i386/xen: implement HYPERVISOR_sched_op, SCHEDOP_shutdown

It allows to shutdown itself via hypercall with any of the 3 reasons:
  1) self-reboot
  2) shutdown
  3) crash

Implementing SCHEDOP_shutdown sub op let us handle crashes gracefully rather
than leading to triple faults if it remains unimplemented.

In addition, the SHUTDOWN_soft_reset reason is used for kexec, to reset
Xen shared pages and other enlightenments and leave a clean slate for the
new kernel without the hypervisor helpfully writing information at
unexpected addresses.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
[dwmw2: Ditch sched_op_compat which was never available for HVM guests,
        Add SCHEDOP_soft_reset]
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>

3 files changed, 77 insertions, 0 deletions

diff --git a/include/sysemu/kvm_xen.h b/include/sysemu/kvm_xen.h
index 296533f..5dffcc0 100644
--- a/include/sysemu/kvm_xen.h
+++ b/include/sysemu/kvm_xen.h
@@ -12,6 +12,7 @@
 #ifndef QEMU_SYSEMU_KVM_XEN_H
 #define QEMU_SYSEMU_KVM_XEN_H
 
+int kvm_xen_soft_reset(void);
 uint32_t kvm_xen_get_caps(void);
 
 #define kvm_xen_has_cap(cap) (!!(kvm_xen_get_caps() &           \
diff --git a/target/i386/kvm/trace-events b/target/i386/kvm/trace-events
index cd6f842..bb732e1 100644
--- a/target/i386/kvm/trace-events
+++ b/target/i386/kvm/trace-events
@@ -8,3 +8,4 @@ kvm_x86_update_msi_routes(int num) "Updated %d MSI routes"
 
 # xen-emu.c
 kvm_xen_hypercall(int cpu, uint8_t cpl, uint64_t input, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t ret) "xen_hypercall: cpu %d cpl %d input %" PRIu64 " a0 0x%" PRIx64 " a1 0x%" PRIx64 " a2 0x%" PRIx64" ret 0x%" PRIx64
+kvm_xen_soft_reset(void) ""
diff --git a/target/i386/kvm/xen-emu.c b/target/i386/kvm/xen-emu.c
index 56b80a7..4ed8336 100644
--- a/target/i386/kvm/xen-emu.c
+++ b/target/i386/kvm/xen-emu.c
@@ -11,14 +11,17 @@
 
 #include "qemu/osdep.h"
 #include "qemu/log.h"
+#include "qemu/main-loop.h"
 #include "sysemu/kvm_int.h"
 #include "sysemu/kvm_xen.h"
 #include "kvm/kvm_i386.h"
 #include "exec/address-spaces.h"
 #include "xen-emu.h"
 #include "trace.h"
+#include "sysemu/runstate.h"
 
 #include "hw/xen/interface/version.h"
+#include "hw/xen/interface/sched.h"
 
 static int kvm_gva_rw(CPUState *cs, uint64_t gva, void *_buf, size_t sz,
                       bool is_write)
@@ -170,6 +173,75 @@ static bool kvm_xen_hcall_xen_version(struct kvm_xen_exit *exit, X86CPU *cpu,
     return true;
 }
 
+int kvm_xen_soft_reset(void)
+{
+    assert(qemu_mutex_iothread_locked());
+
+    trace_kvm_xen_soft_reset();
+
+    /* Nothing to reset... yet. */
+    return 0;
+}
+
+static int schedop_shutdown(CPUState *cs, uint64_t arg)
+{
+    struct sched_shutdown shutdown;
+    int ret = 0;
+
+    /* No need for 32/64 compat handling */
+    qemu_build_assert(sizeof(shutdown) == 4);
+
+    if (kvm_copy_from_gva(cs, arg, &shutdown, sizeof(shutdown))) {
+        return -EFAULT;
+    }
+
+    switch (shutdown.reason) {
+    case SHUTDOWN_crash:
+        cpu_dump_state(cs, stderr, CPU_DUMP_CODE);
+        qemu_system_guest_panicked(NULL);
+        break;
+
+    case SHUTDOWN_reboot:
+        qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
+        break;
+
+    case SHUTDOWN_poweroff:
+        qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
+        break;
+
+    case SHUTDOWN_soft_reset:
+        qemu_mutex_lock_iothread();
+        ret = kvm_xen_soft_reset();
+        qemu_mutex_unlock_iothread();
+        break;
+
+    default:
+        ret = -EINVAL;
+        break;
+    }
+
+    return ret;
+}
+
+static bool kvm_xen_hcall_sched_op(struct kvm_xen_exit *exit, X86CPU *cpu,
+                                   int cmd, uint64_t arg)
+{
+    CPUState *cs = CPU(cpu);
+    int err = -ENOSYS;
+
+    switch (cmd) {
+    case SCHEDOP_shutdown:
+        err = schedop_shutdown(cs, arg);
+        break;
+
+    default:
+        return false;
+    }
+
+    exit->u.hcall.result = err;
+    return true;
+}
+
 static bool do_kvm_xen_handle_exit(X86CPU *cpu, struct kvm_xen_exit *exit)
 {
     uint16_t code = exit->u.hcall.input;
@@ -180,6 +252,9 @@ static bool do_kvm_xen_handle_exit(X86CPU *cpu, struct kvm_xen_exit *exit)
     }
 
     switch (code) {
+    case __HYPERVISOR_sched_op:
+        return kvm_xen_hcall_sched_op(exit, cpu, exit->u.hcall.params[0],
+                                      exit->u.hcall.params[1]);
     case __HYPERVISOR_xen_version:
         return kvm_xen_hcall_xen_version(exit, cpu, exit->u.hcall.params[0],
                                          exit->u.hcall.params[1]);