Commit 6cd8e300 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
  KVM: Prevent overflow in largepages calculation
  KVM: Disable large pages on misaligned memory slots
  KVM: Add VT-x machine check support
  KVM: VMX: Rename rmode.active to rmode.vm86_active
  KVM: Move "exit due to NMI" handling into vmx_complete_interrupts()
  KVM: Disable CR8 intercept if tpr patching is active
  KVM: Do not migrate pending software interrupts.
  KVM: inject NMI after IRET from a previous NMI, not before.
  KVM: Always request IRQ/NMI window if an interrupt is pending
  KVM: Do not re-execute INTn instruction.
  KVM: skip_emulated_instruction() decode instruction if size is not known
  KVM: Remove irq_pending bitmap
  KVM: Do not allow interrupt injection from userspace if there is a pending event.
  KVM: Unprotect a page if #PF happens during NMI injection.
  KVM: s390: Verify memory in kvm run
  KVM: s390: Sanity check on validity intercept
  KVM: s390: Unlink vcpu on destroy - v2
  KVM: s390: optimize float int lock: spin_lock_bh --> spin_lock
  KVM: s390: use hrtimer for clock wakeup from idle - v2
  KVM: s390: Fix memory slot versus run - v3
  ...
parents ddbb8684 09f8ca74
......@@ -371,6 +371,7 @@ struct kvm_vcpu_arch {
int last_run_cpu;
int vmm_tr_slot;
int vm_tr_slot;
int sn_rtc_tr_slot;
#define KVM_MP_STATE_RUNNABLE 0
#define KVM_MP_STATE_UNINITIALIZED 1
......@@ -465,6 +466,7 @@ struct kvm_arch {
unsigned long vmm_init_rr;
int online_vcpus;
int is_sn2;
struct kvm_ioapic *vioapic;
struct kvm_vm_stat stat;
......@@ -472,6 +474,7 @@ struct kvm_arch {
struct list_head assigned_dev_head;
struct iommu_domain *iommu_domain;
int iommu_flags;
struct hlist_head irq_ack_notifier_list;
unsigned long irq_sources_bitmap;
......@@ -578,6 +581,8 @@ struct kvm_vmm_info{
kvm_vmm_entry *vmm_entry;
kvm_tramp_entry *tramp_entry;
unsigned long vmm_ivt;
unsigned long patch_mov_ar;
unsigned long patch_mov_ar_sn2;
};
int kvm_highest_pending_irq(struct kvm_vcpu *vcpu);
......@@ -585,7 +590,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu);
int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
void kvm_sal_emul(struct kvm_vcpu *vcpu);
static inline void kvm_inject_nmi(struct kvm_vcpu *vcpu) {}
#endif /* __ASSEMBLY__*/
#endif
......@@ -146,6 +146,8 @@
#define PAGE_GATE __pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_X_RX)
#define PAGE_KERNEL __pgprot(__DIRTY_BITS | _PAGE_PL_0 | _PAGE_AR_RWX)
#define PAGE_KERNELRX __pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_RX)
#define PAGE_KERNEL_UC __pgprot(__DIRTY_BITS | _PAGE_PL_0 | _PAGE_AR_RWX | \
_PAGE_MA_UC)
# ifndef __ASSEMBLY__
......
......@@ -610,6 +610,9 @@ static struct irqaction ipi_irqaction = {
.name = "IPI"
};
/*
* KVM uses this interrupt to force a cpu out of guest mode
*/
static struct irqaction resched_irqaction = {
.handler = dummy_handler,
.flags = IRQF_DISABLED,
......
......@@ -23,7 +23,7 @@ if VIRTUALIZATION
config KVM
tristate "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM && EXPERIMENTAL
depends on HAVE_KVM && MODULES && EXPERIMENTAL
# for device assignment:
depends on PCI
select PREEMPT_NOTIFIERS
......
