Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pc,pci,vhost,virtio: misc fixes

Just a bunch of bugfixes all over the place.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Fri 30 Oct 2020 12:44:31 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream:
  intel_iommu: Fix two misuse of "0x%u" prints
  virtio: skip guest index check on device load
  vhost-blk: set features before setting inflight feature
  pci: Disallow improper BAR registration for type 1
  pci: Change error_report to assert(3)
  pci: advertise a page aligned ATS
  pc: Implement -no-hpet as sugar for -machine hpet=on
  vhost: Don't special case vq->used_phys in vhost_get_log_size()
  pci: Assert irqnum is between 0 and bus->nirqs in pci_bus_change_irq_level
  hw/pci: Extract pci_bus_change_irq_level() from pci_change_irq_level()
  hw/virtio/vhost-vdpa: Fix Coverity CID 1432864
  acpi/crs: Support ranges > 32b for hosts
  acpi/crs: Prevent bad ranges for host bridges
  vhost-vsock: set vhostfd to non-blocking mode
  vhost-vdpa: negotiate VIRTIO_NET_F_STATUS with driver

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

16 files changed, 122 insertions, 56 deletions

diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c
index a076b1e54d..f67b29bbf3 100644
--- a/hw/block/vhost-user-blk.c
+++ b/hw/block/vhost-user-blk.c
@@ -131,6 +131,12 @@ static int vhost_user_blk_start(VirtIODevice *vdev)
 
     s->dev.acked_features = vdev->guest_features;
 
+    ret = vhost_dev_prepare_inflight(&s->dev);
+    if (ret < 0) {
+        error_report("Error set inflight format: %d", -ret);
+        goto err_guest_notifiers;
+    }
+
     if (!s->inflight->addr) {
         ret = vhost_dev_get_inflight(&s->dev, s->queue_size, s->inflight);
         if (ret < 0) {
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index e3a4bc206c..4f66642d88 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -786,8 +786,14 @@ static Aml *build_crs(PCIHostState *host, CrsRangeSet *range_set)
                 crs_range_insert(temp_range_set.io_ranges,
                                  range_base, range_limit);
             } else { /* "memory" */
-                crs_range_insert(temp_range_set.mem_ranges,
-                                 range_base, range_limit);
+                uint64_t length = range_limit - range_base + 1;
+                if (range_limit <= UINT32_MAX && length <= UINT32_MAX) {
+                    crs_range_insert(temp_range_set.mem_ranges, range_base,
+                                     range_limit);
+                } else {
+                    crs_range_insert(temp_range_set.mem_64bit_ranges,
+                                     range_base, range_limit);
+                }
             }
         }
 
@@ -866,6 +872,8 @@ static Aml *build_crs(PCIHostState *host, CrsRangeSet *range_set)
     crs_range_merge(temp_range_set.mem_ranges);
     for (i = 0; i < temp_range_set.mem_ranges->len; i++) {
         entry = g_ptr_array_index(temp_range_set.mem_ranges, i);
+        assert(entry->limit <= UINT32_MAX &&
+               (entry->limit - entry->base + 1) <= UINT32_MAX);
         aml_append(crs,
                    aml_dword_memory(AML_POS_DECODE, AML_MIN_FIXED,
                                     AML_MAX_FIXED, AML_NON_CACHEABLE,
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 749eb6ad63..70ac837733 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -2665,7 +2665,7 @@ static uint64_t vtd_mem_read(void *opaque, hwaddr addr, unsigned size)
 
     if (addr + size > DMAR_REG_SIZE) {
         error_report_once("%s: MMIO over range: addr=0x%" PRIx64
-                          " size=0x%u", __func__, addr, size);
+                          " size=0x%x", __func__, addr, size);
         return (uint64_t)-1;
     }
 
