[Qemu-devel] [PATCH 4/8] kvm: First step to push iothread lock out of inner run loop

[Paolo Bonzini <pbonzini@redhat.com>]

From: Jan Kiszka <jan.kiszka@siemens.com>

This opens the path to get rid of the iothread lock on vmexits in KVM
mode. On x86, the in-kernel irqchips has to be used because we otherwise
need to synchronize APIC and other per-cpu state accesses that could be
changed concurrently.

s390x and ARM should be fine without specific locking as their
pre/post-run callbacks are empty. MIPS and POWER require locking for
the pre-run callback.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 kvm-all.c         | 14 ++++++++++++--
 target-i386/kvm.c | 18 ++++++++++++++++++
 target-mips/kvm.c |  4 ++++
 target-ppc/kvm.c  |  4 ++++
 4 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/kvm-all.c b/kvm-all.c
index 55025cc..8da1deb 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -1765,6 +1765,8 @@ int kvm_cpu_exec(CPUState *cpu)
         return EXCP_HLT;
     }
 
+    qemu_mutex_unlock_iothread();
+
     do {
         if (cpu->kvm_vcpu_dirty) {
             kvm_arch_put_registers(cpu, KVM_PUT_RUNTIME_STATE);
@@ -1781,11 +1783,9 @@ int kvm_cpu_exec(CPUState *cpu)
              */
             qemu_cpu_kick_self();
         }
-        qemu_mutex_unlock_iothread();
 
         run_ret = kvm_vcpu_ioctl(cpu, KVM_RUN, 0);
 
-        qemu_mutex_lock_iothread();
         kvm_arch_post_run(cpu, run);
 
         if (run_ret < 0) {
@@ -1804,19 +1804,23 @@ int kvm_cpu_exec(CPUState *cpu)
         switch (run->exit_reason) {
         case KVM_EXIT_IO:
             DPRINTF("handle_io\n");
+            qemu_mutex_lock_iothread();
             kvm_handle_io(run->io.port,
                           (uint8_t *)run + run->io.data_offset,
                           run->io.direction,
                           run->io.size,
                           run->io.count);
+            qemu_mutex_unlock_iothread();
             ret = 0;
             break;
         case KVM_EXIT_MMIO:
             DPRINTF("handle_mmio\n");
+            qemu_mutex_lock_iothread();
             cpu_physical_memory_rw(run->mmio.phys_addr,
                                    run->mmio.data,
                                    run->mmio.len,
                                    run->mmio.is_write);
+            qemu_mutex_unlock_iothread();
             ret = 0;
             break;
         case KVM_EXIT_IRQ_WINDOW_OPEN:
@@ -1825,7 +1829,9 @@ int kvm_cpu_exec(CPUState *cpu)
             break;
         case KVM_EXIT_SHUTDOWN:
             DPRINTF("shutdown\n");
+            qemu_mutex_lock_iothread();
             qemu_system_reset_request();
+            qemu_mutex_unlock_iothread();
             ret = EXCP_INTERRUPT;
             break;
         case KVM_EXIT_UNKNOWN:
@@ -1854,11 +1860,15 @@ int kvm_cpu_exec(CPUState *cpu)
             break;
         default:
             DPRINTF("kvm_arch_handle_exit\n");
+            qemu_mutex_lock_iothread();
             ret = kvm_arch_handle_exit(cpu, run);
+            qemu_mutex_unlock_iothread();
             break;
         }
     } while (ret == 0);
 
+    qemu_mutex_lock_iothread();
+
     if (ret < 0) {
         cpu_dump_state(cpu, stderr, fprintf, CPU_DUMP_CODE);
         vm_stop(RUN_STATE_INTERNAL_ERROR);
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 41d09e5..94cff8c 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -2191,7 +2191,10 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run)
 
     /* Inject NMI */
     if (cpu->interrupt_request & CPU_INTERRUPT_NMI) {
+        qemu_mutex_lock_iothread();
         cpu->interrupt_request &= ~CPU_INTERRUPT_NMI;
+        qemu_mutex_unlock_iothread();
+
         DPRINTF("injected NMI\n");
         ret = kvm_vcpu_ioctl(cpu, KVM_NMI);
         if (ret < 0) {
@@ -2200,6 +2203,10 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run)
         }
     }
 
+    if (!kvm_irqchip_in_kernel()) {
+        qemu_mutex_lock_iothread();
+    }
+
     /* Force the VCPU out of its inner loop to process any INIT requests
      * or (for userspace APIC, but it is cheap to combine the checks here)
      * pending TPR access reports.
@@ -2243,6 +2250,8 @@ void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run)
 
         DPRINTF("setting tpr\n");
         run->cr8 = cpu_get_apic_tpr(x86_cpu->apic_state);
+
+        qemu_mutex_unlock_iothread();
     }
 }
 
@@ -2256,8 +2265,17 @@ void kvm_arch_post_run(CPUState *cpu, struct kvm_run *run)
     } else {
         env->eflags &= ~IF_MASK;
     }
+
+    /* We need to protect the apic state against concurrent accesses from
+     * different threads in case the userspace irqchip is used. */
+    if (!kvm_irqchip_in_kernel()) {
+        qemu_mutex_lock_iothread();
+    }
     cpu_set_apic_tpr(x86_cpu->apic_state, run->cr8);
     cpu_set_apic_base(x86_cpu->apic_state, run->apic_base);
+    if (!kvm_irqchip_in_kernel()) {
+        qemu_mutex_unlock_iothread();
+    }
 }
 
 int kvm_arch_process_async_events(CPUState *cs)
diff --git a/target-mips/kvm.c b/target-mips/kvm.c
index 4d1f7ea..7f02be7 100644
--- a/target-mips/kvm.c
+++ b/target-mips/kvm.c
@@ -98,6 +98,8 @@ void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
     int r;
     struct kvm_mips_interrupt intr;
 
+    qemu_mutex_lock_iothread();
+
     if ((cs->interrupt_request & CPU_INTERRUPT_HARD) &&
             cpu_mips_io_interrupts_pending(cpu)) {
         intr.cpu = -1;
@@ -108,6 +110,8 @@ void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
                          __func__, cs->cpu_index, intr.irq);
         }
     }
+
+    qemu_mutex_unlock_iothread();
 }
 
 void kvm_arch_post_run(CPUState *cs, struct kvm_run *run)
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 12328a4..ce2498a 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -1241,6 +1241,8 @@ void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
     int r;
     unsigned irq;
 
+    qemu_mutex_lock_iothread();
+
     /* PowerPC QEMU tracks the various core input pins (interrupt, critical
      * interrupt, reset, etc) in PPC-specific env->irq_input_state. */
     if (!cap_interrupt_level &&
@@ -1268,6 +1270,8 @@ void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run)
     /* We don't know if there are more interrupts pending after this. However,
      * the guest will return to userspace in the course of handling this one
      * anyways, so we will get a chance to deliver the rest. */
+
+    qemu_mutex_unlock_iothread();
 }
 
 void kvm_arch_post_run(CPUState *cpu, struct kvm_run *run)
-- 
2.3.0