x86/HVM: allow per-domain usage of hardware virtualized APIC

Introduce a new per-domain creation x86 specific flag to
select whether hardware assisted virtualization should be used for
x{2}APIC.

A per-domain option is added to xl in order to select the usage of
x{2}APIC hardware assisted virtualization, as well as a global
configuration option.

Having all APIC interaction exit to Xen for emulation is slow and can
induce much overhead. Hardware can speed up x{2}APIC by decoding the
APIC access and providing a VM exit with a more specific exit reason
than a regular EPT fault or by altogether avoiding a VM exit.

On the other hand, being able to disable x{2}APIC hardware assisted
virtualization can be useful for testing and debugging purposes.

Note:

- vmx_install_vlapic_mapping doesn't require modifications regardless
of whether the guest has "Virtualize APIC accesses" enabled or not,
i.e., setting the APIC_ACCESS_ADDR VMCS field is fine so long as
virtualize_apic_accesses is supported by the CPU.

- Both per-domain and global assisted_x{2}apic options are not part of
the migration stream, unless explicitly set in the respective
configuration files. Default settings of assisted_x{2}apic done
internally by the toolstack, based on host capabilities at create
time, are not migrated.

Suggested-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Jane Malalane <jane.malalane@citrix.com>
Acked-by: Christian Lindig <christian.lindig@citrix.com>
Reviewed-by: "Roger Pau Monné" <roger.pau@citrix.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: George Dunlap <george.dunlap@citrix.com>
This commit is contained in:
Jane Malalane authored and Jan Beulich committed 2022-07-11 12:15:05 +02:00
1 parent 6b2b9b3405
commit 2ce11ce249
23 files changed
+187 -29

