[PATCH v4 0/2] x86: Enable user wait instructions

[PATCH v4 0/2] x86: Enable user wait instructions

[Tao Xu]

UMONITOR, UMWAIT and TPAUSE are a set of user wait instructions.

UMONITOR arms address monitoring hardware using an address. A store
to an address within the specified address range triggers the
monitoring hardware to wake up the processor waiting in umwait.

UMWAIT instructs the processor to enter an implementation-dependent
optimized state while monitoring a range of addresses. The optimized
state may be either a light-weight power/performance optimized state
(c0.1 state) or an improved power/performance optimized state
(c0.2 state).

TPAUSE instructs the processor to enter an implementation-dependent
optimized state c0.1 or c0.2 state and wake up when time-stamp counter
reaches specified timeout.

Availability of the user wait instructions is indicated by the presence
of the CPUID feature flag WAITPKG CPUID.0x07.0x0:ECX[5].

The patches enable the umonitor, umwait and tpause features in KVM.
Because umwait and tpause can put a (psysical) CPU into a power saving
state, by default we dont't expose it in kvm and provide a capability to
enable it. Use kvm capability to enable UMONITOR, UMWAIT and TPAUSE when
QEMU use "-overcommit cpu-pm=on, a VM can use UMONITOR, UMWAIT and TPAUSE
instructions. If the instruction causes a delay, the amount of time
delayed is called here the physical delay. The physical delay is first
computed by determining the virtual delay (the time to delay relative to
the VM’s timestamp counter). Otherwise, UMONITOR, UMWAIT and TPAUSE cause
an invalid-opcode exception(#UD).

The dependency KVM patch link:
https://lkml.org/lkml/2019/7/16/58

The release document ref below link:
https://software.intel.com/sites/default/files/\
managed/39/c5/325462-sdm-vol-1-2abcd-3abcd.pdf

Changelog:
v4:
	Set IA32_UMWAIT_CONTROL 32bits
v3:
	Simplify the patches, expose user wait instructions when the guest
	has CPUID (Paolo)
v2:
	Separated from the series
	https://www.mail-archive.com/qemu-devel@nongnu.org/msg549526.html
	Use kvm capability to enable UMONITOR, UMWAIT and TPAUSE when
	QEMU use "-overcommit cpu-pm=on"	
v1:
	Sent out with MOVDIRI/MOVDIR64B instructions patches

Tao Xu (2):
  x86/cpu: Add support for UMONITOR/UMWAIT/TPAUSE
  target/i386: Add support for save/load IA32_UMWAIT_CONTROL MSR

 target/i386/cpu.c     |  3 ++-
 target/i386/cpu.h     |  3 +++
 target/i386/kvm.c     | 17 +++++++++++++++++
 target/i386/machine.c | 20 ++++++++++++++++++++
 4 files changed, 42 insertions(+), 1 deletion(-)

-- 
2.20.1

[PATCH v4 1/2] x86/cpu: Add support for UMONITOR/UMWAIT/TPAUSE

[Tao Xu]

UMONITOR, UMWAIT and TPAUSE are a set of user wait instructions.
This patch adds support for user wait instructions in KVM. Availability
of the user wait instructions is indicated by the presence of the CPUID
feature flag WAITPKG CPUID.0x07.0x0:ECX[5]. User wait instructions may
be executed at any privilege level, and use IA32_UMWAIT_CONTROL MSR to
set the maximum time.

The patch enable the umonitor, umwait and tpause features in KVM.
Because umwait and tpause can put a (psysical) CPU into a power saving
state, by default we dont't expose it to kvm and enable it only when
guest CPUID has it. And use QEMU command-line "-overcommit cpu-pm=on"
(enable_cpu_pm is enabled), a VM can use UMONITOR, UMWAIT and TPAUSE
instructions. If the instruction causes a delay, the amount of time
delayed is called here the physical delay. The physical delay is first
computed by determining the virtual delay (the time to delay relative to
the VM’s timestamp counter). Otherwise, UMONITOR, UMWAIT and TPAUSE cause
an invalid-opcode exception(#UD).

The release document ref below link:
https://software.intel.com/sites/default/files/\
managed/39/c5/325462-sdm-vol-1-2abcd-3abcd.pdf

Co-developed-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
---

No changes in v4.
---
 target/i386/cpu.c | 3 ++-
 target/i386/cpu.h | 1 +
 target/i386/kvm.c | 4 ++++
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 805ce95247..9546a40d8a 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -1061,7 +1061,7 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
         .type = CPUID_FEATURE_WORD,
         .feat_names = {
             NULL, "avx512vbmi", "umip", "pku",
-            NULL /* ospke */, NULL, "avx512vbmi2", NULL,
+            NULL /* ospke */, "waitpkg", "avx512vbmi2", NULL,
             "gfni", "vaes", "vpclmulqdq", "avx512vnni",
             "avx512bitalg", NULL, "avx512-vpopcntdq", NULL,
             "la57", NULL, NULL, NULL,
@@ -5193,6 +5193,7 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp)
             host_cpuid(5, 0, &cpu->mwait.eax, &cpu->mwait.ebx,
                        &cpu->mwait.ecx, &cpu->mwait.edx);
             env->features[FEAT_1_ECX] |= CPUID_EXT_MONITOR;
+            env->features[FEAT_7_0_ECX] |= CPUID_7_0_ECX_WAITPKG;
         }
     }
 
