* kvm: reuse per-vcpu stats fd to avoid vcpu interruption

* Validate cluster and NUMA node boundary on ARM and RISC-V
 * various small TCG features from newer processors
 * Remove dubious 'event_notifier-posix.c' include
 * fix git-submodule.sh in releases
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmSZS0IUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroN+tgf/axJdG9NXKCyXgc0vzjKVhSR4Y+tC
 EPxkg7Rq7uOMgbph9oTS/2Kzh9LnP6kLt2qnS4igRHGuEBd58yD6fFNDv0LJsK/l
 B/d0WGHMKV0KMYOX24rkyfohVu37GhVRsiVSIlIiQVTC9JtYer7WxdnyoDaPKvY8
 dpbKgDrd59vAlsHrpj7ZubVQPcL3lXrLryimpDohMH6Ba+4wZq+7dKPpal97QOP2
 3i7isUBTQiMOcVjW6GEiNcDLSJqj5DSgylhdFnaBsq/ThpC2PxWoXcCbV28QELzf
 5+J+RXQavmeWKZMR0q98iBzWbrsVtaSxAkHHiwbUMMqQvkfY6Dpo5dMHWw==
 =WHE2
 -----END PGP SIGNATURE-----

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

* kvm: reuse per-vcpu stats fd to avoid vcpu interruption
* Validate cluster and NUMA node boundary on ARM and RISC-V
* various small TCG features from newer processors
* Remove dubious 'event_notifier-posix.c' include
* fix git-submodule.sh in releases

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmSZS0IUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroN+tgf/axJdG9NXKCyXgc0vzjKVhSR4Y+tC
# EPxkg7Rq7uOMgbph9oTS/2Kzh9LnP6kLt2qnS4igRHGuEBd58yD6fFNDv0LJsK/l
# B/d0WGHMKV0KMYOX24rkyfohVu37GhVRsiVSIlIiQVTC9JtYer7WxdnyoDaPKvY8
# dpbKgDrd59vAlsHrpj7ZubVQPcL3lXrLryimpDohMH6Ba+4wZq+7dKPpal97QOP2
# 3i7isUBTQiMOcVjW6GEiNcDLSJqj5DSgylhdFnaBsq/ThpC2PxWoXcCbV28QELzf
# 5+J+RXQavmeWKZMR0q98iBzWbrsVtaSxAkHHiwbUMMqQvkfY6Dpo5dMHWw==
# =WHE2
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 26 Jun 2023 10:24:34 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:
  git-submodule.sh: allow running in validate mode without previous update
  target/i386: implement SYSCALL/SYSRET in 32-bit emulators
  target/i386: implement RDPID in TCG
  target/i386: sysret and sysexit are privileged
  target/i386: AMD only supports SYSENTER/SYSEXIT in 32-bit mode
  target/i386: Intel only supports SYSCALL/SYSRET in long mode
  target/i386: TCG supports WBNOINVD
  target/i386: TCG supports XSAVEERPTR
  target/i386: do not accept RDSEED if CPUID bit absent
  target/i386: TCG supports RDSEED
  target/i386: TCG supports 3DNow! prefetch(w)
  target/i386: fix INVD vmexit
  kvm: reuse per-vcpu stats fd to avoid vcpu interruption
  hw/riscv: Validate cluster and NUMA node boundary
  hw/arm: Validate cluster and NUMA node boundary
  numa: Validate cluster and NUMA node boundary if required
  hw/remote/proxy: Remove dubious 'event_notifier-posix.c' include
  build: further refine build.ninja rules

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

Makefile

@@ -83,16 +83,17 @@ config-host.mak: $(SRC_PATH)/configure $(SRC_PATH)/scripts/meson-buildoptions.sh
 	@if test -f meson-private/coredata.dat; then \
 	  ./config.status --skip-meson; \
 	else \
-	  ./config.status && touch build.ninja.stamp; \
+	  ./config.status; \
 	fi
 
 # 2. meson.stamp exists if meson has run at least once (so ninja reconfigure
 # works), but otherwise never needs to be updated
+
 meson-private/coredata.dat: meson.stamp
 meson.stamp: config-host.mak
 	@touch meson.stamp
 
