* Make named CPU models usable for qemu-{i386,x86_64}

* Fix backwards time with -icount auto
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmSdRiQUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroOqcwf9FGAqZ+0V34Y8XeXMu8Es3bFjEKG8
 t3BpVNhTBOYDPvpshnPVx2I29nRT2opc1C4YkjMAv5/1nivj1kDM7hDObOSJQvqy
 5FgTsJYqRtGj+J7uVBrspWZsP8BYeykKmXR6deBOPvCuw5nnLdDQ3dLV2F26lKUu
 lsFyEVbi4dzf8+TVuNIXEg7mVBYytjBQwBmmHgeOofeikjq9WEudr49mwJMCHyzl
 iXCatnctXGKZYSnp+eHIBiFRdSzjqdgrDRa0ysSqABoBI1pmkhyQKSay6cSjfG4n
 gFlqPF/i9RqAWpsQrM1IMGgPK39SrT2dYlHDJV2P/NEQrS6kLh2HoW/ArQ==
 =oj3B
 -----END PGP SIGNATURE-----

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

* Make named CPU models usable for qemu-{i386,x86_64}
* Fix backwards time with -icount auto

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmSdRiQUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroOqcwf9FGAqZ+0V34Y8XeXMu8Es3bFjEKG8
# t3BpVNhTBOYDPvpshnPVx2I29nRT2opc1C4YkjMAv5/1nivj1kDM7hDObOSJQvqy
# 5FgTsJYqRtGj+J7uVBrspWZsP8BYeykKmXR6deBOPvCuw5nnLdDQ3dLV2F26lKUu
# lsFyEVbi4dzf8+TVuNIXEg7mVBYytjBQwBmmHgeOofeikjq9WEudr49mwJMCHyzl
# iXCatnctXGKZYSnp+eHIBiFRdSzjqdgrDRa0ysSqABoBI1pmkhyQKSay6cSjfG4n
# gFlqPF/i9RqAWpsQrM1IMGgPK39SrT2dYlHDJV2P/NEQrS6kLh2HoW/ArQ==
# =oj3B
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 29 Jun 2023 10:51:48 AM CEST
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [undefined]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# 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' of https://gitlab.com/bonzini/qemu:
  target/i386: emulate 64-bit ring 0 for linux-user if LM feature is set
  target/i386: ignore CPL0-specific features in user mode emulation
  target/i386: ignore ARCH_CAPABILITIES features in user mode emulation
  target/i386: Export MSR_ARCH_CAPABILITIES bits to guests
  icount: don't adjust virtual time backwards after warp

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

linux-user/i386/cpu_loop.c

@@ -47,7 +47,7 @@ static void write_dt(void *ptr, unsigned long addr, unsigned long limit,
 }
 
 static uint64_t *idt_table;
-#ifdef TARGET_X86_64
+
 static void set_gate64(void *ptr, unsigned int type, unsigned int dpl,
                        uint64_t addr, unsigned int sel)
 {
@@ -60,8 +60,10 @@ static void set_gate64(void *ptr, unsigned int type, unsigned int dpl,
     p[2] = tswap32(addr >> 32);
     p[3] = 0;
 }
+
+#ifdef TARGET_X86_64
 /* only dpl matters as we do only user space emulation */
-static void set_idt(int n, unsigned int dpl)
+static void set_idt(int n, unsigned int dpl, bool is64)
 {
     set_gate64(idt_table + n * 2, 0, dpl, 0, 0);
 }
@@ -78,9 +80,13 @@ static void set_gate(void *ptr, unsigned int type, unsigned int dpl,
 }
 
 /* only dpl matters as we do only user space emulation */
-static void set_idt(int n, unsigned int dpl)
+static void set_idt(int n, unsigned int dpl, bool is64)
 {
-    set_gate(idt_table + n, 0, dpl, 0, 0);
+    if (is64) {
+        set_gate64(idt_table + n * 2, 0, dpl, 0, 0);
+    } else {
+        set_gate(idt_table + n, 0, dpl, 0, 0);
+    }
 }
 #endif
 
@@ -325,6 +331,9 @@ static void target_cpu_free(void *obj)
 void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
 {
     CPUState *cpu = env_cpu(env);
+    bool is64 = (env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) != 0;
+    int i;
+
     OBJECT(cpu)->free = target_cpu_free;
     env->cr[0] = CR0_PG_MASK | CR0_WP_MASK | CR0_PE_MASK;
     env->hflags |= HF_PE_MASK | HF_CPL_MASK;
@@ -332,15 +341,18 @@ void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
         env->cr[4] |= CR4_OSFXSR_MASK;
         env->hflags |= HF_OSFXSR_MASK;
     }
-#ifndef TARGET_ABI32
+
     /* enable 64 bit mode if possible */
-    if (!(env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM)) {
+    if (is64) {
+        env->cr[4] |= CR4_PAE_MASK;
+        env->efer |= MSR_EFER_LMA | MSR_EFER_LME;
+        env->hflags |= HF_LMA_MASK;
+    }
+#ifndef TARGET_ABI32
+    else {
         fprintf(stderr, "The selected x86 CPU does not support 64 bit mode\n");
         exit(EXIT_FAILURE);
     }
-    env->cr[4] |= CR4_PAE_MASK;
-    env->efer |= MSR_EFER_LMA | MSR_EFER_LME;
-    env->hflags |= HF_LMA_MASK;
 #endif
 
     /* flags setup : we activate the IRQs by default as in user mode */
@@ -379,27 +391,12 @@ void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
                                 PROT_READ|PROT_WRITE,
                                 MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
     idt_table = g2h_untagged(env->idt.base);
-    set_idt(0, 0);
+    for (i = 0; i < 20; i++) {
-    set_idt(1, 0);
+        set_idt(i, 0, is64);
-    set_idt(2, 0);
+    }
-    set_idt(3, 3);
+    set_idt(3, 3, is64);
-    set_idt(4, 3);
+    set_idt(4, 3, is64);
-    set_idt(5, 0);
+    set_idt(0x80, 3, is64);
-    set_idt(6, 0);
-    set_idt(7, 0);
-    set_idt(8, 0);
-    set_idt(9, 0);
-    set_idt(10, 0);
-    set_idt(11, 0);
-    set_idt(12, 0);
-    set_idt(13, 0);
-    set_idt(14, 0);
-    set_idt(15, 0);
-    set_idt(16, 0);
-    set_idt(17, 0);
-    set_idt(18, 0);
-    set_idt(19, 0);
-    set_idt(0x80, 3);
 
     /* linux segment setup */
     {

softmmu/icount.c

@@ -259,11 +259,16 @@ static void icount_warp_rt(void)
         warp_delta = clock - timers_state.vm_clock_warp_start;
         if (icount_enabled() == 2) {
             /*
-             * In adaptive mode, do not let QEMU_CLOCK_VIRTUAL run too
+             * In adaptive mode, do not let QEMU_CLOCK_VIRTUAL run too far
-             * far ahead of real time.
+             * ahead of real time (it might already be ahead so careful not
+             * to go backwards).
              */
             int64_t cur_icount = icount_get_locked();
             int64_t delta = clock - cur_icount;
+
+            if (delta < 0) {
+                delta = 0;
+            }
             warp_delta = MIN(warp_delta, delta);
         }
         qatomic_set_i64(&timers_state.qemu_icount_bias,

target/i386/cpu.c

@@ -623,13 +623,25 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
           CPUID_MTRR, CPUID_MCA, CPUID_CLFLUSH (needed for Win64) */
           /* missing:
           CPUID_VME, CPUID_DTS, CPUID_SS, CPUID_HT, CPUID_TM, CPUID_PBE */
+
+/*
+ * Kernel-only features that can be shown to usermode programs even if
+ * they aren't actually supported by TCG, because qemu-user only runs
+ * in CPL=3; remove them if they are ever implemented for system emulation.
+ */
+#if defined CONFIG_USER_ONLY
+#define CPUID_EXT_KERNEL_FEATURES (CPUID_EXT_PCID | CPUID_EXT_TSC_DEADLINE_TIMER | \
+                                 CPUID_EXT_X2APIC)
+#else
+#define CPUID_EXT_KERNEL_FEATURES 0
+#endif
 #define TCG_EXT_FEATURES (CPUID_EXT_SSE3 | CPUID_EXT_PCLMULQDQ | \
           CPUID_EXT_MONITOR | CPUID_EXT_SSSE3 | CPUID_EXT_CX16 | \
           CPUID_EXT_SSE41 | CPUID_EXT_SSE42 | CPUID_EXT_POPCNT | \
           CPUID_EXT_XSAVE | /* CPUID_EXT_OSXSAVE is dynamic */   \
           CPUID_EXT_MOVBE | CPUID_EXT_AES | CPUID_EXT_HYPERVISOR | \
           CPUID_EXT_RDRAND | CPUID_EXT_AVX | CPUID_EXT_F16C | \
-          CPUID_EXT_FMA)
+          CPUID_EXT_FMA | CPUID_EXT_KERNEL_FEATURES)
           /* missing:
           CPUID_EXT_DTES64, CPUID_EXT_DSCPL, CPUID_EXT_VMX, CPUID_EXT_SMX,
           CPUID_EXT_EST, CPUID_EXT_TM2, CPUID_EXT_CID,
@@ -642,22 +654,66 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
 #define TCG_EXT2_X86_64_FEATURES 0
 #endif
 