No files matched your search

+15
View File
@@ -1862,6 +1862,21 @@ firmware tables when using certain older guest Operating
Systems. These tables have been superseded by newer constructs within
the ACPI tables.
=item B<assisted_xapic=BOOLEAN>
B<(x86 only)> Enables or disables hardware assisted virtualization for
xAPIC. With this option enabled, a memory-mapped APIC access will be
decoded by hardware and either issue a more specific VM exit than just
a p2m fault, or altogether avoid a VM exit. The
default is settable via L<xl.conf(5)>.
=item B<assisted_x2apic=BOOLEAN>
B<(x86 only)> Enables or disables hardware assisted virtualization for
x2APIC. With this option enabled, certain accesses to MSR APIC
registers will avoid a VM exit into the hypervisor. The default is
settable via L<xl.conf(5)>.
=item B<nx=BOOLEAN>
B<(x86 only)> Hides or exposes the No-eXecute capability. This allows a guest
+12
View File
@@ -107,6 +107,18 @@ Sets the default value for the C<max_grant_version> domain config value.
Default: maximum grant version supported by the hypervisor.
=item B<assisted_xapic=BOOLEAN>
If enabled, domains will use xAPIC hardware assisted virtualization by default.
Default: enabled if supported.
=item B<assisted_x2apic=BOOLEAN>
If enabled, domains will use x2APIC hardware assisted virtualization by default.
Default: enabled if supported.
=item B<vif.default.script="PATH">
Configures the default hotplug script used by virtual network devices.
+12
View File
@@ -1120,6 +1120,12 @@ x.ArchArm.Vuart = VuartType(xc.arch_arm.vuart)
if err := x.ArchX86.MsrRelaxed.fromC(&xc.arch_x86.msr_relaxed);err != nil {
return fmt.Errorf("converting field ArchX86.MsrRelaxed: %v", err)
}
if err := x.ArchX86.AssistedXapic.fromC(&xc.arch_x86.assisted_xapic);err != nil {
return fmt.Errorf("converting field ArchX86.AssistedXapic: %v", err)
}
if err := x.ArchX86.AssistedX2Apic.fromC(&xc.arch_x86.assisted_x2apic);err != nil {
return fmt.Errorf("converting field ArchX86.AssistedX2Apic: %v", err)
}
x.Altp2M = Altp2MMode(xc.altp2m)
x.VmtraceBufKb = int(xc.vmtrace_buf_kb)
if err := x.Vpmu.fromC(&xc.vpmu);err != nil {
@@ -1605,6 +1611,12 @@ xc.arch_arm.vuart = C.libxl_vuart_type(x.ArchArm.Vuart)
if err := x.ArchX86.MsrRelaxed.toC(&xc.arch_x86.msr_relaxed); err != nil {
return fmt.Errorf("converting field ArchX86.MsrRelaxed: %v", err)
}
if err := x.ArchX86.AssistedXapic.toC(&xc.arch_x86.assisted_xapic); err != nil {
return fmt.Errorf("converting field ArchX86.AssistedXapic: %v", err)
}
if err := x.ArchX86.AssistedX2Apic.toC(&xc.arch_x86.assisted_x2apic); err != nil {
return fmt.Errorf("converting field ArchX86.AssistedX2Apic: %v", err)
}
xc.altp2m = C.libxl_altp2m_mode(x.Altp2M)
xc.vmtrace_buf_kb = C.int(x.VmtraceBufKb)
if err := x.Vpmu.toC(&xc.vpmu); err != nil {
+2
View File
@@ -520,6 +520,8 @@ Vuart VuartType
}
ArchX86 struct {
MsrRelaxed Defbool
AssistedXapic Defbool
AssistedX2Apic Defbool
}
Altp2M Altp2MMode
VmtraceBufKb int
+7
View File
@@ -542,6 +542,13 @@
*/
#define LIBXL_HAVE_PHYSINFO_ASSISTED_APIC 1
/*
* LIBXL_HAVE_ASSISTED_APIC indicates that libxl_domain_build_info has
* assisted_xapic and assisted_x2apic fields for enabling hardware
* assisted virtualization for x{2}apic per domain.
*/
#define LIBXL_HAVE_ASSISTED_APIC 1
/*
* libxl ABI compatibility
*
+3 -2
View File
@@ -71,8 +71,9 @@ void libxl__arch_domain_create_info_setdefault(libxl__gc *gc,
libxl_domain_create_info *c_info);
_hidden
void libxl__arch_domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info);
int libxl__arch_domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info,
const libxl_physinfo *physinfo);
_hidden
int libxl__arch_passthrough_mode_setdefault(libxl__gc *gc,
+6 -3
View File
@@ -1384,14 +1384,15 @@ void libxl__arch_domain_create_info_setdefault(libxl__gc *gc,
}
}
void libxl__arch_domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info)
