt->eflags); + break; + default: + DPRINTF("Cannot emulate %02x\n", c->b); + rc = X86EMUL_UNHANDLEABLE; + break; + } +done: + return rc; +} + +static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + + switch (c->modrm_reg) { + case 0: /* inc */ + emulate_1op("inc", c->dst, ctxt->eflags); + break; + case 1: /* dec */ + emulate_1op("dec", c->dst, ctxt->eflags); + break; + case 4: /* jmp abs */ + if (c->b == 0xff) + c->eip = c->dst.val; + else { + DPRINTF("Cannot emulate %02x\n", c->b); + return X86EMUL_UNHANDLEABLE; + } + break; + case 6: /* push */ + + /* 64-bit mode: PUSH always pushes a 64-bit operand. */ + + if (ctxt->mode == X86EMUL_MODE_PROT64) { + c->dst.bytes = 8; + rc = ops->read_std((unsigned long)c->dst.ptr, + &c->dst.val, 8, ctxt->vcpu); + if (rc != 0) + return rc; + } + register_address_increment(c->regs[VCPU_REGS_RSP], + -c->dst.bytes); + rc = ops->write_emulated(register_address(ctxt->ss_base, + c->regs[VCPU_REGS_RSP]), &c->dst.val, + c->dst.bytes, ctxt->vcpu); + if (rc != 0) + return rc; + c->dst.type = OP_NONE; + break; + default: + DPRINTF("Cannot emulate %02x\n", c->b); + return X86EMUL_UNHANDLEABLE; + } + return 0; +} + +static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + unsigned long memop) +{ + struct decode_cache *c = &ctxt->decode; + u64 old, new; + int rc; + + rc = ops->read_emulated(memop, &old, 8, ctxt->vcpu); + if (rc != 0) + return rc; + + if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) || + ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) { + + c->regs[VCPU_REGS_RAX] = (u32) (old >> 0); + c->regs[VCPU_REGS_RDX] = (u32) (old >> 32); + ctxt->eflags &= ~EFLG_ZF; + + } else { + new = ((u64)c->regs[VCPU_REGS_RCX] << 32) | + (u32) c->regs[VCPU_REGS_RBX]; + + rc = ops->cmpxchg_emulated(memop, &old, &new, 8, ctxt->vcpu); + if (rc != 0) + return rc; + ctxt->eflags |= EFLG_ZF; + } + return 0; +} + +static inline int writeback(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + int rc; + struct decode_cache *c = &ctxt->decode; + + switch (c->dst.type) { + case OP_REG: + /* The 4-byte case *is* correct: + * in 64-bit mode we zero-extend. + */ + switch (c->dst.bytes) { + case 1: + *(u8 *)c->dst.ptr = (u8)c->dst.val; + break; + case 2: + *(u16 *)c->dst.ptr = (u16)c->dst.val; + break; + case 4: + *c->dst.ptr = (u32)c->dst.val; + break; /* 64b: zero-ext */ + case 8: + *c->dst.ptr = c->dst.val; + break; + } + break; + case OP_MEM: + if (c->lock_prefix) + rc = ops->cmpxchg_emulated( + (unsigned long)c->dst.ptr, + &c->dst.orig_val, + &c->dst.val, + c->dst.bytes, + ctxt->vcpu); + else + rc = ops->write_emulated( + (unsigned long)c->dst.ptr, + &c->dst.val, + c->dst.bytes, + ctxt->vcpu); + if (rc != 0) + return rc; + break; + case OP_NONE: + /* no writeback */ + break; + default: + break; + } + return 0; +} + +int +x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) +{ + unsigned long memop = 0; + u64 msr_data; + unsigned long saved_eip = 0; + struct decode_cache *c = &ctxt->decode; + int rc = 0; + + /* Shadow copy of register state. Committed on successful emulation. + * NOTE: we can copy them from vcpu as x86_decode_insn() doesn't + * modify them. + */ + + memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); + saved_eip = c->eip; + + if (((c->d & ModRM) && (c->modrm_mod != 3)) || (c->d & MemAbs)) + memop = c->modrm_ea; + + if (c->rep_prefix && (c->d & String)) { + /* All REP prefixes