Merge remote-tracking branch 'remotes/stefanha/tags/net-pull-request' into staging

[mirror_qemu.git] / kvm-all.c

diff --git a/kvm-all.c b/kvm-all.c
index e98a7c74a7506d3a60335a58f985dccb15dee85a..335438adb526c133b93cac095b76f973836aa0e3 100644 (file)
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -71,7 +71,7 @@ typedef struct KVMSlot
 
 typedef struct kvm_dirty_log KVMDirtyLog;
 
-typedef struct KVMState
+struct KVMState
 {
     AccelState parent_obj;
 
@@ -107,7 +107,7 @@ typedef struct KVMState
     QTAILQ_HEAD(msi_hashtab, KVMMSIRoute) msi_hashtab[KVM_MSI_HASHTAB_SIZE];
     bool direct_msi;
 #endif
-} KVMState;
+};
 
 #define TYPE_KVM_ACCEL ACCEL_CLASS_NAME("kvm")
 
@@ -120,11 +120,13 @@ bool kvm_async_interrupts_allowed;
 bool kvm_halt_in_kernel_allowed;
 bool kvm_eventfds_allowed;
 bool kvm_irqfds_allowed;
+bool kvm_resamplefds_allowed;
 bool kvm_msi_via_irqfd_allowed;
 bool kvm_gsi_routing_allowed;
 bool kvm_gsi_direct_mapping;
 bool kvm_allowed;
 bool kvm_readonly_mem_allowed;
+bool kvm_vm_attributes_allowed;
 
 static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_INFO(USER_MEMORY),
@@ -132,7 +134,7 @@ static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_LAST_INFO
 };
 
-static KVMSlot *kvm_alloc_slot(KVMState *s)
+static KVMSlot *kvm_get_free_slot(KVMState *s)
 {
     int i;
 
@@ -142,6 +144,22 @@ static KVMSlot *kvm_alloc_slot(KVMState *s)
         }
     }
 
+    return NULL;
+}
+
+bool kvm_has_free_slot(MachineState *ms)
+{
+    return kvm_get_free_slot(KVM_STATE(ms->accelerator));
+}
+
+static KVMSlot *kvm_alloc_slot(KVMState *s)
+{
+    KVMSlot *slot = kvm_get_free_slot(s);
+
+    if (slot) {
+        return slot;
+    }
+
     fprintf(stderr, "%s: no free slot available\n", __func__);
     abort();
 }
@@ -349,7 +367,7 @@ static void kvm_log_stop(MemoryListener *listener,
     }
 }
 
-static int kvm_set_migration_log(int enable)
+static int kvm_set_migration_log(bool enable)
 {
     KVMState *s = kvm_state;
     KVMSlot *mem;
@@ -400,7 +418,7 @@ static int kvm_physical_sync_dirty_bitmap(MemoryRegionSection *section)
 {
     KVMState *s = kvm_state;
     unsigned long size, allocated_size = 0;
-    KVMDirtyLog d;
+    KVMDirtyLog d = {};
     KVMSlot *mem;
     int ret = 0;
     hwaddr start_addr = section->offset_within_address_space;
@@ -510,13 +528,33 @@ int kvm_vm_check_extension(KVMState *s, unsigned int extension)
     return ret;
 }
 
+static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size)
+{
+#if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN)
+    /* The kernel expects ioeventfd values in HOST_WORDS_BIGENDIAN
+     * endianness, but the memory core hands them in target endianness.
+     * For example, PPC is always treated as big-endian even if running
+     * on KVM and on PPC64LE.  Correct here.
+     */
+    switch (size) {
+    case 2:
+        val = bswap16(val);
+        break;
+    case 4:
+        val = bswap32(val);
+        break;
+    }
+#endif
+    return val;
+}
+
 static int kvm_set_ioeventfd_mmio(int fd, hwaddr addr, uint32_t val,
                                   bool assign, uint32_t size, bool datamatch)
 {
     int ret;
     struct kvm_ioeventfd iofd;
 
-    iofd.datamatch = datamatch ? val : 0;
+    iofd.datamatch = datamatch ? adjust_ioeventfd_endianness(val, size) : 0;
     iofd.addr = addr;
     iofd.len = size;
     iofd.flags = 0;
@@ -546,7 +584,7 @@ static int kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint16_t val,
                                  bool assign, uint32_t size, bool datamatch)
 {
     struct kvm_ioeventfd kick = {
-        .datamatch = datamatch ? val : 0,
+        .datamatch = datamatch ? adjust_ioeventfd_endianness(val, size) : 0,
         .addr = addr,
         .flags = KVM_IOEVENTFD_FLAG_PIO,
         .len = size,
@@ -634,8 +672,10 @@ static void kvm_set_phys_mem(MemoryRegionSection *section, bool add)
     unsigned delta;
 
