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>
qemu · Jun 26, 2023 · cd041dd · cd041dd
2 parents 52ed34c + 8edddaa
commit cd041dd
Show file tree

Hide file tree

Showing 22 changed files with 224 additions and 94 deletions.
diff --git a/Makefile b/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 > $@

diff --git a/accel/kvm/kvm-all.c b/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 = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
+    int stats_fd = cpu->kvm_vcpu_stats_fd;
     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);
-    close(stats_fd);
+                kvm_stats_args->names, stats_fd, cpu,
+                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 = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
+    int stats_fd = cpu->kvm_vcpu_stats_fd;
     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);
     }
 }
diff --git a/bsd-user/i386/target_arch_cpu.h b/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;

diff --git a/configure b/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

diff --git a/hw/arm/sbsa-ref.c b/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 = {

diff --git a/hw/arm/virt.c b/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";
 

diff --git a/hw/core/machine.c b/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);
+            }
         }
     }
 

diff --git a/hw/remote/proxy.c b/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);

diff --git a/hw/riscv/spike.c b/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",

diff --git a/hw/riscv/virt.c b/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;

diff --git a/include/hw/boards.h b/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;
 

diff --git a/include/hw/core/cpu.h b/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;

diff --git a/linux-user/i386/cpu_loop.c b/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;

diff --git a/meson.build b/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>'))