have the same first termination condition */ + if (c->regs[VCPU_REGS_RCX] == 0) { + ctxt->vcpu->arch.rip = c->eip; + goto done; + } + /* The second termination condition only applies for REPE + * and REPNE. Test if the repeat string operation prefix is + * REPE/REPZ or REPNE/REPNZ and if it's the case it tests the + * corresponding termination condition according to: + * - if REPE/REPZ and ZF = 0 then done + * - if REPNE/REPNZ and ZF = 1 then done + */ + if ((c->b == 0xa6) || (c->b == 0xa7) || + (c->b == 0xae) || (c->b == 0xaf)) { + if ((c->rep_prefix == REPE_PREFIX) && + ((ctxt->eflags & EFLG_ZF) == 0)) { + ctxt->vcpu->arch.rip = c->eip; + goto done; + } + if ((c->rep_prefix == REPNE_PREFIX) && + ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) { + ctxt->vcpu->arch.rip = c->eip; + goto done; + } + } + c->regs[VCPU_REGS_RCX]--; + c->eip = ctxt->vcpu->arch.rip; + } + + if (c->src.type == OP_MEM) { + c->src.ptr = (unsigned long *)memop; + c->src.val = 0; + rc = ops->read_emulated((unsigned long)c->src.ptr, + &c->src.val, + c->src.bytes, + ctxt->vcpu); + if (rc != 0) + goto done; + c->src.orig_val = c->src.val; + } + + if ((c->d & DstMask) == ImplicitOps) + goto special_insn; + + + if (c->dst.type == OP_MEM) { + c->dst.ptr = (unsigned long *)memop; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.val = 0; + if (c->d & BitOp) { + unsigned long mask = ~(c->dst.bytes * 8 - 1); + + c->dst.ptr = (void *)c->dst.ptr + + (c->src.val & mask) / 8; + } + if (!(c->d & Mov) && + /* optimisation - avoid slow emulated read */ + ((rc = ops->read_emulated((unsigned long)c->dst.ptr, + &c->dst.val, + c->dst.bytes, ctxt->vcpu)) != 0)) + goto done; + } + c->dst.orig_val = c->dst.val; + +special_insn: + + if (c->twobyte) + goto twobyte_insn; + + switch (c->b) { + case 0x00 ... 0x05: + add: /* add */ + emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); + break; + case 0x08 ... 0x0d: + or: /* or */ + emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); + break; + case 0x10 ... 0x15: + adc: /* adc */ + emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); + break; + case 0x18 ... 0x1d: + sbb: /* sbb */ + emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); + break; + case 0x20 ... 0x23: + and: /* and */ + emulate_2op_SrcV("and", c->src, c->dst, ctxt->eflags); + break; + case 0x24: /* and al imm8 */ + c->dst.type = OP_REG; + c->dst.ptr = &c->regs[VCPU_REGS_RAX]; + c->dst.val = *(u8 *)c->dst.ptr; + c->dst.bytes = 1; + c->dst.orig_val = c->dst.val; + goto and; + case 0x25: /* and ax imm16, or eax imm32 */ + c->dst.type = OP_REG; + c->dst.bytes = c->op_bytes; + c->dst.ptr = &c->regs[VCPU_REGS_RAX]; + if (c->op_bytes == 2) + c->dst.val = *(u16 *)c->dst.ptr; + else + c->dst.val = *(u32 *)c->dst.ptr; + c->dst.orig_val = c->dst.val; + goto and; + case 0x28 ... 0x2d: + sub: /* sub */ + emulate_2op_SrcV("sub", c->src, c->dst, ctxt->eflags); + break; + case 0x30 ... 0x35: + xor: /* xor */ + emulate_2op_SrcV("xor", c->src, c->dst, ctxt->eflags); + break; + case 0x38 ... 0x3d: + cmp: /* cmp */ + emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); + break; + case 0x40 ... 0x47: /* inc r16/r32 */ + emulate_1op("inc", c->dst, ctxt->eflags); + break; + case 0x48 ... 0x4f: /* dec r16/r32 */ + emulate_1op("dec", c->dst, ctxt->eflags); + break; + case 0x50 ... 