+/*
+ * CPUID_*_KERNEL_FEATURES denotes bits and features that are not usable
+ * in usermode or by 32-bit programs.  Those are added to supported
+ * TCG features unconditionally in user-mode emulation mode.  This may
+ * indeed seem strange or incorrect, but it works because code running
+ * under usermode emulation cannot access them.
+ *
+ * Even for long mode, qemu-i386 is not running "a userspace program on a
+ * 32-bit CPU"; it's running "a userspace program with a 32-bit code segment"
+ * and therefore using the 32-bit ABI; the CPU itself might be 64-bit
+ * but again the difference is only visible in kernel mode.
+ */
+#if defined CONFIG_LINUX_USER
+#define CPUID_EXT2_KERNEL_FEATURES (CPUID_EXT2_LM | CPUID_EXT2_FFXSR)
+#elif defined CONFIG_USER_ONLY
+/* FIXME: Long mode not yet supported for i386 bsd-user */
+#define CPUID_EXT2_KERNEL_FEATURES CPUID_EXT2_FFXSR
+#else
+#define CPUID_EXT2_KERNEL_FEATURES 0
+#endif
+
 #define TCG_EXT2_FEATURES ((TCG_FEATURES & CPUID_EXT2_AMD_ALIASES) | \
           CPUID_EXT2_NX | CPUID_EXT2_MMXEXT | CPUID_EXT2_RDTSCP | \
           CPUID_EXT2_3DNOW | CPUID_EXT2_3DNOWEXT | CPUID_EXT2_PDPE1GB | \
-          CPUID_EXT2_SYSCALL | TCG_EXT2_X86_64_FEATURES)
+          CPUID_EXT2_SYSCALL | TCG_EXT2_X86_64_FEATURES | \
+          CPUID_EXT2_KERNEL_FEATURES)
+
+#if defined CONFIG_USER_ONLY
+#define CPUID_EXT3_KERNEL_FEATURES CPUID_EXT3_OSVW
+#else
+#define CPUID_EXT3_KERNEL_FEATURES 0
+#endif
+
 #define TCG_EXT3_FEATURES (CPUID_EXT3_LAHF_LM | CPUID_EXT3_SVM | \
           CPUID_EXT3_CR8LEG | CPUID_EXT3_ABM | CPUID_EXT3_SSE4A | \
-          CPUID_EXT3_3DNOWPREFETCH)
+          CPUID_EXT3_3DNOWPREFETCH | CPUID_EXT3_KERNEL_FEATURES)
+
 #define TCG_EXT4_FEATURES 0
+
+#if defined CONFIG_USER_ONLY
+#define CPUID_SVM_KERNEL_FEATURES (CPUID_SVM_NRIPSAVE | CPUID_SVM_VNMI)
+#else
+#define CPUID_SVM_KERNEL_FEATURES 0
+#endif
 #define TCG_SVM_FEATURES (CPUID_SVM_NPT | CPUID_SVM_VGIF | \
-          CPUID_SVM_SVME_ADDR_CHK)
+          CPUID_SVM_SVME_ADDR_CHK | CPUID_SVM_KERNEL_FEATURES)
+
 #define TCG_KVM_FEATURES 0
+
+#if defined CONFIG_USER_ONLY
+#define CPUID_7_0_EBX_KERNEL_FEATURES CPUID_7_0_EBX_INVPCID
+#else
+#define CPUID_7_0_EBX_KERNEL_FEATURES 0
+#endif
 #define TCG_7_0_EBX_FEATURES (CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_SMAP | \
           CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_ADX | \
           CPUID_7_0_EBX_PCOMMIT | CPUID_7_0_EBX_CLFLUSHOPT |            \
           CPUID_7_0_EBX_CLWB | CPUID_7_0_EBX_MPX | CPUID_7_0_EBX_FSGSBASE | \
-          CPUID_7_0_EBX_ERMS | CPUID_7_0_EBX_AVX2 | CPUID_7_0_EBX_RDSEED)
+          CPUID_7_0_EBX_ERMS | CPUID_7_0_EBX_AVX2 | CPUID_7_0_EBX_RDSEED | \
+          CPUID_7_0_EBX_KERNEL_FEATURES)
           /* missing:
           CPUID_7_0_EBX_HLE
           CPUID_7_0_EBX_INVPCID, CPUID_7_0_EBX_RTM */
@@ -672,7 +728,14 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
           CPUID_7_0_ECX_LA57 | CPUID_7_0_ECX_PKS | CPUID_7_0_ECX_VAES | \
           TCG_7_0_ECX_RDPID)
 
