Re: [Qemu-devel] [PATCH v6 1/2] kvm: support -overcommit cpu-pm=on|off

[Eduardo Habkost]

On Tue, Jun 26, 2018 at 06:16:24PM +0300, Michael S. Tsirkin wrote:
> On Tue, Jun 26, 2018 at 05:13:18PM +0200, Igor Mammedov wrote:
> > On Tue, 26 Jun 2018 17:06:12 +0300
> > "Michael S. Tsirkin" <address@hidden> wrote:
> > 
> > > On Mon, Jun 25, 2018 at 11:40:12AM +0200, Igor Mammedov wrote:
> > > > On Fri, 22 Jun 2018 22:22:05 +0300
> > > > "Michael S. Tsirkin" <address@hidden> wrote:
> > > >   
> > > > > With this flag, kvm allows guest to control host CPU power state.  
> > > > > This
> > > > > increases latency for other processes using same host CPU in an
> > > > > unpredictable way, but if decreases idle entry/exit times for the
> > > > > running VCPU, so to use it QEMU needs a hint about whether host CPU is
> > > > > overcommitted, hence the flag name.
> > > > > 
> > > > > Follow-up patches will expose this capability to guest
> > > > > (using mwait leaf).
> > > > > 
> > > > > Based on a patch by Wanpeng Li <address@hidden> .
> > > > > 
> > > > > Signed-off-by: Michael S. Tsirkin <address@hidden>
> > > > > ---
> > > > >  include/sysemu/sysemu.h |  1 +
> > > > >  target/i386/kvm.c       | 23 +++++++++++++++++++++++
> > > > >  vl.c                    | 32 +++++++++++++++++++++++++++++++-
> > > > >  qemu-options.hx         | 27 +++++++++++++++++++++++++--
> > > > >  4 files changed, 80 insertions(+), 3 deletions(-)
> > > > > 
> > > > > diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
> > > > > index e893f72f3b..b921c6f3b7 100644
> > > > > --- a/include/sysemu/sysemu.h
> > > > > +++ b/include/sysemu/sysemu.h
> > > > > @@ -128,6 +128,7 @@ extern bool boot_strict;
> > > > >  extern uint8_t *boot_splash_filedata;
> > > > >  extern size_t boot_splash_filedata_size;
> > > > >  extern bool enable_mlock;
> > > > > +extern bool enable_cpu_pm;
> > > > >  extern uint8_t qemu_extra_params_fw[2];
> > > > >  extern QEMUClockType rtc_clock;
> > > > >  extern const char *mem_path;
> > > > > diff --git a/target/i386/kvm.c b/target/i386/kvm.c
> > > > > index 44f70733e7..cf9107be4b 100644
> > > > > --- a/target/i386/kvm.c
> > > > > +++ b/target/i386/kvm.c
> > > > > @@ -1357,6 +1357,29 @@ int kvm_arch_init(MachineState *ms, KVMState 
> > > > > *s)
> > > > >          smram_machine_done.notify = register_smram_listener;
> > > > >          qemu_add_machine_init_done_notifier(&smram_machine_done);
> > > > >      }
> > > > > +
> > > > > +    if (enable_cpu_pm) {
> > > > > +        int disable_exits = kvm_check_extension(s, 
> > > > > KVM_CAP_X86_DISABLE_EXITS);
> > > > > +        int ret;
> > > > > +
> > > > > +/* Work around for kernel header with a typo. TODO: fix header and 
> > > > > drop. */
> > > > > +#if defined(KVM_X86_DISABLE_EXITS_HTL) && 
> > > > > !defined(KVM_X86_DISABLE_EXITS_HLT)
> > > > > +#define KVM_X86_DISABLE_EXITS_HLT KVM_X86_DISABLE_EXITS_HTL
> > > > > +#endif
> > > > > +        if (disable_exits) {
> > > > > +            disable_exits &= (KVM_X86_DISABLE_EXITS_MWAIT |
> > > > > +                              KVM_X86_DISABLE_EXITS_HLT |
> > > > > +                              KVM_X86_DISABLE_EXITS_PAUSE);
> > > > > +        }
> > > > > +
> > > > > +        ret = kvm_vm_enable_cap(s, KVM_CAP_X86_DISABLE_EXITS, 0,
> > > > > +                                disable_exits);
> > > > > +        if (ret < 0) {
> > > > > +            error_report("kvm: guest stopping CPU not supported: %s",
> > > > > +                         strerror(-ret));
> > > > > +        }
> > > > > +    }
> > > > > +
> > > > >      return 0;
> > > > >  }
> > > > >  
> > > > > diff --git a/vl.c b/vl.c
> > > > > index 06031715ac..c9530efed5 100644
> > > > > --- a/vl.c
> > > > > +++ b/vl.c
> > > > > @@ -142,6 +142,7 @@ ram_addr_t ram_size;
> > > > >  const char *mem_path = NULL;
> > > > >  int mem_prealloc = 0; /* force preallocation of physical target 
> > > > > memory */
> > > > >  bool enable_mlock = false;
> > > > > +bool enable_cpu_pm = false;
> > > > >  int nb_nics;
> > > > >  NICInfo nd_table[MAX_NICS];
> > > > >  int autostart;
> > > > > @@ -390,6 +391,22 @@ static QemuOptsList qemu_realtime_opts = {
> > > > >      },
> > > > >  };
> > > > >  
> > > > > +static QemuOptsList qemu_overcommit_opts = {
> > > > > +    .name = "overcommit",
> > > > > +    .head = QTAILQ_HEAD_INITIALIZER(qemu_overcommit_opts.head),
> > > > > +    .desc = {
> > > > > +        {
> > > > > +            .name = "mem-lock",
> > > > > +            .type = QEMU_OPT_BOOL,
> > > > > +        },
> > > > > +        {
> > > > > +            .name = "cpu-pm",
> > > > > +            .type = QEMU_OPT_BOOL,
> > > > > +        },
> > > > > +        { /* end of list */ }
> > > > > +    },
> > > > > +};
> > > > > +
> > > > >  static QemuOptsList qemu_msg_opts = {
> > > > >      .name = "msg",
> > > > >      .head = QTAILQ_HEAD_INITIALIZER(qemu_msg_opts.head),
> > > > > @@ -3903,7 +3920,20 @@ int main(int argc, char **argv, char **envp)
> > > > >                  if (!opts) {
> > > > >                      exit(1);
> > > > >                  }
> > > > > -                enable_mlock = qemu_opt_get_bool(opts, "mlock", 
> > > > > true);
> > > > > +                /* Don't override the -overcommit option if set */
> > > > > +                enable_mlock = enable_mlock ||
> > > > > +                    qemu_opt_get_bool(opts, "mlock", true);
> > > > > +                break;
> > > > > +            case QEMU_OPTION_overcommit:
> > > > > +                opts = 
> > > > > qemu_opts_parse_noisily(qemu_find_opts("overcommit"),
> > > > > +                                               optarg, false);
> > > > > +                if (!opts) {
> > > > > +                    exit(1);
> > > > > +                }
> > > > > +                /* Don't override the -realtime option if set */
> > > > > +                enable_mlock = enable_mlock ||
> > > > > +                    qemu_opt_get_bool(opts, "mem-lock", false);
> > > > > +                enable_cpu_pm = qemu_opt_get_bool(opts, "cpu-pm", 
> > > > > false);  
> > > > should we error out or complain if the option can't be used
> > > > /i.e. in case of non kvm accelerator/
> > > > instead of silently ignoring it
> > > > and making user wonder why it doesn't work?  
> > > 
> > > 
> > > Well it also only applies with -cpu host right now.
> > > And guest works fine, even if it's somewhat slower.
> > > 
> > > As there's no interface to discover which configurations
> > > work, I *suspect* it's easier for management if we keep guest
> > > running rather than fail and make it guess.
> > 
> > not perfect but better than nothing
> 
> So the point is that the flag means "allow guest to do
> power management". Whether guest knows it can do it
> is a separate question.

Exactly.  The way I see it, the flag is just about allowing (not
requiring) the device emulation code (and the guest code running
on the VCPU) to have more control of the host CPU.

If necessary we can introduce an option to make mwait and/or
disable-exits mandatory.  But I'm not sure management software
would really use it, and it doesn't need to be on the first
version.

-- 
Eduardo