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 05393cf9d1..19caf82729 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -672,6 +672,7 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS];
 #define CPUID_7_0_ECX_UMIP     (1U << 2)
 #define CPUID_7_0_ECX_PKU      (1U << 3)
 #define CPUID_7_0_ECX_OSPKE    (1U << 4)
+#define CPUID_7_0_ECX_WAITPKG  (1U << 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
 #define CPUID_7_0_ECX_VBMI2    (1U << 6) /* Additional VBMI Instrs */
 #define CPUID_7_0_ECX_GFNI     (1U << 8)
 #define CPUID_7_0_ECX_VAES     (1U << 9)
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index ec7870c6af..f8daa13f10 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -390,6 +390,10 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
         if (host_tsx_blacklisted()) {
             ret &= ~(CPUID_7_0_EBX_RTM | CPUID_7_0_EBX_HLE);
         }
+    } else if (function == 7 && index == 0 && reg == R_ECX) {
+        if (enable_cpu_pm) {
+            ret |= CPUID_7_0_ECX_WAITPKG;
+        }
     } else if (function == 7 && index == 0 && reg == R_EDX) {
         /*
          * Linux v4.17-v4.20 incorrectly return ARCH_CAPABILITIES on SVM hosts.
-- 
2.20.1

[PATCH v4 2/2] target/i386: Add support for save/load IA32_UMWAIT_CONTROL MSR

[Tao Xu]

UMWAIT and TPAUSE instructions use 32bits IA32_UMWAIT_CONTROL at MSR
index E1H to determines the maximum time in TSC-quanta that the processor
can reside in either C0.1 or C0.2.

This patch is to Add support for save/load IA32_UMWAIT_CONTROL MSR in
guest.

Co-developed-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
---

Changes in v4:
        Set IA32_UMWAIT_CONTROL 32bits
---
 target/i386/cpu.h     |  2 ++
 target/i386/kvm.c     | 13 +++++++++++++
 target/i386/machine.c | 20 ++++++++++++++++++++
 3 files changed, 35 insertions(+)

diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 19caf82729..e5d4c81926 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -451,6 +451,7 @@ typedef enum X86Seg {
 
 #define MSR_IA32_BNDCFGS                0x00000d90
 #define MSR_IA32_XSS                    0x00000da0
+#define MSR_IA32_UMWAIT_CONTROL         0xe1
 
 #define XSTATE_FP_BIT                   0
 #define XSTATE_SSE_BIT                  1
@@ -1385,6 +1386,7 @@ typedef struct CPUX86State {
     uint16_t fpregs_format_vmstate;
 
     uint64_t xss;
+    uint32_t umwait;
 
     TPRAccess tpr_access_type;
 
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index f8daa13f10..ba0ee01598 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -91,6 +91,7 @@ static bool has_msr_hv_stimer;
 static bool has_msr_hv_frequencies;
 static bool has_msr_hv_reenlightenment;
 static bool has_msr_xss;
+static bool has_msr_umwait;
 static bool has_msr_spec_ctrl;
 static bool has_msr_virt_ssbd;
 static bool has_msr_smi_count;
@@ -1914,6 +1915,9 @@ static int kvm_get_supported_msrs(KVMState *s)
                 case MSR_IA32_XSS:
                     has_msr_xss = true;
                     break;
+                case MSR_IA32_UMWAIT_CONTROL:
+                    has_msr_umwait = true;
+                    break;
                 case HV_X64_MSR_CRASH_CTL:
                     has_msr_hv_crash = true;
                     break;
@@ -2464,6 +2468,9 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
     if (has_msr_xss) {
         kvm_msr_entry_add(cpu, MSR_IA32_XSS, env->xss);
     }
+    if (has_msr_umwait) {
+        kvm_msr_entry_add(cpu, MSR_IA32_UMWAIT_CONTROL, env->umwait);
+    }
     if (has_msr_spec_ctrl) {
         kvm_msr_entry_add(cpu, MSR_IA32_SPEC_CTRL, env->spec_ctrl);
     }
@@ -2863,6 +2870,9 @@ static int kvm_get_msrs(X86CPU *cpu)
     if (has_msr_xss) {
         kvm_msr_entry_add(cpu, MSR_IA32_XSS, 0);
     }
+    if (has_msr_umwait) {
+        kvm_msr_entry_add(cpu, MSR_IA32_UMWAIT_CONTROL, 0);
+    }
     if (has_msr_spec_ctrl) {
         kvm_msr_entry_add(cpu, MSR_IA32_SPEC_CTRL, 0);
     }
@@ -3112,6 +3122,9 @@ static int kvm_get_msrs(X86CPU *cpu)
         case MSR_IA32_XSS:
             env->xss = msrs[i].data;
             break;
+        case MSR_IA32_UMWAIT_CONTROL:
+            env->umwait = msrs[i].data;
+            break;
         default:
             if (msrs[i].index >= MSR_MC0_CTL &&
                 msrs[i].index < MSR_MC0_CTL + (env->mcg_cap & 0xff) * 4) {
diff --git a/target/i386/machine.c b/target/i386/machine.c
index 704ba6de46..861a5c5a20 100644
--- a/target/i386/machine.c
+++ b/target/i386/machine.c
@@ -910,6 +910,25 @@ static const VMStateDescription vmstate_xss = {
     }
 };
 
+static bool umwait_needed(void *opaque)
+{
+    X86CPU *cpu = opaque;
+    CPUX86State *env = &cpu->env;
+
+    return env->umwait != 0;
+}
+
+static const VMStateDescription vmstate_umwait = {
+    .name = "cpu/umwait",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = umwait_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(env.umwait, X86CPU),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 #ifdef TARGET_X86_64
 static bool pkru_needed(void *opaque)
 {
@@ -1376,6 +1395,7 @@ VMStateDescription vmstate_x86_cpu = {
         &vmstate_msr_hyperv_reenlightenment,
         &vmstate_avx512,
         &vmstate_xss,
+        &vmstate_umwait,
         &vmstate_tsc_khz,
         &vmstate_msr_smi_count,
 #ifdef TARGET_X86_64
-- 
2.20.1