@@ -2716,7 +2716,7 @@ static void vtd_mem_write(void *opaque, hwaddr addr,
 
     if (addr + size > DMAR_REG_SIZE) {
         error_report_once("%s: MMIO over range: addr=0x%" PRIx64
-                          " size=0x%u", __func__, addr, size);
+                          " size=0x%x", __func__, addr, size);
         return;
     }
 
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 0d9bd7d635..5e6c0023e0 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1142,28 +1142,31 @@ void pc_basic_device_init(struct PCMachineState *pcms,
      * 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 (!no_hpet && (!kvm_irqchip_in_kernel() || kvm_has_pit_state2())) {
+    if (pcms->hpet_enabled && (!kvm_irqchip_in_kernel() ||
+                               kvm_has_pit_state2())) {
         hpet = qdev_try_new(TYPE_HPET);
-        if (hpet) {
-            /* For pc-piix-*, hpet's intcap is always IRQ2. For pc-q35-1.7
-             * and earlier, use IRQ2 for compat. Otherwise, use IRQ16~23,
-             * IRQ8 and IRQ2.
-             */
-            uint8_t compat = object_property_get_uint(OBJECT(hpet),
-                    HPET_INTCAP, NULL);
-            if (!compat) {
-                qdev_prop_set_uint32(hpet, HPET_INTCAP, hpet_irqs);
-            }
-            sysbus_realize_and_unref(SYS_BUS_DEVICE(hpet), &error_fatal);
-            sysbus_mmio_map(SYS_BUS_DEVICE(hpet), 0, HPET_BASE);
+        if (!hpet) {
+            error_report("couldn't create HPET device");
+            exit(1);
+        }
+        /* For pc-piix-*, hpet's intcap is always IRQ2. For pc-q35-1.7
+            * and earlier, use IRQ2 for compat. Otherwise, use IRQ16~23,
+            * IRQ8 and IRQ2.
+            */
+        uint8_t compat = object_property_get_uint(OBJECT(hpet),
+                HPET_INTCAP, NULL);
+        if (!compat) {
+            qdev_prop_set_uint32(hpet, HPET_INTCAP, hpet_irqs);
+        }
+        sysbus_realize_and_unref(SYS_BUS_DEVICE(hpet), &error_fatal);
+        sysbus_mmio_map(SYS_BUS_DEVICE(hpet), 0, HPET_BASE);
 
-            for (i = 0; i < GSI_NUM_PINS; i++) {
-                sysbus_connect_irq(SYS_BUS_DEVICE(hpet), i, gsi[i]);
-            }
-            pit_isa_irq = -1;
-            pit_alt_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_PIT_INT);
-            rtc_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_RTC_INT);
+        for (i = 0; i < GSI_NUM_PINS; i++) {
+            sysbus_connect_irq(SYS_BUS_DEVICE(hpet), i, gsi[i]);
         }
+        pit_isa_irq = -1;
+        pit_alt_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_PIT_INT);
+        rtc_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_RTC_INT);
     }
     *rtc_state = mc146818_rtc_init(isa_bus, 2000, rtc_irq);
 
@@ -1529,6 +1532,20 @@ static void pc_machine_set_pit(Object *obj, bool value, Error **errp)
     pcms->pit_enabled = value;
 }
 
+static bool pc_machine_get_hpet(Object *obj, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    return pcms->hpet_enabled;
+}
+
+static void pc_machine_set_hpet(Object *obj, bool value, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    pcms->hpet_enabled = value;
+}
+
 static void pc_machine_get_max_ram_below_4g(Object *obj, Visitor *v,
                                             const char *name, void *opaque,
                                             Error **errp)
@@ -1579,6 +1596,9 @@ static void pc_machine_initfn(Object *obj)
     pcms->smbus_enabled = true;
     pcms->sata_enabled = true;
     pcms->pit_enabled = true;
+#ifdef CONFIG_HPET
+    pcms->hpet_enabled = true;
+#endif
 
     pc_system_flash_create(pcms);
     pcms->pcspk = isa_new(TYPE_PC_SPEAKER);
@@ -1699,6 +1719,9 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
 
