diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-05 14:47:31 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-05 14:47:31 -0700 |
commit | 01227a889ed56ae53aeebb9f93be9d54dd8b2de8 (patch) | |
tree | d5eba9359a9827e84d4112b84d48c54df5c5acde /arch/x86/kvm | |
parent | 9e6879460c8edb0cd3c24c09b83d06541b5af0dc (diff) | |
parent | db6ae6158186a17165ef990bda2895ae7594b039 (diff) | |
download | lwn-01227a889ed56ae53aeebb9f93be9d54dd8b2de8.tar.gz lwn-01227a889ed56ae53aeebb9f93be9d54dd8b2de8.zip |
Merge tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Gleb Natapov:
"Highlights of the updates are:
general:
- new emulated device API
- legacy device assignment is now optional
- irqfd interface is more generic and can be shared between arches
x86:
- VMCS shadow support and other nested VMX improvements
- APIC virtualization and Posted Interrupt hardware support
- Optimize mmio spte zapping
ppc:
- BookE: in-kernel MPIC emulation with irqfd support
- Book3S: in-kernel XICS emulation (incomplete)
- Book3S: HV: migration fixes
- BookE: more debug support preparation
- BookE: e6500 support
ARM:
- reworking of Hyp idmaps
s390:
- ioeventfd for virtio-ccw
And many other bug fixes, cleanups and improvements"
* tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
kvm: Add compat_ioctl for device control API
KVM: x86: Account for failing enable_irq_window for NMI window request
KVM: PPC: Book3S: Add API for in-kernel XICS emulation
kvm/ppc/mpic: fix missing unlock in set_base_addr()
kvm/ppc: Hold srcu lock when calling kvm_io_bus_read/write
kvm/ppc/mpic: remove users
kvm/ppc/mpic: fix mmio region lists when multiple guests used
kvm/ppc/mpic: remove default routes from documentation
kvm: KVM_CAP_IOMMU only available with device assignment
ARM: KVM: iterate over all CPUs for CPU compatibility check
KVM: ARM: Fix spelling in error message
ARM: KVM: define KVM_ARM_MAX_VCPUS unconditionally
KVM: ARM: Fix API documentation for ONE_REG encoding
ARM: KVM: promote vfp_host pointer to generic host cpu context
ARM: KVM: add architecture specific hook for capabilities
ARM: KVM: perform HYP initilization for hotplugged CPUs
ARM: KVM: switch to a dual-step HYP init code
ARM: KVM: rework HYP page table freeing
ARM: KVM: enforce maximum size for identity mapped code
ARM: KVM: move to a KVM provided HYP idmap
...
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 14 | ||||
-rw-r--r-- | arch/x86/kvm/Makefile | 5 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 31 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.c | 4 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 189 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 22 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 108 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 11 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 14 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 40 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 1077 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 243 |
13 files changed, 1253 insertions, 507 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 586f00059805..a47a3e54b964 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -21,14 +21,13 @@ config KVM tristate "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM depends on HIGH_RES_TIMERS - # for device assignment: - depends on PCI # for TASKSTATS/TASK_DELAY_ACCT: depends on NET select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE select KVM_ASYNC_PF @@ -82,6 +81,17 @@ config KVM_MMU_AUDIT This option adds a R/W kVM module parameter 'mmu_audit', which allows audit KVM MMU at runtime. +config KVM_DEVICE_ASSIGNMENT + bool "KVM legacy PCI device assignment support" + depends on KVM && PCI && IOMMU_API + default y + ---help--- + Provide support for legacy PCI device assignment through KVM. The + kernel now also supports a full featured userspace device driver + framework through VFIO, which supersedes much of this support. + + If unsure, say Y. + # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/vhost/Kconfig diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 04d30401c5cb..d609e1d84048 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -7,8 +7,9 @@ CFLAGS_vmx.o := -I. kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ coalesced_mmio.o irq_comm.o eventfd.o \ - assigned-dev.o) -kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) + irqchip.o) +kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(addprefix ../../../virt/kvm/, \ + assigned-dev.o iommu.o) kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a335cc6cde72..8e517bba6a7c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -132,8 +132,9 @@ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) #define PageTable (1 << 29) /* instruction used to write page table */ +#define NotImpl (1 << 30) /* instruction is not implemented */ /* Source 2 operand type */ -#define Src2Shift (30) +#define Src2Shift (31) #define Src2None (OpNone << Src2Shift) #define Src2CL (OpCL << Src2Shift) #define Src2ImmByte (OpImmByte << Src2Shift) @@ -1578,12 +1579,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, memset(&seg_desc, 0, sizeof seg_desc); - if ((seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86) - || ctxt->mode == X86EMUL_MODE_REAL) { - /* set real mode segment descriptor */ + if (ctxt->mode == X86EMUL_MODE_REAL) { + /* set real mode segment descriptor (keep limit etc. for + * unreal mode) */ ctxt->ops->get_segment(ctxt, &dummy, &seg_desc, NULL, seg); set_desc_base(&seg_desc, selector << 4); goto load; + } else if (seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86) { + /* VM86 needs a clean new segment descriptor */ + set_desc_base(&seg_desc, selector << 4); + set_desc_limit(&seg_desc, 0xffff); + seg_desc.type = 3; + seg_desc.p = 1; + seg_desc.s = 1; + seg_desc.dpl = 3; + goto load; } rpl = selector & 3; @@ -3615,7 +3625,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) #define DI(_y, _i) { .flags = (_y), .intercept = x86_intercept_##_i } #define DIP(_y, _i, _p) { .flags = (_y), .intercept = x86_intercept_##_i, \ .check_perm = (_p) } -#define N D(0) +#define N D(NotImpl) #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) } #define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) } #define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) } @@ -3713,7 +3723,7 @@ static const struct opcode group5[] = { I(SrcMemFAddr | ImplicitOps | Stack, em_call_far), I(SrcMem | Stack, em_grp45), I(SrcMemFAddr | ImplicitOps, em_grp45), - I(SrcMem | Stack, em_grp45), N, + I(SrcMem | Stack, em_grp45), D(Undefined), }; static const struct opcode group6[] = { @@ -4162,6 +4172,10 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, break; case OpMem8: ctxt->memop.bytes = 1; + if (ctxt->memop.type == OP_REG) { + ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1); + fetch_register_operand(&ctxt->memop); + } goto mem_common; case OpMem16: ctxt->memop.bytes = 2; @@ -4373,7 +4387,7 @@ done_prefixes: ctxt->intercept = opcode.intercept; /* Unrecognised? */ - if (ctxt->d == 0 || (ctxt->d & Undefined)) + if (ctxt->d == 0 || (ctxt->d & NotImpl)) return EMULATION_FAILED; if (!(ctxt->d & VendorSpecific) && ctxt->only_vendor_specific_insn) @@ -4511,7 +4525,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) ctxt->mem_read.pos = 0; - if (ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) { + if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) || + (ctxt->d & Undefined)) { rc = emulate_ud(ctxt); goto done; } diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index c1d30b2fc9bb..412a5aa0ef94 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -290,8 +290,8 @@ static void pit_do_work(struct kthread_work *work) } spin_unlock(&ps->inject_lock); if (inject) { - kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); - kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1, false); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0, false); /* * Provides NMI watchdog support via Virtual Wire mode. diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f77df1c5de6e..e1adbb4aca75 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -94,6 +94,14 @@ static inline int apic_test_vector(int vec, void *bitmap) return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } +bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + return apic_test_vector(vector, apic->regs + APIC_ISR) || + apic_test_vector(vector, apic->regs + APIC_IRR); +} + static inline void apic_set_vector(int vec, void *bitmap) { set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -145,53 +153,6 @@ static inline int kvm_apic_id(struct kvm_lapic *apic) return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } -void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, - struct kvm_lapic_irq *irq, - u64 *eoi_exit_bitmap) -{ - struct kvm_lapic **dst; - struct kvm_apic_map *map; - unsigned long bitmap = 1; - int i; - - rcu_read_lock(); - map = rcu_dereference(vcpu->kvm->arch.apic_map); - - if (unlikely(!map)) { - __set_bit(irq->vector, (unsigned long *)eoi_exit_bitmap); - goto out; - } - - if (irq->dest_mode == 0) { /* physical mode */ - if (irq->delivery_mode == APIC_DM_LOWEST || - irq->dest_id == 0xff) { - __set_bit(irq->vector, - (unsigned long *)eoi_exit_bitmap); - goto out; - } - dst = &map->phys_map[irq->dest_id & 0xff]; - } else { - u32 mda = irq->dest_id << (32 - map->ldr_bits); - - dst = map->logical_map[apic_cluster_id(map, mda)]; - - bitmap = apic_logical_id(map, mda); - } - - for_each_set_bit(i, &bitmap, 16) { - if (!dst[i]) - continue; - if (dst[i]->vcpu == vcpu) { - __set_bit(irq->vector, - (unsigned long *)eoi_exit_bitmap); - break; - } - } - -out: - rcu_read_unlock(); -} - static void recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -256,7 +217,7 @@ out: if (old) kfree_rcu(old, rcu); - kvm_ioapic_make_eoibitmap_request(kvm); + kvm_vcpu_request_scan_ioapic(kvm); } static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id) @@ -357,6 +318,19 @@ static u8 count_vectors(void *bitmap) return count; } +void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) +{ + u32 i, pir_val; + struct kvm_lapic *apic = vcpu->arch.apic; + + for (i = 0; i <= 7; i++) { + pir_val = xchg(&pir[i], 0); + if (pir_val) + *((u32 *)(apic->regs + APIC_IRR + i * 0x10)) |= pir_val; + } +} +EXPORT_SYMBOL_GPL(kvm_apic_update_irr); + static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) { apic->irr_pending = true; @@ -379,6 +353,7 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) if (!apic->irr_pending) return -1; + kvm_x86_ops->sync_pir_to_irr(apic->vcpu); result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); @@ -431,14 +406,16 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) } static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, - int vector, int level, int trig_mode); + int vector, int level, int trig_mode, + unsigned long *dest_map); -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, + unsigned long *dest_map) { struct kvm_lapic *apic = vcpu->arch.apic; return __apic_accept_irq(apic, irq->delivery_mode, irq->vector, - irq->level, irq->trig_mode); + irq->level, irq->trig_mode, dest_map); } static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val) @@ -505,6 +482,15 @@ static inline int apic_find_highest_isr(struct kvm_lapic *apic) return result; } +void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + int i; + + for (i = 0; i < 8; i++) + apic_set_reg(apic, APIC_TMR + 0x10 * i, tmr[i]); +} + static void apic_update_ppr(struct kvm_lapic *apic) { u32 tpr, isrv, ppr, old_ppr; @@ -611,7 +597,7 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, } bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, int *r) + struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map) { struct kvm_apic_map *map; unsigned long bitmap = 1; @@ -622,7 +608,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, *r = -1; if (irq->shorthand == APIC_DEST_SELF) { - *r = kvm_apic_set_irq(src->vcpu, irq); + *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); return true; } @@ -667,7 +653,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, continue; if (*r < 0) *r = 0; - *r += kvm_apic_set_irq(dst[i]->vcpu, irq); + *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map); } ret = true; @@ -681,7 +667,8 @@ out: * 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 vector, int level, int trig_mode, + unsigned long *dest_map) { int result = 0; struct kvm_vcpu *vcpu = apic->vcpu; @@ -694,24 +681,28 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (unlikely(!apic_enabled(apic))) 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 (dest_map) + __set_bit(vcpu->vcpu_id, dest_map); - result = !apic_test_and_set_irr(vector, apic); - trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, - trig_mode, vector, !result); - if (!result) { - if (trig_mode) - apic_debug("level trig mode repeatedly for " - "vector %d", vector); - break; - } + if (kvm_x86_ops->deliver_posted_interrupt) { + result = 1; + kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); + } else { + result = !apic_test_and_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_vcpu_kick(vcpu); + if (!result) { + if (trig_mode) + apic_debug("level trig mode repeatedly " + "for vector %d", vector); + goto out; + } + + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } +out: + trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector, !result); break; case APIC_DM_REMRD: @@ -731,7 +722,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, case APIC_DM_INIT: if (!trig_mode || level) { result = 1; - vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + /* assumes that there are only KVM_APIC_INIT/SIPI */ + apic->pending_events = (1UL << KVM_APIC_INIT); + /* make sure pending_events is visible before sending + * the request */ + smp_wmb(); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } else { @@ -743,13 +738,13 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, case APIC_DM_STARTUP: apic_debug("SIPI to vcpu %d vector 0x%02x\n", vcpu->vcpu_id, vector); - if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { - result = 1; - vcpu->arch.sipi_vector = vector; - vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED; - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_vcpu_kick(vcpu); - } + result = 1; + apic->sipi_vector = vector; + /* make sure sipi_vector is visible for the receiver */ + smp_wmb(); + set_bit(KVM_APIC_SIPI, &apic->pending_events); + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); break; case APIC_DM_EXTINT: @@ -782,7 +777,7 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; - kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); + kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); } } @@ -848,7 +843,7 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, irq.vector); - kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); + kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL); } static u32 apic_get_tmcct(struct kvm_lapic *apic) @@ -1484,7 +1479,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode); + return __apic_accept_irq(apic, mode, vector, 1, trig_mode, + NULL); } return 0; } @@ -1654,6 +1650,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, apic->highest_isr_cache = -1; kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_rtc_eoi_tracking_restore_one(vcpu); } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) @@ -1860,6 +1857,34 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) addr, sizeof(u8)); } +void kvm_apic_accept_events(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + unsigned int sipi_vector; + + if (!kvm_vcpu_has_lapic(vcpu)) + return; + + if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) { + kvm_lapic_reset(vcpu); + kvm_vcpu_reset(vcpu); + if (kvm_vcpu_is_bsp(apic->vcpu)) + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + else + vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + } + if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) && + vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { + /* evaluate pending_events before reading the vector */ + smp_rmb(); + sipi_vector = apic->sipi_vector; + pr_debug("vcpu %d received sipi with vector # %x\n", + vcpu->vcpu_id, sipi_vector); + kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + } +} + void kvm_lapic_init(void) { /* do not patch jump label more than once per second */ diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 1676d34ddb4e..c730ac9fe801 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -5,6 +5,9 @@ #include <linux/kvm_host.h> +#define KVM_APIC_INIT 0 +#define KVM_APIC_SIPI 1 + struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ @@ -32,6 +35,8 @@ struct kvm_lapic { void *regs; gpa_t vapic_addr; struct page *vapic_page; + unsigned long pending_events; + unsigned int sipi_vector; }; int kvm_create_lapic(struct kvm_vcpu *vcpu); void kvm_free_lapic(struct kvm_vcpu *vcpu); @@ -39,6 +44,7 @@ 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_apic_accept_events(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); @@ -47,13 +53,16 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); +void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr); +void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); 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, struct kvm_lapic_irq *irq); +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, + unsigned long *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, int *r); + struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); @@ -154,8 +163,11 @@ static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) return ldr & map->lid_mask; } -void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, - struct kvm_lapic_irq *irq, - u64 *eoi_bitmap); +static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.apic->pending_events; +} + +bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 956ca358108a..004cc87b781c 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -199,8 +199,11 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); static void mark_mmio_spte(u64 *sptep, u64 gfn, unsigned access) { + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + access &= ACC_WRITE_MASK | ACC_USER_MASK; + sp->mmio_cached = true; trace_mark_mmio_spte(sptep, gfn, access); mmu_spte_set(sptep, shadow_mmio_mask | access | gfn << PAGE_SHIFT); } @@ -1502,6 +1505,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, u64 *parent_pte, int direct) { struct kvm_mmu_page *sp; + sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache); sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); if (!direct) @@ -1644,16 +1648,14 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); -#define for_each_gfn_sp(kvm, sp, gfn) \ - hlist_for_each_entry(sp, \ - &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ - if ((sp)->gfn != (gfn)) {} else +#define for_each_gfn_sp(_kvm, _sp, _gfn) \ + hlist_for_each_entry(_sp, \ + &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ + if ((_sp)->gfn != (_gfn)) {} else -#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn) \ - hlist_for_each_entry(sp, \ - &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ - if ((sp)->gfn != (gfn) || (sp)->role.direct || \ - (sp)->role.invalid) {} else +#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ + for_each_gfn_sp(_kvm, _sp, _gfn) \ + if ((_sp)->role.direct || (_sp)->role.invalid) {} else /* @sp->gfn should be write-protected at the call site */ static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -2089,7 +2091,7 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list) { - struct kvm_mmu_page *sp; + struct kvm_mmu_page *sp, *nsp; if (list_empty(invalid_list)) return; @@ -2106,11 +2108,25 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, */ kvm_flush_remote_tlbs(kvm); - do { - sp = list_first_entry(invalid_list, struct kvm_mmu_page, link); + list_for_each_entry_safe(sp, nsp, invalid_list, link) { WARN_ON(!sp->role.invalid || sp->root_count); kvm_mmu_free_page(sp); - } while (!list_empty(invalid_list)); + } +} + +static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, + struct list_head *invalid_list) +{ + struct kvm_mmu_page *sp; + + if (list_empty(&kvm->arch.active_mmu_pages)) + return false; + + sp = list_entry(kvm->arch.active_mmu_pages.prev, + struct kvm_mmu_page, link); + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + + return true; } /* @@ -2120,23 +2136,15 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) { LIST_HEAD(invalid_list); - /* - * 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 - */ spin_lock(&kvm->mmu_lock); if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) { - while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages && - !list_empty(&kvm->arch.active_mmu_pages)) { - struct kvm_mmu_page *page; + /* Need to free some mmu pages to achieve the goal. */ + while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) + if (!prepare_zap_oldest_mmu_page(kvm, &invalid_list)) + break; - page = container_of(kvm->arch.active_mmu_pages.prev, - struct kvm_mmu_page, link); - kvm_mmu_prepare_zap_page(kvm, page, &invalid_list); - } kvm_mmu_commit_zap_page(kvm, &invalid_list); goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages; } @@ -2794,6 +2802,7 @@ exit: static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, pfn_t *pfn, bool write, bool *writable); +static void make_mmu_pages_available(struct kvm_vcpu *vcpu); static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, gfn_t gfn, bool prefault) @@ -2835,7 +2844,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn, @@ -2913,7 +2922,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL, NULL); ++sp->root_count; @@ -2925,7 +2934,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL, @@ -2964,7 +2973,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL, 0, ACC_ALL, NULL); root = __pa(sp->spt); @@ -2998,7 +3007,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) return 1; } spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, 0, ACC_ALL, NULL); @@ -3304,7 +3313,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); r = __direct_map(vcpu, gpa, write, map_writable, @@ -4006,17 +4015,17 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) +static void make_mmu_pages_available(struct kvm_vcpu *vcpu) { LIST_HEAD(invalid_list); - while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES && - !list_empty(&vcpu->kvm->arch.active_mmu_pages)) { - struct kvm_mmu_page *sp; + if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) + return; + + while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { + if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) + break; - sp = container_of(vcpu->kvm->arch.active_mmu_pages.prev, - struct kvm_mmu_page, link); - kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_recycled; } kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); @@ -4185,17 +4194,22 @@ restart: spin_unlock(&kvm->mmu_lock); } -static void kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, - struct list_head *invalid_list) +void kvm_mmu_zap_mmio_sptes(struct kvm *kvm) { - struct kvm_mmu_page *page; + struct kvm_mmu_page *sp, *node; + LIST_HEAD(invalid_list); - if (list_empty(&kvm->arch.active_mmu_pages)) - return; + spin_lock(&kvm->mmu_lock); +restart: + list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { + if (!sp->mmio_cached) + continue; + if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list)) + goto restart; + } - page = container_of(kvm->arch.active_mmu_pages.prev, - struct kvm_mmu_page, link); - kvm_mmu_prepare_zap_page(kvm, page, invalid_list); + kvm_mmu_commit_zap_page(kvm, &invalid_list); + spin_unlock(&kvm->mmu_lock); } static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) @@ -4232,7 +4246,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); - kvm_mmu_remove_some_alloc_mmu_pages(kvm, &invalid_list); + prepare_zap_oldest_mmu_page(kvm, &invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 69871080e866..2adcbc2cac6d 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -57,14 +57,11 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { - return kvm->arch.n_max_mmu_pages - - kvm->arch.n_used_mmu_pages; -} + if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages) + return kvm->arch.n_max_mmu_pages - + kvm->arch.n_used_mmu_pages; -static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) -{ - if (unlikely(kvm_mmu_available_pages(vcpu->kvm)< KVM_MIN_FREE_MMU_PAGES)) - __kvm_mmu_free_some_pages(vcpu); + return 0; } static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 105dd5bd550e..da20860b457a 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -627,7 +627,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); - kvm_mmu_free_some_pages(vcpu); + make_mmu_pages_available(vcpu); if (!force_pt_level) transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index cfc258a6bf97..c53e797e7369 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -360,10 +360,12 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) return 1; } -int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; + u32 index = msr_info->index; + u64 data = msr_info->data; switch (index) { case MSR_CORE_PERF_FIXED_CTR_CTRL: @@ -375,6 +377,10 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) } break; case MSR_CORE_PERF_GLOBAL_STATUS: + if (msr_info->host_initiated) { + pmu->global_status = data; + return 0; + } break; /* RO MSR */ case MSR_CORE_PERF_GLOBAL_CTRL: if (pmu->global_ctrl == data) @@ -386,7 +392,8 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) break; case MSR_CORE_PERF_GLOBAL_OVF_CTRL: if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { - pmu->global_status &= ~data; + if (!msr_info->host_initiated) + pmu->global_status &= ~data; pmu->global_ovf_ctrl = data; return 0; } @@ -394,7 +401,8 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) default: if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || (pmc = get_fixed_pmc(pmu, index))) { - data = (s64)(s32)data; + if (!msr_info->host_initiated) + data = (s64)(s32)data; pmc->counter += data - read_pmc(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 7d39d70647e3..a14a6eaf871d 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1131,17 +1131,11 @@ static void init_vmcb(struct vcpu_svm *svm) init_seg(&save->gs); save->cs.selector = 0xf000; + save->cs.base = 0xffff0000; /* 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; @@ -1191,7 +1185,7 @@ static void init_vmcb(struct vcpu_svm *svm) enable_gif(svm); } -static int svm_vcpu_reset(struct kvm_vcpu *vcpu) +static void svm_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); u32 dummy; @@ -1199,16 +1193,8 @@ static int svm_vcpu_reset(struct kvm_vcpu *vcpu) init_vmcb(svm); - if (!kvm_vcpu_is_bsp(vcpu)) { - kvm_rip_write(vcpu, 0); - svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12; - svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8; - } - kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy); kvm_register_write(vcpu, VCPU_REGS_RDX, eax); - - return 0; } static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) @@ -3487,7 +3473,7 @@ static int handle_exit(struct kvm_vcpu *vcpu) exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x " + printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " "exit_code 0x%x\n", __func__, svm->vmcb->control.exit_int_info, exit_code); @@ -3591,6 +3577,11 @@ static void svm_hwapic_isr_update(struct kvm *kvm, int isr) return; } +static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + return; +} + static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3641,7 +3632,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) return ret; } -static void enable_irq_window(struct kvm_vcpu *vcpu) +static int enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3655,15 +3646,16 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) svm_set_vintr(svm); svm_inject_irq(svm, 0x0); } + return 0; } -static void enable_nmi_window(struct kvm_vcpu *vcpu) +static int enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); if ((svm->vcpu.arch.hflags & (HF_NMI_MASK | HF_IRET_MASK)) == HF_NMI_MASK) - return; /* IRET will cause a vm exit */ + return 0; /* IRET will cause a vm exit */ /* * Something prevents NMI from been injected. Single step over possible @@ -3672,6 +3664,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); update_db_bp_intercept(vcpu); + return 0; } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -4247,6 +4240,11 @@ out: return ret; } +static void svm_handle_external_intr(struct kvm_vcpu *vcpu) +{ + local_irq_enable(); +} + static struct kvm_x86_ops svm_x86_ops = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -4314,6 +4312,7 @@ static struct kvm_x86_ops svm_x86_ops = { .vm_has_apicv = svm_vm_has_apicv, .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_isr_update = svm_hwapic_isr_update, + .sync_pir_to_irr = svm_sync_pir_to_irr, .set_tss_addr = svm_set_tss_addr, .get_tdp_level = get_npt_level, @@ -4342,6 +4341,7 @@ static struct kvm_x86_ops svm_x86_ops = { .set_tdp_cr3 = set_tdp_cr3, .check_intercept = svm_check_intercept, + .handle_external_intr = svm_handle_external_intr, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 867b81037f96..25a791ed21c8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -84,8 +84,11 @@ module_param(vmm_exclusive, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv_reg_vid; +static bool __read_mostly enable_apicv = 1; +module_param(enable_apicv, bool, S_IRUGO); +static bool __read_mostly enable_shadow_vmcs = 1; +module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not @@ -298,7 +301,8 @@ struct __packed vmcs12 { u32 guest_activity_state; u32 guest_sysenter_cs; u32 host_ia32_sysenter_cs; - u32 padding32[8]; /* room for future expansion */ + u32 vmx_preemption_timer_value; + u32 padding32[7]; /* room for future expansion */ u16 virtual_processor_id; u16 guest_es_selector; u16 guest_cs_selector; @@ -351,6 +355,12 @@ struct nested_vmx { /* The host-usable pointer to the above */ struct page *current_vmcs12_page; struct vmcs12 *current_vmcs12; + struct vmcs *current_shadow_vmcs; + /* + * Indicates if the shadow vmcs must be updated with the + * data hold by vmcs12 + */ + bool sync_shadow_vmcs; /* vmcs02_list cache of VMCSs recently used to run L2 guests */ struct list_head vmcs02_pool; @@ -365,6 +375,31 @@ struct nested_vmx { struct page *apic_access_page; }; +#define POSTED_INTR_ON 0 +/* Posted-Interrupt Descriptor */ +struct pi_desc { + u32 pir[8]; /* Posted interrupt requested */ + u32 control; /* bit 0 of control is outstanding notification bit */ + u32 rsvd[7]; +} __aligned(64); + +static bool pi_test_and_set_on(struct pi_desc *pi_desc) +{ + return test_and_set_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static bool pi_test_and_clear_on(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +{ + return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); +} + struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; @@ -377,6 +412,7 @@ struct vcpu_vmx { struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; + unsigned long host_idt_base; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; @@ -428,6 +464,9 @@ struct vcpu_vmx { bool rdtscp_enabled; + /* Posted interrupt descriptor */ + struct pi_desc pi_desc; + /* Support for a guest hypervisor (nested VMX) */ struct nested_vmx nested; }; @@ -451,6 +490,64 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) #define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ [number##_HIGH] = VMCS12_OFFSET(name)+4 + +static const unsigned long shadow_read_only_fields[] = { + /* + * We do NOT shadow fields that are modified when L0 + * traps and emulates any vmx instruction (e.g. VMPTRLD, + * VMXON...) executed by L1. + * For example, VM_INSTRUCTION_ERROR is read + * by L1 if a vmx instruction fails (part of the error path). + * Note the code assumes this logic. If for some reason + * we start shadowing these fields then we need to + * force a shadow sync when L0 emulates vmx instructions + * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified + * by nested_vmx_failValid) + */ + VM_EXIT_REASON, + VM_EXIT_INTR_INFO, + VM_EXIT_INSTRUCTION_LEN, + IDT_VECTORING_INFO_FIELD, + IDT_VECTORING_ERROR_CODE, + VM_EXIT_INTR_ERROR_CODE, + EXIT_QUALIFICATION, + GUEST_LINEAR_ADDRESS, + GUEST_PHYSICAL_ADDRESS +}; +static const int max_shadow_read_only_fields = + ARRAY_SIZE(shadow_read_only_fields); + +static const unsigned long shadow_read_write_fields[] = { + GUEST_RIP, + GUEST_RSP, + GUEST_CR0, + GUEST_CR3, + GUEST_CR4, + GUEST_INTERRUPTIBILITY_INFO, + GUEST_RFLAGS, + GUEST_CS_SELECTOR, + GUEST_CS_AR_BYTES, + GUEST_CS_LIMIT, + GUEST_CS_BASE, + GUEST_ES_BASE, + CR0_GUEST_HOST_MASK, + CR0_READ_SHADOW, + CR4_READ_SHADOW, + TSC_OFFSET, + EXCEPTION_BITMAP, + CPU_BASED_VM_EXEC_CONTROL, + VM_ENTRY_EXCEPTION_ERROR_CODE, + VM_ENTRY_INTR_INFO_FIELD, + VM_ENTRY_INSTRUCTION_LEN, + VM_ENTRY_EXCEPTION_ERROR_CODE, + HOST_FS_BASE, + HOST_GS_BASE, + HOST_FS_SELECTOR, + HOST_GS_SELECTOR +}; +static const int max_shadow_read_write_fields = + ARRAY_SIZE(shadow_read_write_fields); + static const unsigned short vmcs_field_to_offset_table[] = { FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id), FIELD(GUEST_ES_SELECTOR, guest_es_selector), @@ -537,6 +634,7 @@ static const unsigned short vmcs_field_to_offset_table[] = { FIELD(GUEST_ACTIVITY_STATE, guest_activity_state), FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs), FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs), + FIELD(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value), FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask), FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask), FIELD(CR0_READ_SHADOW, cr0_read_shadow), @@ -624,6 +722,9 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static bool guest_state_valid(struct kvm_vcpu *vcpu); static u32 vmx_segment_access_rights(struct kvm_segment *var); +static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu); +static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); +static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -640,6 +741,8 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static unsigned long *vmx_msr_bitmap_legacy_x2apic; static unsigned long *vmx_msr_bitmap_longmode_x2apic; +static unsigned long *vmx_vmread_bitmap; +static unsigned long *vmx_vmwrite_bitmap; static bool cpu_has_load_ia32_efer; static bool cpu_has_load_perf_global_ctrl; @@ -782,6 +885,18 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; } +static inline bool cpu_has_vmx_posted_intr(void) +{ + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; +} + +static inline bool cpu_has_vmx_apicv(void) +{ + return cpu_has_vmx_apic_register_virt() && + cpu_has_vmx_virtual_intr_delivery() && + cpu_has_vmx_posted_intr(); +} + static inline bool cpu_has_vmx_flexpriority(void) { return cpu_has_vmx_tpr_shadow() && @@ -895,6 +1010,18 @@ static inline bool cpu_has_vmx_wbinvd_exit(void) SECONDARY_EXEC_WBINVD_EXITING; } +static inline bool cpu_has_vmx_shadow_vmcs(void) +{ + u64 vmx_msr; + rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); + /* check if the cpu supports writing r/o exit information fields */ + if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + return false; + + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_SHADOW_VMCS; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -1790,7 +1917,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, u32 intr_info = nr | INTR_INFO_VALID_MASK; if (nr == PF_VECTOR && is_guest_mode(vcpu) && - nested_pf_handled(vcpu)) + !vmx->nested.nested_run_pending && nested_pf_handled(vcpu)) return; if (has_error_code) { @@ -2022,6 +2149,7 @@ static u32 nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high; static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high; static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high; static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high; +static u32 nested_vmx_misc_low, nested_vmx_misc_high; static __init void nested_vmx_setup_ctls_msrs(void) { /* @@ -2040,30 +2168,40 @@ static __init void nested_vmx_setup_ctls_msrs(void) */ /* pin-based controls */ + rdmsr(MSR_IA32_VMX_PINBASED_CTLS, + nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high); /* * According to the Intel spec, if bit 55 of VMX_BASIC is off (as it is * in our case), bits 1, 2 and 4 (i.e., 0x16) must be 1 in this MSR. */ - nested_vmx_pinbased_ctls_low = 0x16 ; - nested_vmx_pinbased_ctls_high = 0x16 | - PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | - PIN_BASED_VIRTUAL_NMIS; + nested_vmx_pinbased_ctls_low |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; + nested_vmx_pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK | + PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | + PIN_BASED_VMX_PREEMPTION_TIMER; + nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; - /* exit controls */ - nested_vmx_exit_ctls_low = 0; + /* + * Exit controls + * If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and + * 17 must be 1. + */ + nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; /* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */ #ifdef CONFIG_X86_64 nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE; #else nested_vmx_exit_ctls_high = 0; #endif + nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high); - nested_vmx_entry_ctls_low = 0; + /* If bit 55 of VMX_BASIC is off, bits 0-8 and 12 must be 1. */ + nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; nested_vmx_entry_ctls_high &= VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE; + nested_vmx_entry_ctls_high |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; /* cpu-based controls */ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, @@ -2080,6 +2218,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING | + CPU_BASED_PAUSE_EXITING | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the @@ -2094,7 +2233,14 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high); nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_WBINVD_EXITING; + + /* miscellaneous data */ + rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high); + nested_vmx_misc_low &= VMX_MISC_PREEMPTION_TIMER_RATE_MASK | + VMX_MISC_SAVE_EFER_LMA; + nested_vmx_misc_high = 0; } static inline bool vmx_control_verify(u32 control, u32 low, u32 high) @@ -2165,7 +2311,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) nested_vmx_entry_ctls_high); break; case MSR_IA32_VMX_MISC: - *pdata = 0; + *pdata = vmx_control_msr(nested_vmx_misc_low, + nested_vmx_misc_high); break; /* * These MSRs specify bits which the guest must keep fixed (on or off) @@ -2529,12 +2676,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) u32 _vmexit_control = 0; u32 _vmentry_control = 0; - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS; - 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 | @@ -2573,7 +2714,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | + SECONDARY_EXEC_SHADOW_VMCS; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2605,11 +2747,23 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) #ifdef CONFIG_X86_64 min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; #endif - opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT; + opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT | + VM_EXIT_ACK_INTR_ON_EXIT; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, &_vmexit_control) < 0) return -EIO; + min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; + opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR; + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, + &_pin_based_exec_control) < 0) + return -EIO; + + if (!(_cpu_based_2nd_exec_control & + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) || + !(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT)) + _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; + min = 0; opt = VM_ENTRY_LOAD_IA32_PAT; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, @@ -2762,6 +2916,8 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_vpid()) enable_vpid = 0; + if (!cpu_has_vmx_shadow_vmcs()) + enable_shadow_vmcs = 0; if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels()) { @@ -2788,14 +2944,16 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ple()) ple_gap = 0; - if (!cpu_has_vmx_apic_register_virt() || - !cpu_has_vmx_virtual_intr_delivery()) - enable_apicv_reg_vid = 0; + if (!cpu_has_vmx_apicv()) + enable_apicv = 0; - if (enable_apicv_reg_vid) + if (enable_apicv) kvm_x86_ops->update_cr8_intercept = NULL; - else + else { kvm_x86_ops->hwapic_irr_update = NULL; + kvm_x86_ops->deliver_posted_interrupt = NULL; + kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy; + } if (nested) nested_vmx_setup_ctls_msrs(); @@ -2876,22 +3034,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->cpl = 0; } -static gva_t rmode_tss_base(struct kvm *kvm) -{ - if (!kvm->arch.tss_addr) { - struct kvm_memslots *slots; - struct kvm_memory_slot *slot; - gfn_t base_gfn; - - slots = kvm_memslots(kvm); - slot = id_to_memslot(slots, 0); - base_gfn = slot->base_gfn + slot->npages - 3; - - return base_gfn << PAGE_SHIFT; - } - return kvm->arch.tss_addr; -} - static void fix_rmode_seg(int seg, struct kvm_segment *save) { const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; @@ -2942,19 +3084,15 @@ static void enter_rmode(struct kvm_vcpu *vcpu) /* * Very old userspace does not call KVM_SET_TSS_ADDR before entering - * vcpu. Call it here with phys address pointing 16M below 4G. + * vcpu. Warn the user that an update is overdue. */ - if (!vcpu->kvm->arch.tss_addr) { + if (!vcpu->kvm->arch.tss_addr) printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " "called before entering vcpu\n"); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - vmx_set_tss_addr(vcpu->kvm, 0xfeffd000); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - } vmx_segment_cache_clear(vmx); - vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); + vmcs_writel(GUEST_TR_BASE, vcpu->kvm->arch.tss_addr); vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); @@ -3214,7 +3352,9 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) */ if (!nested_vmx_allowed(vcpu)) return 1; - } else if (to_vmx(vcpu)->nested.vmxon) + } + if (to_vmx(vcpu)->nested.vmxon && + ((cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) return 1; vcpu->arch.cr4 = cr4; @@ -3550,7 +3690,7 @@ static bool guest_state_valid(struct kvm_vcpu *vcpu) return true; /* real mode guest state checks */ - if (!is_protmode(vcpu)) { + if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) { if (!rmode_segment_valid(vcpu, VCPU_SREG_CS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_SS)) @@ -3599,7 +3739,7 @@ static int init_rmode_tss(struct kvm *kvm) int r, idx, ret = 0; idx = srcu_read_lock(&kvm->srcu); - fn = rmode_tss_base(kvm) >> PAGE_SHIFT; + fn = kvm->arch.tss_addr >> PAGE_SHIFT; r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -3692,7 +3832,7 @@ static int alloc_apic_access_page(struct kvm *kvm) 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, false); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); if (r) goto out; @@ -3722,7 +3862,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) kvm_userspace_mem.guest_phys_addr = kvm->arch.ept_identity_map_addr; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); if (r) goto out; @@ -3869,13 +4009,59 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr) msr, MSR_TYPE_W); } +static int vmx_vm_has_apicv(struct kvm *kvm) +{ + return enable_apicv && irqchip_in_kernel(kvm); +} + +/* + * Send interrupt to vcpu via posted interrupt way. + * 1. If target vcpu is running(non-root mode), send posted interrupt + * notification to vcpu and hardware will sync PIR to vIRR atomically. + * 2. If target vcpu isn't running(root mode), kick it to pick up the + * interrupt from PIR in next vmentry. + */ +static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int r; + + if (pi_test_and_set_pir(vector, &vmx->pi_desc)) + return; + + r = pi_test_and_set_on(&vmx->pi_desc); + kvm_make_request(KVM_REQ_EVENT, vcpu); +#ifdef CONFIG_SMP + if (!r && (vcpu->mode == IN_GUEST_MODE)) + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), + POSTED_INTR_VECTOR); + else +#endif + kvm_vcpu_kick(vcpu); +} + +static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!pi_test_and_clear_on(&vmx->pi_desc)) + return; + + kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); +} + +static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu) +{ + return; +} + /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. * Note that host-state that does change is set elsewhere. E.g., host-state * that is set differently for each CPU is set in vmx_vcpu_load(), not here. */ -static void vmx_set_constant_host_state(void) +static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) { u32 low32, high32; unsigned long tmpl; @@ -3903,6 +4089,7 @@ static void vmx_set_constant_host_state(void) native_store_idt(&dt); vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */ + vmx->host_idt_base = dt.address; vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */ @@ -3928,6 +4115,15 @@ static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits); } +static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) +{ + u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; + + if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; + return pin_based_exec_ctrl; +} + static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; @@ -3945,11 +4141,6 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) return exec_control; } -static int vmx_vm_has_apicv(struct kvm *kvm) -{ - return enable_apicv_reg_vid && irqchip_in_kernel(kvm); -} - static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; @@ -3971,6 +4162,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD + (handle_vmptrld). + We can NOT enable shadow_vmcs here because we don't have yet + a current VMCS12 + */ + exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; return exec_control; } @@ -3999,14 +4196,17 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a)); vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b)); + if (enable_shadow_vmcs) { + vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); + vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); + } if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ /* Control */ - vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, - vmcs_config.pin_based_exec_ctrl); + vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx)); @@ -4015,13 +4215,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmx_secondary_exec_control(vmx)); } - if (enable_apicv_reg_vid) { + if (vmx_vm_has_apicv(vmx->vcpu.kvm)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); vmcs_write64(EOI_EXIT_BITMAP3, 0); vmcs_write16(GUEST_INTR_STATUS, 0); + + vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); } if (ple_gap) { @@ -4035,7 +4238,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ - vmx_set_constant_host_state(); + vmx_set_constant_host_state(vmx); #ifdef CONFIG_X86_64 rdmsrl(MSR_FS_BASE, a); vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */ @@ -4089,11 +4292,10 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) +static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 msr; - int ret; vmx->rmode.vm86_active = 0; @@ -4109,12 +4311,8 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx_segment_cache_clear(vmx); seg_setup(VCPU_SREG_CS); - if (kvm_vcpu_is_bsp(&vmx->vcpu)) - vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - else { - vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8); - vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12); - } + vmcs_write16(GUEST_CS_SELECTOR, 0xf000); + vmcs_write32(GUEST_CS_BASE, 0xffff0000); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); @@ -4137,10 +4335,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_SYSENTER_EIP, 0); vmcs_writel(GUEST_RFLAGS, 0x02); - if (kvm_vcpu_is_bsp(&vmx->vcpu)) - kvm_rip_write(vcpu, 0xfff0); - else - kvm_rip_write(vcpu, 0); + kvm_rip_write(vcpu, 0xfff0); vmcs_writel(GUEST_GDTR_BASE, 0); vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); @@ -4171,23 +4366,20 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->vcpu.kvm->arch.apic_access_page)); + if (vmx_vm_has_apicv(vcpu->kvm)) + memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); + if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); vmx_set_cr4(&vmx->vcpu, 0); vmx_set_efer(&vmx->vcpu, 0); vmx_fpu_activate(&vmx->vcpu); update_exception_bitmap(&vmx->vcpu); vpid_sync_context(vmx); - - ret = 0; - - return ret; } /* @@ -4200,40 +4392,45 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) PIN_BASED_EXT_INTR_MASK; } -static void enable_irq_window(struct kvm_vcpu *vcpu) +static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) +{ + return get_vmcs12(vcpu)->pin_based_vm_exec_control & + PIN_BASED_NMI_EXITING; +} + +static int enable_irq_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { + + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) /* * We get here if vmx_interrupt_allowed() said we can't - * inject to L1 now because L2 must run. Ask L2 to exit - * right after entry, so we can inject to L1 more promptly. + * inject to L1 now because L2 must run. The caller will have + * to make L2 exit right after entry, so we can inject to L1 + * more promptly. */ - kvm_make_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); - return; - } + return -EBUSY; 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); + return 0; } -static