0x57: /* push reg */ + c->dst.type = OP_MEM; + c->dst.bytes = c->op_bytes; + c->dst.val = c->src.val; + register_address_increment(c->regs[VCPU_REGS_RSP], + -c->op_bytes); + c->dst.ptr = (void *) register_address( + ctxt->ss_base, c->regs[VCPU_REGS_RSP]); + break; + case 0x58 ... 0x5f: /* pop reg */ + pop_instruction: + if ((rc = ops->read_std(register_address(ctxt->ss_base, + c->regs[VCPU_REGS_RSP]), c->dst.ptr, + c->op_bytes, ctxt->vcpu)) != 0) + goto done; + + register_address_increment(c->regs[VCPU_REGS_RSP], + c->op_bytes); + c->dst.type = OP_NONE; /* Disable writeback. */ + break; + case 0x63: /* movsxd */ + if (ctxt->mode != X86EMUL_MODE_PROT64) + goto cannot_emulate; + c->dst.val = (s32) c->src.val; + break; + case 0x6a: /* push imm8 */ + c->src.val = 0L; + c->src.val = insn_fetch(s8, 1, c->eip); + emulate_push(ctxt); + break; + case 0x6c: /* insb */ + case 0x6d: /* insw/insd */ + if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + 1, + (c->d & ByteOp) ? 1 : c->op_bytes, + c->rep_prefix ? + address_mask(c->regs[VCPU_REGS_RCX]) : 1, + (ctxt->eflags & EFLG_DF), + register_address(ctxt->es_base, + c->regs[VCPU_REGS_RDI]), + c->rep_prefix, + c->regs[VCPU_REGS_RDX]) == 0) { + c->eip = saved_eip; + return -1; + } + return 0; + case 0x6e: /* outsb */ + case 0x6f: /* outsw/outsd */ + if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + 0, + (c->d & ByteOp) ? 1 : c->op_bytes, + c->rep_prefix ? + address_mask(c->regs[VCPU_REGS_RCX]) : 1, + (ctxt->eflags & EFLG_DF), + register_address(c->override_base ? + *c->override_base : + ctxt->ds_base, + c->regs[VCPU_REGS_RSI]), + c->rep_prefix, + c->regs[VCPU_REGS_RDX]) == 0) { + c->eip = saved_eip; + return -1; + } + return 0; + case 0x70 ... 0x7f: /* jcc (short) */ { + int rel = insn_fetch(s8, 1, c->eip); + + if (test_cc(c->b, ctxt->eflags)) + JMP_REL(rel); + break; + } + case 0x80 ... 0x83: /* Grp1 */ + switch (c->modrm_reg) { + case 0: + goto add; + case 1: + goto or; + case 2: + goto adc; + case 3: + goto sbb; + case 4: + goto and; + case 5: + goto sub; + case 6: + goto xor; + case 7: + goto cmp; + } + break; + case 0x84 ... 0x85: + emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags); + break; + case 0x86 ... 0x87: /* xchg */ + /* Write back the register source. */ + switch (c->dst.bytes) { + case 1: + *(u8 *) c->src.ptr = (u8) c->dst.val; + break; + case 2: + *(u16 *) c->src.ptr = (u16) c->dst.val; + break; + case 4: + *c->src.ptr = (u32) c->dst.val; + break; /* 64b reg: zero-extend */ + case 8: + *c->src.ptr = c->dst.val; + break; + } + /* + * Write back the memory destination with implicit LOCK + * prefix. + */ + c->dst.val = c->src.val; + c->lock_prefix = 1; + break; + case 0x88 ... 0x8b: /* mov */ + goto mov; + case 0x8d: /* lea r16/r32, m */ + c->dst.val = c->modrm_val; + break; + case 0x8f: /* pop (sole member of Grp1a) */ + rc = emulate_grp1a(ctxt, ops); + if (rc != 0) + goto done; + break; + case 0x9c: /* pushf */ + c->src.val = (unsigned long) ctxt->eflags; + emulate_push(ctxt); + break; + case 0x9d: /* popf */ + c->dst.ptr = (unsigned long *) &ctxt->eflags; + goto pop_instruction; + case 0xa0 ... 0xa1: /* mov */ + c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX]; + c->dst.val = c->src.val; + break; + case 0xa2 ... 0xa3: /* mov */ + c->dst.val = (unsigned long)c->regs[VCPU_REGS_RAX]; + break; + case 0xa4 ... 