int libxl__arch_domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info,
const libxl_physinfo *physinfo)
{
/* ACPI is disabled by default */
libxl_defbool_setdefault(&b_info->acpi, false);
if (b_info->type != LIBXL_DOMAIN_TYPE_PV)
return;
return 0;
LOG(DEBUG, "Converting build_info to PVH");
@@ -1399,6 +1400,8 @@ void libxl__arch_domain_build_info_setdefault(libxl__gc *gc,
memset(&b_info->u, '\0', sizeof(b_info->u));
b_info->type = LIBXL_DOMAIN_TYPE_INVALID;
libxl_domain_build_info_init_type(b_info, LIBXL_DOMAIN_TYPE_PVH);
return 0;
}
int libxl__arch_passthrough_mode_setdefault(libxl__gc *gc,
+13 -9
View File
@@ -75,6 +75,7 @@ int libxl__domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info)
{
int i, rc;
libxl_physinfo info;
if (b_info->type != LIBXL_DOMAIN_TYPE_HVM &&
b_info->type != LIBXL_DOMAIN_TYPE_PV &&
@@ -264,7 +265,18 @@ int libxl__domain_build_info_setdefault(libxl__gc *gc,
if (!b_info->event_channels)
b_info->event_channels = 1023;
libxl__arch_domain_build_info_setdefault(gc, b_info);
rc = libxl_get_physinfo(CTX, &info);
if (rc) {
LOG(ERROR, "failed to get hypervisor info");
return rc;
}
rc = libxl__arch_domain_build_info_setdefault(gc, b_info, &info);
if (rc) {
LOG(ERROR, "unable to set domain arch build info defaults");
return rc;
}
libxl_defbool_setdefault(&b_info->dm_restrict, false);
if (b_info->iommu_memkb == LIBXL_MEMKB_DEFAULT)
@@ -457,14 +469,6 @@ int libxl__domain_build_info_setdefault(libxl__gc *gc,
}
if (b_info->max_grant_version == LIBXL_MAX_GRANT_DEFAULT) {
libxl_physinfo info;
rc = libxl_get_physinfo(CTX, &info);
if (rc) {
LOG(ERROR, "failed to get hypervisor info");
return rc;
}
if (info.cap_gnttab_v2)
b_info->max_grant_version = 2;
else if (info.cap_gnttab_v1)
+2
View File
@@ -648,6 +648,8 @@ libxl_domain_build_info = Struct("domain_build_info",[
("vuart", libxl_vuart_type),
])),
("arch_x86", Struct(None, [("msr_relaxed", libxl_defbool),
("assisted_xapic", libxl_defbool),
("assisted_x2apic", libxl_defbool),
])),
# Alternate p2m is not bound to any architecture or guest type, as it is
# supported by x86 HVM and ARM support is planned.
+26 -2
View File
@@ -23,6 +23,15 @@ int libxl__arch_domain_prepare_config(libxl__gc *gc,
if (libxl_defbool_val(d_config->b_info.arch_x86.msr_relaxed))
config->arch.misc_flags |= XEN_X86_MSR_RELAXED;
if (d_config->c_info.type != LIBXL_DOMAIN_TYPE_PV)
{
if (libxl_defbool_val(d_config->b_info.arch_x86.assisted_xapic))
config->arch.misc_flags |= XEN_X86_ASSISTED_XAPIC;
if (libxl_defbool_val(d_config->b_info.arch_x86.assisted_x2apic))
config->arch.misc_flags |= XEN_X86_ASSISTED_X2APIC;
}
return 0;
}
@@ -819,11 +828,26 @@ void libxl__arch_domain_create_info_setdefault(libxl__gc *gc,
{
}
void libxl__arch_domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info)
int libxl__arch_domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info,
const libxl_physinfo *physinfo)
{
libxl_defbool_setdefault(&b_info->acpi, true);
libxl_defbool_setdefault(&b_info->arch_x86.msr_relaxed, false);
if (b_info->type != LIBXL_DOMAIN_TYPE_PV) {
libxl_defbool_setdefault(&b_info->arch_x86.assisted_xapic,
physinfo->cap_assisted_xapic);
libxl_defbool_setdefault(&b_info->arch_x86.assisted_x2apic,
physinfo->cap_assisted_x2apic);
}
else if (!libxl_defbool_is_default(b_info->arch_x86.assisted_xapic) ||
!libxl_defbool_is_default(b_info->arch_x86.assisted_x2apic)) {
LOG(ERROR, "Interrupt Controller Virtualization not supported for PV");
return ERROR_INVAL;
}
return 0;
}
int libxl__arch_passthrough_mode_setdefault(libxl__gc *gc,
+2
View File
@@ -50,6 +50,8 @@ type x86_arch_emulation_flags =
type x86_arch_misc_flags =
| X86_MSR_RELAXED
| X86_ASSISTED_XAPIC
| X86_ASSISTED_X2APIC
type xen_x86_arch_domainconfig =
{
+2
View File
@@ -44,6 +44,8 @@ type x86_arch_emulation_flags =
type x86_arch_misc_flags =
| X86_MSR_RELAXED
| X86_ASSISTED_XAPIC
| X86_ASSISTED_X2APIC
type xen_x86_arch_domainconfig = {
emulation_flags: x86_arch_emulation_flags list;