     /* kvm works in page size chunks, but the function may be called
-       with sub-page size and unaligned start address. */
-    delta = TARGET_PAGE_ALIGN(size) - size;
+       with sub-page size and unaligned start address. Pad the start
+       address to next and truncate size to previous page boundary. */
+    delta = (TARGET_PAGE_SIZE - (start_addr & ~TARGET_PAGE_MASK));
+    delta &= ~TARGET_PAGE_MASK;
     if (delta > size) {
         return;
     }
@@ -1206,6 +1246,10 @@ int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg)
     kroute.u.msi.address_lo = (uint32_t)msg.address;
     kroute.u.msi.address_hi = msg.address >> 32;
     kroute.u.msi.data = le32_to_cpu(msg.data);
+    if (kvm_arch_fixup_msi_route(&kroute, msg.address, msg.data)) {
+        kvm_irqchip_release_virq(s, virq);
+        return -EINVAL;
+    }
 
     kvm_add_routing_entry(s, &kroute);
     kvm_irqchip_commit_routes(s);
@@ -1231,6 +1275,9 @@ int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
     kroute.u.msi.address_lo = (uint32_t)msg.address;
     kroute.u.msi.address_hi = msg.address >> 32;
     kroute.u.msi.data = le32_to_cpu(msg.data);
+    if (kvm_arch_fixup_msi_route(&kroute, msg.address, msg.data)) {
+        return -EINVAL;
+    }
 
     return kvm_update_routing_entry(s, &kroute);
 }
@@ -1258,7 +1305,7 @@ static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int rfd, int virq,
 
 int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
 {
-    struct kvm_irq_routing_entry kroute;
+    struct kvm_irq_routing_entry kroute = {};
     int virq;
 
     if (!kvm_gsi_routing_enabled()) {
@@ -1334,11 +1381,11 @@ int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
            false);
 }
 
-static int kvm_irqchip_create(KVMState *s)
+static int kvm_irqchip_create(MachineState *machine, KVMState *s)
 {
     int ret;
 
-    if (!qemu_opt_get_bool(qemu_get_machine_opts(), "kernel_irqchip", true) ||
+    if (!machine_kernel_irqchip_allowed(machine) ||
         (!kvm_check_extension(s, KVM_CAP_IRQCHIP) &&
          (kvm_vm_enable_cap(s, KVM_CAP_S390_IRQCHIP, 0) < 0))) {
         return 0;
@@ -1566,12 +1613,21 @@ static int kvm_init(MachineState *ms)
     kvm_eventfds_allowed =
         (kvm_check_extension(s, KVM_CAP_IOEVENTFD) > 0);
 
-    ret = kvm_arch_init(s);
+    kvm_irqfds_allowed =
+        (kvm_check_extension(s, KVM_CAP_IRQFD) > 0);
+
+    kvm_resamplefds_allowed =
+        (kvm_check_extension(s, KVM_CAP_IRQFD_RESAMPLE) > 0);
+
+    kvm_vm_attributes_allowed =
+        (kvm_check_extension(s, KVM_CAP_VM_ATTRIBUTES) > 0);
+
+    ret = kvm_arch_init(ms, s);
     if (ret < 0) {
         goto err;
     }
 
-    ret = kvm_irqchip_create(s);
+    ret = kvm_irqchip_create(ms, s);
     if (ret < 0) {
         goto err;
     }
@@ -1904,6 +1960,23 @@ int kvm_device_ioctl(int fd, int type, ...)
     return ret;
 }
 
+int kvm_vm_check_attr(KVMState *s, uint32_t group, uint64_t attr)
+{
+    int ret;
+    struct kvm_device_attr attribute = {
+        .group = group,
+        .attr = attr,
+    };
+
+    if (!kvm_vm_attributes_allowed) {
+        return 0;
+    }
+
+    ret = kvm_vm_ioctl(s, KVM_HAS_DEVICE_ATTR, &attribute);
+    /* kvm returns 0 on success for HAS_DEVICE_ATTR */
+    return ret ? 0 : 1;
+}
+
 int kvm_has_sync_mmu(void)
 {
     return kvm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
@@ -2038,10 +2111,6 @@ int kvm_insert_breakpoint(CPUState *cpu, target_ulong addr,
         }
 
         bp = g_malloc(sizeof(struct kvm_sw_breakpoint));
-        if (!bp) {
-            return -ENOMEM;
-        }
-
         bp->pc = addr;
         bp->use_count = 1;
         err = kvm_arch_insert_sw_breakpoint(cpu, bp);