1 files changed, 141 insertions, 20 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index ca00daa2f5..b2f1a5bcb5 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -41,6 +41,9 @@
 #include "hw/irq.h"
 #include "sysemu/sev.h"
 #include "sysemu/balloon.h"
+#include "qapi/visitor.h"
+#include "qapi/qapi-types-common.h"
+#include "qapi/qapi-visit-common.h"
 
 #include "hw/boards.h"
 
@@ -92,6 +95,10 @@ struct KVMState
     int max_nested_state_len;
     int many_ioeventfds;
     int intx_set_mask;
+    int kvm_shadow_mem;
+    bool kernel_irqchip_allowed;
+    bool kernel_irqchip_required;
+    bool kernel_irqchip_split;
     bool sync_mmu;
     bool manual_dirty_log_protect;
     /* The man page (and posix) say ioctl numbers are signed int, but
@@ -518,6 +525,27 @@ static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section,
 
 #define ALIGN(x, y)  (((x)+(y)-1) & ~((y)-1))
 
+/* Allocate the dirty bitmap for a slot  */
+static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem)
+{
+    /*
+     * XXX bad kernel interface alert
+     * For dirty bitmap, kernel allocates array of size aligned to
+     * bits-per-long.  But for case when the kernel is 64bits and
+     * the userspace is 32bits, userspace can't align to the same
+     * bits-per-long, since sizeof(long) is different between kernel
+     * and user space.  This way, userspace will provide buffer which
+     * may be 4 bytes less than the kernel will use, resulting in
+     * userspace memory corruption (which is not detectable by valgrind
+     * too, in most cases).
+     * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
+     * a hope that sizeof(long) won't become >8 any time soon.
+     */
+    hwaddr bitmap_size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
+                                        /*HOST_LONG_BITS*/ 64) / 8;
+    mem->dirty_bmap = g_malloc0(bitmap_size);
+}
+
 /**
  * kvm_physical_sync_dirty_bitmap - Sync dirty bitmap from kernel space
  *
@@ -550,23 +578,9 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
             goto out;
         }
 
-        /* XXX bad kernel interface alert
-         * For dirty bitmap, kernel allocates array of size aligned to
-         * bits-per-long.  But for case when the kernel is 64bits and
-         * the userspace is 32bits, userspace can't align to the same
-         * bits-per-long, since sizeof(long) is different between kernel
-         * and user space.  This way, userspace will provide buffer which
-         * may be 4 bytes less than the kernel will use, resulting in
-         * userspace memory corruption (which is not detectable by valgrind
-         * too, in most cases).
-         * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
-         * a hope that sizeof(long) won't become >8 any time soon.
-         */
         if (!mem->dirty_bmap) {
-            hwaddr bitmap_size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
-                                        /*HOST_LONG_BITS*/ 64) / 8;
             /* Allocate on the first log_sync, once and for all */
-            mem->dirty_bmap = g_malloc0(bitmap_size);
+            kvm_memslot_init_dirty_bitmap(mem);
         }
 
         d.dirty_bitmap = mem->dirty_bmap;
@@ -1067,6 +1081,13 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
         mem->ram = ram;
         mem->flags = kvm_mem_flags(mr);
 
+        if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+            /*
+             * Reallocate the bmap; it means it doesn't disappear in
+             * middle of a migrate.
+             */
+            kvm_memslot_init_dirty_bitmap(mem);
+        }
         err = kvm_set_user_memory_region(kml, mem, true);
         if (err) {
             fprintf(stderr, "%s: error registering slot: %s\n", __func__,
@@ -1758,7 +1779,7 @@ void kvm_irqchip_set_qemuirq_gsi(KVMState *s, qemu_irq irq, int gsi)
     g_hash_table_insert(s->gsimap, irq, GINT_TO_POINTER(gsi));
 }
 
-static void kvm_irqchip_create(MachineState *machine, KVMState *s)
+static void kvm_irqchip_create(KVMState *s)
 {
     int ret;
 
@@ -1776,9 +1797,9 @@ static void kvm_irqchip_create(MachineState *machine, KVMState *s)
 
     /* First probe and see if there's a arch-specific hook to create the
      * in-kernel irqchip for us */
-    ret = kvm_arch_irqchip_create(machine, s);
+    ret = kvm_arch_irqchip_create(s);
     if (ret == 0) {
-        if (machine_kernel_irqchip_split(machine)) {
+        if (s->kernel_irqchip_split) {
             perror("Split IRQ chip mode not supported.");
             exit(1);
         } else {
@@ -2049,8 +2070,8 @@ static int kvm_init(MachineState *ms)
         goto err;
     }
 
