1 files changed, 95 insertions, 35 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index f89568b..a106d1b 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -33,8 +33,9 @@
 #include "system/cpus.h"
 #include "system/accel-blocker.h"
 #include "qemu/bswap.h"
-#include "exec/memory.h"
-#include "exec/ram_addr.h"
+#include "exec/tswap.h"
+#include "system/memory.h"
+#include "system/ram_addr.h"
 #include "qemu/event_notifier.h"
 #include "qemu/main-loop.h"
 #include "trace.h"
@@ -57,6 +58,11 @@
 #include <sys/eventfd.h>
 #endif
 
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+# define KVM_HAVE_MCE_INJECTION 1
+#endif
+
+
 /* KVM uses PAGE_SIZE in its definition of KVM_COALESCED_MMIO_MAX. We
  * need to use the real host PAGE_SIZE, as that's what KVM will use.
  */
@@ -93,6 +99,7 @@ bool kvm_allowed;
 bool kvm_readonly_mem_allowed;
 bool kvm_vm_attributes_allowed;
 bool kvm_msi_use_devid;
+bool kvm_pre_fault_memory_supported;
 static bool kvm_has_guest_debug;
 static int kvm_sstep_flags;
 static bool kvm_immediate_exit;
@@ -437,9 +444,8 @@ int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id)
     return kvm_fd;
 }
 
-static void kvm_reset_parked_vcpus(void *param)
+static void kvm_reset_parked_vcpus(KVMState *s)
 {
-    KVMState *s = param;
     struct KVMParkedVcpu *cpu;
 
     QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) {
@@ -447,7 +453,13 @@ static void kvm_reset_parked_vcpus(void *param)
     }
 }
 
-int kvm_create_vcpu(CPUState *cpu)
+/**
+ * kvm_create_vcpu - Gets a parked KVM vCPU or creates a KVM vCPU
+ * @cpu: QOM CPUState object for which KVM vCPU has to be fetched/created.
+ *
+ * @returns: 0 when success, errno (<0) when failed.
+ */
+static int kvm_create_vcpu(CPUState *cpu)
 {
     unsigned long vcpu_id = kvm_arch_vcpu_id(cpu);
     KVMState *s = kvm_state;
@@ -466,7 +478,9 @@ int kvm_create_vcpu(CPUState *cpu)
 
     cpu->kvm_fd = kvm_fd;
     cpu->kvm_state = s;
-    cpu->vcpu_dirty = true;
+    if (!s->guest_state_protected) {
+        cpu->vcpu_dirty = true;
+    }
     cpu->dirty_pages = 0;
     cpu->throttle_us_per_full = 0;
 
@@ -507,16 +521,23 @@ static int do_kvm_destroy_vcpu(CPUState *cpu)
         goto err;
     }
 
+    /* If I am the CPU that created coalesced_mmio_ring, then discard it */
+    if (s->coalesced_mmio_ring == (void *)cpu->kvm_run + PAGE_SIZE) {
+        s->coalesced_mmio_ring = NULL;
+    }
+
     ret = munmap(cpu->kvm_run, mmap_size);
     if (ret < 0) {
         goto err;
     }
+    cpu->kvm_run = NULL;
 
     if (cpu->kvm_dirty_gfns) {
         ret = munmap(cpu->kvm_dirty_gfns, s->kvm_dirty_ring_bytes);
         if (ret < 0) {
             goto err;
         }
+        cpu->kvm_dirty_gfns = NULL;
     }
 
     kvm_park_vcpu(cpu);
@@ -540,6 +561,11 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp)
 
     trace_kvm_init_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
 
+    ret = kvm_arch_pre_create_vcpu(cpu, errp);
+    if (ret < 0) {
+        goto err;
+    }
+
     ret = kvm_create_vcpu(cpu);
     if (ret < 0) {
         error_setg_errno(errp, -ret,
@@ -595,6 +621,31 @@ err:
     return ret;
 }
 
+void kvm_close(void)
+{
+    CPUState *cpu;
+
+    if (!kvm_state || kvm_state->fd == -1) {
+        return;
+    }
+
+    CPU_FOREACH(cpu) {
+        cpu_remove_sync(cpu);
+        close(cpu->kvm_fd);
+        cpu->kvm_fd = -1;
+        close(cpu->kvm_vcpu_stats_fd);
+        cpu->kvm_vcpu_stats_fd = -1;
+    }
+
+    if (kvm_state && kvm_state->fd != -1) {
+        close(kvm_state->vmfd);
+        kvm_state->vmfd = -1;
+        close(kvm_state->fd);
+        kvm_state->fd = -1;
+    }
+    kvm_state = NULL;
+}
+
 /*
  * dirty pages logging control
  */
@@ -1314,21 +1365,22 @@ bool kvm_hwpoisoned_mem(void)
 
 static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size)
 {
-#if HOST_BIG_ENDIAN != TARGET_BIG_ENDIAN
-    /* The kernel expects ioeventfd values in HOST_BIG_ENDIAN
-     * 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;
+    if (target_needs_bswap()) {
+        /*
+         * The kernel expects ioeventfd values in HOST_BIG_ENDIAN
+         * 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, swapping back.
+         */
+        switch (size) {
+        case 2:
+            val = bswap16(val);
+            break;
+        case 4:
+            val = bswap32(val);
+            break;
+        }
     }
-#endif
     return val;
 }
 
