diff options
author | Igor Mammedov <imammedo@redhat.com> | 2017-05-10 13:29:45 +0200 |
---|---|---|
committer | Eduardo Habkost <ehabkost@redhat.com> | 2017-05-11 16:08:48 -0300 |
commit | ea089eebbd80e61d3c3cd03741dd5d9535c551fc (patch) | |
tree | f868c4e6bc6f311b8513aaf465da5f343f96d6db /hw | |
parent | d9c34f9c6c745f6a8123a872b33990ab564c614a (diff) | |
download | qemu-ea089eebbd80e61d3c3cd03741dd5d9535c551fc.zip |
numa: move source of default CPUs to NUMA node mapping into boards
Originally CPU threads were by default assigned in
round-robin fashion. However it was causing issues in
guest since CPU threads from the same socket/core could
be placed on different NUMA nodes.
Commit fb43b73b (pc: fix default VCPU to NUMA node mapping)
fixed it by grouping threads within a socket on the same node
introducing cpu_index_to_socket_id() callback and commit
20bb648d (spapr: Fix default NUMA node allocation for threads)
reused callback to fix similar issues for SPAPR machine
even though socket doesn't make much sense there.
As result QEMU ended up having 3 default distribution rules
used by 3 targets /virt-arm, spapr, pc/.
In effort of moving NUMA mapping for CPUs into possible_cpus,
generalize default mapping in numa.c by making boards decide
on default mapping and let them explicitly tell generic
numa code to which node a CPU thread belongs to by replacing
cpu_index_to_socket_id() with @cpu_index_to_instance_props()
which provides default node_id assigned by board to specified
cpu_index.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <1494415802-227633-2-git-send-email-imammedo@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Diffstat (limited to 'hw')
-rw-r--r-- | hw/arm/virt.c | 20 | ||||
-rw-r--r-- | hw/i386/pc.c | 23 | ||||
-rw-r--r-- | hw/ppc/spapr.c | 28 |
3 files changed, 56 insertions, 15 deletions
diff --git a/hw/arm/virt.c b/hw/arm/virt.c index acc748ec40..dfd6fd446c 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -1539,6 +1539,16 @@ static void virt_set_gic_version(Object *obj, const char *value, Error **errp) } } +static CpuInstanceProperties +virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index) +{ + MachineClass *mc = MACHINE_GET_CLASS(ms); + const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms); + + assert(cpu_index < possible_cpus->len); + return possible_cpus->cpus[cpu_index].props; +} + static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms) { int n; @@ -1558,8 +1568,13 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms) ms->possible_cpus->cpus[n].props.has_thread_id = true; ms->possible_cpus->cpus[n].props.thread_id = n; - /* TODO: add 'has_node/node' here to describe - to which node core belongs */ + /* default distribution of CPUs over NUMA nodes */ + if (nb_numa_nodes) { + /* preset values but do not enable them i.e. 'has_node_id = false', + * numa init code will enable them later if manual mapping wasn't + * present on CLI */ + ms->possible_cpus->cpus[n].props.node_id = n % nb_numa_nodes; + } } return ms->possible_cpus; } @@ -1581,6 +1596,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) /* We know we will never create a pre-ARMv7 CPU which needs 1K pages */ mc->minimum_page_bits = 12; mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids; + mc->cpu_index_to_instance_props = virt_cpu_index_to_props; } static const TypeInfo virt_machine_info = { diff --git a/hw/i386/pc.c b/hw/i386/pc.c index f3b372a18f..01693d54ca 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -2243,12 +2243,14 @@ static void pc_machine_reset(void) } } -static unsigned pc_cpu_index_to_socket_id(unsigned cpu_index) +static CpuInstanceProperties +pc_cpu_index_to_props(MachineState *ms, unsigned cpu_index) { - X86CPUTopoInfo topo; - x86_topo_ids_from_idx(smp_cores, smp_threads, cpu_index, - &topo); - return topo.pkg_id; + MachineClass *mc = MACHINE_GET_CLASS(ms); + const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms); + + assert(cpu_index < possible_cpus->len); + return possible_cpus->cpus[cpu_index].props; } static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *ms) @@ -2280,6 +2282,15 @@ static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *ms) ms->possible_cpus->cpus[i].props.core_id = topo.core_id; ms->possible_cpus->cpus[i].props.has_thread_id = true; ms->possible_cpus->cpus[i].props.thread_id = topo.smt_id; + + /* default distribution of CPUs over NUMA nodes */ + if (nb_numa_nodes) { + /* preset values but do not enable them i.e. 'has_node_id = false', + * numa init code will enable them later if manual mapping wasn't + * present on CLI */ + ms->possible_cpus->cpus[i].props.node_id = + topo.pkg_id % nb_numa_nodes; + } } return ms->possible_cpus; } @@ -2322,7 +2333,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) pcmc->acpi_data_size = 0x20000 + 0x8000; pcmc->save_tsc_khz = true; mc->get_hotplug_handler = pc_get_hotpug_handler; - mc->cpu_index_to_socket_id = pc_cpu_index_to_socket_id; + mc->cpu_index_to_instance_props = pc_cpu_index_to_props; mc->possible_cpu_arch_ids = pc_possible_cpu_arch_ids; mc->has_hotpluggable_cpus = true; mc->default_boot_order = "cad"; diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index bdc31ce56c..2077e4b3c6 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -2981,11 +2981,18 @@ static HotplugHandler *spapr_get_hotplug_handler(MachineState *machine, return NULL; } -static unsigned spapr_cpu_index_to_socket_id(unsigned cpu_index) +static CpuInstanceProperties +spapr_cpu_index_to_props(MachineState *machine, unsigned cpu_index) { - /* Allocate to NUMA nodes on a "socket" basis (not that concept of - * socket means much for the paravirtualized PAPR platform) */ - return cpu_index / smp_threads / smp_cores; + CPUArchId *core_slot; + MachineClass *mc = MACHINE_GET_CLASS(machine); + + /* make sure possible_cpu are intialized */ + mc->possible_cpu_arch_ids(machine); + /* get CPU core slot containing thread that matches cpu_index */ + core_slot = spapr_find_cpu_slot(machine, cpu_index, NULL); + assert(core_slot); + return core_slot->props; } static const CPUArchIdList *spapr_possible_cpu_arch_ids(MachineState *machine) @@ -3012,8 +3019,15 @@ static const CPUArchIdList *spapr_possible_cpu_arch_ids(MachineState *machine) machine->possible_cpus->cpus[i].arch_id = core_id; machine->possible_cpus->cpus[i].props.has_core_id = true; machine->possible_cpus->cpus[i].props.core_id = core_id; - /* TODO: add 'has_node/node' here to describe - to which node core belongs */ + + /* default distribution of CPUs over NUMA nodes */ + if (nb_numa_nodes) { + /* preset values but do not enable them i.e. 'has_node_id = false', + * numa init code will enable them later if manual mapping wasn't + * present on CLI */ + machine->possible_cpus->cpus[i].props.node_id = + core_id / smp_threads / smp_cores % nb_numa_nodes; + } } return machine->possible_cpus; } @@ -3138,7 +3152,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) hc->pre_plug = spapr_machine_device_pre_plug; hc->plug = spapr_machine_device_plug; hc->unplug = spapr_machine_device_unplug; - mc->cpu_index_to_socket_id = spapr_cpu_index_to_socket_id; + mc->cpu_index_to_instance_props = spapr_cpu_index_to_props; mc->possible_cpu_arch_ids = spapr_possible_cpu_arch_ids; hc->unplug_request = spapr_machine_device_unplug_request; |