-# 3. ensure generated build files are up-to-date
+# 3. ensure meson-generated build files are up-to-date
 
 ifneq ($(NINJA),)
 Makefile.ninja: build.ninja
@@ -106,11 +107,19 @@ Makefile.ninja: build.ninja
 endif
 
 ifneq ($(MESON),)
-# A separate rule is needed for Makefile dependencies to avoid -n
+# The path to meson always points to pyvenv/bin/meson, but the absolute
+# paths could change.  In that case, force a regeneration of build.ninja.
+# Note that this invocation of $(NINJA), just like when Make rebuilds
+# Makefiles, does not include -n.
 build.ninja: build.ninja.stamp
 $(build-files):
 build.ninja.stamp: meson.stamp $(build-files)
-	$(MESON) setup --reconfigure $(SRC_PATH) && touch $@
+	@if test "$$(cat build.ninja.stamp)" = "$(MESON)" && test -n "$(NINJA)"; then \
+	  $(NINJA) build.ninja; \
+	else \
+	  echo "$(MESON) setup --reconfigure $(SRC_PATH)"; \
+	  $(MESON) setup --reconfigure $(SRC_PATH); \
+	fi && echo "$(MESON)" > $@
 
 Makefile.mtest: build.ninja scripts/mtest2make.py
 	$(MESON) introspect --targets --tests --benchmarks | $(PYTHON) scripts/mtest2make.py > $@

accel/kvm/kvm-all.c

@@ -450,6 +450,8 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp)
                          "kvm_init_vcpu: kvm_arch_init_vcpu failed (%lu)",
                          kvm_arch_vcpu_id(cpu));
     }
+    cpu->kvm_vcpu_stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
+
 err:
     return ret;
 }
@@ -4007,7 +4009,7 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd
 
     /* Read stats header */
     kvm_stats_header = &descriptors->kvm_stats_header;
-    ret = read(stats_fd, kvm_stats_header, sizeof(*kvm_stats_header));
+    ret = pread(stats_fd, kvm_stats_header, sizeof(*kvm_stats_header), 0);
     if (ret != sizeof(*kvm_stats_header)) {
         error_setg(errp, "KVM stats: failed to read stats header: "
                    "expected %zu actual %zu",
@@ -4038,7 +4040,8 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd
 }
 
 static void query_stats(StatsResultList **result, StatsTarget target,
-                        strList *names, int stats_fd, Error **errp)
+                        strList *names, int stats_fd, CPUState *cpu,
+                        Error **errp)
 {
     struct kvm_stats_desc *kvm_stats_desc;
     struct kvm_stats_header *kvm_stats_header;
@@ -4096,7 +4099,7 @@ static void query_stats(StatsResultList **result, StatsTarget target,
         break;
     case STATS_TARGET_VCPU:
         add_stats_entry(result, STATS_PROVIDER_KVM,
-                        current_cpu->parent_obj.canonical_path,
+                        cpu->parent_obj.canonical_path,
                         stats_list);
         break;
     default:
@@ -4133,10 +4136,9 @@ static void query_stats_schema(StatsSchemaList **result, StatsTarget target,
     add_stats_schema(result, STATS_PROVIDER_KVM, target, stats_list);
 }
 
-static void query_stats_vcpu(CPUState *cpu, run_on_cpu_data data)
+static void query_stats_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
 {
-    StatsArgs *kvm_stats_args = (StatsArgs *) data.host_ptr;
+    int stats_fd = cpu->kvm_vcpu_stats_fd;
-    int stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
     Error *local_err = NULL;
 
     if (stats_fd == -1) {
@@ -4145,14 +4147,13 @@ static void query_stats_vcpu(CPUState *cpu, run_on_cpu_data data)
         return;
     }
     query_stats(kvm_stats_args->result.stats, STATS_TARGET_VCPU,
-                kvm_stats_args->names, stats_fd, kvm_stats_args->errp);
+                kvm_stats_args->names, stats_fd, cpu,
-    close(stats_fd);
+                kvm_stats_args->errp);
 }
 
-static void query_stats_schema_vcpu(CPUState *cpu, run_on_cpu_data data)
+static void query_stats_schema_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
 {
-    StatsArgs *kvm_stats_args = (StatsArgs *) data.host_ptr;
+    int stats_fd = cpu->kvm_vcpu_stats_fd;
-    int stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
     Error *local_err = NULL;
 
     if (stats_fd == -1) {
@@ -4162,7 +4163,6 @@ static void query_stats_schema_vcpu(CPUState *cpu, run_on_cpu_data data)
     }
     query_stats_schema(kvm_stats_args->result.schema, STATS_TARGET_VCPU, stats_fd,
                        kvm_stats_args->errp);
-    close(stats_fd);
 }
 