......@@ -41,6 +41,9 @@
#include <asm/div64.h>
#include <asm/tlb.h>
#include <asm/elf.h>
#include <asm/sn/addrs.h>
#include <asm/sn/clksupport.h>
#include <asm/sn/shub_mmr.h>
#include "misc.h"
#include "vti.h"
......@@ -65,6 +68,16 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ NULL }
};
static unsigned long kvm_get_itc(struct kvm_vcpu *vcpu)
{
#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
if (vcpu->kvm->arch.is_sn2)
return rtc_time();
else
#endif
return ia64_getreg(_IA64_REG_AR_ITC);
}
static void kvm_flush_icache(unsigned long start, unsigned long len)
{
int l;
......@@ -119,8 +132,7 @@ void kvm_arch_hardware_enable(void *garbage)
unsigned long saved_psr;
int slot;
pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
PAGE_KERNEL));
pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL));
local_irq_save(saved_psr);
slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
local_irq_restore(saved_psr);
......@@ -283,6 +295,18 @@ static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
static int __apic_accept_irq(struct kvm_vcpu *vcpu, uint64_t vector)
{
struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
if (!test_and_set_bit(vector, &vpd->irr[0])) {
vcpu->arch.irq_new_pending = 1;
kvm_vcpu_kick(vcpu);
return 1;
}
return 0;
}
/*
* offset: address offset to IPI space.
* value: deliver value.
......@@ -292,20 +316,20 @@ static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm,
{
switch (dm) {
case SAPIC_FIXED:
kvm_apic_set_irq(vcpu, vector, 0);
break;
case SAPIC_NMI:
kvm_apic_set_irq(vcpu, 2, 0);
vector = 2;
break;
case SAPIC_EXTINT:
kvm_apic_set_irq(vcpu, 0, 0);
vector = 0;
break;
case SAPIC_INIT:
case SAPIC_PMI:
default:
printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n");
break;
return;
}
__apic_accept_irq(vcpu, vector);
}
static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
......@@ -413,6 +437,23 @@ static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
static int kvm_sn2_setup_mappings(struct kvm_vcpu *vcpu)
{
unsigned long pte, rtc_phys_addr, map_addr;
int slot;
map_addr = KVM_VMM_BASE + (1UL << KVM_VMM_SHIFT);
rtc_phys_addr = LOCAL_MMR_OFFSET | SH_RTC;
pte = pte_val(mk_pte_phys(rtc_phys_addr, PAGE_KERNEL_UC));
slot = ia64_itr_entry(0x3, map_addr, pte, PAGE_SHIFT);
vcpu->arch.sn_rtc_tr_slot = slot;
if (slot < 0) {
printk(KERN_ERR "Mayday mayday! RTC mapping failed!\n");
slot = 0;
}
return slot;
}
int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
......@@ -426,7 +467,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
if (irqchip_in_kernel(vcpu->kvm)) {
vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset;
vcpu_now_itc = kvm_get_itc(vcpu) + vcpu->arch.itc_offset;
if (time_after(vcpu_now_itc, vpd->itm)) {
vcpu->arch.timer_check = 1;
......@@ -447,10 +488,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
hrtimer_cancel(p_ht);
vcpu->arch.ht_active = 0;
if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) ||
kvm_cpu_has_pending_timer(vcpu))
if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
vcpu->arch.mp_state =
KVM_MP_STATE_RUNNABLE;
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
return -EINTR;
......@@ -551,22 +592,35 @@ static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu)
if (r < 0)
goto out;
vcpu->arch.vm_tr_slot = r;
#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
if (kvm->arch.is_sn2) {
r = kvm_sn2_setup_mappings(vcpu);
if (r < 0)
goto out;
}
#endif
r = 0;
out:
return r;
}
static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot);
ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot);
#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
if (kvm->arch.is_sn2)
ia64_ptr_entry(0x3, vcpu->arch.sn_rtc_tr_slot);
#endif
}
static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
{
unsigned long psr;
int r;
int cpu = smp_processor_id();
if (vcpu->arch.last_run_cpu != cpu ||
......@@ -578,36 +632,27 @@ static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
vcpu->arch.host_rr6 = ia64_get_rr(RR6);
vti_set_rr6(vcpu->arch.vmm_rr);
return kvm_insert_vmm_mapping(vcpu);
local_irq_save(psr);
r = kvm_insert_vmm_mapping(vcpu);
local_irq_restore(psr);
return r;
}
static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
{
kvm_purge_vmm_mapping(vcpu);
vti_set_rr6(vcpu->arch.host_rr6);
}
static int vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
union context *host_ctx, *guest_ctx;
int r;
/*Get host and guest context with guest address space.*/