+1 -1
View File
@@ -244,7 +244,7 @@ CAMLprim value stub_xc_domain_create(value xch, value wanted_domid, value config
cfg.arch.misc_flags = ocaml_list_to_c_bitmap
/* ! x86_arch_misc_flags X86_ none */
/* ! XEN_X86_ XEN_X86_MSR_RELAXED all */
/* ! XEN_X86_ XEN_X86_MISC_FLAGS_MAX max */
(VAL_MISC_FLAGS);
#undef VAL_MISC_FLAGS
+8
View File
@@ -57,6 +57,8 @@ int max_grant_frames = -1;
int max_maptrack_frames = -1;
int max_grant_version = LIBXL_MAX_GRANT_DEFAULT;
libxl_domid domid_policy = INVALID_DOMID;
int assisted_xapic = -1;
int assisted_x2apic = -1;
xentoollog_level minmsglevel = minmsglevel_default;
@@ -201,6 +203,12 @@ static void parse_global_config(const char *configfile,
if (!xlu_cfg_get_long (config, "claim_mode", &l, 0))
claim_mode = l;
if (!xlu_cfg_get_long (config, "assisted_xapic", &l, 0))
assisted_xapic = l;
if (!xlu_cfg_get_long (config, "assisted_x2apic", &l, 0))
assisted_x2apic = l;
xlu_cfg_replace_string (config, "remus.default.netbufscript",
&default_remus_netbufscript, 0);
xlu_cfg_replace_string (config, "colo.default.proxyscript",
+2
View File
@@ -286,6 +286,8 @@ extern libxl_bitmap global_vm_affinity_mask;
extern libxl_bitmap global_hvm_affinity_mask;
extern libxl_bitmap global_pv_affinity_mask;
extern libxl_domid domid_policy;
extern int assisted_xapic;
extern int assisted_x2apic;
enum output_format {
OUTPUT_FORMAT_JSON,
+19
View File
@@ -2765,6 +2765,25 @@ skip_usbdev:
xlu_cfg_get_defbool(config, "vpmu", &b_info->vpmu, 0);
if (b_info->type != LIBXL_DOMAIN_TYPE_PV) {
e = xlu_cfg_get_long(config, "assisted_xapic", &l , 0);
if (!e)
libxl_defbool_set(&b_info->arch_x86.assisted_xapic, l);
else if (e != ESRCH)
exit(1);
else if (assisted_xapic != -1) /* use global default if present */
libxl_defbool_set(&b_info->arch_x86.assisted_xapic, assisted_xapic);
e = xlu_cfg_get_long(config, "assisted_x2apic", &l, 0);
if (!e)
libxl_defbool_set(&b_info->arch_x86.assisted_x2apic, l);
else if (e != ESRCH)
exit(1);
else if (assisted_x2apic != -1) /* use global default if present */
libxl_defbool_set(&b_info->arch_x86.assisted_x2apic,
assisted_x2apic);
}
xlu_cfg_destroy(config);
}
+28 -1
View File
@@ -50,6 +50,7 @@
#include <asm/cpuidle.h>
#include <asm/mpspec.h>
#include <asm/ldt.h>
#include <asm/hvm/domain.h>
#include <asm/hvm/hvm.h>
#include <asm/hvm/nestedhvm.h>
#include <asm/hvm/support.h>
@@ -619,6 +620,8 @@ int arch_sanitise_domain_config(struct xen_domctl_createdomain *config)
bool hvm = config->flags & XEN_DOMCTL_CDF_hvm;
bool hap = config->flags & XEN_DOMCTL_CDF_hap;
bool nested_virt = config->flags & XEN_DOMCTL_CDF_nested_virt;
bool assisted_xapic = config->arch.misc_flags & XEN_X86_ASSISTED_XAPIC;
bool assisted_x2apic = config->arch.misc_flags & XEN_X86_ASSISTED_X2APIC;
unsigned int max_vcpus;
if ( hvm ? !hvm_enabled : !IS_ENABLED(CONFIG_PV) )
@@ -685,13 +688,31 @@ int arch_sanitise_domain_config(struct xen_domctl_createdomain *config)
}
}
if ( config->arch.misc_flags & ~XEN_X86_MSR_RELAXED )
if ( config->arch.misc_flags & ~(XEN_X86_MSR_RELAXED |
XEN_X86_ASSISTED_XAPIC |
XEN_X86_ASSISTED_X2APIC) )
{
dprintk(XENLOG_INFO, "Invalid arch misc flags %#x\n",
config->arch.misc_flags);
return -EINVAL;
}
if ( (assisted_xapic || assisted_x2apic) && !hvm )
{
dprintk(XENLOG_INFO,
"Interrupt Controller Virtualization not supported for PV\n");
return -EINVAL;
}
if ( (assisted_xapic && !assisted_xapic_available) ||
(assisted_x2apic && !assisted_x2apic_available) )
{
dprintk(XENLOG_INFO,
"Hardware assisted x%sAPIC requested but not available\n",
assisted_xapic && !assisted_xapic_available ? "" : "2");
return -ENODEV;
}
return 0;
}
@@ -864,6 +885,12 @@ int arch_domain_create(struct domain *d,
d->arch.msr_relaxed = config->arch.misc_flags & XEN_X86_MSR_RELAXED;
d->arch.hvm.assisted_xapic =
config->arch.misc_flags & XEN_X86_ASSISTED_XAPIC;
d->arch.hvm.assisted_x2apic =
config->arch.misc_flags & XEN_X86_ASSISTED_X2APIC;