void enable_nmi_window(struct kvm_vcpu *vcpu) +static int enable_nmi_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (!cpu_has_virtual_nmis()) { - enable_irq_window(vcpu); - return; - } + if (!cpu_has_virtual_nmis()) + return enable_irq_window(vcpu); + + if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) + return enable_irq_window(vcpu); - if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { - enable_irq_window(vcpu); - return; - } cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + return 0; } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -4294,16 +4491,6 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); } -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) -{ - if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked) - return 0; - - return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI - | GUEST_INTR_STATE_NMI)); -} - static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { if (!cpu_has_virtual_nmis()) @@ -4333,18 +4520,52 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) } } +static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + if (to_vmx(vcpu)->nested.nested_run_pending) + return 0; + if (nested_exit_on_nmi(vcpu)) { + nested_vmx_vmexit(vcpu); + vmcs12->vm_exit_reason = EXIT_REASON_EXCEPTION_NMI; + vmcs12->vm_exit_intr_info = NMI_VECTOR | + INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK; + /* + * The NMI-triggered VM exit counts as injection: + * clear this one and block further NMIs. + */ + vcpu->arch.nmi_pending = 0; + vmx_set_nmi_mask(vcpu, true); + return 0; + } + } + + if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked) + return 0; + + return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI + | GUEST_INTR_STATE_NMI)); +} + static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { + if (is_guest_mode(vcpu)) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (to_vmx(vcpu)->nested.nested_run_pending || - (vmcs12->idt_vectoring_info_field & - VECTORING_INFO_VALID_MASK)) + + if (to_vmx(vcpu)->nested.nested_run_pending) return 0; - nested_vmx_vmexit(vcpu); - vmcs12->vm_exit_reason = EXIT_REASON_EXTERNAL_INTERRUPT; - vmcs12->vm_exit_intr_info = 0; - /* fall through to normal code, but now in L1, not L2 */ + if (nested_exit_on_intr(vcpu)) { + nested_vmx_vmexit(vcpu); + vmcs12->vm_exit_reason = + EXIT_REASON_EXTERNAL_INTERRUPT; + vmcs12->vm_exit_intr_info = 0; + /* + * fall through to normal code, but now in L1, not L2 + */ + } } return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && @@ -4362,7 +4583,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) .flags = 0, }; - ret = kvm_set_memory_region(kvm, &tss_mem, false); + ret = kvm_set_memory_region(kvm, &tss_mem); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -4603,34 +4824,50 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) /* called to set cr0 as appropriate for a mov-to-cr0 exit. */ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) { - if (to_vmx(vcpu)->nested.vmxon && - ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON)) - return 1; - if (is_guest_mode(vcpu)) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned long orig_val = val; + /* * We get here when L2 changed cr0 in a way that did not change * any of L1's shadowed bits (see nested_vmx_exit_handled_cr), - * but did change L0 shadowed bits. This can currently happen - * with the TS bit: L0 may want to leave TS on (for lazy fpu - * loading) while pretending to allow the guest to change it. + * but did change L0 shadowed bits. So we first calculate the + * effective cr0 value that L1 would like to write into the + * hardware. It consists of the L2-owned bits from the new + * value combined with the L1-owned bits from L1's guest_cr0. */ - if (kvm_set_cr0(vcpu, (val & vcpu->arch.cr0_guest_owned_bits) | - (vcpu->arch.cr0 & ~vcpu->arch.cr0_guest_owned_bits))) + val = (val & ~vmcs12->cr0_guest_host_mask) | + (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); + + /* TODO: will have to take unrestricted guest mode into + * account */ + if ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) return 1; - vmcs_writel(CR0_READ_SHADOW, val); + + if (kvm_set_cr0(vcpu, val)) + return 1; + vmcs_writel(CR0_READ_SHADOW, orig_val); return 0; - } else + } else { + if (to_vmx(vcpu)->nested.vmxon && + ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON)) + return 1; return kvm_set_cr0(vcpu, val); + } } static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) { if (is_guest_mode(vcpu)) { - if (kvm_set_cr4(vcpu, (val & vcpu->arch.cr4_guest_owned_bits) | - (vcpu->arch.cr4 & ~vcpu->arch.cr4_guest_owned_bits))) + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned long orig_val = val; + + /* analogously to handle_set_cr0 */ + val = (val & ~vmcs12->cr4_guest_host_mask) | + (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask); + if (kvm_set_cr4(vcpu, val)) return 1; - vmcs_writel(CR4_READ_SHADOW, val); + vmcs_writel(CR4_READ_SHADOW, orig_val); return 0; } else return kvm_set_cr4(vcpu, val); @@ -5183,7 +5420,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) return 1; - err = emulate_instruction(vcpu, 0); + err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE); if (err == EMULATE_DO_MMIO) { ret = 0; @@ -5259,8 +5496,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) } /* Create a new VMCS */ - item = (struct vmcs02_list *) - kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); + item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); if (!item) return NULL; item->vmcs02.vmcs = alloc_vmcs(); @@ -5309,6 +5545,9 @@ static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) free_loaded_vmcs(&vmx->vmcs01); } +static void nested_vmx_failValid(struct kvm_vcpu *vcpu, + u32 vm_instruction_error); + /* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even @@ -5321,6 +5560,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) { struct kvm_segment cs; struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs *shadow_vmcs; /* The Intel VMX Instruction Reference lists a bunch of bits that * are prerequisite to running VMXON, most notably cr4.VMXE must be @@ -5344,6 +5584,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu) kvm_inject_gp(vcpu, 0); return 1; } + if (vmx->nested.vmxon) { + nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); + skip_emulated_instruction(vcpu); + return 1; + } + if (enable_shadow_vmcs) { + shadow_vmcs = alloc_vmcs(); + if (!shadow_vmcs) + return -ENOMEM; + /* mark vmcs as shadow */ + shadow_vmcs->revision_id |= (1u << 31); + /* init shadow vmcs */ + vmcs_clear(shadow_vmcs); + vmx->nested.current_shadow_vmcs = shadow_vmcs; + } INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); vmx->nested.vmcs02_num = 0; @@ -5384,6 +5639,25 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } +static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) +{ + u32 exec_control; + if (enable_shadow_vmcs) { + if (vmx->nested.current_vmcs12 != NULL) { + /* copy to memory all shadowed fields in case + they were modified */ + copy_shadow_to_vmcs12(vmx); + vmx->nested.sync_shadow_vmcs = false; + exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_write64(VMCS_LINK_POINTER, -1ull); + } + } + kunmap(vmx->nested.current_vmcs12_page); + nested_release_page(vmx->nested.current_vmcs12_page); +} + /* * Free whatever needs to be freed from vmx->nested when L1 goes down, or * just stops using VMX. @@ -5394,11 +5668,12 @@ static void free_nested(struct vcpu_vmx *vmx) return; vmx->nested.vmxon = false; if (vmx->nested.current_vmptr != -1ull) { - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); + nested_release_vmcs12(vmx); vmx->nested.current_vmptr = -1ull; vmx->nested.current_vmcs12 = NULL; } + if (enable_shadow_vmcs) + free_vmcs(vmx->nested.current_shadow_vmcs); /* Unpin physical memory we referred to in current vmcs02 */ if (vmx->nested.apic_access_page) { nested_release_page(vmx->nested.apic_access_page); @@ -5507,6 +5782,10 @@ static void nested_vmx_failValid(struct kvm_vcpu *vcpu, X86_EFLAGS_SF | X86_EFLAGS_OF)) | X86_EFLAGS_ZF); get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error; + /* + * We don't need to force a shadow sync because + * VM_INSTRUCTION_ERROR is not shadowed + */ } /* Emulate the VMCLEAR instruction */ @@ -5539,8 +5818,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) } if (vmptr == vmx->nested.current_vmptr) { - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); + nested_release_vmcs12(vmx); vmx->nested.current_vmptr = -1ull; vmx->nested.current_vmcs12 = NULL; } @@ -5639,6 +5917,111 @@ static inline bool vmcs12_read_any(struct kvm_vcpu *vcpu, } } + +static inline bool vmcs12_write_any(struct kvm_vcpu *vcpu, + unsigned long field, u64 field_value){ + short offset = vmcs_field_to_offset(field); + char *p = ((char *) get_vmcs12(vcpu)) + offset; + if (offset < 0) + return false; + + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + *(u16 *)p = field_value; + return true; + case VMCS_FIELD_TYPE_U32: + *(u32 *)p = field_value; + return true; + case VMCS_FIELD_TYPE_U64: + *(u64 *)p = field_value; + return true; + case VMCS_FIELD_TYPE_NATURAL_WIDTH: + *(natural_width *)p = field_value; + return true; + default: + return false; /* can never happen. */ + } + +} + +static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) +{ + int i; + unsigned long field; + u64 field_value; + struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs; + unsigned long *fields = (unsigned long *)shadow_read_write_fields; + int num_fields = max_shadow_read_write_fields; + + vmcs_load(shadow_vmcs); + + for (i = 0; i < num_fields; i++) { + field = fields[i]; + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + field_value = vmcs_read16(field); + break; + case VMCS_FIELD_TYPE_U32: + field_value = vmcs_read32(field); + break; + case VMCS_FIELD_TYPE_U64: + field_value = vmcs_read64(field); + break; + case VMCS_FIELD_TYPE_NATURAL_WIDTH: + field_value = vmcs_readl(field); + break; + } + vmcs12_write_any(&vmx->vcpu, field, field_value); + } + + vmcs_clear(shadow_vmcs); + vmcs_load(vmx->loaded_vmcs->vmcs); +} + +static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) +{ + unsigned long *fields[] = { + (unsigned long *)shadow_read_write_fields, + (unsigned long *)shadow_read_only_fields + }; + int num_lists = ARRAY_SIZE(fields); + int max_fields[] = { + max_shadow_read_write_fields, + max_shadow_read_only_fields + }; + int i, q; + unsigned long field; + u64 field_value = 0; + struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs; + + vmcs_load(shadow_vmcs); + + for (q = 0; q < num_lists; q++) { + for (i = 0; i < max_fields[q]; i++) { + field = fields[q][i]; + vmcs12_read_any(&vmx->vcpu, field, &field_value); + + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + vmcs_write16(field, (u16)field_value); + break; + case VMCS_FIELD_TYPE_U32: + vmcs_write32(field, (u32)field_value); + break; + case VMCS_FIELD_TYPE_U64: + vmcs_write64(field, (u64)field_value); + break; + case VMCS_FIELD_TYPE_NATURAL_WIDTH: + vmcs_writel(field, (long)field_value); + break; + } + } + } + + vmcs_clear(shadow_vmcs); + vmcs_load(vmx->loaded_vmcs->vmcs); +} + /* * VMX instructions which assume a current vmcs12 (i.e., that VMPTRLD was * used before) all generate the same failure when it is missing. @@ -5703,8 +6086,6 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) gva_t gva; unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - char *p; - short offset; /* The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 @@ -5741,28 +6122,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return 1; } - offset = vmcs_field_to_offset(field); - if (offset < 0) { - nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); - skip_emulated_instruction(vcpu); - return 1; - } - p = ((char *) get_vmcs12(vcpu)) + offset; - - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: - *(u16 *)p = field_value; - break; - case VMCS_FIELD_TYPE_U32: - *(u32 *)p = field_value; - break; - case VMCS_FIELD_TYPE_U64: - *(u64 *)p = field_value; - break; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: - *(natural_width *)p = field_value; - break; - default: + if (!vmcs12_write_any(vcpu, field, field_value)) { nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); skip_emulated_instruction(vcpu); return 1; @@ -5780,6 +6140,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) gva_t gva; gpa_t vmptr; struct x86_exception e; + u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -5818,14 +6179,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); return 1; } - if (vmx->nested.current_vmptr != -1ull) { - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); - } + if (vmx->nested.current_vmptr != -1ull) + nested_release_vmcs12(vmx); vmx->nested.current_vmptr = vmptr; vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; + if (enable_shadow_vmcs) { + exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + exec_control |= SECONDARY_EXEC_SHADOW_VMCS; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_write64(VMCS_LINK_POINTER, + __pa(vmx->nested.current_shadow_vmcs)); + vmx->nested.sync_shadow_vmcs = true; + } } nested_vmx_succeed(vcpu); @@ -5908,6 +6275,52 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + gpa_t bitmap, last_bitmap; + unsigned int port; + int size; + u8 b; + + if (nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING)) + return 1; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return 0; + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + last_bitmap = (gpa_t)-1; + b = -1; + + while (size > 0) { + if (port < 0x8000) + bitmap = vmcs12->io_bitmap_a; + else if (port < 0x10000) + bitmap = vmcs12->io_bitmap_b; + else + return 1; + bitmap += (port & 0x7fff) / 8; + + if (last_bitmap != bitmap) + if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) + return 1; + if (b & (1 << (port & 7))) + return 1; + + port++; + size--; + last_bitmap = bitmap; + } + + return 0; +} + /* * Return 1 if we should exit from L2 to L1 to handle an MSR access access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed @@ -5939,7 +6352,8 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, /* Then read the msr_index'th bit from this bitmap: */ if (msr_index < 1024*8) { unsigned char b; - kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1); + if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) + return 1; return 1 & (b >> (msr_index & 7)); } else return 1; /* let L1 handle the wrong parameter */ @@ -6033,10 +6447,10 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, */ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) { - u32 exit_reason = vmcs_read32(VM_EXIT_REASON); u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + u32 exit_reason = vmx->exit_reason; if (vmx->nested.nested_run_pending) return 0; @@ -6060,14 +6474,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_TRIPLE_FAULT: return 1; case EXIT_REASON_PENDING_INTERRUPT: + return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); case EXIT_REASON_NMI_WINDOW: - /* - * prepare_vmcs02() set the CPU_BASED_VIRTUAL_INTR_PENDING bit - * (aka Interrupt Window Exiting) only when L1 turned it on, - * so if we got a PENDING_INTERRUPT exit, this must be for L1. - * Same for NMI Window Exiting. - */ - return 1; + return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); case EXIT_REASON_TASK_SWITCH: return 1; case EXIT_REASON_CPUID: @@ -6097,8 +6506,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_DR_ACCESS: return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING); case EXIT_REASON_IO_INSTRUCTION: - /* TODO: support IO bitmaps */ - return 1; + return nested_vmx_exit_handled_io(vcpu, vmcs12); case EXIT_REASON_MSR_READ: case EXIT_REASON_MSR_WRITE: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); @@ -6122,6 +6530,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_EPT_VIOLATION: case EXIT_REASON_EPT_MISCONFIG: return 0; + case EXIT_REASON_PREEMPTION_TIMER: + return vmcs12->pin_based_vm_exec_control & + PIN_BASED_VMX_PREEMPTION_TIMER; case EXIT_REASON_WBINVD: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: @@ -6316,6 +6727,9 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { + if (!vmx_vm_has_apicv(vcpu->kvm)) + return; + vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); @@ -6346,6 +6760,52 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) } } +static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) +{ + u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + /* + * If external interrupt exists, IF bit is set in rflags/eflags on the + * interrupt stack frame, and interrupt will be enabled on a return + * from interrupt handler. + */ + if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) + == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) { + unsigned int vector; + unsigned long entry; + gate_desc *desc; + struct vcpu_vmx *vmx = to_vmx(vcpu); +#ifdef CONFIG_X86_64 + unsigned long tmp; +#endif + + vector = exit_intr_info & INTR_INFO_VECTOR_MASK; + desc = (gate_desc *)vmx->host_idt_base + vector; + entry = gate_offset(*desc); + asm volatile( +#ifdef CONFIG_X86_64 + "mov %%" _ASM_SP ", %[sp]\n\t" + "and $0xfffffffffffffff0, %%" _ASM_SP "\n\t" + "push $%c[ss]\n\t" + "push %[sp]\n\t" +#endif + "pushf\n\t" + "orl $0x200, (%%" _ASM_SP ")\n\t" + __ASM_SIZE(push) " $%c[cs]\n\t" + "call *%[entry]\n\t" + : +#ifdef CONFIG_X86_64 + [sp]"=&r"(tmp) +#endif + : + [entry]"r"(entry), + [ss]"i"(__KERNEL_DS), + [cs]"i"(__KERNEL_CS) + ); + } else + local_irq_enable(); +} + static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -6388,7 +6848,7 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) ktime_to_ns(ktime_sub(ktime_get(), vmx->entry_time)); } -static void __vmx_complete_interrupts(struct vcpu_vmx *vmx, +static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, u32 idt_vectoring_info, int instr_len_field, int error_code_field) @@ -6399,46 +6859,43 @@ static void __vmx_complete_interrupts(struct vcpu_vmx *vmx, idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; - vmx->vcpu.arch.nmi_injected = false; - kvm_clear_exception_queue(&vmx->vcpu); - kvm_clear_interrupt_queue(&vmx->vcpu); + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); if (!idtv_info_valid) return; - kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu); + kvm_make_request(KVM_REQ_EVENT, vcpu); vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK; type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK; switch (type) { case INTR_TYPE_NMI_INTR: - vmx->vcpu.arch.nmi_injected = true; + vcpu->arch.nmi_injected = true; /* * SDM 3: 27.7.1.2 (September 2008) * Clear bit "block by NMI" before VM entry if a NMI * delivery faulted. */ - vmx_set_nmi_mask(&vmx->vcpu, false); + vmx_set_nmi_mask(vcpu, false); break; case INTR_TYPE_SOFT_EXCEPTION: - vmx->vcpu.arch.event_exit_inst_len = - vmcs_read32(instr_len_field); + vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); /* fall through */ case INTR_TYPE_HARD_EXCEPTION: if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { u32 err = vmcs_read32(error_code_field); - kvm_queue_exception_e(&vmx->vcpu, vector, err); + kvm_queue_exception_e(vcpu, vector, err); } else - kvm_queue_exception(&vmx->vcpu, vector); + kvm_queue_exception(vcpu, vector); break; case INTR_TYPE_SOFT_INTR: - vmx->vcpu.arch.event_exit_inst_len = - vmcs_read32(instr_len_field); + vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); /* fall through */ case INTR_TYPE_EXT_INTR: - kvm_queue_interrupt(&vmx->vcpu, vector, - type == INTR_TYPE_SOFT_INTR); + kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); break; default: break; @@ -6447,18 +6904,14 @@ static void __vmx_complete_interrupts(struct vcpu_vmx *vmx, static void vmx_complete_interrupts(struct vcpu_vmx *vmx) { - if (is_guest_mode(&vmx->vcpu)) - return; - __vmx_complete_interrupts(vmx, vmx->idt_vectoring_info, + __vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info, VM_EXIT_INSTRUCTION_LEN, IDT_VECTORING_ERROR_CODE); } static void vmx_cancel_injection(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) - return; - __vmx_complete_interrupts(to_vmx(vcpu), + __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), VM_ENTRY_INSTRUCTION_LEN, VM_ENTRY_EXCEPTION_ERROR_CODE); @@ -6489,21 +6942,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long debugctlmsr; - if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (vmcs12->idt_vectoring_info_field & - VECTORING_INFO_VALID_MASK) { - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - vmcs12->idt_vectoring_info_field); - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmcs12->vm_exit_instruction_len); - if (vmcs12->idt_vectoring_info_field & - VECTORING_INFO_DELIVER_CODE_MASK) - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, - vmcs12->idt_vectoring_error_code); - } - } - /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) vmx->entry_time = ktime_get(); @@ -6513,6 +6951,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return; + if (vmx->nested.sync_shadow_vmcs) { + copy_vmcs12_to_shadow(vmx); + vmx->nested.sync_shadow_vmcs = false; + } + if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) @@ -6662,17 +7105,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - vmcs12->idt_vectoring_info_field = vmx->idt_vectoring_info; - if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) { - vmcs12->idt_vectoring_error_code = - vmcs_read32(IDT_VECTORING_ERROR_CODE); - vmcs12->vm_exit_instruction_len = - vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - } - } - vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); @@ -6734,10 +7166,11 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) put_cpu(); if (err) goto free_vmcs; - if (vm_need_virtualize_apic_accesses(kvm)) + if (vm_need_virtualize_apic_accesses(kvm)) { err = alloc_apic_access_page(kvm); if (err) goto free_vmcs; + } if (enable_ept) { if (!kvm->arch.ept_identity_map_addr) @@ -6931,9 +7364,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->vm_entry_instruction_len); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs12->guest_interruptibility_info); - vmcs_write32(GUEST_ACTIVITY_STATE, vmcs12->guest_activity_state); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); - vmcs_writel(GUEST_DR7, vmcs12->guest_dr7); + kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmcs_writel(GUEST_RFLAGS, vmcs12->guest_rflags); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, vmcs12->guest_pending_dbg_exceptions); @@ -6946,6 +7378,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs_config.pin_based_exec_ctrl | vmcs12->pin_based_vm_exec_control)); + if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, + vmcs12->vmx_preemption_timer_value); + /* * Whether page-faults are trapped is determined by a combination of * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. @@ -7016,7 +7452,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * Other fields are different per CPU, and will be set later when * vmx_vcpu_load() is called, and when vmx_save_host_state() is called. */ - vmx_set_constant_host_state(); + vmx_set_constant_host_state(vmx); /* * HOST_RSP is normally set correctly in vmx_vcpu_run() just before @@ -7082,7 +7518,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->guest_ia32_efer; - if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) + else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); else vcpu->arch.efer &= ~(EFER_LMA | EFER_LME); @@ -7121,6 +7557,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; struct loaded_vmcs *vmcs02; + bool ia32e; if (!nested_vmx_check_permission(vcpu) || !nested_vmx_check_vmcs12(vcpu)) @@ -7129,6 +7566,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) skip_emulated_instruction(vcpu); vmcs12 = get_vmcs12(vcpu); + if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + /* * The nested entry process starts with enforcing various prerequisites * on vmcs12 as required by the Intel SDM, and act appropriately when @@ -7146,6 +7586,11 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } + if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE) { + nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); + return 1; + } + if ((vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_MSR_BITMAPS) && !IS_ALIGNED(vmcs12->msr_bitmap, PAGE_SIZE)) { /*TODO: Also verify bits beyond physical address width are 0*/ @@ -7204,6 +7649,45 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } /* + * If the load IA32_EFER VM-entry control is 1, the following checks + * are performed on the field for the IA32_EFER MSR: + * - Bits reserved in the IA32_EFER MSR must be 0. + * - Bit 10 (corresponding to IA32_EFER.LMA) must equal the value of + * the IA-32e mode guest VM-exit control. It must also be identical + * to bit 8 (LME) if bit 31 in the CR0 field (corresponding to + * CR0.PG) is 1. + */ + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) { + ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; + if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || + ((vmcs12->guest_cr0 & X86_CR0_PG) && + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) { + nested_vmx_entry_failure(vcpu, vmcs12, + EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + return 1; + } + } + + /* + * If the load IA32_EFER VM-exit control is 1, bits reserved in the + * IA32_EFER MSR must be 0 in the field for that register. In addition, + * the values of the LMA and LME bits in the field must each be that of + * the host address-space size VM-exit control. + */ + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) { + ia32e = (vmcs12->vm_exit_controls & + VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; + if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || + ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || + ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) { + nested_vmx_entry_failure(vcpu, vmcs12, + EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + return 1; + } + } + + /* * We're finally done with prerequisite checking, and can start with * the nested entry. */ @@ -7223,6 +7707,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vcpu->cpu = cpu; put_cpu(); + vmx_segment_cache_clear(vmx); + vmcs12->launch_state = 1; prepare_vmcs02(vcpu, vmcs12); @@ -7273,6 +7759,48 @@ vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vcpu->arch.cr4_guest_owned_bits)); } +static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + u32 idt_vectoring; + unsigned int nr; + + if (vcpu->arch.exception.pending) { + nr = vcpu->arch.exception.nr; + idt_vectoring = nr | VECTORING_INFO_VALID_MASK; + + if (kvm_exception_is_soft(nr)) { + vmcs12->vm_exit_instruction_len = + vcpu->arch.event_exit_inst_len; + idt_vectoring |= INTR_TYPE_SOFT_EXCEPTION; + } else + idt_vectoring |= INTR_TYPE_HARD_EXCEPTION; + + if (vcpu->arch.exception.has_error_code) { + idt_vectoring |= VECTORING_INFO_DELIVER_CODE_MASK; + vmcs12->idt_vectoring_error_code = + vcpu->arch.exception.error_code; + } + + vmcs12->idt_vectoring_info_field = idt_vectoring; + } else if (vcpu->arch.nmi_pending) { + vmcs12->idt_vectoring_info_field = + INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR; + } else if (vcpu->arch.interrupt.pending) { + nr = vcpu->arch.interrupt.nr; + idt_vectoring = nr | VECTORING_INFO_VALID_MASK; + + if (vcpu->arch.interrupt.soft) { + idt_vectoring |= INTR_TYPE_SOFT_INTR; + vmcs12->vm_entry_instruction_len = + vcpu->arch.event_exit_inst_len; + } else + idt_vectoring |= INTR_TYPE_EXT_INTR; + + vmcs12->idt_vectoring_info_field = idt_vectoring; + } +} + /* * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), @@ -7284,7 +7812,7 @@ vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * exit-information fields only. Other fields are modified by L1 with VMWRITE, * which already writes to vmcs12 directly. */ -void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) +static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { /* update guest state fields: */ vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); @@ -7332,16 +7860,19 @@ void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE); vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE); - vmcs12->guest_activity_state = vmcs_read32(GUEST_ACTIVITY_STATE); vmcs12->guest_interruptibility_info = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + vmcs12->vm_entry_controls = + (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | + (vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_IA32E_MODE); + /* TODO: These cannot have changed unless we have MSR bitmaps and * the relevant bit asks not to trap the change */ vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); - if (vmcs12->vm_entry_controls & VM_EXIT_SAVE_IA32_PAT) + if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT); vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); @@ -7349,21 +7880,38 @@ void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) /* update exit information fields: */ - vmcs12->vm_exit_reason = vmcs_read32(VM_EXIT_REASON); + vmcs12->vm_exit_reason = to_vmx(vcpu)->exit_reason; vmcs12->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); vmcs12->vm_exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - vmcs12->vm_exit_intr_error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); - vmcs12->idt_vectoring_info_field = - vmcs_read32(IDT_VECTORING_INFO_FIELD); - vmcs12->idt_vectoring_error_code = - vmcs_read32(IDT_VECTORING_ERROR_CODE); + if ((vmcs12->vm_exit_intr_info & + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) + vmcs12->vm_exit_intr_error_code = + vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + vmcs12->idt_vectoring_info_field = 0; vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - /* clear vm-entry fields which are to be cleared on exit */ - if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { + /* vm_entry_intr_info_field is cleared on exit. Emulate this + * instead of reading the real value. */ vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK; + + /* + * Transfer the event that L0 or L1 may wanted to inject into + * L2 to IDT_VECTORING_INFO_FIELD. + */ + vmcs12_save_pending_event(vcpu, vmcs12); + } + + /* + * Drop what we picked up for L2 via vmx_complete_interrupts. It is + * preserved above and would only end up incorrectly in L1. + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); } /* @@ -7375,11 +7923,12 @@ void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * Failures During or After Loading Guest State"). * This function should be called when the active VMCS is L1's (vmcs01). */ -void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) +static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) { if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; - if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) + else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); else vcpu->arch.efer &= ~(EFER_LMA | EFER_LME); @@ -7387,6 +7936,7 @@ void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp); kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip); + vmx_set_rflags(vcpu, X86_EFLAGS_BIT1); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't * actually changed, because it depends on the current state of @@ -7445,6 +7995,9 @@ void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, vmcs12->host_ia32_perf_global_ctrl); + + kvm_set_dr(vcpu, 7, 0x400); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); } /* @@ -7458,6 +8011,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) int cpu; struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + /* trying to cancel vmlaunch/vmresume is a bug */ + WARN_ON_ONCE(vmx->nested.nested_run_pending); + leave_guest_mode(vcpu); prepare_vmcs12(vcpu, vmcs12); @@ -7468,6 +8024,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) vcpu->cpu = cpu; put_cpu(); + vmx_segment_cache_clear(vmx); + /* if no vmcs02 cache requested, remove the one we used */ if (VMCS02_POOL_SIZE == 0) nested_free_vmcs02(vmx, vmx->nested.current_vmptr); @@ -7496,6 +8054,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) nested_vmx_failValid(vcpu, vmcs_read32(VM_INSTRUCTION_ERROR)); } else nested_vmx_succeed(vcpu); + if (enable_shadow_vmcs) + vmx->nested.sync_shadow_vmcs = true; } /* @@ -7513,6 +8073,8 @@ static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu, vmcs12->vm_exit_reason = reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->exit_qualification = qualification; nested_vmx_succeed(vcpu); + if (enable_shadow_vmcs) + to_vmx(vcpu)->nested.sync_shadow_vmcs = true; } static int vmx_check_intercept(struct kvm_vcpu *vcpu, @@ -7590,6 +8152,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, + .sync_pir_to_irr = vmx_sync_pir_to_irr, + .deliver_posted_interrupt = vmx_deliver_posted_interrupt, .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, @@ -7618,6 +8182,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_tdp_cr3 = vmx_set_cr3, .check_intercept = vmx_check_intercept, + .handle_external_intr = vmx_handle_external_intr, }; static int __init vmx_init(void) @@ -7656,6 +8221,24 @@ static int __init vmx_init(void) (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_msr_bitmap_longmode_x2apic) goto out4; + vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_vmread_bitmap) + goto out5; + + vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_vmwrite_bitmap) + goto out6; + + memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); + memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); + /* shadowed read/write fields */ + for (i = 0; i < max_shadow_read_write_fields; i++) { + clear_bit(shadow_read_write_fields[i], vmx_vmwrite_bitmap); + clear_bit(shadow_read_write_fields[i], vmx_vmread_bitmap); + } + /* shadowed read only fields */ + for (i = 0; i < max_shadow_read_only_fields; i++) + clear_bit(shadow_read_only_fields[i], vmx_vmread_bitmap); /* * Allow direct access to the PC debug port (it is often used for I/O @@ -7674,7 +8257,7 @@ static int __init vmx_init(void) r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) - goto out3; + goto out7; #ifdef CONFIG_KEXEC rcu_assign_pointer(crash_vmclear_loaded_vmcss, @@ -7692,7 +8275,7 @@ static int __init vmx_init(void) memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); - if (enable_apicv_reg_vid) { + if (enable_apicv) { for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); @@ -7722,6 +8305,12 @@ static int __init vmx_init(void) return 0; +out7: + free_page((unsigned long)vmx_vmwrite_bitmap); +out6: + free_page((unsigned long)vmx_vmread_bitmap); +out5: + free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); out4: free_page((unsigned long)vmx_msr_bitmap_longmode); out3: @@ -7743,6 +8332,8 @@ static void __exit vmx_exit(void) free_page((unsigned long)vmx_msr_bitmap_longmode); free_page((unsigned long)vmx_io_bitmap_b); free_page((unsigned long)vmx_io_bitmap_a); + free_page((unsigned long)vmx_vmwrite_bitmap); + free_page((unsigned long)vmx_vmread_bitmap); #ifdef CONFIG_KEXEC rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e1721324c271..05a8b1a2300d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -162,8 +162,6 @@ u64 __read_mostly host_xcr0; static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); -static int kvm_vcpu_reset(struct kvm_vcpu *vcpu); - static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { int i; @@ -263,6 +261,13 @@ void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_apic_base); +asmlinkage void kvm_spurious_fault(void) +{ + /* Fault while not rebooting. We want the trace. */ + BUG(); +} +EXPORT_SYMBOL_GPL(kvm_spurious_fault); + #define EXCPT_BENIGN 0 #define EXCPT_CONTRIBUTORY 1 #define EXCPT_PF 2 @@ -840,23 +845,17 @@ static const u32 emulated_msrs[] = { MSR_IA32_MCG_CTL, }; -static int set_efer(struct kvm_vcpu *vcpu, u64 efer) +bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { - u64 old_efer = vcpu->arch.efer; - if (efer & efer_reserved_bits) - return 1; - - if (is_paging(vcpu) - && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) - return 1; + return false; if (efer & EFER_FFXSR) { struct kvm_cpuid_entry2 *feat; feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) - return 1; + return false; } if (efer & EFER_SVME) { @@ -864,9 +863,24 @@ static int set_efer(struct kvm_vcpu *vcpu, u64 efer) feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) - return 1; + return false; } + return true; +} +EXPORT_SYMBOL_GPL(kvm_valid_efer); + +static int set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + u64 old_efer = vcpu->arch.efer; + + if (!kvm_valid_efer(vcpu, efer)) + return 1; + + if (is_paging(vcpu) + && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) + return 1; + efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; @@ -1079,6 +1093,10 @@ static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) u32 thresh_lo, thresh_hi; int use_scaling = 0; + /* tsc_khz can be zero if TSC calibration fails */ + if (this_tsc_khz == 0) + return; + /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, &vcpu->arch.virtual_tsc_shift, @@ -1156,20 +1174,23 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; - /* n.b - signed multiplication and division required */ - usdiff = data - kvm->arch.last_tsc_write; + if (vcpu->arch.virtual_tsc_khz) { + /* n.b - signed