-    if (machine_kernel_irqchip_allowed(ms)) {
-        kvm_irqchip_create(ms, s);
+    if (s->kernel_irqchip_allowed) {
+        kvm_irqchip_create(s);
     }
 
     if (kvm_eventfds_allowed) {
@@ -2940,6 +2961,93 @@ static bool kvm_accel_has_memory(MachineState *ms, AddressSpace *as,
     return false;
 }
 
+static void kvm_get_kvm_shadow_mem(Object *obj, Visitor *v,
+                                   const char *name, void *opaque,
+                                   Error **errp)
+{
+    KVMState *s = KVM_STATE(obj);
+    int64_t value = s->kvm_shadow_mem;
+
+    visit_type_int(v, name, &value, errp);
+}
+
+static void kvm_set_kvm_shadow_mem(Object *obj, Visitor *v,
+                                   const char *name, void *opaque,
+                                   Error **errp)
+{
+    KVMState *s = KVM_STATE(obj);
+    Error *error = NULL;
+    int64_t value;
+
+    visit_type_int(v, name, &value, &error);
+    if (error) {
+        error_propagate(errp, error);
+        return;
+    }
+
+    s->kvm_shadow_mem = value;
+}
+
+static void kvm_set_kernel_irqchip(Object *obj, Visitor *v,
+                                   const char *name, void *opaque,
+                                   Error **errp)
+{
+    Error *err = NULL;
+    KVMState *s = KVM_STATE(obj);
+    OnOffSplit mode;
+
+    visit_type_OnOffSplit(v, name, &mode, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    } else {
+        switch (mode) {
+        case ON_OFF_SPLIT_ON:
+            s->kernel_irqchip_allowed = true;
+            s->kernel_irqchip_required = true;
+            s->kernel_irqchip_split = false;
+            break;
+        case ON_OFF_SPLIT_OFF:
+            s->kernel_irqchip_allowed = false;
+            s->kernel_irqchip_required = false;
+            s->kernel_irqchip_split = false;
+            break;
+        case ON_OFF_SPLIT_SPLIT:
+            s->kernel_irqchip_allowed = true;
+            s->kernel_irqchip_required = true;
+            s->kernel_irqchip_split = true;
+            break;
+        default:
+            /* The value was checked in visit_type_OnOffSplit() above. If
+             * we get here, then something is wrong in QEMU.
+             */
+            abort();
+        }
+    }
+}
+
+bool kvm_kernel_irqchip_allowed(void)
+{
+    return kvm_state->kernel_irqchip_allowed;
+}
+
+bool kvm_kernel_irqchip_required(void)
+{
+    return kvm_state->kernel_irqchip_required;
+}
+
+bool kvm_kernel_irqchip_split(void)
+{
+    return kvm_state->kernel_irqchip_split;
+}
+
+static void kvm_accel_instance_init(Object *obj)
+{
+    KVMState *s = KVM_STATE(obj);
+
+    s->kvm_shadow_mem = -1;
+}
+
 static void kvm_accel_class_init(ObjectClass *oc, void *data)
 {
     AccelClass *ac = ACCEL_CLASS(oc);
@@ -2947,11 +3055,24 @@ static void kvm_accel_class_init(ObjectClass *oc, void *data)
     ac->init_machine = kvm_init;
     ac->has_memory = kvm_accel_has_memory;
     ac->allowed = &kvm_allowed;
+
+    object_class_property_add(oc, "kernel-irqchip", "on|off|split",
+        NULL, kvm_set_kernel_irqchip,
+        NULL, NULL, &error_abort);
+    object_class_property_set_description(oc, "kernel-irqchip",
+        "Configure KVM in-kernel irqchip", &error_abort);
+
+    object_class_property_add(oc, "kvm-shadow-mem", "int",
+        kvm_get_kvm_shadow_mem, kvm_set_kvm_shadow_mem,
+        NULL, NULL, &error_abort);
+    object_class_property_set_description(oc, "kvm-shadow-mem",
+        "KVM shadow MMU size", &error_abort);
 }
 
 static const TypeInfo kvm_accel_type = {
     .name = TYPE_KVM_ACCEL,
     .parent = TYPE_ACCEL,
+    .instance_init = kvm_accel_instance_init,
     .class_init = kvm_accel_class_init,
     .instance_size = sizeof(KVMState),
 };