Merge tag 'for-upstream-8.0' of https://gitlab.com/bonzini/qemu into staging

* New Sapphire Rapids model support
* x86 bugfixes
* Prepare to drop support for Python 3.6

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmP87gcUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroM+TAf/TcRrukw+FXUs0Ld3AadRY6g3xV2x
# n1VIfkMC2Bp1LVOS1W9aw7V6jPg8KMAV9SCQJjsVtyB5E9yPQg+/w7UgexqISYQG
# 7NK3jDXmslSGIHNHh4qH9xAjQGjw/6e7N/gyWP+99vHPwZSbFJT6k7KP0/3O9yCu
# /9KINq8AvvGbfW5m2d/umV1v1Gq4KwXkTa5uVIOciDMJtaA0QjADHg1MqsHPzBUP
# F4du5BbuMaJkgQgJV5zsn7W9NnEQt1XzSug1c/vp2vyqEV00L4TjL9BzTqsTEBtS
# KjUcQif5R5a+o8QRND9j8f74xjFpOR/nAEleNsfo6iwZQwWAiBQZ8ETsew==
# =2aMG
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 27 Feb 2023 17:53:11 GMT
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* tag 'for-upstream-8.0' of https://gitlab.com/bonzini/qemu:
  i386: Add new CPU model SapphireRapids
  target/i386: KVM: allow fast string operations if host supports them
  target/i386: add FZRM, FSRS, FSRC
  target/i386: add FSRM to TCG
  MAINTAINERS: Cover RCU documentation
  ci, docker: update CentOS and OpenSUSE Python to non-EOL versions
  docs/devel: update and clarify lcitool instructions
  lcitool: update submodule
  configure: Look for auxiliary Python installations
  configure: protect against escaping venv when running Meson
  meson: stop looking for 'sphinx-build-3'
  meson: Avoid duplicates in generated config-poison.h again
  target/i386: Fix BZHI instruction

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 170 insertions, 14 deletions

