expose host-phys-bits to guest
v2 cover expose host-phys-bits to guest
When the guest (firmware specifically) knows how big the address space actually is it can be used better.
Some more background:
https://bugzilla.redhat.com/show_bug.cgi?id=2084533
This is a RfC series exposes the information via cpuid.
v2:
- change fvm hint name.
- better commit message.
take care,
Gerd
Gerd Hoffmann (2):
[temporary] reserve bit KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID [RfC] expose host-phys-bits to guest
include/standard-headers/asm-x86/kvm_para.h | 3 ++- target/i386/cpu.h | 3 --- hw/i386/microvm.c | 7 ++++++- target/i386/cpu.c | 3 +-- target/i386/host-cpu.c | 5 ++++- target/i386/kvm/kvm.c | 1 + 6 files changed, 14 insertions(+), 8 deletions(-)
Signature · 1 line
2.37.3
PATCH v2 1/2 reserve bit KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID
The KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID bit hints to the guest that the size of the physical address space as advertised by CPUID leaf 0x80000008 is actually valid and can be used.
Unfortunately this is not the case today with qemu. Default behavior is to advertise 40 address bits (which I think comes from the very first x64 opteron processors). There are lots of intel desktop processors around which support less than that (36 or 39 depending on age), and when trying to use the full 40 bit address space on those things go south quickly.
This renders the physical address size information effectively useless for guests. This patch paves the way to fix that by adding a hint for the guest so it knows whenever the physical address size is usable or not.
The plan for qemu is to set the bit when the physical address size is valid. That is the case when qemu is started with the host-phys-bits=on option set for the cpu. Eventually qemu can also flip the default for that option from off to on, unfortunately that isn't easy for backward compatibility reasons.
The plan for the firmware is to check that bit and when it is set just query and use the available physical address space. When the bit is not set be conservative and try not exceed 36 bits (aka 64G) address space. The latter is what the firmware does today unconditionally.
[ Temporary qemu patch for RfC patch and testing. This change must
actually be done in the linux kernel, then picked up by qemu via header file sync ].
--- include/standard-headers/asm-x86/kvm_para.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
include/standard-headers/asm-x86/kvm_para.h +2 -1
@@ -37,7 +37,8 @@#define KVM_FEATURE_HC_MAP_GPA_RANGE 16#define KVM_FEATURE_MIGRATION_CONTROL 17 -#define KVM_HINTS_REALTIME 0 +#define KVM_HINTS_REALTIME 0 +#define KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID 1/* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored.
Signature · 1 line
2.37.3
RFC PATCH v2 2/2 expose host-phys-bits to guest
In reply to Gerd HoffmannMove "host-phys-bits" property from cpu->host_phys_bits to cpu->env.features[FEAT_KVM_HINTS] (KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID bit).
This has the effect that the guest can see whenever host-phys-bits is turned on or not and act accordingly.
--- target/i386/cpu.h | 3 --- hw/i386/microvm.c | 7 ++++++- target/i386/cpu.c | 3 +-- target/i386/host-cpu.c | 5 ++++- target/i386/kvm/kvm.c | 1 + 5 files changed, 12 insertions(+), 7 deletions(-)
target/i386/cpu.h +0 -3
@@ -1898,9 +1898,6 @@ struct ArchCPU {/* if true fill the top bits of the MTRR_PHYSMASKn variable range */ bool fill_mtrr_mask; -/* if true override the phys_bits value with a value read from the host */ -bool host_phys_bits; -/* if set, limit maximum value for phys_bits when host_phys_bits is true */ uint8_t host_phys_bits_limit;
hw/i386/microvm.c +6 -1
