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

* target/i386: implement SHA instructions
* target/i386: check CPUID_PAE to determine 36 bit processor address space
* target/i386: improve validation of AVX instructions
* require Linux 4.4 for KVM

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmU5Vi4UHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroNVbwf9HCx+C0MITWjQ+rEkmtiy/Cn+ZsF1
# gbaL31ahymEU3vUcKZX8Z4ycmBFw9b3yvotTVR38lE9p+sKtSaGKUGV0btpS7oBB
# y8IfnVmg5X1j4PtyDxFlLD48qg//2kVgJ6wtaDTSAkgQMOPM9UgHgQD+Ks7kOo8v
# rReL46XVPEZTWt3syX0y87mFinjK2hXGqIdsnJ1uT614BAVVIrmO6aFNNN1FlsRb
# NGRZevJTfEWjWVfWOhUiZdUGDz74sOXdshZX/teadeDJLtWaw0uytMN9qoTN33h/
# OsdR2fO7h8ZknGEc2F1fJEVh4sOfO4fGYAAJGzHP9AjUDV1IVVYELb79dg==
# =WYTo
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 26 Oct 2023 02:53:50 JST
# 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' of https://gitlab.com/bonzini/qemu: (24 commits)
  kvm: i8254: require KVM_CAP_PIT2 and KVM_CAP_PIT_STATE2
  kvm: i386: require KVM_CAP_SET_IDENTITY_MAP_ADDR
  kvm: i386: require KVM_CAP_ADJUST_CLOCK
  kvm: i386: require KVM_CAP_MCE
  kvm: i386: require KVM_CAP_SET_VCPU_EVENTS and KVM_CAP_X86_ROBUST_SINGLESTEP
  kvm: i386: require KVM_CAP_XSAVE
  kvm: i386: require KVM_CAP_DEBUGREGS
  kvm: i386: move KVM_CAP_IRQ_ROUTING detection to kvm_arch_required_capabilities
  kvm: unify listeners for PIO address space
  kvm: require KVM_CAP_IOEVENTFD and KVM_CAP_IOEVENTFD_ANY_LENGTH
  kvm: assume that many ioeventfds can be created
  kvm: drop reference to KVM_CAP_PCI_2_3
  kvm: require KVM_IRQFD for kernel irqchip
  kvm: require KVM_IRQFD for kernel irqchip
  kvm: require KVM_CAP_SIGNAL_MSI
  kvm: require KVM_CAP_INTERNAL_ERROR_DATA
  kvm: remove unnecessary stub
  target/i386: check CPUID_PAE to determine 36 bit processor address space
  target/i386: validate VEX.W for AVX instructions
  target/i386: group common checks in the decoding phase
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

10 files changed, 21 insertions, 73 deletions

diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index f25977d3f6..e756b0aa43 100644
--- a/hw/i386/kvm/clock.c
+++ b/hw/i386/kvm/clock.c
@@ -333,10 +333,6 @@ void kvmclock_create(bool create_always)
     X86CPU *cpu = X86_CPU(first_cpu);
 
     assert(kvm_enabled());
-    if (!kvm_has_adjust_clock()) {
-        return;
-    }
-
     if (create_always ||
         cpu->env.features[FEAT_KVM] & ((1ULL << KVM_FEATURE_CLOCKSOURCE) |
                                        (1ULL << KVM_FEATURE_CLOCKSOURCE2))) {
diff --git a/hw/i386/kvm/i8254.c b/hw/i386/kvm/i8254.c
index a649b2b7ca..e49b9c4b56 100644
--- a/hw/i386/kvm/i8254.c
+++ b/hw/i386/kvm/i8254.c
@@ -97,24 +97,12 @@ static void kvm_pit_get(PITCommonState *pit)
         return;
     }
 
-    if (kvm_has_pit_state2()) {
-        ret = kvm_vm_ioctl(kvm_state, KVM_GET_PIT2, &kpit);
-        if (ret < 0) {
-            fprintf(stderr, "KVM_GET_PIT2 failed: %s\n", strerror(-ret));
-            abort();
-        }
-        pit->channels[0].irq_disabled = kpit.flags & KVM_PIT_FLAGS_HPET_LEGACY;
-    } else {
-        /*
-         * kvm_pit_state2 is superset of kvm_pit_state struct,
-         * so we can use it for KVM_GET_PIT as well.
-         */
-        ret = kvm_vm_ioctl(kvm_state, KVM_GET_PIT, &kpit);
-        if (ret < 0) {
-            fprintf(stderr, "KVM_GET_PIT failed: %s\n", strerror(-ret));
-            abort();
-        }
+    ret = kvm_vm_ioctl(kvm_state, KVM_GET_PIT2, &kpit);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_PIT2 failed: %s\n", strerror(-ret));
+        abort();
     }
+    pit->channels[0].irq_disabled = kpit.flags & KVM_PIT_FLAGS_HPET_LEGACY;
     for (i = 0; i < 3; i++) {
         kchan = &kpit.channels[i];
         sc = &pit->channels[i];
@@ -170,12 +158,9 @@ static void kvm_pit_put(PITCommonState *pit)
         kchan->count_load_time = sc->count_load_time - s->kernel_clock_offset;
     }
 