multiplication and division required */ + usdiff = data - kvm->arch.last_tsc_write; #ifdef CONFIG_X86_64 - usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; + usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; #else - /* do_div() only does unsigned */ - asm("idivl %2; xor %%edx, %%edx" - : "=A"(usdiff) - : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz)); + /* do_div() only does unsigned */ + asm("idivl %2; xor %%edx, %%edx" + : "=A"(usdiff) + : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz)); #endif - do_div(elapsed, 1000); - usdiff -= elapsed; - if (usdiff < 0) - usdiff = -usdiff; + do_div(elapsed, 1000); + usdiff -= elapsed; + if (usdiff < 0) + usdiff = -usdiff; + } else + usdiff = USEC_PER_SEC; /* disable TSC match window below */ /* * Special case: TSC write with a small delta (1 second) of virtual @@ -2034,7 +2055,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_P6_EVNTSEL0: case MSR_P6_EVNTSEL1: if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_set_msr(vcpu, msr, data); + return kvm_pmu_set_msr(vcpu, msr_info); if (pr || data != 0) vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " @@ -2080,7 +2101,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_set_msr(vcpu, msr, data); + return kvm_pmu_set_msr(vcpu, msr_info); if (!ignore_msrs) { vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); @@ -2479,7 +2500,6 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_USER_NMI: case KVM_CAP_REINJECT_CONTROL: case KVM_CAP_IRQ_INJECT_STATUS: - case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: case KVM_CAP_PIT2: @@ -2497,10 +2517,12 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: case KVM_CAP_GET_TSC_KHZ: - case KVM_CAP_PCI_2_3: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: - case KVM_CAP_IRQFD_RESAMPLE: +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT + case KVM_CAP_ASSIGN_DEV_IRQ: + case KVM_CAP_PCI_2_3: +#endif r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2521,9 +2543,11 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PV_MMU: /* obsolete */ r = 0; break; +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_IOMMU: r = iommu_present(&pci_bus_type); break; +#endif case KVM_CAP_MCE: r = KVM_MAX_MCE_BANKS; break; @@ -2679,6 +2703,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { + kvm_x86_ops->sync_pir_to_irr(vcpu); memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); return 0; @@ -2696,7 +2721,7 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { - if (irq->irq < 0 || irq->irq >= KVM_NR_INTERRUPTS) + if (irq->irq >= KVM_NR_INTERRUPTS) return -EINVAL; if (irqchip_in_kernel(vcpu->kvm)) return -ENXIO; @@ -2819,10 +2844,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); events->nmi.pad = 0; - events->sipi_vector = vcpu->arch.sipi_vector; + events->sipi_vector = 0; /* never valid when reporting to user space */ events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SIPI_VECTOR | KVM_VCPUEVENT_VALID_SHADOW); memset(&events->reserved, 0, sizeof(events->reserved)); } @@ -2853,8 +2877,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.nmi_pending = events->nmi.pending; kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); - if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR) - vcpu->arch.sipi_vector = events->sipi_vector; + if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && + kvm_vcpu_has_lapic(vcpu)) + vcpu->arch.apic->sipi_vector = events->sipi_vector; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -3478,13 +3503,15 @@ out: return r; } -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event) +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, + bool line_status) { if (!irqchip_in_kernel(kvm)) return -ENXIO; irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event->irq, irq_event->level); + irq_event->irq, irq_event->level, + line_status); return 0; } @@ -4752,11 +4779,15 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) } static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, - bool write_fault_to_shadow_pgtable) + bool write_fault_to_shadow_pgtable, + int emulation_type) { gpa_t gpa = cr2; pfn_t pfn; + if (emulation_type & EMULTYPE_NO_REEXECUTE) + return false; + if (!vcpu->arch.mmu.direct_map) { /* * Write permission should be allowed since only @@ -4899,8 +4930,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2, - write_fault_to_spt)) + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + emulation_type)) return EMULATE_DONE; if (emulation_type & EMULTYPE_SKIP) return EMULATE_FAIL; @@ -4930,7 +4961,8 @@ restart: return EMULATE_DONE; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt)) + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + emulation_type)) return EMULATE_DONE; return handle_emulation_failure(vcpu); @@ -5641,14 +5673,20 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) #endif } -static void update_eoi_exitmap(struct kvm_vcpu *vcpu) +static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { u64 eoi_exit_bitmap[4]; + u32 tmr[8]; + + if (!kvm_apic_hw_enabled(vcpu->arch.apic)) + return; memset(eoi_exit_bitmap, 0, 32); + memset(tmr, 0, 32); - kvm_ioapic_calculate_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_ioapic_scan_entry(vcpu, eoi_exit_bitmap, tmr); kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_apic_update_tmr(vcpu, tmr); } static int vcpu_enter_guest(struct kvm_vcpu *vcpu) @@ -5656,7 +5694,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; - bool req_immediate_exit = 0; + bool req_immediate_exit = false; if (vcpu->requests) { if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) @@ -5698,24 +5736,30 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) record_steal_time(vcpu); if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - req_immediate_exit = - kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) kvm_handle_pmu_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) kvm_deliver_pmi(vcpu); - if (kvm_check_request(KVM_REQ_EOIBITMAP, vcpu)) - update_eoi_exitmap(vcpu); + if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) + vcpu_scan_ioapic(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + kvm_apic_accept_events(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { + r = 1; + goto out; + } + inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); + req_immediate_exit = + kvm_x86_ops->enable_nmi_window(vcpu) != 0; else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + req_immediate_exit = + kvm_x86_ops->enable_irq_window(vcpu) != 0; if (kvm_lapic_enabled(vcpu)) { /* @@ -5794,7 +5838,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - local_irq_enable(); + + /* Interrupt is enabled by handle_external_intr() */ + kvm_x86_ops->handle_external_intr(vcpu); ++vcpu->stat.exits; @@ -5843,16 +5889,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) int r; struct kvm *kvm = vcpu->kvm; - if (unlikely(vcpu->arch.mp_state == KVM_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_vcpu_reset(vcpu); - if (r) - return r; - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - } - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); r = vapic_enter(vcpu); if (r) { @@ -5869,8 +5905,8 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) - { + if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { + kvm_apic_accept_events(vcpu); switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: vcpu->arch.mp_state = @@ -5878,7 +5914,8 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; break; - case KVM_MP_STATE_SIPI_RECEIVED: + case KVM_MP_STATE_INIT_RECEIVED: + break; default: r = -EINTR; break; @@ -6013,6 +6050,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { kvm_vcpu_block(vcpu); + kvm_apic_accept_events(vcpu); clear_bit(KVM_REQ_UNHALT, &vcpu->requests); r = -EAGAIN; goto out; @@ -6169,6 +6207,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + kvm_apic_accept_events(vcpu); mp_state->mp_state = vcpu->arch.mp_state; return 0; } @@ -6176,7 +6215,15 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - vcpu->arch.mp_state = mp_state->mp_state; + if (!kvm_vcpu_has_lapic(vcpu) && + mp_state->mp_state != KVM_MP_STATE_RUNNABLE) + return -EINVAL; + + if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { + vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); + } else + vcpu->arch.mp_state = mp_state->mp_state; kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } @@ -6475,9 +6522,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) r = vcpu_load(vcpu); if (r) return r; - r = kvm_vcpu_reset(vcpu); - if (r == 0) - r = kvm_mmu_setup(vcpu); + kvm_vcpu_reset(vcpu); + r = kvm_mmu_setup(vcpu); vcpu_put(vcpu); return r; @@ -6514,7 +6560,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_x86_ops->vcpu_free(vcpu); } -static int kvm_vcpu_reset(struct kvm_vcpu *vcpu) +void kvm_vcpu_reset(struct kvm_vcpu *vcpu) { atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; @@ -6541,7 +6587,18 @@ static int kvm_vcpu_reset(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - return kvm_x86_ops->vcpu_reset(vcpu); + kvm_x86_ops->vcpu_reset(vcpu); +} + +void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector) +{ + struct kvm_segment cs; + + kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); + cs.selector = vector << 8; + cs.base = vector << 12; + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_rip_write(vcpu, 0); } int kvm_arch_hardware_enable(void *garbage) @@ -6706,8 +6763,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) } vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; - if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) { + r = -ENOMEM; goto fail_free_mce_banks; + } r = fx_init(vcpu); if (r) @@ -6811,6 +6870,23 @@ void kvm_arch_sync_events(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { + if (current->mm == kvm->mm) { + /* + * Free memory regions allocated on behalf of userspace, + * unless the the memory map has changed due to process exit + * or fd copying. + */ + struct kvm_userspace_memory_region mem; + memset(&mem, 0, sizeof(mem)); + mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + + mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + + mem.slot = TSS_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); @@ -6903,24 +6979,21 @@ out_free: int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - bool user_alloc) + enum kvm_mr_change change) { - int npages = memslot->npages; - /* * Only private memory slots need to be mapped here since * KVM_SET_MEMORY_REGION ioctl is no longer supported. */ - if ((memslot->id >= KVM_USER_MEM_SLOTS) && npages && !old.npages) { + if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) { unsigned long userspace_addr; /* * MAP_SHARED to prevent internal slot pages from being moved * by fork()/COW. */ - userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE, + userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); @@ -6935,17 +7008,17 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - bool user_alloc) + const struct kvm_memory_slot *old, + enum kvm_mr_change change) { - int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT; + int nr_mmu_pages = 0; - if ((mem->slot >= KVM_USER_MEM_SLOTS) && old.npages && !npages) { + if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) { int ret; - ret = vm_munmap(old.userspace_addr, - old.npages * PAGE_SIZE); + ret = vm_munmap(old->userspace_addr, + old->npages * PAGE_SIZE); if (ret < 0) printk(KERN_WARNING "kvm_vm_ioctl_set_memory_region: " @@ -6962,14 +7035,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * Existing largepage mappings are destroyed here and new ones will * not be created until the end of the logging. */ - if (npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) + if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) kvm_mmu_slot_remove_write_access(kvm, mem->slot); /* * If memory slot is created, or moved, we need to clear all * mmio sptes. */ - if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT) { - kvm_mmu_zap_all(kvm); + if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { + kvm_mmu_zap_mmio_sptes(kvm); kvm_reload_remote_mmus(kvm); } } @@ -6991,7 +7064,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted) || !list_empty_careful(&vcpu->async_pf.done) - || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED + || kvm_apic_has_events(vcpu) || atomic_read(&vcpu->arch.nmi_queued) || (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)); |