@@ -54,6 +54,8 @@#include "kvm/kvm_i386.h" #include "hw/xen/start_info.h" +#include "standard-headers/asm-x86/kvm_para.h" +#define MICROVM_QBOOT_FILENAME "qboot.rom"#define MICROVM_BIOS_FILENAME "bios-microvm.bin"
@@ -424,7 +426,10 @@ static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, {X86CPU *cpu =X86_CPU (dev); - cpu->host_phys_bits = true;/* need reliable phys-bits */ +/* need reliable phys-bits */ + cpu->env.features[FEAT_KVM_HINTS ] |= + (1 <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ); +x86_cpu_pre_plug (hotplug_dev, dev, errp); }
target/i386/cpu.c +1 -2
@@ -778,7 +778,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { [FEAT_KVM_HINTS] = { .type = CPUID_FEATURE_WORD, .feat_names = { -"kvm-hint-dedicated" ,NULL ,NULL ,NULL , +"kvm-hint-dedicated" ,"host-phys-bits" ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL , NULL, NULL, NULL, NULL,
@@ -7016,7 +7016,6 @@ static Property x86_cpu_properties[] = {DEFINE_PROP_BOOL ("x-force-features" ,X86CPU , force_features, false),DEFINE_PROP_BOOL ("kvm" ,X86CPU , expose_kvm, true),DEFINE_PROP_UINT32 ("phys-bits" ,X86CPU , phys_bits,0 ), -DEFINE_PROP_BOOL ("host-phys-bits" ,X86CPU , host_phys_bits, false),DEFINE_PROP_UINT8 ("host-phys-bits-limit" ,X86CPU , host_phys_bits_limit,0 ),DEFINE_PROP_BOOL ("fill-mtrr-mask" ,X86CPU , fill_mtrr_mask, true), DEFINE_PROP_UINT32("level-func7", X86CPU, env.cpuid_level_func7,
target/i386/host-cpu.c +4 -1
@@ -13,6 +13,8 @@#include "qapi/error.h" #include "sysemu/sysemu.h" +#include "standard-headers/asm-x86/kvm_para.h" +/* Note: Only safe for use on x86(-64) hosts */ static uint32_t host_cpu_phys_bits (void ) {
@@ -68,7 +70,8 @@ static uint32_t host_cpu_adjust_phys_bits(X86CPU *cpu) warned = true; } -if (cpu->host_phys_bits) { +if (cpu->env.features[FEAT_KVM_HINTS ] & + (1 <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID )) {/* The user asked for us to use the host physical bits */ phys_bits = host_phys_bits; if (cpu->host_phys_bits_limit &&
target/i386/kvm/kvm.c +1 -0
@@ -459,6 +459,7 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, } }else if (function ==KVM_CPUID_FEATURES && reg ==R_EDX ) { ret |=1U <<KVM_HINTS_REALTIME ; + ret |=1U <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ; }return ret;
Signature · 1 line
2.37.3
Quoted 43 lines · Gerd Hoffmann
Move "host-phys-bits" property from
cpu->host_phys_bitsto cpu->env.features[FEAT_KVM_HINTS] (KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALIDbit).This has the effect that the guest can see whenever host-phys-bits is turned on or not and act accordingly.
Signed-off-by Gerd Hoffmann <[email protected]>--- target/i386/cpu.h | 3 --- hw/i386/microvm.c | 7 ++++++- target/i386/cpu.c | 3 +-- target/i386/host-cpu.c | 5 ++++- target/i386/kvm/kvm.c | 1 + 5 files changed, 12 insertions(+), 7 deletions(-)target/i386/cpu.h +0
-3@@ -1898,9 +1898,6 @@ struct ArchCPU {/* if true fill the top bits of the MTRR_PHYSMASKn variable range */ bool fill_mtrr_mask; -/* if true override the phys_bits value with a value read from the host */ -bool host_phys_bits; -/* if set, limit maximum value for phys_bits when host_phys_bits is true */ uint8_t host_phys_bits_limit;hw/i386/microvm.c +2
-0@@ -54,6 +54,8 @@#include "kvm/kvm_i386.h" #include "hw/xen/start_info.h" +#include "standard-headers/asm-x86/kvm_para.h" +#define MICROVM_QBOOT_FILENAME "qboot.rom"#define MICROVM_BIOS_FILENAME "bios-microvm.bin"
hw/i386/microvm.c static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, · line 432
Quoted 8 lines
hw/i386/microvm.c +4
-1@@ -424,7 +426,10 @@ static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, {X86CPU *cpu =X86_CPU (dev); - cpu->host_phys_bits = true;/* need reliable phys-bits */ +/* need reliable phys-bits */ + cpu->env.features[FEAT_KVM_HINTS ] |= + (1 <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ); +
Do we need compat machinery for this?
Quoted 38 lines
hw/i386/microvm.c +0
-0x86_cpu_pre_plug (hotplug_dev, dev, errp); }target/i386/cpu.c +1
-2@@ -778,7 +778,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { [FEAT_KVM_HINTS] = { .type = CPUID_FEATURE_WORD, .feat_names = { -"kvm-hint-dedicated" ,NULL ,NULL ,NULL , +"kvm-hint-dedicated" ,"host-phys-bits" ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL ,NULL , NULL, NULL, NULL, NULL,@@ -7016,7 +7016,6 @@ static Property x86_cpu_properties[] = {DEFINE_PROP_BOOL ("x-force-features" ,X86CPU , force_features, false),DEFINE_PROP_BOOL ("kvm" ,X86CPU , expose_kvm, true),DEFINE_PROP_UINT32 ("phys-bits" ,X86CPU , phys_bits,0 ), -DEFINE_PROP_BOOL ("host-phys-bits" ,X86CPU , host_phys_bits, false),DEFINE_PROP_UINT8 ("host-phys-bits-limit" ,X86CPU , host_phys_bits_limit,0 ),DEFINE_PROP_BOOL ("fill-mtrr-mask" ,X86CPU , fill_mtrr_mask, true), DEFINE_PROP_UINT32("level-func7", X86CPU, env.cpuid_level_func7,target/i386/host-cpu.c +2
-0@@ -13,6 +13,8 @@#include "qapi/error.h" #include "sysemu/sysemu.h" +#include "standard-headers/asm-x86/kvm_para.h" +/* Note: Only safe for use on x86(-64) hosts */ static uint32_t host_cpu_phys_bits (void ) {
target/i386/host-cpu.c static uint32_t host_cpu_adjust_phys_bits(X86CPU *cpu) · line 77
Quoted 9 lines
target/i386/host-cpu.c +2
-1@@ -68,7 +70,8 @@ static uint32_t host_cpu_adjust_phys_bits(X86CPU *cpu) warned = true; } -if (cpu->host_phys_bits) { +if (cpu->env.features[FEAT_KVM_HINTS ] & + (1 <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID )) {/* The user asked for us to use the host physical bits */ phys_bits = host_phys_bits; if (cpu->host_phys_bits_limit &&
I think we still want to key this one off host_phys_bits so it works for e.g. hyperv emulation too.
Quoted 14 lines
target/i386/kvm/kvm.c +1
-0@@ -459,6 +459,7 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, } }else if (function ==KVM_CPUID_FEATURES && reg ==R_EDX ) { ret |=1U <<KVM_HINTS_REALTIME ; + ret |=1U <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ; }return ret;Signature · 1 line
2.37.3
Hi,
Quoted 11 lines
hw/i386/microvm.c static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, · line 432
Quoted 9 lines
hw/i386/microvm.c +4
-1@@ -424,7 +426,10 @@ static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, {X86CPU *cpu =X86_CPU (dev); - cpu->host_phys_bits = true;/* need reliable phys-bits */ +/* need reliable phys-bits */ + cpu->env.features[FEAT_KVM_HINTS ] |= + (1 <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ); +Do we need compat machinery for this?
Don't think so, microvm has no versioned machine types anyway.
Quoted 18 lines
Quoted 7 lines
target/i386/cpu.c +0
-1[FEAT_KVM_HINTS] = { .type = CPUID_FEATURE_WORD, .feat_names = { - "kvm-hint-dedicated", NULL, NULL, NULL,target/i386/cpu.c
Quoted 10 lines
target/i386/cpu.c +3
-2+"kvm-hint-dedicated" ,"host-phys-bits" ,NULL ,NULL , -DEFINE_PROP_BOOL ("host-phys-bits" ,X86CPU , host_phys_bits, false), - if (cpu->host_phys_bits) { + if (cpu->env.features[FEAT_KVM_HINTS] & + (1 << KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID)) {/* The user asked for us to use the host physical bits */ phys_bits = host_phys_bits; if (cpu->host_phys_bits_limit &&
Quoted 2 lines
I think we still want to key this one off
host_phys_bitsso it works for e.g. hyperv emulation too.
I think that should be the case. The chunks above change the host-phys-bits option from setting cpu->host_phys_bits to setting the FEAT_KVM_HINTS bit. That should also happen with hyperv emulation enabled, and the bit should also be visible to the guest then, just at another location (base 0x40000100 instead of 0x40000000).
take care,
Gerd
Quoted 37 lines · Gerd Hoffmann
Hi,
Quoted 11 lines
hw/i386/microvm.c static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, · line 432
Quoted 9 lines
hw/i386/microvm.c +4
-1@@ -424,7 +426,10 @@ static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, {X86CPU *cpu =X86_CPU (dev); - cpu->host_phys_bits = true;/* need reliable phys-bits */ +/* need reliable phys-bits */ + cpu->env.features[FEAT_KVM_HINTS ] |= + (1 <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ); +Do we need compat machinery for this?
Don't think so, microvm has no versioned machine types anyway.
Quoted 18 lines
Quoted 7 lines
target/i386/cpu.c +0
-1[FEAT_KVM_HINTS] = { .type = CPUID_FEATURE_WORD, .feat_names = { - "kvm-hint-dedicated", NULL, NULL, NULL,target/i386/cpu.c
Quoted 10 lines
target/i386/cpu.c +3
-2+"kvm-hint-dedicated" ,"host-phys-bits" ,NULL ,NULL , -DEFINE_PROP_BOOL ("host-phys-bits" ,X86CPU , host_phys_bits, false), - if (cpu->host_phys_bits) { + if (cpu->env.features[FEAT_KVM_HINTS] & + (1 << KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID)) {/* The user asked for us to use the host physical bits */ phys_bits = host_phys_bits; if (cpu->host_phys_bits_limit &&Quoted 2 lines
I think we still want to key this one off
host_phys_bitsso it works for e.g. hyperv emulation too.