-    ret = kvm_vm_ioctl(kvm_state,
-                       kvm_has_pit_state2() ? KVM_SET_PIT2 : KVM_SET_PIT,
-                       &kpit);
+    ret = kvm_vm_ioctl(kvm_state, KVM_SET_PIT2, &kpit);
     if (ret < 0) {
-        fprintf(stderr, "%s failed: %s\n",
-                kvm_has_pit_state2() ? "KVM_SET_PIT2" : "KVM_SET_PIT",
+        fprintf(stderr, "KVM_SET_PIT2 failed: %s\n",
                 strerror(-ret));
         abort();
     }
@@ -261,11 +246,12 @@ static void kvm_pit_realizefn(DeviceState *dev, Error **errp)
     };
     int ret;
 
-    if (kvm_check_extension(kvm_state, KVM_CAP_PIT2)) {
-        ret = kvm_vm_ioctl(kvm_state, KVM_CREATE_PIT2, &config);
-    } else {
-        ret = kvm_vm_ioctl(kvm_state, KVM_CREATE_PIT);
+    if (!kvm_check_extension(kvm_state, KVM_CAP_PIT_STATE2) ||
+        !kvm_check_extension(kvm_state, KVM_CAP_PIT2)) {
+        error_setg(errp, "In-kernel PIT not available");
     }
+
+    ret = kvm_vm_ioctl(kvm_state, KVM_CREATE_PIT2, &config);
     if (ret < 0) {
         error_setg(errp, "Create kernel PIC irqchip failed: %s",
                    strerror(-ret));
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 11fed78d17..6031234a73 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1214,12 +1214,8 @@ void pc_basic_device_init(struct PCMachineState *pcms,
 
     /*
      * Check if an HPET shall be created.
-     *
-     * Without KVM_CAP_PIT_STATE2, we cannot switch off the in-kernel PIT
-     * when the HPET wants to take over. Thus we have to disable the latter.
      */
-    if (pcms->hpet_enabled && (!kvm_irqchip_in_kernel() ||
-                               kvm_has_pit_state2())) {
+    if (pcms->hpet_enabled) {
         qemu_irq rtc_irq;
 
         hpet = qdev_try_new(TYPE_HPET);
diff --git a/hw/intc/arm_gicv3_its_common.c b/hw/intc/arm_gicv3_its_common.c
index abaf77057e..fddd6d490c 100644
--- a/hw/intc/arm_gicv3_its_common.c
+++ b/hw/intc/arm_gicv3_its_common.c
@@ -163,8 +163,7 @@ type_init(gicv3_its_common_register_types)
 const char *its_class_name(void)
 {
     if (kvm_irqchip_in_kernel()) {
-        /* KVM implementation requires this capability */
-        return kvm_direct_msi_enabled() ? "arm-its-kvm" : NULL;
+        return "arm-its-kvm";
     } else {
         /* Software emulation based model */
         return "arm-gicv3-its";
diff --git a/hw/intc/arm_gicv3_its_kvm.c b/hw/intc/arm_gicv3_its_kvm.c
index 61c1cc7bdb..f7df602cff 100644
--- a/hw/intc/arm_gicv3_its_kvm.c
+++ b/hw/intc/arm_gicv3_its_kvm.c
@@ -123,7 +123,7 @@ static void kvm_arm_its_realize(DeviceState *dev, Error **errp)
 
     kvm_msi_use_devid = true;
     kvm_gsi_direct_mapping = false;
-    kvm_msi_via_irqfd_allowed = kvm_irqfds_enabled();
+    kvm_msi_via_irqfd_allowed = true;
 }
 
 /**
diff --git a/hw/misc/pci-testdev.c b/hw/misc/pci-testdev.c
index 49303134e4..acedd0f82b 100644
--- a/hw/misc/pci-testdev.c
+++ b/hw/misc/pci-testdev.c
@@ -245,7 +245,6 @@ static void pci_testdev_realize(PCIDevice *pci_dev, Error **errp)
     uint8_t *pci_conf;
     char *name;
     int r, i;
-    bool fastmmio = kvm_ioeventfd_any_length_enabled();
 
     pci_conf = pci_dev->config;
 
@@ -279,7 +278,7 @@ static void pci_testdev_realize(PCIDevice *pci_dev, Error **errp)
         g_free(name);
         test->hdr->offset = cpu_to_le32(IOTEST_SIZE(i) + i * IOTEST_ACCESS_WIDTH);
         test->match_data = strcmp(IOTEST_TEST(i), "wildcard-eventfd");
-        if (fastmmio && IOTEST_IS_MEM(i) && !test->match_data) {
+        if (IOTEST_IS_MEM(i) && !test->match_data) {
             test->size = 0;
         } else {
             test->size = IOTEST_ACCESS_WIDTH;
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index 17c548b84f..80453718a3 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -768,10 +768,6 @@ static void virtio_ccw_device_realize(VirtioCcwDevice *dev, Error **errp)
         sch->cssid, sch->ssid, sch->schid, sch->devno,
         ccw_dev->devno.valid ? "user-configured" : "auto-configured");
 