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 4d2b8d0444..4bad3d41d3 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -661,8 +661,9 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
 #define TCG_7_0_ECX_FEATURES (CPUID_7_0_ECX_UMIP | CPUID_7_0_ECX_PKU | \
           /* CPUID_7_0_ECX_OSPKE is dynamic */ \
           CPUID_7_0_ECX_LA57 | CPUID_7_0_ECX_PKS | CPUID_7_0_ECX_VAES)
-#define TCG_7_0_EDX_FEATURES 0
-#define TCG_7_1_EAX_FEATURES 0
+#define TCG_7_0_EDX_FEATURES CPUID_7_0_EDX_FSRM
+#define TCG_7_1_EAX_FEATURES (CPUID_7_1_EAX_FZRM | CPUID_7_1_EAX_FSRS | \
+          CPUID_7_1_EAX_FSRC)
 #define TCG_APM_FEATURES 0
 #define TCG_6_EAX_FEATURES CPUID_6_EAX_ARAT
 #define TCG_XSAVE_FEATURES (CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XGETBV1)
@@ -872,8 +873,8 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
         .feat_names = {
             NULL, NULL, NULL, NULL,
             "avx-vnni", "avx512-bf16", NULL, NULL,
-            NULL, NULL, NULL, NULL,
-            NULL, NULL, NULL, NULL,
+            NULL, NULL, "fzrm", "fsrs",
+            "fsrc", NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
@@ -3468,6 +3469,135 @@ static const X86CPUDefinition builtin_x86_defs[] = {
         }
     },
     {
+        .name = "SapphireRapids",
+        .level = 0x20,
+        .vendor = CPUID_VENDOR_INTEL,
+        .family = 6,
+        .model = 143,
+        .stepping = 4,
+        /*
+         * please keep the ascending order so that we can have a clear view of
+         * bit position of each feature.
+         */
+        .features[FEAT_1_EDX] =
+            CPUID_FP87 | CPUID_VME | CPUID_DE | CPUID_PSE | CPUID_TSC |
+            CPUID_MSR | CPUID_PAE | CPUID_MCE | CPUID_CX8 | CPUID_APIC |
+            CPUID_SEP | CPUID_MTRR | CPUID_PGE | CPUID_MCA | CPUID_CMOV |
+            CPUID_PAT | CPUID_PSE36 | CPUID_CLFLUSH | CPUID_MMX | CPUID_FXSR |
+            CPUID_SSE | CPUID_SSE2,
+        .features[FEAT_1_ECX] =
+            CPUID_EXT_SSE3 | CPUID_EXT_PCLMULQDQ | CPUID_EXT_SSSE3 |
+            CPUID_EXT_FMA | CPUID_EXT_CX16 | CPUID_EXT_PCID | CPUID_EXT_SSE41 |
+            CPUID_EXT_SSE42 | CPUID_EXT_X2APIC | CPUID_EXT_MOVBE |
+            CPUID_EXT_POPCNT | CPUID_EXT_TSC_DEADLINE_TIMER | CPUID_EXT_AES |
+            CPUID_EXT_XSAVE | CPUID_EXT_AVX | CPUID_EXT_F16C | CPUID_EXT_RDRAND,
+        .features[FEAT_8000_0001_EDX] =
+            CPUID_EXT2_SYSCALL | CPUID_EXT2_NX | CPUID_EXT2_PDPE1GB |
+            CPUID_EXT2_RDTSCP | CPUID_EXT2_LM,
+        .features[FEAT_8000_0001_ECX] =
+            CPUID_EXT3_LAHF_LM | CPUID_EXT3_ABM | CPUID_EXT3_3DNOWPREFETCH,
+        .features[FEAT_8000_0008_EBX] =
+            CPUID_8000_0008_EBX_WBNOINVD,
+        .features[FEAT_7_0_EBX] =
+            CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_HLE |
+            CPUID_7_0_EBX_AVX2 | CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 |
+            CPUID_7_0_EBX_ERMS | CPUID_7_0_EBX_INVPCID | CPUID_7_0_EBX_RTM |
+            CPUID_7_0_EBX_AVX512F | CPUID_7_0_EBX_AVX512DQ |
+            CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX | CPUID_7_0_EBX_SMAP |
+            CPUID_7_0_EBX_AVX512IFMA | CPUID_7_0_EBX_CLFLUSHOPT |
+            CPUID_7_0_EBX_CLWB | CPUID_7_0_EBX_AVX512CD | CPUID_7_0_EBX_SHA_NI |
+            CPUID_7_0_EBX_AVX512BW | CPUID_7_0_EBX_AVX512VL,
+        .features[FEAT_7_0_ECX] =
+            CPUID_7_0_ECX_AVX512_VBMI | CPUID_7_0_ECX_UMIP | CPUID_7_0_ECX_PKU |
+            CPUID_7_0_ECX_AVX512_VBMI2 | CPUID_7_0_ECX_GFNI |
+            CPUID_7_0_ECX_VAES | CPUID_7_0_ECX_VPCLMULQDQ |
+            CPUID_7_0_ECX_AVX512VNNI | CPUID_7_0_ECX_AVX512BITALG |
+            CPUID_7_0_ECX_AVX512_VPOPCNTDQ | CPUID_7_0_ECX_LA57 |
+            CPUID_7_0_ECX_RDPID | CPUID_7_0_ECX_BUS_LOCK_DETECT,
+        .features[FEAT_7_0_EDX] =
+            CPUID_7_0_EDX_FSRM | CPUID_7_0_EDX_SERIALIZE |
+            CPUID_7_0_EDX_TSX_LDTRK | CPUID_7_0_EDX_AMX_BF16 |
+            CPUID_7_0_EDX_AVX512_FP16 | CPUID_7_0_EDX_AMX_TILE |
+            CPUID_7_0_EDX_AMX_INT8 | CPUID_7_0_EDX_SPEC_CTRL |
+            CPUID_7_0_EDX_ARCH_CAPABILITIES | CPUID_7_0_EDX_SPEC_CTRL_SSBD,
+        .features[FEAT_ARCH_CAPABILITIES] =
+            MSR_ARCH_CAP_RDCL_NO | MSR_ARCH_CAP_IBRS_ALL |
+            MSR_ARCH_CAP_SKIP_L1DFL_VMENTRY | MSR_ARCH_CAP_MDS_NO |
+            MSR_ARCH_CAP_PSCHANGE_MC_NO | MSR_ARCH_CAP_TAA_NO,
+        .features[FEAT_XSAVE] =
+            CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC |
+            CPUID_XSAVE_XGETBV1 | CPUID_XSAVE_XSAVES | CPUID_D_1_EAX_XFD,
+        .features[FEAT_6_EAX] =
+            CPUID_6_EAX_ARAT,
+        .features[FEAT_7_1_EAX] =
+            CPUID_7_1_EAX_AVX_VNNI | CPUID_7_1_EAX_AVX512_BF16 |
+            CPUID_7_1_EAX_FZRM | CPUID_7_1_EAX_FSRS | CPUID_7_1_EAX_FSRC,
+        .features[FEAT_VMX_BASIC] =
+            MSR_VMX_BASIC_INS_OUTS | MSR_VMX_BASIC_TRUE_CTLS,
+        .features[FEAT_VMX_ENTRY_CTLS] =
+            VMX_VM_ENTRY_LOAD_DEBUG_CONTROLS | VMX_VM_ENTRY_IA32E_MODE |
+            VMX_VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |
+            VMX_VM_ENTRY_LOAD_IA32_PAT | VMX_VM_ENTRY_LOAD_IA32_EFER,
+        .features[FEAT_VMX_EPT_VPID_CAPS] =
+            MSR_VMX_EPT_EXECONLY |
+            MSR_VMX_EPT_PAGE_WALK_LENGTH_4 | MSR_VMX_EPT_PAGE_WALK_LENGTH_5 |
+            MSR_VMX_EPT_WB | MSR_VMX_EPT_2MB | MSR_VMX_EPT_1GB |
+            MSR_VMX_EPT_INVEPT | MSR_VMX_EPT_AD_BITS |
+            MSR_VMX_EPT_INVEPT_SINGLE_CONTEXT | MSR_VMX_EPT_INVEPT_ALL_CONTEXT |
+            MSR_VMX_EPT_INVVPID | MSR_VMX_EPT_INVVPID_SINGLE_ADDR |
+            MSR_VMX_EPT_INVVPID_SINGLE_CONTEXT |
+            MSR_VMX_EPT_INVVPID_ALL_CONTEXT |
+            MSR_VMX_EPT_INVVPID_SINGLE_CONTEXT_NOGLOBALS,
+        .features[FEAT_VMX_EXIT_CTLS] =
+            VMX_VM_EXIT_SAVE_DEBUG_CONTROLS |
+            VMX_VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |
+            VMX_VM_EXIT_ACK_INTR_ON_EXIT | VMX_VM_EXIT_SAVE_IA32_PAT |
+            VMX_VM_EXIT_LOAD_IA32_PAT | VMX_VM_EXIT_SAVE_IA32_EFER |
+            VMX_VM_EXIT_LOAD_IA32_EFER | VMX_VM_EXIT_SAVE_VMX_PREEMPTION_TIMER,
+        .features[FEAT_VMX_MISC] =
+            MSR_VMX_MISC_STORE_LMA | MSR_VMX_MISC_ACTIVITY_HLT |
+            MSR_VMX_MISC_VMWRITE_VMEXIT,
+        .features[FEAT_VMX_PINBASED_CTLS] =
+            VMX_PIN_BASED_EXT_INTR_MASK | VMX_PIN_BASED_NMI_EXITING |
+            VMX_PIN_BASED_VIRTUAL_NMIS | VMX_PIN_BASED_VMX_PREEMPTION_TIMER |
+            VMX_PIN_BASED_POSTED_INTR,
+        .features[FEAT_VMX_PROCBASED_CTLS] =
+            VMX_CPU_BASED_VIRTUAL_INTR_PENDING |
+            VMX_CPU_BASED_USE_TSC_OFFSETING | VMX_CPU_BASED_HLT_EXITING |
+            VMX_CPU_BASED_INVLPG_EXITING | VMX_CPU_BASED_MWAIT_EXITING |
+            VMX_CPU_BASED_RDPMC_EXITING | VMX_CPU_BASED_RDTSC_EXITING |
+            VMX_CPU_BASED_CR3_LOAD_EXITING | VMX_CPU_BASED_CR3_STORE_EXITING |
+            VMX_CPU_BASED_CR8_LOAD_EXITING | VMX_CPU_BASED_CR8_STORE_EXITING |
+            VMX_CPU_BASED_TPR_SHADOW | VMX_CPU_BASED_VIRTUAL_NMI_PENDING |
+            VMX_CPU_BASED_MOV_DR_EXITING | VMX_CPU_BASED_UNCOND_IO_EXITING |
+            VMX_CPU_BASED_USE_IO_BITMAPS | VMX_CPU_BASED_MONITOR_TRAP_FLAG |
+            VMX_CPU_BASED_USE_MSR_BITMAPS | VMX_CPU_BASED_MONITOR_EXITING |
+            VMX_CPU_BASED_PAUSE_EXITING |
+            VMX_CPU_BASED_ACTIVATE_SECONDARY_CONTROLS,
+        .features[FEAT_VMX_SECONDARY_CTLS] =
+            VMX_SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+            VMX_SECONDARY_EXEC_ENABLE_EPT | VMX_SECONDARY_EXEC_DESC |
+            VMX_SECONDARY_EXEC_RDTSCP |
+            VMX_SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+            VMX_SECONDARY_EXEC_ENABLE_VPID | VMX_SECONDARY_EXEC_WBINVD_EXITING |
+            VMX_SECONDARY_EXEC_UNRESTRICTED_GUEST |
+            VMX_SECONDARY_EXEC_APIC_REGISTER_VIRT |
+            VMX_SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
+            VMX_SECONDARY_EXEC_RDRAND_EXITING |
+            VMX_SECONDARY_EXEC_ENABLE_INVPCID |
+            VMX_SECONDARY_EXEC_ENABLE_VMFUNC | VMX_SECONDARY_EXEC_SHADOW_VMCS |
+            VMX_SECONDARY_EXEC_RDSEED_EXITING | VMX_SECONDARY_EXEC_ENABLE_PML |
+            VMX_SECONDARY_EXEC_XSAVES,
+        .features[FEAT_VMX_VMFUNC] =
+            MSR_VMX_VMFUNC_EPT_SWITCHING,
+        .xlevel = 0x80000008,
+        .model_id = "Intel Xeon Processor (SapphireRapids)",
+        .versions = (X86CPUVersionDefinition[]) {
+            { .version = 1 },
+            { /* end of list */ },
+        },
+    },
+    {
         .name = "Denverton",
         .level = 21,
         .vendor = CPUID_VENDOR_INTEL,
@@ -5622,7 +5752,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         break;
     }
     case 0x1D: {
-        /* AMX TILE */
+        /* AMX TILE, for now hardcoded for Sapphire Rapids*/
         *eax = 0;
         *ebx = 0;
         *ecx = 0;
@@ -5643,7 +5773,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         break;
     }
     case 0x1E: {
-        /* AMX TMUL */
+        /* AMX TMUL, for now hardcoded for Sapphire Rapids */
         *eax = 0;
         *ebx = 0;
         *ecx = 0;
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index d4bc19577a..41777fb4b0 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -881,10 +881,14 @@ uint64_t x86_cpu_get_supported_feature_word(FeatureWord w,
 #define CPUID_7_0_EDX_TSX_LDTRK         (1U << 16)
 /* Architectural LBRs */
 #define CPUID_7_0_EDX_ARCH_LBR          (1U << 19)
+/* AMX_BF16 instruction */
+#define CPUID_7_0_EDX_AMX_BF16          (1U << 22)
 /* AVX512_FP16 instruction */
 #define CPUID_7_0_EDX_AVX512_FP16       (1U << 23)
 /* AMX tile (two-dimensional register) */
 #define CPUID_7_0_EDX_AMX_TILE          (1U << 24)
+/* AMX_INT8 instruction */
+#define CPUID_7_0_EDX_AMX_INT8          (1U << 25)
 /* Speculation Control */
 #define CPUID_7_0_EDX_SPEC_CTRL         (1U << 26)
 /* Single Thread Indirect Branch Predictors */
@@ -900,6 +904,13 @@ uint64_t x86_cpu_get_supported_feature_word(FeatureWord w,
 #define CPUID_7_1_EAX_AVX_VNNI          (1U << 4)
 /* AVX512 BFloat16 Instruction */
 #define CPUID_7_1_EAX_AVX512_BF16       (1U << 5)
+/* Fast Zero REP MOVS */
+#define CPUID_7_1_EAX_FZRM              (1U << 10)
+/* Fast Short REP STOS */
+#define CPUID_7_1_EAX_FSRS              (1U << 11)
+/* Fast Short REP CMPS/SCAS */
+#define CPUID_7_1_EAX_FSRC              (1U << 12)
+
 /* XFD Extend Feature Disabled */
 #define CPUID_D_1_EAX_XFD               (1U << 4)
 
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 5870301991..d18bd2f3e8 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -352,7 +352,7 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
 {
     struct kvm_cpuid2 *cpuid;
     uint32_t ret = 0;
-    uint32_t cpuid_1_edx;
+    uint32_t cpuid_1_edx, unused;
     uint64_t bitmask;
 
     cpuid = get_supported_cpuid(s);
@@ -399,10 +399,20 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
     } else if (function == 6 && reg == R_EAX) {
         ret |= CPUID_6_EAX_ARAT; /* safe to allow because of emulated APIC */
     } else if (function == 7 && index == 0 && reg == R_EBX) {
+        /* Not new instructions, just an optimization.  */
+        uint32_t ebx;
+        host_cpuid(7, 0, &unused, &ebx, &unused, &unused);
+        ret |= ebx & CPUID_7_0_EBX_ERMS;
+
         if (host_tsx_broken()) {
             ret &= ~(CPUID_7_0_EBX_RTM | CPUID_7_0_EBX_HLE);
         }
     } else if (function == 7 && index == 0 && reg == R_EDX) {
+        /* Not new instructions, just an optimization.  */
+        uint32_t edx;
+        host_cpuid(7, 0, &unused, &unused, &unused, &edx);
+        ret |= edx & CPUID_7_0_EDX_FSRM;
+
         /*
          * Linux v4.17-v4.20 incorrectly return ARCH_CAPABILITIES on SVM hosts.
          * We can detect the bug by checking if MSR_IA32_ARCH_CAPABILITIES is
@@ -411,6 +421,11 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
         if (!has_msr_arch_capabs) {
             ret &= ~CPUID_7_0_EDX_ARCH_CAPABILITIES;
         }
+    } else if (function == 7 && index == 1 && reg == R_EAX) {
+        /* Not new instructions, just an optimization.  */
+        uint32_t eax;
+        host_cpuid(7, 1, &eax, &unused, &unused, &unused);
+        ret |= eax & (CPUID_7_1_EAX_FZRM | CPUID_7_1_EAX_FSRS | CPUID_7_1_EAX_FSRC);
     } else if (function == 0xd && index == 0 &&
                (reg == R_EAX || reg == R_EDX)) {
         /*
diff --git a/target/i386/tcg/emit.c.inc b/target/i386/tcg/emit.c.inc
index e61ae9a2e9..0d01e13002 100644
--- a/target/i386/tcg/emit.c.inc
+++ b/target/i386/tcg/emit.c.inc
@@ -1147,20 +1147,20 @@ static void gen_BLSR(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
 static void gen_BZHI(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
 {
     MemOp ot = decode->op[0].ot;
-    TCGv bound;
+    TCGv bound = tcg_constant_tl(ot == MO_64 ? 63 : 31);
+    TCGv zero = tcg_constant_tl(0);
+    TCGv mone = tcg_constant_tl(-1);
 
-    tcg_gen_ext8u_tl(s->T1, cpu_regs[s->vex_v]);
-    bound = tcg_constant_tl(ot == MO_64 ? 63 : 31);
+    tcg_gen_ext8u_tl(s->T1, s->T1);
 
     /*
      * Note that since we're using BMILG (in order to get O
      * cleared) we need to store the inverse into C.
      */
-    tcg_gen_setcond_tl(TCG_COND_LT, cpu_cc_src, s->T1, bound);
-    tcg_gen_movcond_tl(TCG_COND_GT, s->T1, s->T1, bound, bound, s->T1);
+    tcg_gen_setcond_tl(TCG_COND_LEU, cpu_cc_src, s->T1, bound);
 
-    tcg_gen_movi_tl(s->A0, -1);
-    tcg_gen_shl_tl(s->A0, s->A0, s->T1);
+    tcg_gen_shl_tl(s->A0, mone, s->T1);
+    tcg_gen_movcond_tl(TCG_COND_LEU, s->A0, s->T1, bound, s->A0, zero);
     tcg_gen_andc_tl(s->T0, s->T0, s->A0);
 
     gen_op_update1_cc(s);