KVM: Add documentation for Xen hypercall and shared_info updates

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>

1 files changed, 166 insertions, 5 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index effcc08733fd..5919e9a94f25 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -960,6 +960,14 @@ memory.
 	__u8 pad2[30];
   };
 
+If the KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag is returned from the
+KVM_CAP_XEN_HVM check, it may be set in the flags field of this ioctl.
+This requests KVM to generate the contents of the hypercall page
+automatically; hypercalls will be intercepted and passed to userspace
+through KVM_EXIT_XEN.  In this case, all of the blob size and address
+fields must be zero.
+
+No other flags are currently valid in the struct kvm_xen_hvm_config.
 
 4.29 KVM_GET_CLOCK
 ------------------
@@ -4831,6 +4839,101 @@ into user space.
 If a vCPU is in running state while this ioctl is invoked, the vCPU may
 experience inconsistent filtering behavior on MSR accesses.
 
+4.127 KVM_XEN_HVM_SET_ATTR
+--------------------------
+
+:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_xen_hvm_attr
+:Returns: 0 on success, < 0 on error
+
+::
+
+  struct kvm_xen_hvm_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u8 long_mode;
+		__u8 vector;
+		struct {
+			__u64 gfn;
+		} shared_info;
+		__u64 pad[4];
+	} u;
+  };
+
+type values:
+
+KVM_XEN_ATTR_TYPE_LONG_MODE
+  Sets the ABI mode of the VM to 32-bit or 64-bit (long mode). This
+  determines the layout of the shared info pages exposed to the VM.
+
+KVM_XEN_ATTR_TYPE_SHARED_INFO
+  Sets the guest physical frame number at which the Xen "shared info"
+  page resides. Note that although Xen places vcpu_info for the first
+  32 vCPUs in the shared_info page, KVM does not automatically do so
+  and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used
+  explicitly even when the vcpu_info for a given vCPU resides at the
+  "default" location in the shared_info page. This is because KVM is
+  not aware of the Xen CPU id which is used as the index into the
+  vcpu_info[] array, so cannot know the correct default location.
+
+KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
+  Sets the exception vector used to deliver Xen event channel upcalls.
+
+4.128 KVM_XEN_HVM_GET_ATTR
+--------------------------
+
+:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_xen_hvm_attr
+:Returns: 0 on success, < 0 on error
+
+Allows Xen VM attributes to be read. For the structure and types,
+see KVM_XEN_HVM_SET_ATTR above.
+
+4.129 KVM_XEN_VCPU_SET_ATTR
+---------------------------
+
+:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_xen_vcpu_attr
+:Returns: 0 on success, < 0 on error
+
+::
+
+  struct kvm_xen_vcpu_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u64 gpa;
+		__u64 pad[4];
+	} u;
+  };
+
+type values:
+
+KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO
+  Sets the guest physical address of the vcpu_info for a given vCPU.
+
+KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO
+  Sets the guest physical address of an additional pvclock structure
+  for a given vCPU. This is typically used for guest vsyscall support.
+
+4.130 KVM_XEN_VCPU_GET_ATTR
+--------------------------
+
+:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
+:Architectures: x86
+:Type: vcpu ioctl
+:Parameters: struct kvm_xen_vcpu_attr
+:Returns: 0 on success, < 0 on error
+
+Allows Xen vCPU attributes to be read. For the structure and types,
+see KVM_XEN_VCPU_SET_ATTR above.
 
 5. The kvm_run structure
 ========================
@@ -4998,13 +5101,18 @@ to the byte array.
 
 .. note::
 
-      For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR,
+      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.  Userspace
-      can re-enter the guest with an unmasked signal pending to complete
-      pending operations.
+      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
+      completed before performing a live migration.  Userspace can re-enter the
+      guest with an unmasked signal pending or with the immediate_exit field set
+      to complete pending operations without allowing any further instructions
+      to be executed.
 
 ::
 
@@ -5331,6 +5439,34 @@ vCPU execution. If the MSR write was unsuccessful, user space also sets the
 
 ::
 
+
+		struct kvm_xen_exit {
+  #define KVM_EXIT_XEN_HCALL          1
+			__u32 type;
+			union {
+				struct {
+					__u32 longmode;
+					__u32 cpl;
+					__u64 input;
+					__u64 result;
+					__u64 params[6];
+				} hcall;
+			} u;
+		};
+		/* KVM_EXIT_XEN */
+                struct kvm_hyperv_exit xen;
+
+Indicates that the VCPU exits into userspace to process some tasks
+related to Xen emulation.
+
+Valid values for 'type' are:
+
+  - KVM_EXIT_XEN_HCALL -- synchronously notify user-space about Xen hypercall.
+    Userspace is expected to place the hypercall result into the appropriate
+    field before invoking KVM_RUN again.
+
+::
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -6454,7 +6590,6 @@ guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
 (0x40000001). Otherwise, a guest may use the paravirtual features
 regardless of what has actually been exposed through the CPUID leaf.
 
-
 8.29 KVM_CAP_DIRTY_LOG_RING
 ---------------------------
 
@@ -6541,3 +6676,29 @@ KVM_GET_DIRTY_LOG and KVM_CLEAR_DIRTY_LOG.  After enabling
 KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual
 machine will switch to ring-buffer dirty page tracking and further
 KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail.
+
+8.30 KVM_CAP_XEN_HVM
+--------------------
+
+:Architectures: x86
+
+This capability indicates the features that Xen supports for hosting Xen
+PVHVM guests. Valid flags are::
+
+  #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
+  #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
+  #define KVM_XEN_HVM_CONFIG_SHARED_INFO	(1 << 2)
+
+The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
+ioctl is available, for the guest to set its hypercall page.
+
+If KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL is also set, the same flag may also be
+provided in the flags to KVM_XEN_HVM_CONFIG, without providing hypercall page
+contents, to request that KVM generate hypercall page content automatically
+and also enable interception of guest hypercalls with KVM_EXIT_XEN.
+
+The KVM_XEN_HVM_CONFIG_SHARED_INFO flag indicates the availability of the
+KVM_XEN_HVM_SET_ATTR, KVM_XEN_HVM_GET_ATTR, KVM_XEN_VCPU_SET_ATTR and
+KVM_XEN_VCPU_GET_ATTR ioctls, as well as the delivery of exception vectors
+for event channel upcalls when the evtchn_upcall_pending field of a vcpu's
+vcpu_info is set.