#include "kvm_svm.h"
#include "x86_emulate.h"
+#include "irq.h"
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
-#include <linux/profile.h>
#include <linux/sched.h>
#include <asm/desc.h>
#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);
return svm_features & feat;
}
-static unsigned get_addr_size(struct vcpu_svm *svm)
-{
- struct vmcb_save_area *sa = &svm->vmcb->save;
- u16 cs_attrib;
-
- if (!(sa->cr0 & X86_CR0_PE) || (sa->rflags & X86_EFLAGS_VM))
- return 2;
-
- cs_attrib = sa->cs.attrib;
-
- return (cs_attrib & SVM_SELECTOR_L_MASK) ? 8 :
- (cs_attrib & SVM_SELECTOR_DB_MASK) ? 4 : 2;
-}
-
static inline u8 pop_irq(struct kvm_vcpu *vcpu)
{
int word_index = __ffs(vcpu->irq_summary);
void *iopm_va, *msrpm_va;
int r;
- kvm_emulator_want_group7_invlpg();
-
iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER);
if (!iopm_pages)
*/
/* (1ULL << INTERCEPT_SELECTIVE_CR0) | */
(1ULL << INTERCEPT_CPUID) |
+ (1ULL << INTERCEPT_INVD) |
(1ULL << INTERCEPT_HLT) |
(1ULL << INTERCEPT_INVLPGA) |
(1ULL << INTERCEPT_IOIO_PROT) |
(1ULL << INTERCEPT_STGI) |
(1ULL << INTERCEPT_CLGI) |
(1ULL << INTERCEPT_SKINIT) |
+ (1ULL << INTERCEPT_WBINVD) |
(1ULL << INTERCEPT_MONITOR) |
(1ULL << INTERCEPT_MWAIT);
/* rdx = ?? */
}
+static void 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.sipi_vector << 12;
+ svm->vmcb->save.cs.selector = svm->vcpu.sipi_vector << 8;
+ }
+}
+
static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
{
struct vcpu_svm *svm;
if (err)
goto free_svm;
+ if (irqchip_in_kernel(kvm)) {
+ err = kvm_create_lapic(&svm->vcpu);
+ if (err < 0)
+ goto free_svm;
+ }
+
page = alloc_page(GFP_KERNEL);
if (!page) {
err = -ENOMEM;
delta = vcpu->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++)
wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
rdtscll(vcpu->host_tsc);
+ kvm_put_guest_fpu(vcpu);
}
static void svm_vcpu_decache(struct kvm_vcpu *vcpu)
var->unusable = !var->present;
}
-static void svm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
-{
- struct vmcb_seg *s = svm_seg(vcpu, VCPU_SREG_CS);
-
- *db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
- *l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1;
-}
-
static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
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
svm->vmcb->control.asid = svm_data->next_asid++;
}
-static void svm_invlpg(struct kvm_vcpu *vcpu, gva_t address)
-{
- invlpga(address, to_svm(vcpu)->vmcb->control.asid); // is needed?
-}
-
static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
{
return to_svm(vcpu)->db_regs[dr];
enum emulation_result er;
int r;
- if (is_external_interrupt(exit_int_info))
+ if (!irqchip_in_kernel(kvm) &&
+ is_external_interrupt(exit_int_info))
push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK);
mutex_lock(&kvm->lock);
++svm->vcpu.stat.mmio_exits;
return 0;
case EMULATE_FAIL:
- vcpu_printf(&svm->vcpu, "%s: emulate fail\n", __FUNCTION__);
+ kvm_report_emulation_failure(&svm->vcpu, "pagetable");
break;
default:
BUG();
return 0;
}
-static int io_get_override(struct vcpu_svm *svm,
- struct vmcb_seg **seg,
- int *addr_override)
-{
- u8 inst[MAX_INST_SIZE];
- unsigned ins_length;
- gva_t rip;
- int i;
-
- rip = svm->vmcb->save.rip;
- ins_length = svm->next_rip - rip;
- rip += svm->vmcb->save.cs.base;
-
- if (ins_length > MAX_INST_SIZE)
- printk(KERN_DEBUG
- "%s: inst length err, cs base 0x%llx rip 0x%llx "
- "next rip 0x%llx ins_length %u\n",
- __FUNCTION__,
- svm->vmcb->save.cs.base,
- svm->vmcb->save.rip,
- svm->vmcb->control.exit_info_2,
- ins_length);
-
- if (emulator_read_std(rip, inst, ins_length, &svm->vcpu)
- != X86EMUL_CONTINUE)
- /* #PF */
- return 0;
-
- *addr_override = 0;
- *seg = NULL;
- for (i = 0; i < ins_length; i++)
- switch (inst[i]) {
- case 0xf0:
- case 0xf2:
- case 0xf3:
- case 0x66:
- continue;
- case 0x67:
- *addr_override = 1;
- continue;
- case 0x2e:
- *seg = &svm->vmcb->save.cs;
- continue;
- case 0x36:
- *seg = &svm->vmcb->save.ss;
- continue;
- case 0x3e:
- *seg = &svm->vmcb->save.ds;
- continue;
- case 0x26:
- *seg = &svm->vmcb->save.es;
- continue;
- case 0x64:
- *seg = &svm->vmcb->save.fs;
- continue;
- case 0x65:
- *seg = &svm->vmcb->save.gs;
- continue;
- default:
- return 1;
- }
- printk(KERN_DEBUG "%s: unexpected\n", __FUNCTION__);
- return 0;
-}
-
-static unsigned long io_address(struct vcpu_svm *svm, int ins, gva_t *address)
-{
- unsigned long addr_mask;
- unsigned long *reg;
- struct vmcb_seg *seg;
- int addr_override;
- struct vmcb_save_area *save_area = &svm->vmcb->save;
- u16 cs_attrib = save_area->cs.attrib;
- unsigned addr_size = get_addr_size(svm);
-
- if (!io_get_override(svm, &seg, &addr_override))
- return 0;
-
- if (addr_override)
- addr_size = (addr_size == 2) ? 4: (addr_size >> 1);
-
- if (ins) {
- reg = &svm->vcpu.regs[VCPU_REGS_RDI];
- seg = &svm->vmcb->save.es;
- } else {
- reg = &svm->vcpu.regs[VCPU_REGS_RSI];
- seg = (seg) ? seg : &svm->vmcb->save.ds;
- }
-
- addr_mask = ~0ULL >> (64 - (addr_size * 8));
-
- if ((cs_attrib & SVM_SELECTOR_L_MASK) &&
- !(svm->vmcb->save.rflags & X86_EFLAGS_VM)) {
- *address = (*reg & addr_mask);
- return addr_mask;
- }
-
- if (!(seg->attrib & SVM_SELECTOR_P_SHIFT)) {
- svm_inject_gp(&svm->vcpu, 0);
- return 0;
- }
-
- *address = (*reg & addr_mask) + seg->base;
- return addr_mask;
-}
-
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;
- unsigned long count;
- gva_t address = 0;
++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) == 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;
- string = (io_info & SVM_IOIO_STR_MASK) != 0;
rep = (io_info & SVM_IOIO_REP_MASK) != 0;
- count = 1;
down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0;
- if (string) {
- unsigned addr_mask;
-
- addr_mask = io_address(svm, in, &address);
- if (!addr_mask) {
- printk(KERN_DEBUG "%s: get io address failed\n",
- __FUNCTION__);
- return 1;
- }
-
- if (rep)
- count = svm->vcpu.regs[VCPU_REGS_RCX] & addr_mask;
- }
- return kvm_setup_pio(&svm->vcpu, kvm_run, in, size, count, string,
- down, address, rep, port);
+ 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)
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
[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_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 vcpu_svm *svm, struct kvm_run *kvm_run)
+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 "
}
-static inline void inject_irq(struct vcpu_svm *svm)
+static inline void svm_inject_irq(struct vcpu_svm *svm, int irq)
{
struct vmcb_control_area *control;
control = &svm->vmcb->control;
- control->int_vector = pop_irq(&svm->vcpu);
+ 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 reput_irq(struct vcpu_svm *svm)
+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;
+
+ kvm_inject_pending_timer_irqs(vcpu);
+ 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) {
+ 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);
}
!(control->int_state & SVM_INTERRUPT_SHADOW_MASK);
}
-static void do_interrupt_requests(struct vcpu_svm *svm,
+static void svm_do_inject_vector(struct vcpu_svm *svm)
+{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ int word_index = __ffs(vcpu->irq_summary);
+ int bit_index = __ffs(vcpu->irq_pending[word_index]);
+ int irq = word_index * BITS_PER_LONG + bit_index;
+
+ clear_bit(bit_index, &vcpu->irq_pending[word_index]);
+ if (!vcpu->irq_pending[word_index])
+ clear_bit(word_index, &vcpu->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.interrupt_window_open =
/*
* If interrupts enabled, and not blocked by sti or mov ss. Good.
*/
- inject_irq(svm);
+ svm_do_inject_vector(svm);
/*
* Interrupts blocked. Wait for unblock.
control->intercept &= ~(1ULL << INTERCEPT_VINTR);
}
-static void post_kvm_run_save(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
-{
- kvm_run->ready_for_interrupt_injection
- = (svm->vcpu.interrupt_window_open &&
- svm->vcpu.irq_summary == 0);
- kvm_run->if_flag = (svm->vmcb->save.rflags & X86_EFLAGS_IF) != 0;
- kvm_run->cr8 = svm->vcpu.cr8;
- kvm_run->apic_base = svm->vcpu.apic_base;
-}
-
-/*
- * 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 vcpu_svm *svm,
- struct kvm_run *kvm_run)
-{
- return (!svm->vcpu.irq_summary &&
- kvm_run->request_interrupt_window &&
- svm->vcpu.interrupt_window_open &&
- (svm->vmcb->save.rflags & X86_EFLAGS_IF));
-}
-
static void save_db_regs(unsigned long *db_regs)
{
asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0]));
force_new_asid(vcpu);
}
-static int svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+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;
- int r;
-
-again:
- r = kvm_mmu_reload(vcpu);
- if (unlikely(r))
- return r;
-
- if (!vcpu->mmio_read_completed)
- do_interrupt_requests(svm, kvm_run);
-
- clgi();
-
- vcpu->guest_mode = 1;
- if (vcpu->requests)
- if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
- svm_flush_tlb(vcpu);
pre_svm_run(svm);
load_db_regs(svm->db_regs);
}
- if (vcpu->fpu_active) {
- fx_save(&vcpu->host_fx_image);
- fx_restore(&vcpu->guest_fx_image);
- }
+ clgi();
+
+ local_irq_enable();
asm volatile (
#ifdef CONFIG_X86_64
#endif
: "cc", "memory" );
- vcpu->guest_mode = 0;
-
- if (vcpu->fpu_active) {
- fx_save(&vcpu->guest_fx_image);
- fx_restore(&vcpu->host_fx_image);
- }
-
if ((svm->vmcb->save.dr7 & 0xff))
load_db_regs(svm->host_db_regs);
reload_tss(vcpu);
- /*
- * Profile KVM exit RIPs:
- */
- if (unlikely(prof_on == KVM_PROFILING))
- profile_hit(KVM_PROFILING,
- (void *)(unsigned long)svm->vmcb->save.rip);
+ local_irq_disable();
stgi();
- reput_irq(svm);
-
svm->next_rip = 0;
-
- 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;
- post_kvm_run_save(svm, kvm_run);
- return 0;
- }
-
- r = handle_exit(svm, kvm_run);
- if (r > 0) {
- if (signal_pending(current)) {
- ++vcpu->stat.signal_exits;
- post_kvm_run_save(svm, kvm_run);
- kvm_run->exit_reason = KVM_EXIT_INTR;
- return -EINTR;
- }
-
- if (dm_request_for_irq_injection(svm, kvm_run)) {
- ++vcpu->stat.request_irq_exits;
- post_kvm_run_save(svm, kvm_run);
- kvm_run->exit_reason = KVM_EXIT_INTR;
- return -EINTR;
- }
- kvm_resched(vcpu);
- goto again;
- }
- post_kvm_run_save(svm, kvm_run);
- return r;
}
static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
*(int *)rtn = 0;
}
-static struct kvm_arch_ops svm_arch_ops = {
+static struct kvm_x86_ops svm_x86_ops = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.hardware_setup = svm_hardware_setup,
.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,
.get_segment_base = svm_get_segment_base,
.get_segment = svm_get_segment,
.set_segment = svm_set_segment,
- .get_cs_db_l_bits = svm_get_cs_db_l_bits,
+ .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,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
- .invlpg = svm_invlpg,
.tlb_flush = svm_flush_tlb,
.inject_page_fault = svm_inject_page_fault,
.inject_gp = svm_inject_gp,
.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,
+ .inject_pending_irq = svm_intr_assist,
+ .inject_pending_vectors = do_interrupt_requests,
};
static int __init svm_init(void)
{
- return kvm_init_arch(&svm_arch_ops, sizeof(struct vcpu_svm),
+ return kvm_init_x86(&svm_x86_ops, sizeof(struct vcpu_svm),
THIS_MODULE);
}
static void __exit svm_exit(void)
{
- kvm_exit_arch();
+ kvm_exit_x86();
}
module_init(svm_init)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff