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>

6 files changed, 50 insertions, 1 deletions

diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c
index 0639f97dd5..b774d80291 100644
--- 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
index 9b9f7d9c68..3937e30477 100644
--- 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
index 1000406211..46f8f9a2b0 100644
--- 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
index 1c7786b52c..2052d721e5 100644
--- 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
index 2c5546560a..81f7e53aed 100644
--- 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
index 95708d890e..ed4c27487e 100644
--- 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;