 static void query_stats_cb(StatsResultList **result, StatsTarget target,
@@ -4180,7 +4180,7 @@ static void query_stats_cb(StatsResultList **result, StatsTarget target,
             error_setg_errno(errp, errno, "KVM stats: ioctl failed");
             return;
         }
-        query_stats(result, target, names, stats_fd, errp);
+        query_stats(result, target, names, stats_fd, NULL, errp);
         close(stats_fd);
         break;
     }
@@ -4194,7 +4194,7 @@ static void query_stats_cb(StatsResultList **result, StatsTarget target,
             if (!apply_str_list_filter(cpu->parent_obj.canonical_path, targets)) {
                 continue;
             }
-            run_on_cpu(cpu, query_stats_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
+            query_stats_vcpu(cpu, &stats_args);
         }
         break;
     }
@@ -4220,6 +4220,6 @@ void query_stats_schemas_cb(StatsSchemaList **result, Error **errp)
     if (first_cpu) {
         stats_args.result.schema = result;
         stats_args.errp = errp;
-        run_on_cpu(first_cpu, query_stats_schema_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
+        query_stats_schema_vcpu(first_cpu, &stats_args);
     }
 }

bsd-user/i386/target_arch_cpu.h

@@ -164,6 +164,10 @@ static inline void target_cpu_loop(CPUX86State *env)
             }
             break;
 
+        case EXCP_SYSCALL:
+            /* doesn't do anything */
+            break;
+
         case EXCP_INTERRUPT:
             /* just indicate that signals should be handled asap */
             break;

configure

@@ -758,7 +758,7 @@ done
 
 if ! test -e "$source_path/.git"
 then
-    git_submodules_action="ignore"
+    git_submodules_action="validate"
 fi
 
 # test for any invalid configuration combinations
@@ -1895,6 +1895,7 @@ if test "$skip_meson" = no; then
   if test "$?" -ne 0 ; then
       error_exit "meson setup failed"
   fi
+  echo "$meson" > build.ninja.stamp
 else
   if test -f meson-private/cmd_line.txt; then
     # Adjust old command line options that were removed

hw/arm/sbsa-ref.c

@@ -910,6 +910,8 @@ static void sbsa_ref_class_init(ObjectClass *oc, void *data)
     mc->possible_cpu_arch_ids = sbsa_ref_possible_cpu_arch_ids;
     mc->cpu_index_to_instance_props = sbsa_ref_cpu_index_to_props;
     mc->get_default_cpu_node_id = sbsa_ref_get_default_cpu_node_id;
+    /* platform instead of architectural choice */
+    mc->cpu_cluster_has_numa_boundary = true;
 }
 
 static const TypeInfo sbsa_ref_info = {

hw/arm/virt.c

@@ -3033,6 +3033,8 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     mc->smp_props.clusters_supported = true;
     mc->auto_enable_numa_with_memhp = true;
     mc->auto_enable_numa_with_memdev = true;
+    /* platform instead of architectural choice */
+    mc->cpu_cluster_has_numa_boundary = true;
     mc->default_ram_id = "mach-virt.ram";
     mc->default_nic = "virtio-net-pci";
 

hw/core/machine.c

@@ -1262,6 +1262,45 @@ static void machine_numa_finish_cpu_init(MachineState *machine)
     g_string_free(s, true);
 }
 
+static void validate_cpu_cluster_to_numa_boundary(MachineState *ms)
+{
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    NumaState *state = ms->numa_state;
+    const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms);
+    const CPUArchId *cpus = possible_cpus->cpus;
+    int i, j;
+
+    if (state->num_nodes <= 1 || possible_cpus->len <= 1) {
+        return;
+    }
+
+    /*
+     * The Linux scheduling domain can't be parsed when the multiple CPUs
+     * in one cluster have been associated with different NUMA nodes. However,
+     * it's fine to associate one NUMA node with CPUs in different clusters.
+     */
+    for (i = 0; i < possible_cpus->len; i++) {
+        for (j = i + 1; j < possible_cpus->len; j++) {
+            if (cpus[i].props.has_socket_id &&
+                cpus[i].props.has_cluster_id &&
+                cpus[i].props.has_node_id &&
+                cpus[j].props.has_socket_id &&
+                cpus[j].props.has_cluster_id &&
+                cpus[j].props.has_node_id &&
+                cpus[i].props.socket_id == cpus[j].props.socket_id &&
+                cpus[i].props.cluster_id == cpus[j].props.cluster_id &&
+                cpus[i].props.node_id != cpus[j].props.node_id) {
+                warn_report("CPU-%d and CPU-%d in socket-%" PRId64 "-cluster-%" PRId64
+                             " have been associated with node-%" PRId64 " and node-%" PRId64
+                             " respectively. It can cause OSes like Linux to"
+                             " misbehave", i, j, cpus[i].props.socket_id,
+                             cpus[i].props.cluster_id, cpus[i].props.node_id,
+                             cpus[j].props.node_id);
+            }
+        }
+    }
+}
+
 MemoryRegion *machine_consume_memdev(MachineState *machine,
                                      HostMemoryBackend *backend)
 {
@@ -1355,6 +1394,9 @@ void machine_run_board_init(MachineState *machine, const char *mem_path, Error *
         numa_complete_configuration(machine);
         if (machine->numa_state->num_nodes) {
             machine_numa_finish_cpu_init(machine);
+            if (machine_class->cpu_cluster_has_numa_boundary) {
+                validate_cpu_cluster_to_numa_boundary(machine);
+            }
         }
     }
 

hw/remote/proxy.c

@@ -22,7 +22,6 @@
 #include "qom/object.h"
 #include "qemu/event_notifier.h"
 #include "sysemu/kvm.h"
-#include "util/event_notifier-posix.c"
 
 static void probe_pci_info(PCIDevice *dev, Error **errp);
 static void proxy_device_reset(DeviceState *dev);

hw/riscv/spike.c

@@ -354,6 +354,8 @@ static void spike_machine_class_init(ObjectClass *oc, void *data)
     mc->cpu_index_to_instance_props = riscv_numa_cpu_index_to_props;
     mc->get_default_cpu_node_id = riscv_numa_get_default_cpu_node_id;
     mc->numa_mem_supported = true;
+    /* platform instead of architectural choice */
+    mc->cpu_cluster_has_numa_boundary = true;
     mc->default_ram_id = "riscv.spike.ram";
     object_class_property_add_str(oc, "signature", NULL, spike_set_signature);
     object_class_property_set_description(oc, "signature",

hw/riscv/virt.c

@@ -1669,6 +1669,8 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     mc->cpu_index_to_instance_props = riscv_numa_cpu_index_to_props;
     mc->get_default_cpu_node_id = riscv_numa_get_default_cpu_node_id;
     mc->numa_mem_supported = true;
+    /* platform instead of architectural choice */
+    mc->cpu_cluster_has_numa_boundary = true;
     mc->default_ram_id = "riscv_virt_board.ram";
     assert(!mc->get_hotplug_handler);
     mc->get_hotplug_handler = virt_machine_get_hotplug_handler;

include/hw/boards.h

@@ -274,6 +274,7 @@ struct MachineClass {
     bool nvdimm_supported;
     bool numa_mem_supported;
     bool auto_enable_numa;
+    bool cpu_cluster_has_numa_boundary;
     SMPCompatProps smp_props;
     const char *default_ram_id;
 

include/hw/core/cpu.h

@@ -402,6 +402,7 @@ struct CPUState {
     struct kvm_dirty_gfn *kvm_dirty_gfns;
     uint32_t kvm_fetch_index;
     uint64_t dirty_pages;
+    int kvm_vcpu_stats_fd;
 
     /* Use by accel-block: CPU is executing an ioctl() */
     QemuLockCnt in_ioctl_lock;

linux-user/i386/cpu_loop.c

@@ -211,6 +211,9 @@ void cpu_loop(CPUX86State *env)
 
         switch(trapnr) {
         case 0x80:
+#ifndef TARGET_X86_64
+        case EXCP_SYSCALL:
+#endif
             /* linux syscall from int $0x80 */
             ret = do_syscall(env,
                              env->regs[R_EAX],
@@ -227,9 +230,9 @@ void cpu_loop(CPUX86State *env)
                 env->regs[R_EAX] = ret;
             }
             break;
-#ifndef TARGET_ABI32
+#ifdef TARGET_X86_64
         case EXCP_SYSCALL:
-            /* linux syscall from syscall instruction */
+            /* linux syscall from syscall instruction.  */
             ret = do_syscall(env,
                              env->regs[R_EAX],
                              env->regs[R_EDI],
@@ -245,8 +248,6 @@ void cpu_loop(CPUX86State *env)
                 env->regs[R_EAX] = ret;
             }
             break;
-#endif
-#ifdef TARGET_X86_64
         case EXCP_VSYSCALL:
             emulate_vsyscall(env);
             break;

meson.build

@@ -2232,6 +2232,8 @@ config_host_data.set('CONFIG_CLOCK_ADJTIME', cc.has_function('clock_adjtime'))
 config_host_data.set('CONFIG_DUP3', cc.has_function('dup3'))
 config_host_data.set('CONFIG_FALLOCATE', cc.has_function('fallocate'))
 config_host_data.set('CONFIG_POSIX_FALLOCATE', cc.has_function('posix_fallocate'))
+config_host_data.set('CONFIG_GETCPU', cc.has_function('getcpu', prefix: gnu_source_prefix))
+config_host_data.set('CONFIG_SCHED_GETCPU', cc.has_function('sched_getcpu', prefix: '#include <sched.h>'))
 # Note that we need to specify prefix: here to avoid incorrectly
 # thinking that Windows has posix_memalign()
 config_host_data.set('CONFIG_POSIX_MEMALIGN', cc.has_function('posix_memalign', prefix: '#include <stdlib.h>'))

scripts/git-submodule.sh

@@ -9,13 +9,22 @@ command=$1
 shift
 maybe_modules="$@"
 
-# if not running in a git checkout, do nothing
+test -z "$maybe_modules" && exit 0
-test "$command" = "ignore" && exit 0
-
 test -z "$GIT" && GIT=$(command -v git)
 
 cd "$(dirname "$0")/.."
 
+no_git_error=
+if ! test -e ".git"; then
+    no_git_error='no git checkout exists'
+elif test -z "$GIT"; then
+    no_git_error='git binary not found'
+fi
+
+is_git() {
+    test -z "$no_git_error"
+}
+
 update_error() {
     echo "$0: $*"
     echo
@@ -34,7 +43,7 @@ update_error() {
 }
 
 validate_error() {
-    if test "$1" = "validate"; then
+    if is_git && test "$1" = "validate"; then
         echo "GIT submodules checkout is out of date, and submodules"
         echo "configured for validate only. Please run"
         echo "  scripts/git-submodule.sh update $maybe_modules"
@@ -51,18 +60,8 @@ check_updated() {
     test "$CURSTATUS" = "$OLDSTATUS"
 }
 
-if test -n "$maybe_modules" && ! test -e ".git"
+if is_git; then
-then
+    test -e $substat || touch $substat
-    echo "$0: unexpectedly called with submodules but no git checkout exists"
-    exit 1
-fi
-
-if test -n "$maybe_modules" && test -z "$GIT"
-then
-    echo "$0: unexpectedly called with submodules but git binary not found"
-    exit 1
-fi
-
     modules=""
     for m in $maybe_modules
     do
@@ -70,23 +69,33 @@ do
         if test $? = 0
         then
             modules="$modules $m"
+            grep $m $substat > /dev/null 2>&1 || $GIT submodule status $module >> $substat
         else
             echo "warn: ignoring non-existent submodule $m"
         fi
     done
+else
+    modules=$maybe_modules
+fi
 
 case "$command" in
 status|validate)
-    test -f "$substat" || validate_error "$command"
-    test -z "$maybe_modules" && exit 0
     for module in $modules; do
+        if is_git; then
             check_updated $module || validate_error "$command"
+        elif ! (set xyz "$module"/* && test -e "$2"); then
+            # The directory does not exist or it contains no files
+            echo "$0: sources not available for $module and $no_git_error"
+            validate_error "$command"
+        fi
     done
-    exit 0
     ;;
+
 update)
-    test -e $substat || touch $substat
+    is_git || {
-    test -z "$maybe_modules" && exit 0
+        echo "$0: unexpectedly called with submodules but $no_git_error"
+        exit 1
+    }
 
     $GIT submodule update --init $modules 1>/dev/null
     test $? -ne 0 && update_error "failed to update modules"

target/i386/cpu.c

@@ -637,7 +637,7 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
           CPUID_EXT_X2APIC, CPUID_EXT_TSC_DEADLINE_TIMER */
 
 #ifdef TARGET_X86_64
-#define TCG_EXT2_X86_64_FEATURES (CPUID_EXT2_SYSCALL | CPUID_EXT2_LM)
+#define TCG_EXT2_X86_64_FEATURES CPUID_EXT2_LM
 #else
 #define TCG_EXT2_X86_64_FEATURES 0
 #endif
@@ -645,9 +645,10 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
 #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 | \
-          TCG_EXT2_X86_64_FEATURES)
+          CPUID_EXT2_SYSCALL | TCG_EXT2_X86_64_FEATURES)
 #define TCG_EXT3_FEATURES (CPUID_EXT3_LAHF_LM | CPUID_EXT3_SVM | \
-          CPUID_EXT3_CR8LEG | CPUID_EXT3_ABM | CPUID_EXT3_SSE4A)
+          CPUID_EXT3_CR8LEG | CPUID_EXT3_ABM | CPUID_EXT3_SSE4A | \
+          CPUID_EXT3_3DNOWPREFETCH)
 #define TCG_EXT4_FEATURES 0
 #define TCG_SVM_FEATURES (CPUID_SVM_NPT | CPUID_SVM_VGIF | \
           CPUID_SVM_SVME_ADDR_CHK)
@@ -656,14 +657,21 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
           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_ERMS | CPUID_7_0_EBX_AVX2 | CPUID_7_0_EBX_RDSEED)
           /* missing:
           CPUID_7_0_EBX_HLE
-          CPUID_7_0_EBX_INVPCID, CPUID_7_0_EBX_RTM,
+          CPUID_7_0_EBX_INVPCID, CPUID_7_0_EBX_RTM */
-          CPUID_7_0_EBX_RDSEED */
+
+#if defined CONFIG_SOFTMMU || defined CONFIG_LINUX
+#define TCG_7_0_ECX_RDPID CPUID_7_0_ECX_RDPID
+#else
+#define TCG_7_0_ECX_RDPID 0
+#endif
 #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)
+          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
 #define TCG_7_1_EAX_FEATURES (CPUID_7_1_EAX_FZRM | CPUID_7_1_EAX_FSRS | \
           CPUID_7_1_EAX_FSRC)
@@ -678,6 +686,9 @@ 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
 
+#define TCG_8000_0008_EBX  (CPUID_8000_0008_EBX_XSAVEERPTR | \
+          CPUID_8000_0008_EBX_WBNOINVD)
+
 FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
     [FEAT_1_EDX] = {
         .type = CPUID_FEATURE_WORD,
@@ -939,7 +950,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
             "amd-psfd", NULL, NULL, NULL,
         },
         .cpuid = { .eax = 0x80000008, .reg = R_EBX, },
-        .tcg_features = 0,
+        .tcg_features = TCG_8000_0008_EBX,
         .unmigratable_flags = 0,
     },
     [FEAT_8000_0021_EAX] = {
@@ -6235,6 +6246,10 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
                 *ecx |= 1 << 1;    /* CmpLegacy bit */
             }
         }
+        if (tcg_enabled() && env->cpuid_vendor1 == CPUID_VENDOR_INTEL_1 &&
+            !(env->hflags & HF_LMA_MASK)) {
+            *edx &= ~CPUID_EXT2_SYSCALL;
+        }
         break;
     case 0x80000002:
     case 0x80000003:

target/i386/helper.h

@@ -51,10 +51,8 @@ DEF_HELPER_FLAGS_2(get_dr, TCG_CALL_NO_WG, tl, env, int)
 
 DEF_HELPER_1(sysenter, void, env)
 DEF_HELPER_2(sysexit, void, env, int)
-#ifdef TARGET_X86_64
 DEF_HELPER_2(syscall, void, env, int)
 DEF_HELPER_2(sysret, void, env, int)
-#endif
 DEF_HELPER_FLAGS_2(pause, TCG_CALL_NO_WG, noreturn, env, int)
 DEF_HELPER_FLAGS_3(raise_interrupt, TCG_CALL_NO_WG, noreturn, env, int, int)
 DEF_HELPER_FLAGS_2(raise_exception, TCG_CALL_NO_WG, noreturn, env, int)
@@ -69,8 +67,8 @@ DEF_HELPER_2(into, void, env, int)
 DEF_HELPER_FLAGS_1(single_step, TCG_CALL_NO_WG, noreturn, env)
 DEF_HELPER_1(rechecking_single_step, void, env)
 DEF_HELPER_1(cpuid, void, env)
+DEF_HELPER_FLAGS_1(rdpid, TCG_CALL_NO_WG, tl, env)
 DEF_HELPER_1(rdtsc, void, env)
-DEF_HELPER_1(rdtscp, void, env)
 DEF_HELPER_FLAGS_1(rdpmc, TCG_CALL_NO_WG, noreturn, env)
 
 #ifndef CONFIG_USER_ONLY

target/i386/tcg/misc_helper.c

@@ -75,12 +75,6 @@ void helper_rdtsc(CPUX86State *env)
     env->regs[R_EDX] = (uint32_t)(val >> 32);
 }
 
-void helper_rdtscp(CPUX86State *env)
-{
-    helper_rdtsc(env);
-    env->regs[R_ECX] = (uint32_t)(env->tsc_aux);
-}
-
 G_NORETURN void helper_rdpmc(CPUX86State *env)
 {
     if (((env->cr[4] & CR4_PCE_MASK) == 0 ) &&
@@ -137,3 +131,18 @@ void helper_wrpkru(CPUX86State *env, uint32_t ecx, uint64_t val)
     env->pkru = val;
     tlb_flush(cs);
 }
+
+target_ulong HELPER(rdpid)(CPUX86State *env)
+{
+#if defined CONFIG_SOFTMMU
+    return env->tsc_aux;
+#elif defined CONFIG_LINUX && defined CONFIG_GETCPU
+    unsigned cpu, node;
+    getcpu(&cpu, &node);
+    return (node << 12) | (cpu & 0xfff);
+#elif defined CONFIG_SCHED_GETCPU
+    return sched_getcpu();
+#else
+    return 0;
+#endif
+}