-#define TCG_7_0_EDX_FEATURES CPUID_7_0_EDX_FSRM
+#if defined CONFIG_USER_ONLY
+#define CPUID_7_0_EDX_KERNEL_FEATURES (CPUID_7_0_EDX_SPEC_CTRL | \
+          CPUID_7_0_EDX_ARCH_CAPABILITIES | CPUID_7_0_EDX_SPEC_CTRL_SSBD)
+#else
+#define CPUID_7_0_EDX_KERNEL_FEATURES 0
+#endif
+#define TCG_7_0_EDX_FEATURES (CPUID_7_0_EDX_FSRM | CPUID_7_0_EDX_KERNEL_FEATURES)
+
 #define TCG_7_1_EAX_FEATURES (CPUID_7_1_EAX_FZRM | CPUID_7_1_EAX_FSRS | \
           CPUID_7_1_EAX_FSRC)
 #define TCG_7_1_EDX_FEATURES 0
@@ -686,8 +749,17 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
 #define TCG_SGX_12_0_EBX_FEATURES 0
 #define TCG_SGX_12_1_EAX_FEATURES 0
 
+#if defined CONFIG_USER_ONLY
+#define CPUID_8000_0008_EBX_KERNEL_FEATURES (CPUID_8000_0008_EBX_IBPB | \
+          CPUID_8000_0008_EBX_IBRS | CPUID_8000_0008_EBX_STIBP | \
+          CPUID_8000_0008_EBX_STIBP_ALWAYS_ON | CPUID_8000_0008_EBX_AMD_SSBD | \
+          CPUID_8000_0008_EBX_AMD_PSFD)
+#else
+#define CPUID_8000_0008_EBX_KERNEL_FEATURES 0
+#endif
+
 #define TCG_8000_0008_EBX  (CPUID_8000_0008_EBX_XSAVEERPTR | \
-          CPUID_8000_0008_EBX_WBNOINVD)
+          CPUID_8000_0008_EBX_WBNOINVD | CPUID_8000_0008_EBX_KERNEL_FEATURES)
 
 FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
     [FEAT_1_EDX] = {
@@ -1060,15 +1132,22 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
             "rdctl-no", "ibrs-all", "rsba", "skip-l1dfl-vmentry",
             "ssb-no", "mds-no", "pschange-mc-no", "tsx-ctrl",
             "taa-no", NULL, NULL, NULL,
-            NULL, NULL, NULL, NULL,
+            NULL, "sbdr-ssdp-no", "fbsdp-no", "psdp-no",
             NULL, "fb-clear", NULL, NULL,
             NULL, NULL, NULL, NULL,
-            NULL, NULL, NULL, NULL,
+            "pbrsb-no", NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
         },
         .msr = {
             .index = MSR_IA32_ARCH_CAPABILITIES,
         },
+        /*
+         * FEAT_ARCH_CAPABILITIES only affects a read-only MSR, which
+         * cannot be read from user mode.  Therefore, it has no impact
+         > on any user-mode operation, and warnings about unsupported
+         * features do not matter.
+         */
+        .tcg_features = ~0U,
     },
     [FEAT_CORE_CAPABILITY] = {
         .type = MSR_FEATURE_WORD,
@@ -5463,7 +5542,15 @@ uint64_t x86_cpu_get_supported_feature_word(FeatureWord w,
     }
 #ifndef TARGET_X86_64
     if (w == FEAT_8000_0001_EDX) {
-        r &= ~CPUID_EXT2_LM;
+        /*
+         * 32-bit TCG can emulate 64-bit compatibility mode.  If there is no
+         * way for userspace to get out of its 32-bit jail, we can leave
+         * the LM bit set.
+         */
+        uint32_t unavail = tcg_enabled()
+            ? CPUID_EXT2_LM & ~CPUID_EXT2_KERNEL_FEATURES
+            : CPUID_EXT2_LM;
+        r &= ~unavail;
     }
 #endif
     if (migratable_only) {

target/i386/tcg/translate.c

@@ -173,12 +173,14 @@ typedef struct DisasContext {
 #endif
 #if !defined(TARGET_X86_64)
 #define CODE64(S) false
-#define LMA(S)    false
 #elif defined(CONFIG_USER_ONLY)
 #define CODE64(S) true
-#define LMA(S)    true
 #else
 #define CODE64(S) (((S)->flags & HF_CS64_MASK) != 0)
+#endif
+#if defined(CONFIG_SOFTMMU) && !defined(TARGET_X86_64)
+#define LMA(S)    false
+#else
 #define LMA(S)    (((S)->flags & HF_LMA_MASK) != 0)
 #endif