@@ -2420,7 +2472,7 @@ static int kvm_recommended_vcpus(KVMState *s)
 
 static int kvm_max_vcpus(KVMState *s)
 {
-    int ret = kvm_check_extension(s, KVM_CAP_MAX_VCPUS);
+    int ret = kvm_vm_check_extension(s, KVM_CAP_MAX_VCPUS);
     return (ret) ? ret : kvm_recommended_vcpus(s);
 }
 
@@ -2450,13 +2502,10 @@ uint32_t kvm_dirty_ring_size(void)
     return kvm_state->kvm_dirty_ring_size;
 }
 
-static int do_kvm_create_vm(MachineState *ms, int type)
+static int do_kvm_create_vm(KVMState *s, int type)
 {
-    KVMState *s;
     int ret;
 
-    s = KVM_STATE(ms->accelerator);
-
     do {
         ret = kvm_ioctl(s, KVM_CREATE_VM, type);
     } while (ret == -EINTR);
@@ -2553,7 +2602,7 @@ static int kvm_setup_dirty_ring(KVMState *s)
     return 0;
 }
 
-static int kvm_init(MachineState *ms)
+static int kvm_init(AccelState *as, MachineState *ms)
 {
     MachineClass *mc = MACHINE_GET_CLASS(ms);
     static const char upgrade_note[] =
@@ -2568,15 +2617,13 @@ static int kvm_init(MachineState *ms)
         { /* end of list */ }
     }, *nc = num_cpus;
     int soft_vcpus_limit, hard_vcpus_limit;
-    KVMState *s;
+    KVMState *s = KVM_STATE(as);
     const KVMCapabilityInfo *missing_cap;
     int ret;
     int type;
 
     qemu_mutex_init(&kml_slots_lock);
 
-    s = KVM_STATE(ms->accelerator);
-
     /*
      * On systems where the kernel can support different base page
      * sizes, host page size may be different from TARGET_PAGE_SIZE,
@@ -2628,7 +2675,7 @@ static int kvm_init(MachineState *ms)
         goto err;
     }
 
-    ret = do_kvm_create_vm(ms, type);
+    ret = do_kvm_create_vm(s, type);
     if (ret < 0) {
         goto err;
     }
@@ -2732,13 +2779,13 @@ static int kvm_init(MachineState *ms)
         kvm_check_extension(s, KVM_CAP_GUEST_MEMFD) &&
         kvm_check_extension(s, KVM_CAP_USER_MEMORY2) &&
         (kvm_supported_memory_attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE);
+    kvm_pre_fault_memory_supported = kvm_vm_check_extension(s, KVM_CAP_PRE_FAULT_MEMORY);
 
     if (s->kernel_irqchip_split == ON_OFF_AUTO_AUTO) {
         s->kernel_irqchip_split = mc->default_kernel_irqchip_split ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
     }
 
     qemu_register_reset(kvm_unpoison_all, NULL);
-    qemu_register_reset(kvm_reset_parked_vcpus, s);
 
     if (s->kernel_irqchip_allowed) {
         kvm_irqchip_create(s);
@@ -2908,6 +2955,10 @@ static void do_kvm_cpu_synchronize_post_reset(CPUState *cpu, run_on_cpu_data arg
 void kvm_cpu_synchronize_post_reset(CPUState *cpu)
 {
     run_on_cpu(cpu, do_kvm_cpu_synchronize_post_reset, RUN_ON_CPU_NULL);
+
+    if (cpu == first_cpu) {
+        kvm_reset_parked_vcpus(kvm_state);
+    }
 }
 
 static void do_kvm_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg)
@@ -3073,6 +3124,15 @@ int kvm_convert_memory(hwaddr start, hwaddr size, bool to_private)
     addr = memory_region_get_ram_ptr(mr) + section.offset_within_region;
     rb = qemu_ram_block_from_host(addr, false, &offset);
 
+    ret = ram_block_attributes_state_change(RAM_BLOCK_ATTRIBUTES(mr->rdm),
+                                            offset, size, to_private);
+    if (ret) {
+        error_report("Failed to notify the listener the state change of "
+                     "(0x%"HWADDR_PRIx" + 0x%"HWADDR_PRIx") to %s",
+                     start, size, to_private ? "private" : "shared");
+        goto out_unref;
+    }
+
     if (to_private) {
         if (rb->page_size != qemu_real_host_page_size()) {
             /*
@@ -3758,10 +3818,10 @@ int kvm_get_one_reg(CPUState *cs, uint64_t id, void *target)
     return r;
 }
 
-static bool kvm_accel_has_memory(MachineState *ms, AddressSpace *as,
+static bool kvm_accel_has_memory(AccelState *accel, AddressSpace *as,
                                  hwaddr start_addr, hwaddr size)
 {
-    KVMState *kvm = KVM_STATE(ms->accelerator);
+    KVMState *kvm = KVM_STATE(accel);
     int i;
 
     for (i = 0; i < kvm->nr_as; ++i) {
@@ -3952,12 +4012,12 @@ static void kvm_accel_instance_init(Object *obj)
  * Returns: SSTEP_* flags that KVM supports for guest debug. The
  * support is probed during kvm_init()
  */
-static int kvm_gdbstub_sstep_flags(void)
+static int kvm_gdbstub_sstep_flags(AccelState *as)
 {
     return kvm_sstep_flags;
 }
 
-static void kvm_accel_class_init(ObjectClass *oc, void *data)
+static void kvm_accel_class_init(ObjectClass *oc, const void *data)
 {
     AccelClass *ac = ACCEL_CLASS(oc);
     ac->name = "KVM";