Quoted 8 lines
I think that should be the case. The chunks above change the host-phys-bits option from setting
cpu->host_phys_bitsto setting theFEAT_KVM_HINTSbit. That should also happen with hyperv emulation enabled, and the bit should also be visible to the guest then, just at another location (base0x40000100instead of0x40000000).take care,
Gerd
You are right, I forgot. Hmm, ok. What about !cpu->expose_kvm ?
We have
if (!kvm_enabled() || !cpu->expose_kvm) {
env->features[FEAT_KVM] = 0;
} This is quick grep, I didn't check whether this is called after the point where you currently use it, but
it frankly seems fragile to pass a generic user specified flag inside a cpuid where everyone pokes at it.
Signature · 1 line
MST
Hi,
Quoted 17 lines
Quoted 11 lines
Quoted 2 lines
I think we still want to key this one off
host_phys_bitsso it works for e.g. hyperv emulation too.I think that should be the case. The chunks above change the host-phys-bits option from setting
cpu->host_phys_bitsto setting theFEAT_KVM_HINTSbit. That should also happen with hyperv emulation enabled, and the bit should also be visible to the guest then, just at another location (base0x40000100instead of0x40000000).take care,
GerdYou are right, I forgot. Hmm, ok. What about !cpu->expose_kvm ?
We have
Quoted 8 lines
if (!kvm_enabled() || !cpu->expose_kvm) { env->features[FEAT_KVM] = 0; }This is quick grep, I didn't check whether this is called after the point where you currently use it, but
it frankly seems fragile to pass a generic user specified flag inside a cpuid where everyone pokes at it.
I tried to avoid keeping the state of the host_phys_bits option at multiple places. Maybe that wasn't a good idea after all. How about doing this instead:
target/i386/cpu.c +5 -0
@@ -6219,6 +6219,11 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) env->features[FEAT_KVM ] =0 ; } +if (kvm_enabled () && cpu->host_phys_bits) { + env->features[FEAT_KVM_HINTS ] |= + (1U <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ); + } +x86_cpu_enable_xsave_components (cpu);/* CPUID[EAX=7,ECX=0].EBX always increased level automatically: */
target/i386/kvm/kvm.c +1 -0
@@ -459,6 +459,7 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, } }else if (function ==KVM_CPUID_FEATURES && reg ==R_EDX ) { ret |=1U <<KVM_HINTS_REALTIME ; + ret |=1U <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ; }return ret;
Quoted 53 lines · Gerd Hoffmann
Hi,
Quoted 17 lines
Quoted 11 lines
Quoted 2 lines
I think we still want to key this one off
host_phys_bitsso it works for e.g. hyperv emulation too.I think that should be the case. The chunks above change the host-phys-bits option from setting
cpu->host_phys_bitsto setting theFEAT_KVM_HINTSbit. That should also happen with hyperv emulation enabled, and the bit should also be visible to the guest then, just at another location (base0x40000100instead of0x40000000).take care,
GerdYou are right, I forgot. Hmm, ok. What about !cpu->expose_kvm ?
We have
Quoted 8 lines
if (!kvm_enabled() || !cpu->expose_kvm) { env->features[FEAT_KVM] = 0; }This is quick grep, I didn't check whether this is called after the point where you currently use it, but
it frankly seems fragile to pass a generic user specified flag inside a cpuid where everyone pokes at it.I tried to avoid keeping the state of the
host_phys_bitsoption at multiple places. Maybe that wasn't a good idea after all. How about doing this instead:target/i386/cpu.c +5
-0@@ -6219,6 +6219,11 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) env->features[FEAT_KVM ] =0 ; } +if (kvm_enabled () && cpu->host_phys_bits) { + env->features[FEAT_KVM_HINTS ] |= + (1U <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ); + } +x86_cpu_enable_xsave_components (cpu);/* CPUID[EAX=7,ECX=0].EBX always increased level automatically: */ target/i386/kvm/kvm.c +0
-0
target/i386/kvm/kvm.c uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, · line 465
Quoted 7 lines
target/i386/kvm/kvm.c +1
-0@@ -459,6 +459,7 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, } }else if (function ==KVM_CPUID_FEATURES && reg ==R_EDX ) { ret |=1U <<KVM_HINTS_REALTIME ; + ret |=1U <<KVM_HINTS_PHYS_ADDRESS_SIZE_DATA_VALID ; }return ret;
/me nods.
That seems much more straight-forward.
Signature · 1 line
MST