-    if (kvm_enabled() && !kvm_eventfds_enabled()) {
-        dev->flags &= ~VIRTIO_CCW_FLAG_USE_IOEVENTFD;
-    }
-
     /* fd-based ioevents can't be synchronized in record/replay */
     if (replay_mode != REPLAY_MODE_NONE) {
         dev->flags &= ~VIRTIO_CCW_FLAG_USE_IOEVENTFD;
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index b8a7b5542d..7b42ae8aae 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -264,11 +264,6 @@ struct scrub_regions {
     int fd_idx;
 };
 
-static bool ioeventfd_enabled(void)
-{
-    return !kvm_enabled() || kvm_eventfds_enabled();
-}
-
 static int vhost_user_read_header(struct vhost_dev *dev, VhostUserMsg *msg)
 {
     struct vhost_user *u = dev->opaque;
@@ -1318,7 +1313,7 @@ static int vhost_set_vring_file(struct vhost_dev *dev,
         .hdr.size = sizeof(msg.payload.u64),
     };
 
-    if (ioeventfd_enabled() && file->fd > 0) {
+    if (file->fd > 0) {
         fds[fd_num++] = file->fd;
     } else {
         msg.payload.u64 |= VHOST_USER_VRING_NOFD_MASK;
diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c
index c2c6d85475..22f15e1e02 100644
--- a/hw/virtio/virtio-mmio.c
+++ b/hw/virtio/virtio-mmio.c
@@ -761,10 +761,6 @@ static void virtio_mmio_realizefn(DeviceState *d, Error **errp)
     qbus_init(&proxy->bus, sizeof(proxy->bus), TYPE_VIRTIO_MMIO_BUS, d, NULL);
     sysbus_init_irq(sbd, &proxy->irq);
 
-    if (!kvm_eventfds_enabled()) {
-        proxy->flags &= ~VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD;
-    }
-
     /* fd-based ioevents can't be synchronized in record/replay */
     if (replay_mode != REPLAY_MODE_NONE) {
         proxy->flags &= ~VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD;
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index af1f4bc187..205dbf24fb 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -332,7 +332,6 @@ static int virtio_pci_ioeventfd_assign(DeviceState *d, EventNotifier *notifier,
     VirtQueue *vq = virtio_get_queue(vdev, n);
     bool legacy = virtio_pci_legacy(proxy);
     bool modern = virtio_pci_modern(proxy);
-    bool fast_mmio = kvm_ioeventfd_any_length_enabled();
     bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY;
     MemoryRegion *modern_mr = &proxy->notify.mr;
     MemoryRegion *modern_notify_mr = &proxy->notify_pio.mr;
@@ -343,13 +342,8 @@ static int virtio_pci_ioeventfd_assign(DeviceState *d, EventNotifier *notifier,
 
     if (assign) {
         if (modern) {
-            if (fast_mmio) {
-                memory_region_add_eventfd(modern_mr, modern_addr, 0,
-                                          false, n, notifier);
-            } else {
-                memory_region_add_eventfd(modern_mr, modern_addr, 2,
-                                          false, n, notifier);
-            }
+            memory_region_add_eventfd(modern_mr, modern_addr, 0,
+                                      false, n, notifier);
             if (modern_pio) {
                 memory_region_add_eventfd(modern_notify_mr, 0, 2,
                                               true, n, notifier);
@@ -361,13 +355,8 @@ static int virtio_pci_ioeventfd_assign(DeviceState *d, EventNotifier *notifier,
         }
     } else {
         if (modern) {
-            if (fast_mmio) {
-                memory_region_del_eventfd(modern_mr, modern_addr, 0,
-                                          false, n, notifier);
-            } else {
-                memory_region_del_eventfd(modern_mr, modern_addr, 2,
-                                          false, n, notifier);
-            }
+            memory_region_del_eventfd(modern_mr, modern_addr, 0,
+                                      false, n, notifier);
             if (modern_pio) {
                 memory_region_del_eventfd(modern_notify_mr, 0, 2,
                                           true, n, notifier);
@@ -2114,10 +2103,6 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
     bool pcie_port = pci_bus_is_express(pci_get_bus(pci_dev)) &&
                      !pci_bus_is_root(pci_get_bus(pci_dev));
 
-    if (kvm_enabled() && !kvm_has_many_ioeventfds()) {
-        proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD;
-    }
-
     /* fd-based ioevents can't be synchronized in record/replay */
     if (replay_mode != REPLAY_MODE_NONE) {
         proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD;