Refactor persistent CPU state

This patch reworks the KVM-related layout and encoding of the CPU state
to be saved to disk or migrated. The goal is to define a format, version
9, that is also acceptable for upstream and can later be merged into
QEMU. Besides unconditionally writing KVM states, this format compresses
interrupt_bitmap into a single number as there can be no more than one
pending IRQ at a time.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 44 insertions, 7 deletions

diff --git a/target-i386/machine.c b/target-i386/machine.c
index 124f8dcf5..f280d3d2a 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -29,7 +29,8 @@ void cpu_save(QEMUFile *f, void *opaque)
     uint16_t fptag, fpus, fpuc, fpregs_format;
     uint32_t hflags;
     int32_t a20_mask;
-    int i;
+    int32_t pending_irq;
+    int i, bit;
 
     cpu_synchronize_state(env, 0);
 
@@ -141,11 +142,21 @@ void cpu_save(QEMUFile *f, void *opaque)
         qemu_put_be64s(f, &env->mtrr_var[i].mask);
     }
 
-    for (i = 0; i < sizeof(env->interrupt_bitmap)/8; i++) {
-        qemu_put_be64s(f, &env->interrupt_bitmap[i]);
+    /* KVM-related states */
+
+    /* There can only be one pending IRQ set in the bitmap at a time, so try
+       to find it and save its number instead (-1 for none). */
+    pending_irq = -1;
+    for (i = 0; i < ARRAY_SIZE(env->interrupt_bitmap); i++) {
+        bit = ffsll(env->interrupt_bitmap[i]);
+        if (bit) {
+            pending_irq = i * 64 + bit - 1;
+            break;
+        }
     }
-    qemu_put_be64s(f, &env->tsc);
+    qemu_put_sbe32s(f, &pending_irq);
     qemu_put_be32s(f, &env->mp_state);
+    qemu_put_be64s(f, &env->tsc);
 }
 
 #ifdef USE_X86LDOUBLE
@@ -179,6 +190,7 @@ int cpu_load(QEMUFile *f, void *opaque, int version_id)
     uint32_t hflags;
     uint16_t fpus, fpuc, fptag, fpregs_format;
     int32_t a20_mask;
+    int32_t pending_irq;
 
     if (version_id < 3 || version_id > CPU_SAVE_VERSION)
         return -EINVAL;
@@ -324,12 +336,16 @@ int cpu_load(QEMUFile *f, void *opaque, int version_id)
             qemu_get_be64s(f, &env->mtrr_var[i].mask);
         }
     }
+
     if (version_id >= 9) {
-        for (i = 0; i < sizeof(env->interrupt_bitmap)/8; i++) {
-            qemu_get_be64s(f, &env->interrupt_bitmap[i]);
+        qemu_get_sbe32s(f, &pending_irq);
+        memset(&env->interrupt_bitmap, 0, sizeof(env->interrupt_bitmap));
+        if (pending_irq >= 0) {
+            env->interrupt_bitmap[pending_irq / 64] |=
+                (uint64_t)1 << (pending_irq % 64);
         }
-        qemu_get_be64s(f, &env->tsc);
         qemu_get_be32s(f, &env->mp_state);
+        qemu_get_be64s(f, &env->tsc);
     }
 
     /* XXX: ensure compatiblity for halted bit ? */
@@ -337,5 +353,26 @@ int cpu_load(QEMUFile *f, void *opaque, int version_id)
     env->hflags = hflags;
     tlb_flush(env, 1);
     cpu_synchronize_state(env, 1);
+    if (kvm_enabled()) {
+        /* when in-kernel irqchip is used, env->halted causes deadlock
+           because no userspace IRQs will ever clear this flag */
+        env->halted = 0;
+        if (version_id < 9) {
+            for (i = 0; i < sizeof(env->interrupt_bitmap)/8; i++) {
+                qemu_get_be64s(f, &env->interrupt_bitmap[i]);
+            }
+            qemu_get_be64s(f, &env->tsc);
+            kvm_load_registers(env);
+            kvm_load_tsc(env);
+            if (version_id >= 5) {
+                qemu_get_be32s(f, &env->mp_state);
+                kvm_load_mpstate(env);
+            }
+        } else {
+            kvm_load_registers(env);
+            kvm_load_tsc(env);
+            kvm_load_mpstate(env);
+        }
+    }
     return 0;
 }