VMware products handle hypercalls in userspace. Give KVM the ability
to run VMware guests unmodified by fowarding all hypercalls to the
userspace.
Enabling of the KVM_CAP_X86_VMWARE_HYPERCALL_ENABLE capability turns
the feature on - it's off by default. This allows vmx's built on top
of KVM to support VMware specific hypercalls.
Signed-off-by: Zack Rusin <zack.rusin@xxxxxxxxxxxx>
Cc: Doug Covelli <doug.covelli@xxxxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
Cc: Joel Stanley <joel@xxxxxxxxx>
Cc: Zack Rusin <zack.rusin@xxxxxxxxxxxx>
Cc: kvm@xxxxxxxxxxxxxxx
Cc: linux-doc@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-kselftest@xxxxxxxxxxxxxxx
---
Documentation/virt/kvm/api.rst | 41 +++++++++++++++++++++++++++++----
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/x86.c | 33 ++++++++++++++++++++++++++
include/uapi/linux/kvm.h | 1 +
4 files changed, 72 insertions(+), 4 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 33ef3cc785e4..5a8c7922f64f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6601,10 +6601,11 @@ to the byte array.
.. note::
For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR, KVM_EXIT_XEN,
- KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
- operations are complete (and guest state is consistent) only after userspace
- has re-entered the kernel with KVM_RUN. The kernel side will first finish
- incomplete operations and then check for pending signals.
+ KVM_EXIT_EPR, KVM_EXIT_HYPERCALL, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR
+ the corresponding operations are complete (and guest state is consistent)
+ only after userspace has re-entered the kernel with KVM_RUN. The kernel
+ side will first finish incomplete operations and then check for pending
+ signals.
The pending state of the operation is not preserved in state which is
visible to userspace, thus userspace should ensure that the operation is
@@ -8201,6 +8202,38 @@ default value for it is set via the kvm.enable_vmware_backdoor
kernel parameter (false when not set). Must be set before any
VCPUs have been created.
+7.38 KVM_CAP_X86_VMWARE_HYPERCALL
+---------------------------------
+
+:Architectures: x86
+:Parameters: args[0] whether the feature should be enabled or not
+:Returns: 0 on success.
+
+Capability allows userspace to handle hypercalls. When enabled
+whenever the vcpu has executed a VMCALL(Intel) or a VMMCALL(AMD)
+instruction kvm will exit to userspace with KVM_EXIT_HYPERCALL.
+
+On exit the hypercall structure of the kvm_run structure will
+look as follows:
+
+::
+ /* KVM_EXIT_HYPERCALL */
+ struct {
+ __u64 nr; // rax
+ __u64 args[6]; // rbx, rcx, rdx, rsi, rdi, rbp
+ __u64 ret; // cpl, whatever userspace
+ // sets this to on return will be
+ // written to the rax
+ __u64 flags; // KVM_EXIT_HYPERCALL_LONG_MODE if
+ // the hypercall was executed in
+ // 64bit mode, 0 otherwise
+ } hypercall;
+
+Except when running in compatibility mode with VMware hypervisors
+userspace handling of hypercalls is discouraged. To implement
+such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO
+(all except s390).
+
8. Other capabilities.
======================
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7fcf185e337f..7fbb11682517 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1404,6 +1404,7 @@ struct kvm_arch {
struct kvm_xen xen;
#endif
bool vmware_backdoor_enabled;
+ bool vmware_hypercall_enabled;
bool backwards_tsc_observed;
bool boot_vcpu_runs_old_kvmclock;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d7071907d6a5..b676c54266e7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4689,6 +4689,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_MEMORY_FAULT_INFO:
case KVM_CAP_X86_GUEST_MODE:
case KVM_CAP_X86_VMWARE_BACKDOOR:
+ case KVM_CAP_X86_VMWARE_HYPERCALL:
r = 1;
break;
case KVM_CAP_PRE_FAULT_MEMORY:
@@ -6784,6 +6785,13 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
}
mutex_unlock(&kvm->lock);
break;
+ case KVM_CAP_X86_VMWARE_HYPERCALL:
+ r = -EINVAL;
+ if (cap->args[0] & ~1)
+ break;
+ kvm->arch.vmware_hypercall_enabled = cap->args[0];
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
@@ -10127,6 +10135,28 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
return kvm_skip_emulated_instruction(vcpu);
}
+static int kvm_vmware_hypercall(struct kvm_vcpu *vcpu)
+{
+ struct kvm_run *run = vcpu->run;
+ bool is_64_bit = is_64_bit_hypercall(vcpu);
+ u64 mask = is_64_bit ? U64_MAX : U32_MAX;
+
+ vcpu->run->hypercall.flags = is_64_bit ? KVM_EXIT_HYPERCALL_LONG_MODE : 0;
+ run->hypercall.nr = kvm_rax_read(vcpu) & mask;
+ run->hypercall.args[0] = kvm_rbx_read(vcpu) & mask;
+ run->hypercall.args[1] = kvm_rcx_read(vcpu) & mask;
+ run->hypercall.args[2] = kvm_rdx_read(vcpu) & mask;
+ run->hypercall.args[3] = kvm_rsi_read(vcpu) & mask;
+ run->hypercall.args[4] = kvm_rdi_read(vcpu) & mask;
+ run->hypercall.args[5] = kvm_rbp_read(vcpu) & mask;
+ run->hypercall.ret = kvm_x86_call(get_cpl)(vcpu);
+
+ run->exit_reason = KVM_EXIT_HYPERCALL;
+ vcpu->arch.complete_userspace_io = complete_hypercall_exit;
+
+ return 0;
+}
+
unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
unsigned long a0, unsigned long a1,
unsigned long a2, unsigned long a3,
@@ -10225,6 +10255,9 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
int op_64_bit;
int cpl;
+ if (vcpu->kvm->arch.vmware_hypercall_enabled)
+ return kvm_vmware_hypercall(vcpu);
+
if (kvm_xen_hypercall_enabled(vcpu->kvm))
return kvm_xen_hypercall(vcpu);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index c7b5f1c2ee1c..4c2cc6ed29a0 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -934,6 +934,7 @@ struct kvm_enable_cap {
#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
#define KVM_CAP_X86_GUEST_MODE 238
#define KVM_CAP_X86_VMWARE_BACKDOOR 239
+#define KVM_CAP_X86_VMWARE_HYPERCALL 240
struct kvm_irq_routing_irqchip {
__u32 irqchip;
--
2.43.0