target/i386/tcg/seg_helper.c

@@ -977,6 +977,7 @@ static void do_interrupt64(CPUX86State *env, int intno, int is_int,
                    e2);
     env->eip = offset;
 }
+#endif /* TARGET_X86_64 */
 
 void helper_sysret(CPUX86State *env, int dflag)
 {
@@ -990,6 +991,7 @@ void helper_sysret(CPUX86State *env, int dflag)
         raise_exception_err_ra(env, EXCP0D_GPF, 0, GETPC());
     }
     selector = (env->star >> 48) & 0xffff;
+#ifdef TARGET_X86_64
     if (env->hflags & HF_LMA_MASK) {
         cpu_load_eflags(env, (uint32_t)(env->regs[11]), TF_MASK | AC_MASK
                         | ID_MASK | IF_MASK | IOPL_MASK | VM_MASK | RF_MASK |
@@ -1015,7 +1017,9 @@ void helper_sysret(CPUX86State *env, int dflag)
                                DESC_G_MASK | DESC_B_MASK | DESC_P_MASK |
                                DESC_S_MASK | (3 << DESC_DPL_SHIFT) |
                                DESC_W_MASK | DESC_A_MASK);
-    } else {
+    } else
+#endif
+    {
         env->eflags |= IF_MASK;
         cpu_x86_load_seg_cache(env, R_CS, selector | 3,
                                0, 0xffffffff,
@@ -1030,7 +1034,6 @@ void helper_sysret(CPUX86State *env, int dflag)
                                DESC_W_MASK | DESC_A_MASK);
     }
 }
-#endif /* TARGET_X86_64 */
 
 /* real mode interrupt */
 static void do_interrupt_real(CPUX86State *env, int intno, int is_int,

target/i386/tcg/sysemu/seg_helper.c

@@ -26,7 +26,6 @@
 #include "tcg/helper-tcg.h"
 #include "../seg_helper.h"
 
-#ifdef TARGET_X86_64
 void helper_syscall(CPUX86State *env, int next_eip_addend)
 {
     int selector;
@@ -35,6 +34,7 @@ void helper_syscall(CPUX86State *env, int next_eip_addend)
         raise_exception_err_ra(env, EXCP06_ILLOP, 0, GETPC());
     }
     selector = (env->star >> 32) & 0xffff;
+#ifdef TARGET_X86_64
     if (env->hflags & HF_LMA_MASK) {
         int code64;
 
@@ -61,7 +61,9 @@ void helper_syscall(CPUX86State *env, int next_eip_addend)
         } else {
             env->eip = env->cstar;
         }
-    } else {
+    } else
+#endif
+    {
         env->regs[R_ECX] = (uint32_t)(env->eip + next_eip_addend);
 
         env->eflags &= ~(IF_MASK | RF_MASK | VM_MASK);
@@ -78,7 +80,6 @@ void helper_syscall(CPUX86State *env, int next_eip_addend)
         env->eip = (uint32_t)env->star;
     }
 }
-#endif /* TARGET_X86_64 */
 
 void handle_even_inj(CPUX86State *env, int intno, int is_int,
                      int error_code, int is_hw, int rm)

target/i386/tcg/translate.c

@@ -3924,13 +3924,33 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
             gen_cmpxchg8b(s, env, modrm);
             break;
 