spec_ctrl_init_domain(d);
return 0;
+4
View File
@@ -1134,6 +1134,10 @@ static int construct_vmcs(struct vcpu *v)
__vmwrite(PLE_WINDOW, ple_window);
}
if ( !has_assisted_xapic(d) )
v->arch.hvm.vmx.secondary_exec_control &=
~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
if ( cpu_has_vmx_secondary_exec_control )
__vmwrite(SECONDARY_VM_EXEC_CONTROL,
v->arch.hvm.vmx.secondary_exec_control);
+4 -9
View File
@@ -3376,16 +3376,11 @@ static void vmx_install_vlapic_mapping(struct vcpu *v)
void vmx_vlapic_msr_changed(struct vcpu *v)
{
int virtualize_x2apic_mode;
struct vlapic *vlapic = vcpu_vlapic(v);
unsigned int msr;
virtualize_x2apic_mode = ( (cpu_has_vmx_apic_reg_virt ||
cpu_has_vmx_virtual_intr_delivery) &&
cpu_has_vmx_virtualize_x2apic_mode );
if ( !cpu_has_vmx_virtualize_apic_accesses &&
!virtualize_x2apic_mode )
if ( !has_assisted_xapic(v->domain) &&
!has_assisted_x2apic(v->domain) )
return;
vmx_vmcs_enter(v);
@@ -3395,7 +3390,7 @@ void vmx_vlapic_msr_changed(struct vcpu *v)
if ( !vlapic_hw_disabled(vlapic) &&
(vlapic_base_address(vlapic) == APIC_DEFAULT_PHYS_BASE) )
{
if ( virtualize_x2apic_mode && vlapic_x2apic_mode(vlapic) )
if ( has_assisted_x2apic(v->domain) && vlapic_x2apic_mode(vlapic) )
{
v->arch.hvm.vmx.secondary_exec_control |=
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
@@ -3416,7 +3411,7 @@ void vmx_vlapic_msr_changed(struct vcpu *v)
vmx_clear_msr_intercept(v, MSR_X2APIC_SELF, VMX_MSR_W);
}
}
else
else if ( has_assisted_xapic(v->domain) )
v->arch.hvm.vmx.secondary_exec_control |=
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
}
+6
View File
@@ -117,6 +117,12 @@ struct hvm_domain {
bool is_s3_suspended;
/* xAPIC hardware assisted virtualization. */
bool assisted_xapic;
/* x2APIC hardware assisted virtualization. */
bool assisted_x2apic;
/* hypervisor intercepted msix table */
struct list_head msixtbl_list;
+5
View File
@@ -391,6 +391,9 @@ int hvm_get_param(struct domain *d, uint32_t index, uint64_t *value);
extern bool assisted_xapic_available;
extern bool assisted_x2apic_available;
#define has_assisted_xapic(d) ((d)->arch.hvm.assisted_xapic)
#define has_assisted_x2apic(d) ((d)->arch.hvm.assisted_x2apic)
#define hvm_get_guest_time(v) hvm_get_guest_time_fixed(v, 0)
#define hvm_paging_enabled(v) \
@@ -907,6 +910,8 @@ static inline void hvm_set_reg(struct vcpu *v, unsigned int reg, uint64_t val)
#define assisted_xapic_available false
#define assisted_x2apic_available false
#define has_assisted_xapic(d) ((void)(d), false)
#define has_assisted_x2apic(d) ((void)(d), false)
#define hvm_paging_enabled(v) ((void)(v), false)
#define hvm_wp_enabled(v) ((void)(v), false)
#define hvm_pcid_enabled(v) ((void)(v), false)
+3 -2
View File
@@ -1117,7 +1117,8 @@ void cpuid_hypervisor_leaves(const struct vcpu *v, uint32_t leaf,
if ( !is_hvm_domain(d) || subleaf != 0 )
break;
if ( cpu_has_vmx_apic_reg_virt )
if ( cpu_has_vmx_apic_reg_virt &&
has_assisted_xapic(d) )
res->a |= XEN_HVM_CPUID_APIC_ACCESS_VIRT;
/*
@@ -1126,7 +1127,7 @@ void cpuid_hypervisor_leaves(const struct vcpu *v, uint32_t leaf,
* and wrmsr in the guest will run without VMEXITs (see
* vmx_vlapic_msr_changed()).
*/
if ( cpu_has_vmx_virtualize_x2apic_mode &&
if ( has_assisted_x2apic(d) &&
cpu_has_vmx_apic_reg_virt &&
cpu_has_vmx_virtual_intr_delivery )
res->a |= XEN_HVM_CPUID_X2APIC_VIRT;
+5
View File
@@ -317,9 +317,14 @@ struct xen_arch_domainconfig {
* doesn't allow the guest to read or write to the underlying MSR.
*/
#define XEN_X86_MSR_RELAXED (1u << 0)
#define XEN_X86_ASSISTED_XAPIC (1u << 1)
#define XEN_X86_ASSISTED_X2APIC (1u << 2)
uint32_t misc_flags;
};
/* Max XEN_X86_* constant. Used for ABI checking. */
#define XEN_X86_MISC_FLAGS_MAX XEN_X86_ASSISTED_X2APIC
/* Location of online VCPU bitmap. */
#define XEN_ACPI_CPU_MAP 0xaf00
#define XEN_ACPI_CPU_MAP_LEN ((HVM_MAX_VCPUS + 7) / 8)
Reference in new issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.