summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/x86/kvm/emulate.c10
-rw-r--r--arch/x86/kvm/mmu.c6
-rw-r--r--arch/x86/kvm/vmx.c4
-rw-r--r--arch/x86/kvm/x86.c1
-rw-r--r--include/linux/kvm_host.h1
-rw-r--r--include/uapi/linux/kvm.h6
-rw-r--r--virt/kvm/eventfd.c43
-rw-r--r--virt/kvm/kvm_main.c1
8 files changed, 58 insertions, 14 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 205b17eed93c..0dec502d20be 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2496,7 +2496,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
struct tss_segment_32 *tss)
{
- tss->cr3 = ctxt->ops->get_cr(ctxt, 3);
+ /* CR3 and ldt selector are not saved intentionally */
tss->eip = ctxt->_eip;
tss->eflags = ctxt->eflags;
tss->eax = reg_read(ctxt, VCPU_REGS_RAX);
@@ -2514,7 +2514,6 @@ static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS);
tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS);
tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS);
- tss->ldt_selector = get_segment_selector(ctxt, VCPU_SREG_LDTR);
}
static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
@@ -2604,6 +2603,8 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
struct tss_segment_32 tss_seg;
int ret;
u32 new_tss_base = get_desc_base(new_desc);
+ u32 eip_offset = offsetof(struct tss_segment_32, eip);
+ u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector);
ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
&ctxt->exception);
@@ -2613,8 +2614,9 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
save_state_to_tss32(ctxt, &tss_seg);
- ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
- &ctxt->exception);
+ /* Only GP registers and segment selectors are saved */
+ ret = ops->write_std(ctxt, old_tss_base + eip_offset, &tss_seg.eip,
+ ldt_sel_offset - eip_offset, &ctxt->exception);
if (ret != X86EMUL_CONTINUE)
/* FIXME: need to provide precise fault address */
return ret;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 813d31038b93..668ae5916de9 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3538,7 +3538,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
case PT32E_ROOT_LEVEL:
context->rsvd_bits_mask[0][2] =
rsvd_bits(maxphyaddr, 63) |
- rsvd_bits(7, 8) | rsvd_bits(1, 2); /* PDPTE */
+ rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */
context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 62); /* PDE */
context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
@@ -3550,9 +3550,9 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
break;
case PT64_ROOT_LEVEL:
context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
- rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7);
context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
- rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7);
context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51);
context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1f68c5831924..eb3f2b1b764c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5528,6 +5528,10 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
gpa_t gpa;
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+ if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+ skip_emulated_instruction(vcpu);
+ return 1;
+ }
ret = handle_mmio_page_fault_common(vcpu, gpa, true);
if (likely(ret == RET_MMIO_PF_EMULATE))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8b8fc0b792ba..bc4aaf68190c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2644,6 +2644,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_IRQ_INJECT_STATUS:
case KVM_CAP_IRQFD:
case KVM_CAP_IOEVENTFD:
+ case KVM_CAP_IOEVENTFD_NO_LENGTH:
case KVM_CAP_PIT2:
case KVM_CAP_PIT_STATE2:
case KVM_CAP_SET_IDENTITY_MAP_ADDR:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 471d1400c4ac..32d263f683dc 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -163,6 +163,7 @@ enum kvm_bus {
KVM_MMIO_BUS,
KVM_PIO_BUS,
KVM_VIRTIO_CCW_NOTIFY_BUS,
+ KVM_FAST_MMIO_BUS,
KVM_NR_BUSES
};
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 90acfe4966e7..836e15b7abc8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -515,6 +515,7 @@ enum {
kvm_ioeventfd_flag_nr_pio,
kvm_ioeventfd_flag_nr_deassign,
kvm_ioeventfd_flag_nr_virtio_ccw_notify,
+ kvm_ioeventfd_flag_nr_fast_mmio,
kvm_ioeventfd_flag_nr_max,
};
@@ -529,7 +530,7 @@ enum {
struct kvm_ioeventfd {
__u64 datamatch;
__u64 addr; /* legal pio/mmio address */
- __u32 len; /* 1, 2, 4, or 8 bytes */
+ __u32 len; /* 1, 2, 4, or 8 bytes; or 0 to ignore length */
__s32 fd;
__u32 flags;
__u8 pad[36];
@@ -743,7 +744,8 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
#define KVM_CAP_ENABLE_CAP_VM 98
#define KVM_CAP_S390_IRQCHIP 99
-#define KVM_CAP_VM_ATTRIBUTES 100
+#define KVM_CAP_IOEVENTFD_NO_LENGTH 100
+#define KVM_CAP_VM_ATTRIBUTES 101
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 29c2a04e036e..912ec5a95e2c 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -600,7 +600,15 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
{
u64 _val;
- if (!(addr == p->addr && len == p->length))
+ if (addr != p->addr)
+ /* address must be precise for a hit */
+ return false;
+
+ if (!p->length)
+ /* length = 0 means only look at the address, so always a hit */
+ return true;
+
+ if (len != p->length)
/* address-range must be precise for a hit */
return false;
@@ -671,9 +679,11 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
list_for_each_entry(_p, &kvm->ioeventfds, list)
if (_p->bus_idx == p->bus_idx &&
- _p->addr == p->addr && _p->length == p->length &&
- (_p->wildcard || p->wildcard ||
- _p->datamatch == p->datamatch))
+ _p->addr == p->addr &&
+ (!_p->length || !p->length ||
+ (_p->length == p->length &&
+ (_p->wildcard || p->wildcard ||
+ _p->datamatch == p->datamatch))))
return true;
return false;
@@ -697,8 +707,9 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
int ret;
bus_idx = ioeventfd_bus_from_flags(args->flags);
- /* must be natural-word sized */
+ /* must be natural-word sized, or 0 to ignore length */
switch (args->len) {
+ case 0:
case 1:
case 2:
case 4:
@@ -716,6 +727,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
return -EINVAL;
+ /* ioeventfd with no length can't be combined with DATAMATCH */
+ if (!args->len &&
+ args->flags & (KVM_IOEVENTFD_FLAG_PIO |
+ KVM_IOEVENTFD_FLAG_DATAMATCH))
+ return -EINVAL;
+
eventfd = eventfd_ctx_fdget(args->fd);
if (IS_ERR(eventfd))
return PTR_ERR(eventfd);
@@ -753,6 +770,16 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
if (ret < 0)
goto unlock_fail;
+ /* When length is ignored, MMIO is also put on a separate bus, for
+ * faster lookups.
+ */
+ if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) {
+ ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
+ p->addr, 0, &p->dev);
+ if (ret < 0)
+ goto register_fail;
+ }
+
kvm->buses[bus_idx]->ioeventfd_count++;
list_add_tail(&p->list, &kvm->ioeventfds);
@@ -760,6 +787,8 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
return 0;
+register_fail:
+ kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
unlock_fail:
mutex_unlock(&kvm->slots_lock);
@@ -799,6 +828,10 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
continue;
kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
+ if (!p->length) {
+ kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
+ &p->dev);
+ }
kvm->buses[bus_idx]->ioeventfd_count--;
ioeventfd_release(p);
ret = 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7facdb1f1374..ea46d64c8e75 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2920,6 +2920,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
return -EOPNOTSUPP;
}
+EXPORT_SYMBOL_GPL(kvm_io_bus_write);
/* kvm_io_bus_read - called under kvm->slots_lock */
int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-11 22:54:22 +0300