0xa5: /* movs */ + c->dst.type = OP_MEM; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.ptr = (unsigned long *)register_address( + ctxt->es_base, + c->regs[VCPU_REGS_RDI]); + if ((rc = ops->read_emulated(register_address( + c->override_base ? *c->override_base : + ctxt->ds_base, + c->regs[VCPU_REGS_RSI]), + &c->dst.val, + c->dst.bytes, ctxt->vcpu)) != 0) + goto done; + register_address_increment(c->regs[VCPU_REGS_RSI], + (ctxt->eflags & EFLG_DF) ? -c->dst.bytes + : c->dst.bytes); + register_address_increment(c->regs[VCPU_REGS_RDI], + (ctxt->eflags & EFLG_DF) ? -c->dst.bytes + : c->dst.bytes); + break; + case 0xa6 ... 0xa7: /* cmps */ + c->src.type = OP_NONE; /* Disable writeback. */ + c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->src.ptr = (unsigned long *)register_address( + c->override_base ? *c->override_base : + ctxt->ds_base, + c->regs[VCPU_REGS_RSI]); + if ((rc = ops->read_emulated((unsigned long)c->src.ptr, + &c->src.val, + c->src.bytes, + ctxt->vcpu)) != 0) + goto done; + + c->dst.type = OP_NONE; /* Disable writeback. */ + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.ptr = (unsigned long *)register_address( + ctxt->es_base, + c->regs[VCPU_REGS_RDI]); + if ((rc = ops->read_emulated((unsigned long)c->dst.ptr, + &c->dst.val, + c->dst.bytes, + ctxt->vcpu)) != 0) + goto done; + + DPRINTF("cmps: mem1=0x%p mem2=0x%p\n", c->src.ptr, c->dst.ptr); + + emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); + + register_address_increment(c->regs[VCPU_REGS_RSI], + (ctxt->eflags & EFLG_DF) ? -c->src.bytes + : c->src.bytes); + register_address_increment(c->regs[VCPU_REGS_RDI], + (ctxt->eflags & EFLG_DF) ? -c->dst.bytes + : c->dst.bytes); + + break; + case 0xaa ... 0xab: /* stos */ + c->dst.type = OP_MEM; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.ptr = (unsigned long *)register_address( + ctxt->es_base, + c->regs[VCPU_REGS_RDI]); + c->dst.val = c->regs[VCPU_REGS_RAX]; + register_address_increment(c->regs[VCPU_REGS_RDI], + (ctxt->eflags & EFLG_DF) ? -c->dst.bytes + : c->dst.bytes); + break; + case 0xac ... 0xad: /* lods */ + c->dst.type = OP_REG; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX]; + if ((rc = ops->read_emulated(register_address( + c->override_base ? *c->override_base : + ctxt->ds_base, + c->regs[VCPU_REGS_RSI]), + &c->dst.val, + c->dst.bytes, + ctxt->vcpu)) != 0) + goto done; + register_address_increment(c->regs[VCPU_REGS_RSI], + (ctxt->eflags & EFLG_DF) ? -c->dst.bytes + : c->dst.bytes); + break; + case 0xae ... 0xaf: /* scas */ + DPRINTF("Urk! I don't handle SCAS.\n"); + goto cannot_emulate; + case 0xc0 ... 0xc1: + emulate_grp2(ctxt); + break; + case 0xc3: /* ret */ + c->dst.ptr = &c->eip; + goto pop_instruction; + case 0xc6 ... 0xc7: /* mov (sole member of Grp11) */ + mov: + c->dst.val = c->src.val; + break; + case 0xd0 ... 0xd1: /* Grp2 */ + c->src.val = 1; + emulate_grp2(ctxt); + break; + case 0xd2 ... 0xd3: /* Grp2 */ + c->src.val = c->regs[VCPU_REGS_RCX]; + emulate_grp2(ctxt); + break; + case 0xe8: /* call (near) */ { + long int rel; + switch (c->op_bytes) { + case 2: + rel = insn_fetch(s16, 2, c->eip); + break; + case 4: + rel = insn_fetch(s32, 4, c->eip); + break; + default: + DPRINTF("Call: Invalid op_bytes\n"); + goto cannot_emulate; + } + c->src.val = (unsigned long) c->eip; + JMP_REL(rel); + c->op_bytes = c->ad_bytes; + emulate_push(ctxt); + break; + } + case 0xe9: /* jmp rel */ + case 0xeb: /* jmp rel short */ + JMP_REL(c->src.val); + c->dst.type = OP_NONE; /* Disable writeback. */ + break; + case 0xf4: /* hlt */ + ctxt->vcpu->arch.halt_request = 1; + goto done; + case 0xf5: /* cmc */ + /* complement carry flag from eflags reg */ + ctxt->eflags ^= EFLG_CF; + c->dst.type = OP_NONE; /* Disable writeback. */ + break; + case 0xf6 ... 