-        case 7: /* RDSEED */
+        case 7: /* RDSEED, RDPID with f3 prefix */
+            if (mod != 3 ||
+                (s->prefix & (PREFIX_LOCK | PREFIX_REPNZ))) {
+                goto illegal_op;
+            }
+            if (s->prefix & PREFIX_REPZ) {
+                if (!(s->cpuid_ext_features & CPUID_7_0_ECX_RDPID)) {
+                    goto illegal_op;
+                }
+                gen_helper_rdpid(s->T0, cpu_env);
+                rm = (modrm & 7) | REX_B(s);
+                gen_op_mov_reg_v(s, dflag, rm, s->T0);
+                break;
+            } else {
+                if (!(s->cpuid_7_0_ebx_features & CPUID_7_0_EBX_RDSEED)) {
+                    goto illegal_op;
+                }
+                goto do_rdrand;
+            }
+
         case 6: /* RDRAND */
             if (mod != 3 ||
                 (s->prefix & (PREFIX_LOCK | PREFIX_REPZ | PREFIX_REPNZ)) ||
                 !(s->cpuid_ext_features & CPUID_EXT_RDRAND)) {
                 goto illegal_op;
             }
+        do_rdrand:
             translator_io_start(&s->base);
             gen_helper_rdrand(s->T0, cpu_env);
             rm = (modrm & 7) | REX_B(s);
@@ -5661,9 +5681,10 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
         s->base.is_jmp = DISAS_NORETURN;
         break;
     case 0x134: /* sysenter */
-        /* For Intel SYSENTER is valid on 64-bit */
+        /* For AMD SYSENTER is not valid in long mode */
-        if (CODE64(s) && env->cpuid_vendor1 != CPUID_VENDOR_INTEL_1)
+        if (LMA(s) && env->cpuid_vendor1 != CPUID_VENDOR_INTEL_1) {
             goto illegal_op;
+        }
         if (!PE(s)) {
             gen_exception_gpf(s);
         } else {
@@ -5672,19 +5693,22 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
         }
         break;
     case 0x135: /* sysexit */
-        /* For Intel SYSEXIT is valid on 64-bit */
+        /* For AMD SYSEXIT is not valid in long mode */
-        if (CODE64(s) && env->cpuid_vendor1 != CPUID_VENDOR_INTEL_1)
+        if (LMA(s) && env->cpuid_vendor1 != CPUID_VENDOR_INTEL_1) {
             goto illegal_op;
-        if (!PE(s)) {
+        }
+        if (!PE(s) || CPL(s) != 0) {
             gen_exception_gpf(s);
         } else {
             gen_helper_sysexit(cpu_env, tcg_constant_i32(dflag - 1));
             s->base.is_jmp = DISAS_EOB_ONLY;
         }
         break;
-#ifdef TARGET_X86_64
     case 0x105: /* syscall */
-        /* XXX: is it usable in real mode ? */
+        /* For Intel SYSCALL is only valid in long mode */
+        if (!LMA(s) && env->cpuid_vendor1 == CPUID_VENDOR_INTEL_1) {
+            goto illegal_op;
+        }
         gen_update_cc_op(s);
         gen_update_eip_cur(s);
         gen_helper_syscall(cpu_env, cur_insn_len_i32(s));
@@ -5694,7 +5718,11 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
         gen_eob_worker(s, false, true);
         break;
     case 0x107: /* sysret */
-        if (!PE(s)) {
+        /* For Intel SYSRET is only valid in long mode */
+        if (!LMA(s) && env->cpuid_vendor1 == CPUID_VENDOR_INTEL_1) {
+            goto illegal_op;
+        }
+        if (!PE(s) || CPL(s) != 0) {
             gen_exception_gpf(s);
         } else {
             gen_helper_sysret(cpu_env, tcg_constant_i32(dflag - 1));
@@ -5709,7 +5737,6 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
             gen_eob_worker(s, false, true);
         }
         break;
-#endif
     case 0x1a2: /* cpuid */
         gen_update_cc_op(s);
         gen_update_eip_cur(s);
@@ -6108,7 +6135,9 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
             gen_update_cc_op(s);
             gen_update_eip_cur(s);
             translator_io_start(&s->base);
-            gen_helper_rdtscp(cpu_env);
+            gen_helper_rdtsc(cpu_env);
+            gen_helper_rdpid(s->T0, cpu_env);
+            gen_op_mov_reg_v(s, dflag, R_ECX, s->T0);
             break;
 
         default:
@@ -6117,9 +6146,9 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
         break;
 
     case 0x108: /* invd */
-    case 0x109: /* wbinvd */
+    case 0x109: /* wbinvd; wbnoinvd with REPZ prefix */
         if (check_cpl0(s)) {
-            gen_svm_check_intercept(s, (b & 2) ? SVM_EXIT_INVD : SVM_EXIT_WBINVD);
+            gen_svm_check_intercept(s, (b & 1) ? SVM_EXIT_WBINVD : SVM_EXIT_INVD);
             /* nothing to do */
         }
         break;

target/i386/tcg/user/seg_helper.c

@@ -26,7 +26,6 @@
 #include "tcg/helper-tcg.h"
 #include "tcg/seg_helper.h"
 
-#ifdef TARGET_X86_64
 void helper_syscall(CPUX86State *env, int next_eip_addend)
 {
     CPUState *cs = env_cpu(env);
@@ -36,7 +35,6 @@ void helper_syscall(CPUX86State *env, int next_eip_addend)
     env->exception_next_eip = env->eip + next_eip_addend;
     cpu_loop_exit(cs);
 }
-#endif /* TARGET_X86_64 */
 
 /*
  * fake user mode interrupt. is_int is TRUE if coming from the int