     object_class_property_add_bool(oc, PC_MACHINE_PIT,
         pc_machine_get_pit, pc_machine_set_pit);
+
+    object_class_property_add_bool(oc, "hpet",
+        pc_machine_get_hpet, pc_machine_set_hpet);
 }
 
 static const TypeInfo pc_machine_info = {
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 0cf22a57ad..13d1628f13 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -216,7 +216,7 @@ static void pc_init1(MachineState *machine,
         i440fx_state = NULL;
         isa_bus = isa_bus_new(NULL, get_system_memory(), system_io,
                               &error_abort);
-        no_hpet = 1;
+        pcms->hpet_enabled = false;
     }
     isa_bus_irqs(isa_bus, x86ms->gsi);
 
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 100c9381c2..0131d9d02c 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -248,6 +248,14 @@ static inline void pci_set_irq_state(PCIDevice *d, int irq_num, int level)
         d->irq_state |= level << irq_num;
 }
 
+static void pci_bus_change_irq_level(PCIBus *bus, int irq_num, int change)
+{
+    assert(irq_num >= 0);
+    assert(irq_num < bus->nirq);
+    bus->irq_count[irq_num] += change;
+    bus->set_irq(bus->irq_opaque, irq_num, bus->irq_count[irq_num] != 0);
+}
+
 static void pci_change_irq_level(PCIDevice *pci_dev, int irq_num, int change)
 {
     PCIBus *bus;
@@ -258,8 +266,7 @@ static void pci_change_irq_level(PCIDevice *pci_dev, int irq_num, int change)
             break;
         pci_dev = bus->parent_dev;
     }
-    bus->irq_count[irq_num] += change;
-    bus->set_irq(bus->irq_opaque, irq_num, bus->irq_count[irq_num] != 0);
+    pci_bus_change_irq_level(bus, irq_num, change);
 }
 
 int pci_bus_get_irq_level(PCIBus *bus, int irq_num)
@@ -1141,14 +1148,16 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
     uint32_t addr; /* offset in pci config space */
     uint64_t wmask;
     pcibus_t size = memory_region_size(memory);
+    uint8_t hdr_type;
 
     assert(region_num >= 0);
     assert(region_num < PCI_NUM_REGIONS);
-    if (size & (size-1)) {
-        error_report("ERROR: PCI region size must be pow2 "
-                    "type=0x%x, size=0x%"FMT_PCIBUS"", type, size);
-        exit(1);
-    }
+    assert(is_power_of_2(size));
+
+    /* A PCI bridge device (with Type 1 header) may only have at most 2 BARs */
+    hdr_type =
+        pci_dev->config[PCI_HEADER_TYPE] & ~PCI_HEADER_TYPE_MULTI_FUNCTION;
+    assert(hdr_type != PCI_HEADER_TYPE_BRIDGE || region_num < 2);
 
     r = &pci_dev->io_regions[region_num];
     r->addr = PCI_BAR_UNMAPPED;
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index 5b48bae0f6..d4010cf8f3 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -971,8 +971,9 @@ void pcie_ats_init(PCIDevice *dev, uint16_t offset)
 
     dev->exp.ats_cap = offset;
 
-    /* Invalidate Queue Depth 0, Page Aligned Request 0 */
-    pci_set_word(dev->config + offset + PCI_ATS_CAP, 0);
+    /* Invalidate Queue Depth 0, Page Aligned Request 1 */
+    pci_set_word(dev->config + offset + PCI_ATS_CAP,
+                 PCI_ATS_CAP_PAGE_ALIGNED);
     /* STU 0, Disabled by default */
     pci_set_word(dev->config + offset + PCI_ATS_CTRL, 0);
 
