On Fri, Oct 04, 2013 at 06:18:42PM +0200, Igor Mammedov wrote:
> On Thu, 3 Oct 2013 18:05:35 +0300
> "Michael S. Tsirkin" <m...@redhat.com> wrote:
>
> > This defines a structure that will be used to fill in acpi tables
> > where relevant properties are not yet available using QOM.
> >
> > Reviewed-by: Laszlo Ersek <ler...@redhat.com>
> > Reviewed-by: Gerd Hoffmann <kra...@redhat.com>
> > Tested-by: Gerd Hoffmann <kra...@redhat.com>
> > Signed-off-by: Michael S. Tsirkin <m...@redhat.com>
> > ---
> > include/hw/i386/pc.h | 9 +++++++++
> > hw/i386/pc.c | 31 +++++++++++++++++++++++++++++++
> > 2 files changed, 40 insertions(+)
> >
> > diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
> > index 9b2ddc4..085a621 100644
> > --- a/include/hw/i386/pc.h
> > +++ b/include/hw/i386/pc.h
> > @@ -9,6 +9,9 @@
> > #include "hw/i386/ioapic.h"
> >
> > #include "qemu/range.h"
> > +#include "qemu/bitmap.h"
> > +#include "sysemu/sysemu.h"
> > +#include "hw/pci/pci.h"
> >
> > /* PC-style peripherals (also used by other machines). */
> >
> > @@ -20,6 +23,12 @@ typedef struct PcPciInfo {
> > struct PcGuestInfo {
> > bool has_pci_info;
> > bool isapc_ram_fw;
> > + hwaddr ram_size;
> > + unsigned apic_id_limit;
> > + bool apic_xrupt_override;
> > + uint64_t numa_nodes;
> > + uint64_t *node_mem;
> > + uint64_t *node_cpu;
> > FWCfgState *fw_cfg;
> > };
> >
> > diff --git a/hw/i386/pc.c b/hw/i386/pc.c
> > index 0c313fe..dbae9da 100644
> > --- a/hw/i386/pc.c
> > +++ b/hw/i386/pc.c
> > @@ -1028,6 +1028,23 @@ static void pc_fw_cfg_guest_info(PcGuestInfo
> > *guest_info)
> > fw_cfg_add_file(guest_info->fw_cfg, "etc/pci-info", info, sizeof
> > *info);
> > }
> >
> > +static void pc_set_cpu_guest_info(CPUState *cpu, PcGuestInfo *guest_info)
> > +{
> > + CPUClass *klass = CPU_GET_CLASS(cpu);
> > + uint64_t apic_id = klass->get_arch_id(cpu);
> > + int j;
> > +
> > + assert(apic_id < guest_info->apic_id_limit);
> > +
> > + for (j = 0; j < guest_info->numa_nodes; j++) {
> > + assert(cpu->cpu_index < max_cpus);
> > + if (test_bit(cpu->cpu_index, node_cpumask[j])) {
> > + guest_info->node_cpu[apic_id] = cpu_to_le64(j);
> > + break;
> > + }
> > + }
> > +}
> > +
> > typedef struct PcGuestInfoState {
> > PcGuestInfo info;
> > Notifier machine_done;
> > @@ -1047,6 +1064,20 @@ PcGuestInfo *pc_guest_info_init(ram_addr_t
> > below_4g_mem_size,
> > {
> > PcGuestInfoState *guest_info_state = g_malloc0(sizeof
> > *guest_info_state);
> > PcGuestInfo *guest_info = &guest_info_state->info;
> > + CPUState *cpu;
> > +
> > + guest_info->ram_size = below_4g_mem_size + above_4g_mem_size;
> > + guest_info->apic_id_limit = pc_apic_id_limit(max_cpus);
> > + guest_info->apic_xrupt_override = kvm_allows_irq0_override();
> > + guest_info->numa_nodes = nb_numa_nodes;
> > + guest_info->node_mem = g_memdup(node_mem, guest_info->numa_nodes *
> > + sizeof *guest_info->node_mem);
> > + guest_info->node_cpu = g_malloc0(guest_info->apic_id_limit *
> > + sizeof *guest_info->node_cpu);
> > +
> > + CPU_FOREACH(cpu) {
> > + pc_set_cpu_guest_info(cpu, guest_info);
> > + }
>
> pc_guest_info_init() is called only once, now lets suppose we hotplug CPUs
> and then reboot guest. Hotadded CPUs won't be accounted in guest_info.node_cpu
> since it's initialized only once and is never updated. As result guest will
> get stale SRAT table.
>
> Using a callback in acpi_setup/update could allow to get an updated
> guest_info.
Actually we can fix this simpler just by filling in
all numa info ahead of the time.
Something like the following should fix this, right?
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index bbf11ed..a7fcbf9 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1029,23 +1029,6 @@ static void pc_fw_cfg_guest_info(PcGuestInfo *guest_info)
fw_cfg_add_file(guest_info->fw_cfg, "etc/pci-info", info, sizeof *info);
}
-static void pc_set_cpu_guest_info(CPUState *cpu, PcGuestInfo *guest_info)
-{
- CPUClass *klass = CPU_GET_CLASS(cpu);
- uint64_t apic_id = klass->get_arch_id(cpu);
- int j;
-
- assert(apic_id < guest_info->apic_id_limit);
-
- for (j = 0; j < guest_info->numa_nodes; j++) {
- assert(cpu->cpu_index < max_cpus);
- if (test_bit(cpu->cpu_index, node_cpumask[j])) {
- guest_info->node_cpu[apic_id] = cpu_to_le64(j);
- break;
- }
- }
-}
-
typedef struct PcGuestInfoState {
PcGuestInfo info;
Notifier machine_done;
@@ -1066,7 +1049,7 @@ PcGuestInfo *pc_guest_info_init(ram_addr_t
below_4g_mem_size,
{
PcGuestInfoState *guest_info_state = g_malloc0(sizeof *guest_info_state);
PcGuestInfo *guest_info = &guest_info_state->info;
- CPUState *cpu;
+ int i, j;
guest_info->ram_size = below_4g_mem_size + above_4g_mem_size;
guest_info->apic_id_limit = pc_apic_id_limit(max_cpus);
@@ -1077,8 +1060,15 @@ PcGuestInfo *pc_guest_info_init(ram_addr_t
below_4g_mem_size,
guest_info->node_cpu = g_malloc0(guest_info->apic_id_limit *
sizeof *guest_info->node_cpu);
- CPU_FOREACH(cpu) {
- pc_set_cpu_guest_info(cpu, guest_info);
+ for (i = 0; i < max_cpus; i++) {
+ unsigned int apic_id = x86_cpu_apic_id_from_index(i);
+ assert(apic_id < guest_info->apic_id_limit);
+ for (j = 0; j < nb_numa_nodes; j++) {
+ if (test_bit(i, node_cpumask[j])) {
+ guest_info->node_cpu[apic_id] = j;
+ break;
+ }
+ }
}
guest_info_state->machine_done.notify = pc_guest_info_machine_done;