host_ctx = kvm_get_host_context(vcpu);
guest_ctx = kvm_get_guest_context(vcpu);
r = kvm_vcpu_pre_transition(vcpu);
if (r < 0)
goto out;
kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
kvm_vcpu_post_transition(vcpu);
r = 0;
out:
return r;
}
static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
/*
* down_read() may sleep and return with interrupts enabled
*/
down_read(&vcpu->kvm->slots_lock);
again:
if (signal_pending(current)) {
......@@ -616,26 +661,31 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
goto out;
}
/*
* down_read() may sleep and return with interrupts enabled
*/
down_read(&vcpu->kvm->slots_lock);
preempt_disable();
local_irq_disable();
vcpu->guest_mode = 1;
/*Get host and guest context with guest address space.*/
host_ctx = kvm_get_host_context(vcpu);
guest_ctx = kvm_get_guest_context(vcpu);
clear_bit(KVM_REQ_KICK, &vcpu->requests);
r = kvm_vcpu_pre_transition(vcpu);
if (r < 0)
goto vcpu_run_fail;
up_read(&vcpu->kvm->slots_lock);
kvm_guest_enter();
r = vti_vcpu_run(vcpu, kvm_run);
if (r < 0) {
local_irq_enable();
preempt_enable();
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
goto out;
}
/*
* Transition to the guest
*/
kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
kvm_vcpu_post_transition(vcpu);
vcpu->arch.launched = 1;
vcpu->guest_mode = 0;
set_bit(KVM_REQ_KICK, &vcpu->requests);
local_irq_enable();
/*
......@@ -646,9 +696,10 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
*/
barrier();
kvm_guest_exit();
up_read(&vcpu->kvm->slots_lock);
preempt_enable();
down_read(&vcpu->kvm->slots_lock);
r = kvm_handle_exit(kvm_run, vcpu);
if (r > 0) {
......@@ -657,12 +708,20 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
out:
up_read(&vcpu->kvm->slots_lock);
if (r > 0) {
kvm_resched(vcpu);
down_read(&vcpu->kvm->slots_lock);
goto again;
}
return r;
vcpu_run_fail:
local_irq_enable();
preempt_enable();
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
goto out;
}
static void kvm_set_mmio_data(struct kvm_vcpu *vcpu)
......@@ -788,6 +847,9 @@ struct kvm *kvm_arch_create_vm(void)
if (IS_ERR(kvm))
return ERR_PTR(-ENOMEM);
kvm->arch.is_sn2 = ia64_platform_is("sn2");
kvm_init_vm(kvm);
kvm->arch.online_vcpus = 0;
......@@ -884,7 +946,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
RESTORE_REGS(saved_gp);
vcpu->arch.irq_new_pending = 1;
vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC);
vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu);
set_bit(KVM_REQ_RESUME, &vcpu->requests);
vcpu_put(vcpu);
......@@ -1043,10 +1105,6 @@ static void kvm_free_vmm_area(void)
}
}
static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
}
static int vti_init_vpd(struct kvm_vcpu *vcpu)
{
int i;
......@@ -1165,7 +1223,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
regs->cr_iip = PALE_RESET_ENTRY;
/*Initialize itc offset for vcpus*/
itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
itc_offset = 0UL - kvm_get_itc(vcpu);
for (i = 0; i < kvm->arch.online_vcpus; i++) {
v = (struct kvm_vcpu *)((char *)vcpu +
sizeof(struct kvm_vcpu_data) * i);
......@@ -1237,6 +1295,7 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
local_irq_save(psr);
r = kvm_insert_vmm_mapping(vcpu);
local_irq_restore(psr);
if (r)
goto fail;
r = kvm_vcpu_init(vcpu, vcpu->kvm, id);
......@@ -1254,13 +1313,11 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
goto uninit;
kvm_purge_vmm_mapping(vcpu);
local_irq_restore(psr);
return 0;
uninit:
kvm_vcpu_uninit(vcpu);
fail:
local_irq_restore(psr);
return r;
}
......@@ -1291,7 +1348,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu->kvm = kvm;
cpu = get_cpu();
vti_vcpu_load(vcpu, cpu);
r = vti_vcpu_setup(vcpu, id);
put_cpu();
......@@ -1427,7 +1483,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
}
for (i = 0; i < 4; i++)
regs->insvc[i] = vcpu->arch.insvc[i];
regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC);
regs->saved_itc = vcpu->arch.itc_offset + kvm_get_itc(vcpu);
SAVE_REGS(xtp);
SAVE_REGS(metaphysical_rr0);
SAVE_REGS(metaphysical_rr4);
......@@ -1574,6 +1630,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
void kvm_arch_flush_shadow(struct kvm *kvm)
{
kvm_flush_remote_tlbs(kvm);
}
long kvm_arch_dev_ioctl(struct file *filp,
......@@ -1616,8 +1673,37 @@ static int vti_cpu_has_kvm_support(void)
return 0;
}
/*
* On SN2, the ITC isn't stable, so copy in fast path code to use the
* SN2 RTC, replacing the ITC based default verion.
*/
static void kvm_patch_vmm(struct kvm_vmm_info *vmm_info,
struct module *module)
{
unsigned long new_ar, new_ar_sn2;
unsigned long module_base;
if (!ia64_platform_is("sn2"))
return;
module_base = (unsigned long)module->module_core;
new_ar = kvm_vmm_base + vmm_info->patch_mov_ar - module_base;
new_ar_sn2 = kvm_vmm_base + vmm_info->patch_mov_ar_sn2 - module_base;
printk(KERN_INFO "kvm: Patching ITC emulation to use SGI SN2 RTC "
"as source\n");
/*
* Copy the SN2 version of mov_ar into place. They are both
* the same size, so 6 bundles is sufficient (6 * 0x10).
*/
memcpy((void *)new_ar, (void *)new_ar_sn2, 0x60);
}
static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
struct module *module)
struct module *module)
{
unsigned long module_base;
unsigned long vmm_size;
......@@ -1639,6 +1725,7 @@ static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
return -EFAULT;
memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size);
kvm_patch_vmm(vmm_info, module);
kvm_flush_icache(kvm_vmm_base, vmm_size);
/*Recalculate kvm_vmm_info based on new VMM*/
......@@ -1792,38 +1879,24 @@ void kvm_arch_hardware_unsetup(void)
{
}
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;
int cpu = get_cpu();
int me;
int cpu = vcpu->cpu;
if (waitqueue_active(&vcpu->wq))
wake_up_interruptible(&vcpu->wq);
if (vcpu->guest_mode && cpu != ipi_pcpu)
smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);
me = get_cpu();
if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu))
if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
smp_send_reschedule(cpu);
put_cpu();
}
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
{
struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
if (!test_and_set_bit(vec, &vpd->irr[0])) {
vcpu->arch.irq_new_pending = 1;
kvm_vcpu_kick(vcpu);
return 1;
}
return 0;
return __apic_accept_irq(vcpu, irq->vector);
}
int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
......@@ -1836,20 +1909,18 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
return 0;
}
struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
unsigned long bitmap)
int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
{
struct kvm_vcpu *lvcpu = kvm->vcpus[0];
int i;
for (i = 1; i < kvm->arch.online_vcpus; i++) {
if (!kvm->vcpus[i])
continue;
if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp)
lvcpu = kvm->vcpus[i];
}
return vcpu1->arch.xtp - vcpu2->arch.xtp;
}
return lvcpu;
int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, int dest, int dest_mode)
{
struct kvm_lapic *target = vcpu->arch.apic;
return (dest_mode == 0) ?
kvm_apic_match_physical_addr(target, dest) :
kvm_apic_match_logical_addr(target, dest);
}
static int find_highest_bits(int *dat)
......@@ -1888,6 +1959,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
return 0;
}
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
{
/* do real check here */
return 1;
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
return vcpu->arch.timer_fired;
......@@ -1918,6 +1995,7 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
long psr;
local_irq_save(psr);
r = kvm_insert_vmm_mapping(vcpu);
local_irq_restore(psr);
if (r)
goto fail;
......@@ -1930,7 +2008,6 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
kvm_purge_vmm_mapping(vcpu);
r = 0;
fail:
local_irq_restore(psr);
return r;
}
......
......@@ -21,6 +21,9 @@
#include <linux/kvm_host.h>
#include <linux/smp.h>
#include <asm/sn/addrs.h>
#include <asm/sn/clksupport.h>
#include <asm/sn/shub_mmr.h>
#include "vti.h"
#include "misc.h"
......@@ -188,12 +191,35 @@ static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu)
return result;
}
static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu)
/*
* On the SGI SN2, the ITC isn't stable. Emulation backed by the SN2
* RTC is used instead. This function patches the ratios from SAL
* to match the RTC before providing them to the guest.
*/
static void sn2_patch_itc_freq_ratios(struct ia64_pal_retval *result)