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 4f1039910a..01d2101d09 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -90,7 +90,7 @@ static void vhost_vdpa_listener_begin(MemoryListener *listener)
 {
     struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener);
     struct vhost_dev *dev = v->dev;
-    struct vhost_msg_v2 msg;
+    struct vhost_msg_v2 msg = {};
     int fd = v->device_fd;
 
     if (!(dev->backend_cap & (0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH))) {
@@ -110,7 +110,7 @@ static void vhost_vdpa_listener_commit(MemoryListener *listener)
 {
     struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener);
     struct vhost_dev *dev = v->dev;
-    struct vhost_msg_v2 msg;
+    struct vhost_msg_v2 msg = {};
     int fd = v->device_fd;
 
     if (!(dev->backend_cap & (0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH))) {
diff --git a/hw/virtio/vhost-vsock.c b/hw/virtio/vhost-vsock.c
index f9db4beb47..8ddfb9abfe 100644
--- a/hw/virtio/vhost-vsock.c
+++ b/hw/virtio/vhost-vsock.c
@@ -16,6 +16,7 @@
 #include "qapi/error.h"
 #include "hw/virtio/virtio-access.h"
 #include "qemu/error-report.h"
+#include "qemu/sockets.h"
 #include "hw/qdev-properties.h"
 #include "hw/virtio/vhost-vsock.h"
 #include "monitor/monitor.h"
@@ -148,6 +149,13 @@ static void vhost_vsock_device_realize(DeviceState *dev, Error **errp)
             error_prepend(errp, "vhost-vsock: unable to parse vhostfd: ");
             return;
         }
+
+        ret = qemu_try_set_nonblock(vhostfd);
+        if (ret < 0) {
+            error_setg_errno(errp, -ret,
+                             "vhost-vsock: unable to set non-blocking mode");
+            return;
+        }
     } else {
         vhostfd = open("/dev/vhost-vsock", O_RDWR);
         if (vhostfd < 0) {
@@ -155,6 +163,8 @@ static void vhost_vsock_device_realize(DeviceState *dev, Error **errp)
                              "vhost-vsock: failed to open vhost device");
             return;
         }
+
+        qemu_set_nonblock(vhostfd);
     }
 
     vhost_vsock_common_realize(vdev, "vhost-vsock");
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 3077fa6ef5..f2482378c6 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -172,16 +172,6 @@ static uint64_t vhost_get_log_size(struct vhost_dev *dev)
                                        reg->memory_size);
         log_size = MAX(log_size, last / VHOST_LOG_CHUNK + 1);
     }
-    for (i = 0; i < dev->nvqs; ++i) {
-        struct vhost_virtqueue *vq = dev->vqs + i;
-
-        if (!vq->used_phys && !vq->used_size) {
-            continue;
-        }
-
-        uint64_t last = vq->used_phys + vq->used_size - 1;
-        log_size = MAX(log_size, last / VHOST_LOG_CHUNK + 1);
-    }
     return log_size;
 }
 
@@ -1655,6 +1645,24 @@ int vhost_dev_load_inflight(struct vhost_inflight *inflight, QEMUFile *f)
     return 0;
 }
 