0xf7: /* Grp3 */ + rc = emulate_grp3(ctxt, ops); + if (rc != 0) + goto done; + break; + case 0xf8: /* clc */ + ctxt->eflags &= ~EFLG_CF; + c->dst.type = OP_NONE; /* Disable writeback. */ + break; + case 0xfa: /* cli */ + ctxt->eflags &= ~X86_EFLAGS_IF; + c->dst.type = OP_NONE; /* Disable writeback. */ + break; + case 0xfb: /* sti */ + ctxt->eflags |= X86_EFLAGS_IF; + c->dst.type = OP_NONE; /* Disable writeback. */ + break; + case 0xfe ... 0xff: /* Grp4/Grp5 */ + rc = emulate_grp45(ctxt, ops); + if (rc != 0) + goto done; + break; + } + +writeback: + rc = writeback(ctxt, ops); + if (rc != 0) + goto done; + + /* Commit shadow register state. */ + memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs); + ctxt->vcpu->arch.rip = c->eip; + +done: + if (rc == X86EMUL_UNHANDLEABLE) { + c->eip = saved_eip; + return -1; + } + return 0; + +twobyte_insn: + switch (c->b) { + case 0x01: /* lgdt, lidt, lmsw */ + switch (c->modrm_reg) { + u16 size; + unsigned long address; + + case 0: /* vmcall */ + if (c->modrm_mod != 3 || c->modrm_rm != 1) + goto cannot_emulate; + + rc = kvm_fix_hypercall(ctxt->vcpu); + if (rc) + goto done; + + kvm_emulate_hypercall(ctxt->vcpu); + break; + case 2: /* lgdt */ + rc = read_descriptor(ctxt, ops, c->src.ptr, + &size, &address, c->op_bytes); + if (rc) + goto done; + realmode_lgdt(ctxt->vcpu, size, address); + break; + case 3: /* lidt/vmmcall */ + if (c->modrm_mod == 3 && c->modrm_rm == 1) { + rc = kvm_fix_hypercall(ctxt->vcpu); + if (rc) + goto done; + kvm_emulate_hypercall(ctxt->vcpu); + } else { + rc = read_descriptor(ctxt, ops, c->src.ptr, + &size, &address, + c->op_bytes); + if (rc) + goto done; + realmode_lidt(ctxt->vcpu, size, address); + } + break; + case 4: /* smsw */ + if (c->modrm_mod != 3) + goto cannot_emulate; + *(u16 *)&c->regs[c->modrm_rm] + = realmode_get_cr(ctxt->vcpu, 0); + break; + case 6: /* lmsw */ + if (c->modrm_mod != 3) + goto cannot_emulate; + realmode_lmsw(ctxt->vcpu, (u16)c->modrm_val, + &ctxt->eflags); + break; + case 7: /* invlpg*/ + emulate_invlpg(ctxt->vcpu, memop); + break; + default: + goto cannot_emulate; + } + /* Disable writeback. */ + c->dst.type = OP_NONE; + break; + case 0x06: + emulate_clts(ctxt->vcpu); + c->dst.type = OP_NONE; + break; + case 0x08: /* invd */ + case 0x09: /* wbinvd */ + case 0x0d: /* GrpP (prefetch) */ + case 0x18: /* Grp16 (prefetch/nop) */ + c->dst.type = OP_NONE; + break; + case 0x20: /* mov cr, reg */ + if (c->modrm_mod != 3) + goto cannot_emulate; + c->regs[c->modrm_rm] = + realmode_get_cr(ctxt->vcpu, c->modrm_reg); + c->dst.type = OP_NONE; /* no writeback */ + break; + case 0x21: /* mov from dr to reg */ + if (c->modrm_mod != 3) + goto cannot_emulate; + rc = emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]); + if (rc) + goto cannot_emulate; + c->dst.type = OP_NONE; /* no writeback */ + break; + case 0x22: /* mov reg, cr */ + if (c->modrm_mod != 3) + goto cannot_emulate; + realmode_set_cr(ctxt->vcpu, + c->modrm_reg, c->modrm_val, &ctxt->eflags); + c->dst.type = OP_NONE; + break; + case 0x23: /* mov from reg to dr */ + if (c->modrm_mod != 3) + goto cannot_emulate; + rc = emulator_set_dr(ctxt, c->modrm_reg, + c->regs[c->modrm_rm]); + if (rc) + goto cannot_emulate; + c->dst.type = OP_NONE; /* no writeback */ + break; + case 0x30: + /* wrmsr */ + msr_data = (u32)c->regs[VCPU_REGS_RAX] + | ((u64)c->regs[VCPU_REGS_RDX] << 32); + rc = kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data); + if (rc) { + kvm_inject_gp(ctxt->vcpu, 0); + c->eip = ctxt->vcpu->arch.rip; + } + rc = X86EMUL_CONTINUE; + c->dst.type = OP_NONE; + break; + case 0x32: + /* rdmsr */ + rc = kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data); + if (rc) { + kvm_inject_gp(ctxt->vcpu, 0); + c->eip = ctxt->vcpu->arch.rip; + } else { + c->regs[VCPU_REGS_RAX] = (u32)msr_data; + c->regs[VCPU_REGS_RDX] = msr_data >> 32; + } + rc = X86EMUL_CONTINUE; + c->dst.type = OP_NONE; + break; + case 0x40 ... 0x4f: /* cmov */ + c->dst.val = c->dst.orig_val = c->src.val; + if (!test_cc(c->b, ctxt->eflags)) + c->dst.type = OP_NONE; /* no writeback */ + break; + case 0x80 ... 0x8f: /* jnz rel, etc*/ { + long int rel; + + switch (c->op_bytes) { + case 2: + rel = insn_fetch(s16, 2, c->eip); + break; + case 4: + rel = insn_fetch(s32, 4, c->eip); + break; + case 8: + rel = insn_fetch(s64, 8, c->eip); + break; + default: + DPRINTF("jnz: Invalid op_bytes\n"); + goto cannot_emulate; + } + if (test_cc(c->b, ctxt->eflags)) + JMP_REL(rel); + c->dst.type = OP_NONE; + break; + } + case 0xa3: + bt: /* bt */ + c->dst.type = OP_NONE; + /* only subword offset */ + c->src.val &= (c->dst.bytes << 3) - 1; + emulate_2op_SrcV_nobyte("bt", c->src, c->dst, ctxt->eflags); + break; + case 0xab: + bts: /* bts */ + /* only subword offset */ + c->src.val &= (c->dst.bytes << 3) - 1; + emulate_2op_SrcV_nobyte("bts", c->src, c->dst, ctxt->eflags); + break; + case 0xb0 ... 0xb1: /* cmpxchg */ + /* + * Save real source value, then compare EAX against + * destination. + */ + c->src.orig_val = c->src.val; + c->src.val = c->regs[VCPU_REGS_RAX]; + emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); + if (ctxt->eflags & EFLG_ZF) { + /* Success: write back to memory. */ + c->dst.val = c->src.orig_val; + } else { + /* Failure: write the value we saw to EAX. */ + c->dst.type = OP_REG; + c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX]; + } + break; + case 0xb3: + btr: /* btr */ + /* only subword offset */ + c->src.val &= (c->dst.bytes << 3) - 1; + emulate_2op_SrcV_nobyte("btr", c->src, c->dst, ctxt->eflags); + break; + case 0xb6 ... 0xb7: /* movzx */ + c->dst.bytes = c->op_bytes; + c->dst.val = (c->d & ByteOp) ? (u8) c->src.val + : (u16) c->src.val; + break; + case 0xba: /* Grp8 */ + switch (c->modrm_reg & 3) { + case 0: + goto bt; + case 1: + goto bts; + case 2: + goto btr; + case 3: + goto btc; + } + break; + case 0xbb: + btc: /* btc */ + /* only subword offset */ + c->src.val &= (c->dst.bytes << 3) - 1; + emulate_2op_SrcV_nobyte("btc", c->src, c->dst, ctxt->eflags); + break; + case 0xbe ... 0xbf: /* movsx */ + c->dst.bytes = c->op_bytes; + c->dst.val = (c->d & ByteOp) ? (s8) c->src.val : + (s16) c->src.val; + break; + case 0xc3: /* movnti */ + c->dst.bytes = c->op_bytes; + c->dst.val = (c->op_bytes == 4) ? (u32) c->src.val : + (u64) c->src.val; + break; + case 0xc7: /* Grp9 (cmpxchg8b) */ + rc = emulate_grp9(ctxt, ops, memop); + if (rc != 0) + goto done; + c->dst.type = OP_NONE; + break; + } + goto writeback; + +cannot_emulate: + DPRINTF("Cannot emulate %02x\n", c->b); + c->eip = saved_eip; + return -1; +} |