+int vhost_dev_prepare_inflight(struct vhost_dev *hdev)
+{
+    int r;
+ 
+    if (hdev->vhost_ops->vhost_get_inflight_fd == NULL ||
+        hdev->vhost_ops->vhost_set_inflight_fd == NULL) {
+        return 0;
+    }
+ 
+    r = vhost_dev_set_features(hdev, hdev->log_enabled);
+    if (r < 0) {
+        VHOST_OPS_DEBUG("vhost_dev_prepare_inflight failed");
+        return r;
+    }
+
+    return 0;
+}
+
 int vhost_dev_set_inflight(struct vhost_dev *dev,
                            struct vhost_inflight *inflight)
 {
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 6f8f865aff..ceb58fda6c 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -17,6 +17,7 @@
 #include "trace.h"
 #include "exec/address-spaces.h"
 #include "qemu/error-report.h"
+#include "qemu/log.h"
 #include "qemu/main-loop.h"
 #include "qemu/module.h"
 #include "hw/virtio/virtio.h"
@@ -3160,12 +3161,12 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id)
             nheads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx;
             /* Check it isn't doing strange things with descriptor numbers. */
             if (nheads > vdev->vq[i].vring.num) {
-                error_report("VQ %d size 0x%x Guest index 0x%x "
-                             "inconsistent with Host index 0x%x: delta 0x%x",
-                             i, vdev->vq[i].vring.num,
-                             vring_avail_idx(&vdev->vq[i]),
-                             vdev->vq[i].last_avail_idx, nheads);
-                return -1;
+                qemu_log_mask(LOG_GUEST_ERROR,
+                              "VQ %d size 0x%x Guest index 0x%x "
+                              "inconsistent with Host index 0x%x: delta 0x%x",
+                              i, vdev->vq[i].vring.num,
+                              vring_avail_idx(&vdev->vq[i]),
+                              vdev->vq[i].last_avail_idx, nheads);
             }
             vdev->vq[i].used_idx = vring_used_idx(&vdev->vq[i]);
             vdev->vq[i].shadow_avail_idx = vring_avail_idx(&vdev->vq[i]);
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 84639d0ebc..911e460097 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -43,6 +43,7 @@ typedef struct PCMachineState {
     bool smbus_enabled;
     bool sata_enabled;
     bool pit_enabled;
+    bool hpet_enabled;
 
     /* NUMA information: */
     uint64_t numa_nodes;
diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h
index bfa9cb2a25..739fac5087 100644
--- a/include/hw/i386/x86.h
+++ b/include/hw/i386/x86.h
@@ -126,7 +126,4 @@ qemu_irq x86_allocate_cpu_irq(void);
 void gsi_handler(void *opaque, int n, int level);
 void ioapic_init_gsi(GSIState *gsi_state, const char *parent_name);
 
-/* hpet.c */
-extern int no_hpet;
-
 #endif
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 94585067f7..839bfb153c 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -141,6 +141,7 @@ void vhost_dev_reset_inflight(struct vhost_inflight *inflight);
 void vhost_dev_free_inflight(struct vhost_inflight *inflight);
 void vhost_dev_save_inflight(struct vhost_inflight *inflight, QEMUFile *f);
 int vhost_dev_load_inflight(struct vhost_inflight *inflight, QEMUFile *f);
+int vhost_dev_prepare_inflight(struct vhost_dev *hdev);
 int vhost_dev_set_inflight(struct vhost_dev *dev,
                            struct vhost_inflight *inflight);
 int vhost_dev_get_inflight(struct vhost_dev *dev, uint16_t queue_size,
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index e2b3ba85bf..99c476db8c 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -55,6 +55,7 @@ const int vdpa_feature_bits[] = {
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_PACKED,
     VIRTIO_NET_F_GUEST_ANNOUNCE,
+    VIRTIO_NET_F_STATUS,
     VHOST_INVALID_FEATURE_BIT
 };
 
diff --git a/softmmu/vl.c b/softmmu/vl.c
index 7c1c6d37ef..a537a0377f 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -146,7 +146,6 @@ static Chardev **serial_hds;
 Chardev *parallel_hds[MAX_PARALLEL_PORTS];
 int win2k_install_hack = 0;
 int singlestep = 0;
-int no_hpet = 0;
 int fd_bootchk = 1;
 static int no_reboot;
 int no_shutdown = 0;
@@ -3562,7 +3561,8 @@ void qemu_init(int argc, char **argv, char **envp)
                 qemu_opts_parse_noisily(olist, "acpi=off", false);
                 break;
             case QEMU_OPTION_no_hpet:
-                no_hpet = 1;
+                olist = qemu_find_opts("machine");
+                qemu_opts_parse_noisily(olist, "hpet=off", false);
                 break;
             case QEMU_OPTION_no_reboot:
                 no_reboot = 1;