aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--MAINTAINERS11
-rw-r--r--docs/devel/index-internals.rst1
-rw-r--r--docs/devel/s390-cpu-topology.rst170
-rw-r--r--docs/system/s390x/cpu-topology.rst244
-rw-r--r--docs/system/target-s390x.rst1
-rw-r--r--hw/core/machine-hmp-cmds.c6
-rw-r--r--hw/core/machine-smp.c48
-rw-r--r--hw/core/machine.c4
-rw-r--r--hw/core/qdev-properties-system.c13
-rw-r--r--hw/s390x/cpu-topology.c469
-rw-r--r--hw/s390x/meson.build1
-rw-r--r--hw/s390x/s390-virtio-ccw.c29
-rw-r--r--hw/s390x/sclp.c5
-rw-r--r--include/hw/boards.h10
-rw-r--r--include/hw/qdev-properties-system.h4
-rw-r--r--include/hw/s390x/cpu-topology.h83
-rw-r--r--include/hw/s390x/s390-virtio-ccw.h6
-rw-r--r--include/hw/s390x/sclp.h4
-rw-r--r--qapi/machine-common.json21
-rw-r--r--qapi/machine-target.json121
-rw-r--r--qapi/machine.json85
-rw-r--r--qapi/meson.build1
-rw-r--r--qapi/qapi-schema.json1
-rw-r--r--qemu-options.hx7
-rw-r--r--system/vl.c6
-rw-r--r--target/s390x/cpu-sysemu.c13
-rw-r--r--target/s390x/cpu.c16
-rw-r--r--target/s390x/cpu.h82
-rw-r--r--target/s390x/cpu_models.c1
-rw-r--r--target/s390x/kvm/kvm.c166
-rw-r--r--target/s390x/kvm/kvm_s390x.h1
-rw-r--r--target/s390x/kvm/meson.build3
-rw-r--r--target/s390x/kvm/stsi-topology.c334
-rw-r--r--tests/avocado/s390_topology.py439
-rw-r--r--tests/qtest/migration-test.c4
35 files changed, 2285 insertions, 125 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index e1a96c1..7f9912b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1714,6 +1714,16 @@ F: hw/s390x/event-facility.c
F: hw/s390x/sclp*.c
L: qemu-s390x@nongnu.org
+S390 CPU topology
+M: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
+S: Supported
+F: include/hw/s390x/cpu-topology.h
+F: hw/s390x/cpu-topology.c
+F: target/s390x/kvm/stsi-topology.c
+F: docs/devel/s390-cpu-topology.rst
+F: docs/system/s390x/cpu-topology.rst
+F: tests/avocado/s390_topology.py
+
X86 Machines
------------
PC
@@ -1797,6 +1807,7 @@ F: hw/core/null-machine.c
F: hw/core/numa.c
F: hw/cpu/cluster.c
F: qapi/machine.json
+F: qapi/machine-common.json
F: qapi/machine-target.json
F: include/hw/boards.h
F: include/hw/core/cpu.h
diff --git a/docs/devel/index-internals.rst b/docs/devel/index-internals.rst
index e1a93df..6f81df9 100644
--- a/docs/devel/index-internals.rst
+++ b/docs/devel/index-internals.rst
@@ -14,6 +14,7 @@ Details about QEMU's various subsystems including how to add features to them.
migration
multi-process
reset
+ s390-cpu-topology
s390-dasd-ipl
tracing
vfio-migration
diff --git a/docs/devel/s390-cpu-topology.rst b/docs/devel/s390-cpu-topology.rst
new file mode 100644
index 0000000..9eab28d
--- /dev/null
+++ b/docs/devel/s390-cpu-topology.rst
@@ -0,0 +1,170 @@
+QAPI interface for S390 CPU topology
+====================================
+
+The following sections will explain the QAPI interface for S390 CPU topology
+with the help of exemplary output.
+For this, let's assume that QEMU has been started with the following
+command, defining 4 CPUs, where CPU[0] is defined by the -smp argument and will
+have default values:
+
+.. code-block:: bash
+
+ qemu-system-s390x \
+ -enable-kvm \
+ -cpu z14,ctop=on \
+ -smp 1,drawers=3,books=3,sockets=2,cores=2,maxcpus=36 \
+ -device z14-s390x-cpu,core-id=19,entitlement=high \
+ -device z14-s390x-cpu,core-id=11,entitlement=low \
+ -device z14-s390x-cpu,core-id=112,entitlement=high \
+ ...
+
+Additions to query-cpus-fast
+----------------------------
+
+The command query-cpus-fast allows querying the topology tree and
+modifiers for all configured vCPUs.
+
+.. code-block:: QMP
+
+ { "execute": "query-cpus-fast" }
+ {
+ "return": [
+ {
+ "dedicated": false,
+ "thread-id": 536993,
+ "props": {
+ "core-id": 0,
+ "socket-id": 0,
+ "drawer-id": 0,
+ "book-id": 0
+ },
+ "cpu-state": "operating",
+ "entitlement": "medium",
+ "qom-path": "/machine/unattached/device[0]",
+ "cpu-index": 0,
+ "target": "s390x"
+ },
+ {
+ "dedicated": false,
+ "thread-id": 537003,
+ "props": {
+ "core-id": 19,
+ "socket-id": 1,
+ "drawer-id": 0,
+ "book-id": 2
+ },
+ "cpu-state": "operating",
+ "entitlement": "high",
+ "qom-path": "/machine/peripheral-anon/device[0]",
+ "cpu-index": 19,
+ "target": "s390x"
+ },
+ {
+ "dedicated": false,
+ "thread-id": 537004,
+ "props": {
+ "core-id": 11,
+ "socket-id": 1,
+ "drawer-id": 0,
+ "book-id": 1
+ },
+ "cpu-state": "operating",
+ "entitlement": "low",
+ "qom-path": "/machine/peripheral-anon/device[1]",
+ "cpu-index": 11,
+ "target": "s390x"
+ },
+ {
+ "dedicated": true,
+ "thread-id": 537005,
+ "props": {
+ "core-id": 112,
+ "socket-id": 0,
+ "drawer-id": 3,
+ "book-id": 2
+ },
+ "cpu-state": "operating",
+ "entitlement": "high",
+ "qom-path": "/machine/peripheral-anon/device[2]",
+ "cpu-index": 112,
+ "target": "s390x"
+ }
+ ]
+ }
+
+
+QAPI command: set-cpu-topology
+------------------------------
+
+The command set-cpu-topology allows modifying the topology tree
+or the topology modifiers of a vCPU in the configuration.
+
+.. code-block:: QMP
+
+ { "execute": "set-cpu-topology",
+ "arguments": {
+ "core-id": 11,
+ "socket-id": 0,
+ "book-id": 0,
+ "drawer-id": 0,
+ "entitlement": "low",
+ "dedicated": false
+ }
+ }
+ {"return": {}}
+
+The core-id parameter is the only mandatory parameter and every
+unspecified parameter keeps its previous value.
+
+QAPI event CPU_POLARIZATION_CHANGE
+----------------------------------
+
+When a guest requests a modification of the polarization,
+QEMU sends a CPU_POLARIZATION_CHANGE event.
+
+When requesting the change, the guest only specifies horizontal or
+vertical polarization.
+It is the job of the entity administrating QEMU to set the dedication and fine
+grained vertical entitlement in response to this event.
+
+Note that a vertical polarized dedicated vCPU can only have a high
+entitlement, giving 6 possibilities for vCPU polarization:
+
+- Horizontal
+- Horizontal dedicated
+- Vertical low
+- Vertical medium
+- Vertical high
+- Vertical high dedicated
+
+Example of the event received when the guest issues the CPU instruction
+Perform Topology Function PTF(0) to request an horizontal polarization:
+
+.. code-block:: QMP
+
+ {
+ "timestamp": {
+ "seconds": 1687870305,
+ "microseconds": 566299
+ },
+ "event": "CPU_POLARIZATION_CHANGE",
+ "data": {
+ "polarization": "horizontal"
+ }
+ }
+
+QAPI query command: query-s390x-cpu-polarization
+------------------------------------------------
+
+The query command query-s390x-cpu-polarization returns the current
+CPU polarization of the machine.
+In this case the guest previously issued a PTF(1) to request vertical polarization:
+
+.. code-block:: QMP
+
+ { "execute": "query-s390x-cpu-polarization" }
+ {
+ "return": {
+ "polarization": "vertical"
+ }
+ }
diff --git a/docs/system/s390x/cpu-topology.rst b/docs/system/s390x/cpu-topology.rst
new file mode 100644
index 0000000..5133fdc
--- /dev/null
+++ b/docs/system/s390x/cpu-topology.rst
@@ -0,0 +1,244 @@
+.. _cpu-topology-s390x:
+
+CPU topology on s390x
+=====================
+
+Since QEMU 8.2, CPU topology on s390x provides up to 3 levels of
+topology containers: drawers, books and sockets. They define a
+tree-shaped hierarchy.
+
+The socket container has one or more CPU entries.
+Each of these CPU entries consists of a bitmap and three CPU attributes:
+
+- CPU type
+- entitlement
+- dedication
+
+Each bit set in the bitmap correspond to a core-id of a vCPU with matching
+attributes.
+
+This documentation provides general information on S390 CPU topology,
+how to enable it and explains the new CPU attributes.
+For information on how to modify the S390 CPU topology and how to
+monitor polarization changes, see ``docs/devel/s390-cpu-topology.rst``.
+
+Prerequisites
+-------------
+
+To use the CPU topology, you need to run with KVM on a s390x host that
+uses the Linux kernel v6.0 or newer (which provide the so-called
+``KVM_CAP_S390_CPU_TOPOLOGY`` capability that allows QEMU to signal the
+CPU topology facility via the so-called STFLE bit 11 to the VM).
+
+Enabling CPU topology
+---------------------
+
+Currently, CPU topology is only enabled in the host model by default.
+
+Enabling CPU topology in a CPU model is done by setting the CPU flag
+``ctop`` to ``on`` as in:
+
+.. code-block:: bash
+
+ -cpu gen16b,ctop=on
+
+Having the topology disabled by default allows migration between
+old and new QEMU without adding new flags.
+
+Default topology usage
+----------------------
+
+The CPU topology can be specified on the QEMU command line
+with the ``-smp`` or the ``-device`` QEMU command arguments.
+
+Note also that since 7.2 threads are no longer supported in the topology
+and the ``-smp`` command line argument accepts only ``threads=1``.
+
+If none of the containers attributes (drawers, books, sockets) are
+specified for the ``-smp`` flag, the number of these containers
+is 1.
+
+Thus the following two options will result in the same topology:
+
+.. code-block:: bash
+
+ -smp cpus=5,drawer=1,books=1,sockets=8,cores=4,maxcpus=32
+
+and
+
+.. code-block:: bash
+
+ -smp cpus=5,sockets=8,cores=4,maxcpus=32
+
+When a CPU is defined by the ``-smp`` command argument, its position
+inside the topology is calculated by adding the CPUs to the topology
+based on the core-id starting with core-0 at position 0 of socket-0,
+book-0, drawer-0 and filling all CPUs of socket-0 before filling socket-1
+of book-0 and so on up to the last socket of the last book of the last
+drawer.
+
+When a CPU is defined by the ``-device`` command argument, the
+tree topology attributes must all be defined or all not defined.
+
+.. code-block:: bash
+
+ -device gen16b-s390x-cpu,drawer-id=1,book-id=1,socket-id=2,core-id=1
+
+or
+
+.. code-block:: bash
+
+ -device gen16b-s390x-cpu,core-id=1,dedicated=true
+
+If none of the tree attributes (drawer, book, sockets), are specified
+for the ``-device`` argument, like for all CPUs defined with the ``-smp``
+command argument the topology tree attributes will be set by simply
+adding the CPUs to the topology based on the core-id.
+
+QEMU will not try to resolve collisions and will report an error if the
+CPU topology defined explicitly or implicitly on a ``-device``
+argument collides with the definition of a CPU implicitly defined
+on the ``-smp`` argument.
+
+When the topology modifier attributes are not defined for the
+``-device`` command argument they takes following default values:
+
+- dedicated: ``false``
+- entitlement: ``medium``
+
+
+Hot plug
+++++++++
+
+New CPUs can be plugged using the device_add hmp command as in:
+
+.. code-block:: bash
+
+ (qemu) device_add gen16b-s390x-cpu,core-id=9
+
+The placement of the CPU is derived from the core-id as described above.
+
+The topology can of course also be fully defined:
+
+.. code-block:: bash
+
+ (qemu) device_add gen16b-s390x-cpu,drawer-id=1,book-id=1,socket-id=2,core-id=1
+
+
+Examples
+++++++++
+
+In the following machine we define 8 sockets with 4 cores each.
+
+.. code-block:: bash
+
+ $ qemu-system-s390x -m 2G \
+ -cpu gen16b,ctop=on \
+ -smp cpus=5,sockets=8,cores=4,maxcpus=32 \
+ -device host-s390x-cpu,core-id=14 \
+
+A new CPUs can be plugged using the device_add hmp command as before:
+
+.. code-block:: bash
+
+ (qemu) device_add gen16b-s390x-cpu,core-id=9
+
+The core-id defines the placement of the core in the topology by
+starting with core 0 in socket 0 up to maxcpus.
+
+In the example above:
+
+* There are 5 CPUs provided to the guest with the ``-smp`` command line
+ They will take the core-ids 0,1,2,3,4
+ As we have 4 cores in a socket, we have 4 CPUs provided
+ to the guest in socket 0, with core-ids 0,1,2,3.
+ The last CPU, with core-id 4, will be on socket 1.
+
+* the core with ID 14 provided by the ``-device`` command line will
+ be placed in socket 3, with core-id 14
+
+* the core with ID 9 provided by the ``device_add`` qmp command will
+ be placed in socket 2, with core-id 9
+
+
+Polarization, entitlement and dedication
+----------------------------------------
+
+Polarization
+++++++++++++
+
+The polarization affects how the CPUs of a shared host are utilized/distributed
+among guests.
+The guest determines the polarization by using the PTF instruction.
+
+Polarization defines two models of CPU provisioning: horizontal
+and vertical.
+
+The horizontal polarization is the default model on boot and after
+subsystem reset. When horizontal polarization is in effect all vCPUs should
+have about equal resource provisioning.
+
+In the vertical polarization model vCPUs are unequal, but overall more resources
+might be available.
+The guest can make use of the vCPU entitlement information provided by the host
+to optimize kernel thread scheduling.
+
+A subsystem reset puts all vCPU of the configuration into the
+horizontal polarization.
+
+Entitlement
++++++++++++
+
+The vertical polarization specifies that the guest's vCPU can get
+different real CPU provisioning:
+
+- a vCPU with vertical high entitlement specifies that this
+ vCPU gets 100% of the real CPU provisioning.
+
+- a vCPU with vertical medium entitlement specifies that this
+ vCPU shares the real CPU with other vCPUs.
+
+- a vCPU with vertical low entitlement specifies that this
+ vCPU only gets real CPU provisioning when no other vCPUs needs it.
+
+In the case a vCPU with vertical high entitlement does not use
+the real CPU, the unused "slack" can be dispatched to other vCPU
+with medium or low entitlement.
+
+A vCPU can be "dedicated" in which case the vCPU is fully dedicated to a single
+real CPU.
+
+The dedicated bit is an indication of affinity of a vCPU for a real CPU
+while the entitlement indicates the sharing or exclusivity of use.
+
+Defining the topology on the command line
+-----------------------------------------
+
+The topology can entirely be defined using -device cpu statements,
+with the exception of CPU 0 which must be defined with the -smp
+argument.
+
+For example, here we set the position of the cores 1,2,3 to
+drawer 1, book 1, socket 2 and cores 0,9 and 14 to drawer 0,
+book 0, socket 0 without defining entitlement or dedication.
+Core 4 will be set on its default position on socket 1
+(since we have 4 core per socket) and we define it as dedicated and
+with vertical high entitlement.
+
+.. code-block:: bash
+
+ $ qemu-system-s390x -m 2G \
+ -cpu gen16b,ctop=on \
+ -smp cpus=1,sockets=8,cores=4,maxcpus=32 \
+ \
+ -device gen16b-s390x-cpu,drawer-id=1,book-id=1,socket-id=2,core-id=1 \
+ -device gen16b-s390x-cpu,drawer-id=1,book-id=1,socket-id=2,core-id=2 \
+ -device gen16b-s390x-cpu,drawer-id=1,book-id=1,socket-id=2,core-id=3 \
+ \
+ -device gen16b-s390x-cpu,drawer-id=0,book-id=0,socket-id=0,core-id=9 \
+ -device gen16b-s390x-cpu,drawer-id=0,book-id=0,socket-id=0,core-id=14 \
+ \
+ -device gen16b-s390x-cpu,core-id=4,dedicated=on,entitlement=high
+
+The entitlement defined for the CPU 4 will only be used after the guest
+successfully enables vertical polarization by using the PTF instruction.
diff --git a/docs/system/target-s390x.rst b/docs/system/target-s390x.rst
index f6f1143..94c981e 100644
--- a/docs/system/target-s390x.rst
+++ b/docs/system/target-s390x.rst
@@ -34,3 +34,4 @@ Architectural features
.. toctree::
s390x/bootdevices
s390x/protvirt
+ s390x/cpu-topology
diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c
index c3e55ef..9a4b59c 100644
--- a/hw/core/machine-hmp-cmds.c
+++ b/hw/core/machine-hmp-cmds.c
@@ -71,6 +71,12 @@ void hmp_hotpluggable_cpus(Monitor *mon, const QDict *qdict)
if (c->has_node_id) {
monitor_printf(mon, " node-id: \"%" PRIu64 "\"\n", c->node_id);
}
+ if (c->has_drawer_id) {
+ monitor_printf(mon, " drawer-id: \"%" PRIu64 "\"\n", c->drawer_id);
+ }
+ if (c->has_book_id) {
+ monitor_printf(mon, " book-id: \"%" PRIu64 "\"\n", c->book_id);
+ }
if (c->has_socket_id) {
monitor_printf(mon, " socket-id: \"%" PRIu64 "\"\n", c->socket_id);
}
diff --git a/hw/core/machine-smp.c b/hw/core/machine-smp.c
index 0f4d9b6..25019c9 100644
--- a/hw/core/machine-smp.c
+++ b/hw/core/machine-smp.c
@@ -33,6 +33,14 @@ static char *cpu_hierarchy_to_string(MachineState *ms)
MachineClass *mc = MACHINE_GET_CLASS(ms);
GString *s = g_string_new(NULL);
+ if (mc->smp_props.drawers_supported) {
+ g_string_append_printf(s, "drawers (%u) * ", ms->smp.drawers);
+ }
+
+ if (mc->smp_props.books_supported) {
+ g_string_append_printf(s, "books (%u) * ", ms->smp.books);
+ }
+
g_string_append_printf(s, "sockets (%u)", ms->smp.sockets);
if (mc->smp_props.dies_supported) {
@@ -75,6 +83,8 @@ void machine_parse_smp_config(MachineState *ms,
{
MachineClass *mc = MACHINE_GET_CLASS(ms);
unsigned cpus = config->has_cpus ? config->cpus : 0;
+ unsigned drawers = config->has_drawers ? config->drawers : 0;
+ unsigned books = config->has_books ? config->books : 0;
unsigned sockets = config->has_sockets ? config->sockets : 0;
unsigned dies = config->has_dies ? config->dies : 0;
unsigned clusters = config->has_clusters ? config->clusters : 0;
@@ -87,6 +97,8 @@ void machine_parse_smp_config(MachineState *ms,
* explicit configuration like "cpus=0" is not allowed.
*/
if ((config->has_cpus && config->cpus == 0) ||
+ (config->has_drawers && config->drawers == 0) ||
+ (config->has_books && config->books == 0) ||
(config->has_sockets && config->sockets == 0) ||
(config->has_dies && config->dies == 0) ||
(config->has_clusters && config->clusters == 0) ||
@@ -113,6 +125,19 @@ void machine_parse_smp_config(MachineState *ms,
dies = dies > 0 ? dies : 1;
clusters = clusters > 0 ? clusters : 1;
+ if (!mc->smp_props.books_supported && books > 1) {
+ error_setg(errp, "books not supported by this machine's CPU topology");
+ return;
+ }
+ books = books > 0 ? books : 1;
+
+ if (!mc->smp_props.drawers_supported && drawers > 1) {
+ error_setg(errp,
+ "drawers not supported by this machine's CPU topology");
+ return;
+ }
+ drawers = drawers > 0 ? drawers : 1;
+
/* compute missing values based on the provided ones */
if (cpus == 0 && maxcpus == 0) {
sockets = sockets > 0 ? sockets : 1;
@@ -126,33 +151,41 @@ void machine_parse_smp_config(MachineState *ms,
if (sockets == 0) {
cores = cores > 0 ? cores : 1;
threads = threads > 0 ? threads : 1;
- sockets = maxcpus / (dies * clusters * cores * threads);
+ sockets = maxcpus /
+ (drawers * books * dies * clusters * cores * threads);
} else if (cores == 0) {
threads = threads > 0 ? threads : 1;
- cores = maxcpus / (sockets * dies * clusters * threads);
+ cores = maxcpus /
+ (drawers * books * sockets * dies * clusters * threads);
}
} else {
/* prefer cores over sockets since 6.2 */
if (cores == 0) {
sockets = sockets > 0 ? sockets : 1;
threads = threads > 0 ? threads : 1;
- cores = maxcpus / (sockets * dies * clusters * threads);
+ cores = maxcpus /
+ (drawers * books * sockets * dies * clusters * threads);
} else if (sockets == 0) {
threads = threads > 0 ? threads : 1;
- sockets = maxcpus / (dies * clusters * cores * threads);
+ sockets = maxcpus /
+ (drawers * books * dies * clusters * cores * threads);
}
}
/* try to calculate omitted threads at last */
if (threads == 0) {
- threads = maxcpus / (sockets * dies * clusters * cores);
+ threads = maxcpus /
+ (drawers * books * sockets * dies * clusters * cores);
}
}
- maxcpus = maxcpus > 0 ? maxcpus : sockets * dies * clusters * cores * threads;
+ maxcpus = maxcpus > 0 ? maxcpus : drawers * books * sockets * dies *
+ clusters * cores * threads;
cpus = cpus > 0 ? cpus : maxcpus;
ms->smp.cpus = cpus;
+ ms->smp.drawers = drawers;
+ ms->smp.books = books;
ms->smp.sockets = sockets;
ms->smp.dies = dies;
ms->smp.clusters = clusters;
@@ -163,7 +196,8 @@ void machine_parse_smp_config(MachineState *ms,
mc->smp_props.has_clusters = config->has_clusters;
/* sanity-check of the computed topology */
- if (sockets * dies * clusters * cores * threads != maxcpus) {
+ if (drawers * books * sockets * dies * clusters * cores * threads !=
+ maxcpus) {
g_autofree char *topo_msg = cpu_hierarchy_to_string(ms);
error_setg(errp, "Invalid CPU topology: "
"product of the hierarchy must match maxcpus: "
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 05aef2c..50edaab 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -863,6 +863,8 @@ static void machine_get_smp(Object *obj, Visitor *v, const char *name,
MachineState *ms = MACHINE(obj);
SMPConfiguration *config = &(SMPConfiguration){
.has_cpus = true, .cpus = ms->smp.cpus,
+ .has_drawers = true, .drawers = ms->smp.drawers,
+ .has_books = true, .books = ms->smp.books,
.has_sockets = true, .sockets = ms->smp.sockets,
.has_dies = true, .dies = ms->smp.dies,
.has_clusters = true, .clusters = ms->smp.clusters,
@@ -1137,6 +1139,8 @@ static void machine_initfn(Object *obj)
/* default to mc->default_cpus */
ms->smp.cpus = mc->default_cpus;
ms->smp.max_cpus = mc->default_cpus;
+ ms->smp.drawers = 1;
+ ms->smp.books = 1;
ms->smp.sockets = 1;
ms->smp.dies = 1;
ms->smp.clusters = 1;
diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c
index 6883406..7c6dfab 100644
--- a/hw/core/qdev-properties-system.c
+++ b/hw/core/qdev-properties-system.c
@@ -1139,3 +1139,16 @@ const PropertyInfo qdev_prop_uuid = {
.set = set_uuid,
.set_default_value = set_default_uuid_auto,
};
+
+/* --- s390 cpu entitlement policy --- */
+
+QEMU_BUILD_BUG_ON(sizeof(CpuS390Entitlement) != sizeof(int));
+
+const PropertyInfo qdev_prop_cpus390entitlement = {
+ .name = "CpuS390Entitlement",
+ .description = "low/medium (default)/high",
+ .enum_table = &CpuS390Entitlement_lookup,
+ .get = qdev_propinfo_get_enum,
+ .set = qdev_propinfo_set_enum,
+ .set_default_value = qdev_propinfo_set_default_value_enum,
+};
diff --git a/hw/s390x/cpu-topology.c b/hw/s390x/cpu-topology.c
new file mode 100644
index 0000000..f16bdf6
--- /dev/null
+++ b/hw/s390x/cpu-topology.c
@@ -0,0 +1,469 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CPU Topology
+ *
+ * Copyright IBM Corp. 2022, 2023
+ * Author(s): Pierre Morel <pmorel@linux.ibm.com>
+ *
+ * S390 topology handling can be divided in two parts:
+ *
+ * - The first part in this file is taking care of all common functions
+ * used by KVM and TCG to create and modify the topology.
+ *
+ * - The second part, building the topology information data for the
+ * guest with CPU and KVM specificity will be implemented inside
+ * the target/s390/kvm sub tree.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "hw/qdev-properties.h"
+#include "hw/boards.h"
+#include "target/s390x/cpu.h"
+#include "hw/s390x/s390-virtio-ccw.h"
+#include "hw/s390x/cpu-topology.h"
+#include "qapi/qapi-commands-machine-target.h"
+#include "qapi/qapi-events-machine-target.h"
+
+/*
+ * s390_topology is used to keep the topology information.
+ * .cores_per_socket: tracks information on the count of cores
+ * per socket.
+ * .polarization: tracks machine polarization.
+ */
+S390Topology s390_topology = {
+ /* will be initialized after the CPU model is realized */
+ .cores_per_socket = NULL,
+ .polarization = S390_CPU_POLARIZATION_HORIZONTAL,
+};
+
+/**
+ * s390_socket_nb:
+ * @cpu: s390x CPU
+ *
+ * Returns the socket number used inside the cores_per_socket array
+ * for a topology tree entry
+ */
+static int s390_socket_nb_from_ids(int drawer_id, int book_id, int socket_id)
+{
+ return (drawer_id * current_machine->smp.books + book_id) *
+ current_machine->smp.sockets + socket_id;
+}
+
+/**
+ * s390_socket_nb:
+ * @cpu: s390x CPU
+ *
+ * Returns the socket number used inside the cores_per_socket array
+ * for a cpu.
+ */
+static int s390_socket_nb(S390CPU *cpu)
+{
+ return s390_socket_nb_from_ids(cpu->env.drawer_id, cpu->env.book_id,
+ cpu->env.socket_id);
+}
+
+/**
+ * s390_has_topology:
+ *
+ * Return: true if the topology is supported by the machine.
+ */
+bool s390_has_topology(void)
+{
+ return s390_has_feat(S390_FEAT_CONFIGURATION_TOPOLOGY);
+}
+
+/**
+ * s390_topology_init:
+ * @ms: the machine state where the machine topology is defined
+ *
+ * Keep track of the machine topology.
+ *
+ * Allocate an array to keep the count of cores per socket.
+ * The index of the array starts at socket 0 from book 0 and
+ * drawer 0 up to the maximum allowed by the machine topology.
+ */
+static void s390_topology_init(MachineState *ms)
+{
+ CpuTopology *smp = &ms->smp;
+
+ s390_topology.cores_per_socket = g_new0(uint8_t, smp->sockets *
+ smp->books * smp->drawers);
+}
+
+/*
+ * s390_handle_ptf:
+ *
+ * @register 1: contains the function code
+ *
+ * Function codes 0 (horizontal) and 1 (vertical) define the CPU
+ * polarization requested by the guest.
+ *
+ * Function code 2 is handling topology changes and is interpreted
+ * by the SIE.
+ */
+void s390_handle_ptf(S390CPU *cpu, uint8_t r1, uintptr_t ra)
+{
+ CpuS390Polarization polarization;
+ CPUS390XState *env = &cpu->env;
+ uint64_t reg = env->regs[r1];
+ int fc = reg & S390_TOPO_FC_MASK;
+
+ if (!s390_has_feat(S390_FEAT_CONFIGURATION_TOPOLOGY)) {
+ s390_program_interrupt(env, PGM_OPERATION, ra);
+ return;
+ }
+
+ if (env->psw.mask & PSW_MASK_PSTATE) {
+ s390_program_interrupt(env, PGM_PRIVILEGED, ra);
+ return;
+ }
+
+ if (reg & ~S390_TOPO_FC_MASK) {
+ s390_program_interrupt(env, PGM_SPECIFICATION, ra);
+ return;
+ }
+
+ polarization = S390_CPU_POLARIZATION_VERTICAL;
+ switch (fc) {
+ case 0:
+ polarization = S390_CPU_POLARIZATION_HORIZONTAL;
+ /* fallthrough */
+ case 1:
+ if (s390_topology.polarization == polarization) {
+ env->regs[r1] |= S390_PTF_REASON_DONE;
+ setcc(cpu, 2);
+ } else {
+ s390_topology.polarization = polarization;
+ s390_cpu_topology_set_changed(true);
+ qapi_event_send_cpu_polarization_change(polarization);
+ setcc(cpu, 0);
+ }
+ break;
+ default:
+ /* Note that fc == 2 is interpreted by the SIE */
+ s390_program_interrupt(env, PGM_SPECIFICATION, ra);
+ }
+}
+
+/**
+ * s390_topology_reset:
+ *
+ * Generic reset for CPU topology, calls s390_topology_reset()
+ * to reset the kernel Modified Topology Change Record.
+ */
+void s390_topology_reset(void)
+{
+ s390_cpu_topology_set_changed(false);
+ s390_topology.polarization = S390_CPU_POLARIZATION_HORIZONTAL;
+}
+
+/**
+ * s390_topology_cpu_default:
+ * @cpu: pointer to a S390CPU
+ * @errp: Error pointer
+ *
+ * Setup the default topology if no attributes are already set.
+ * Passing a CPU with some, but not all, attributes set is considered
+ * an error.
+ *
+ * The function calculates the (drawer_id, book_id, socket_id)
+ * topology by filling the cores starting from the first socket
+ * (0, 0, 0) up to the last (smp->drawers, smp->books, smp->sockets).
+ *
+ * CPU type and dedication have defaults values set in the
+ * s390x_cpu_properties, entitlement must be adjust depending on the
+ * dedication.
+ *
+ * Returns false if it is impossible to setup a default topology
+ * true otherwise.
+ */
+static bool s390_topology_cpu_default(S390CPU *cpu, Error **errp)
+{
+ CpuTopology *smp = &current_machine->smp;
+ CPUS390XState *env = &cpu->env;
+
+ /* All geometry topology attributes must be set or all unset */
+ if ((env->socket_id < 0 || env->book_id < 0 || env->drawer_id < 0) &&
+ (env->socket_id >= 0 || env->book_id >= 0 || env->drawer_id >= 0)) {
+ error_setg(errp,
+ "Please define all or none of the topology geometry attributes");
+ return false;
+ }
+
+ /* If one value is unset all are unset -> calculate defaults */
+ if (env->socket_id < 0) {
+ env->socket_id = s390_std_socket(env->core_id, smp);
+ env->book_id = s390_std_book(env->core_id, smp);
+ env->drawer_id = s390_std_drawer(env->core_id, smp);
+ }
+
+ /*
+ * When the user specifies the entitlement as 'auto' on the command line,
+ * QEMU will set the entitlement as:
+ * Medium when the CPU is not dedicated.
+ * High when dedicated is true.
+ */
+ if (env->entitlement == S390_CPU_ENTITLEMENT_AUTO) {
+ if (env->dedicated) {
+ env->entitlement = S390_CPU_ENTITLEMENT_HIGH;
+ } else {
+ env->entitlement = S390_CPU_ENTITLEMENT_MEDIUM;
+ }
+ }
+ return true;
+}
+
+/**
+ * s390_topology_check:
+ * @socket_id: socket to check
+ * @book_id: book to check
+ * @drawer_id: drawer to check
+ * @entitlement: entitlement to check
+ * @dedicated: dedication to check
+ * @errp: Error pointer
+ *
+ * The function checks if the topology
+ * attributes fits inside the system topology.
+ *
+ * Returns false if the specified topology does not match with
+ * the machine topology.
+ */
+static bool s390_topology_check(uint16_t socket_id, uint16_t book_id,
+ uint16_t drawer_id, uint16_t entitlement,
+ bool dedicated, Error **errp)
+{
+ CpuTopology *smp = &current_machine->smp;
+
+ if (socket_id >= smp->sockets) {
+ error_setg(errp, "Unavailable socket: %d", socket_id);
+ return false;
+ }
+ if (book_id >= smp->books) {
+ error_setg(errp, "Unavailable book: %d", book_id);
+ return false;
+ }
+ if (drawer_id >= smp->drawers) {
+ error_setg(errp, "Unavailable drawer: %d", drawer_id);
+ return false;
+ }
+ if (entitlement >= S390_CPU_ENTITLEMENT__MAX) {
+ error_setg(errp, "Unknown entitlement: %d", entitlement);
+ return false;
+ }
+ if (dedicated && (entitlement == S390_CPU_ENTITLEMENT_LOW ||
+ entitlement == S390_CPU_ENTITLEMENT_MEDIUM)) {
+ error_setg(errp, "A dedicated CPU implies high entitlement");
+ return false;
+ }
+ return true;
+}
+
+/**
+ * s390_topology_need_report
+ * @cpu: Current cpu
+ * @drawer_id: future drawer ID
+ * @book_id: future book ID
+ * @socket_id: future socket ID
+ * @entitlement: future entitlement
+ * @dedicated: future dedicated
+ *
+ * A modified topology change report is needed if the topology
+ * tree or the topology attributes change.
+ */
+static bool s390_topology_need_report(S390CPU *cpu, int drawer_id,
+ int book_id, int socket_id,
+ uint16_t entitlement, bool dedicated)
+{
+ return cpu->env.drawer_id != drawer_id ||
+ cpu->env.book_id != book_id ||
+ cpu->env.socket_id != socket_id ||
+ cpu->env.entitlement != entitlement ||
+ cpu->env.dedicated != dedicated;
+}
+
+/**
+ * s390_update_cpu_props:
+ * @ms: the machine state
+ * @cpu: the CPU for which to update the properties from the environment.
+ *
+ */
+static void s390_update_cpu_props(MachineState *ms, S390CPU *cpu)
+{
+ CpuInstanceProperties *props;
+
+ props = &ms->possible_cpus->cpus[cpu->env.core_id].props;
+
+ props->socket_id = cpu->env.socket_id;
+ props->book_id = cpu->env.book_id;
+ props->drawer_id = cpu->env.drawer_id;
+}
+
+/**
+ * s390_topology_setup_cpu:
+ * @ms: MachineState used to initialize the topology structure on
+ * first call.
+ * @cpu: the new S390CPU to insert in the topology structure
+ * @errp: the error pointer
+ *
+ * Called from CPU hotplug to check and setup the CPU attributes
+ * before the CPU is inserted in the topology.
+ * There is no need to update the MTCR explicitly here because it
+ * will be updated by KVM on creation of the new CPU.
+ */
+void s390_topology_setup_cpu(MachineState *ms, S390CPU *cpu, Error **errp)
+{
+ int entry;
+
+ /*
+ * We do not want to initialize the topology if the CPU model
+ * does not support topology, consequently, we have to wait for
+ * the first CPU to be realized, which realizes the CPU model
+ * to initialize the topology structures.
+ *
+ * s390_topology_setup_cpu() is called from the CPU hotplug.
+ */
+ if (!s390_topology.cores_per_socket) {
+ s390_topology_init(ms);
+ }
+
+ if (!s390_topology_cpu_default(cpu, errp)) {
+ return;
+ }
+
+ if (!s390_topology_check(cpu->env.socket_id, cpu->env.book_id,
+ cpu->env.drawer_id, cpu->env.entitlement,
+ cpu->env.dedicated, errp)) {
+ return;
+ }
+
+ /* Do we still have space in the socket */
+ entry = s390_socket_nb(cpu);
+ if (s390_topology.cores_per_socket[entry] >= ms->smp.cores) {
+ error_setg(errp, "No more space on this socket");
+ return;
+ }
+
+ /* Update the count of cores in sockets */
+ s390_topology.cores_per_socket[entry] += 1;
+
+ /* topology tree is reflected in props */
+ s390_update_cpu_props(ms, cpu);
+}
+
+static void s390_change_topology(uint16_t core_id,
+ bool has_socket_id, uint16_t socket_id,
+ bool has_book_id, uint16_t book_id,
+ bool has_drawer_id, uint16_t drawer_id,
+ bool has_entitlement,
+ CpuS390Entitlement entitlement,
+ bool has_dedicated, bool dedicated,
+ Error **errp)
+{
+ MachineState *ms = current_machine;
+ int old_socket_entry;
+ int new_socket_entry;
+ bool report_needed;
+ S390CPU *cpu;
+
+ cpu = s390_cpu_addr2state(core_id);
+ if (!cpu) {
+ error_setg(errp, "Core-id %d does not exist!", core_id);
+ return;
+ }
+
+ /* Get attributes not provided from cpu and verify the new topology */
+ if (!has_socket_id) {
+ socket_id = cpu->env.socket_id;
+ }
+ if (!has_book_id) {
+ book_id = cpu->env.book_id;
+ }
+ if (!has_drawer_id) {
+ drawer_id = cpu->env.drawer_id;
+ }
+ if (!has_dedicated) {
+ dedicated = cpu->env.dedicated;
+ }
+
+ /*
+ * When the user specifies the entitlement as 'auto' on the command line,
+ * QEMU will set the entitlement as:
+ * Medium when the CPU is not dedicated.
+ * High when dedicated is true.
+ */
+ if (!has_entitlement || entitlement == S390_CPU_ENTITLEMENT_AUTO) {
+ if (dedicated) {
+ entitlement = S390_CPU_ENTITLEMENT_HIGH;
+ } else {
+ entitlement = S390_CPU_ENTITLEMENT_MEDIUM;
+ }
+ }
+
+ if (!s390_topology_check(socket_id, book_id, drawer_id,
+ entitlement, dedicated, errp)) {
+ return;
+ }
+
+ /* Check for space on new socket */
+ old_socket_entry = s390_socket_nb(cpu);
+ new_socket_entry = s390_socket_nb_from_ids(drawer_id, book_id, socket_id);
+
+ if (new_socket_entry != old_socket_entry) {
+ if (s390_topology.cores_per_socket[new_socket_entry] >=
+ ms->smp.cores) {
+ error_setg(errp, "No more space on this socket");
+ return;
+ }
+ /* Update the count of cores in sockets */
+ s390_topology.cores_per_socket[new_socket_entry] += 1;
+ s390_topology.cores_per_socket[old_socket_entry] -= 1;
+ }
+
+ /* Check if we will need to report the modified topology */
+ report_needed = s390_topology_need_report(cpu, drawer_id, book_id,
+ socket_id, entitlement,
+ dedicated);
+
+ /* All checks done, report new topology into the vCPU */
+ cpu->env.drawer_id = drawer_id;
+ cpu->env.book_id = book_id;
+ cpu->env.socket_id = socket_id;
+ cpu->env.dedicated = dedicated;
+ cpu->env.entitlement = entitlement;
+
+ /* topology tree is reflected in props */
+ s390_update_cpu_props(ms, cpu);
+
+ /* Advertise the topology change */
+ if (report_needed) {
+ s390_cpu_topology_set_changed(true);
+ }
+}
+
+void qmp_set_cpu_topology(uint16_t core,
+ bool has_socket, uint16_t socket,
+ bool has_book, uint16_t book,
+ bool has_drawer, uint16_t drawer,
+ bool has_entitlement, CpuS390Entitlement entitlement,
+ bool has_dedicated, bool dedicated,
+ Error **errp)
+{
+ if (!s390_has_topology()) {
+ error_setg(errp, "This machine doesn't support topology");
+ return;
+ }
+
+ s390_change_topology(core, has_socket, socket, has_book, book,
+ has_drawer, drawer, has_entitlement, entitlement,
+ has_dedicated, dedicated, errp);
+}
+
+CpuPolarizationInfo *qmp_query_s390x_cpu_polarization(Error **errp)
+{
+ CpuPolarizationInfo *info = g_new0(CpuPolarizationInfo, 1);
+
+ info->polarization = s390_topology.polarization;
+ return info;
+}
diff --git a/hw/s390x/meson.build b/hw/s390x/meson.build
index 6fd0968..482fd13 100644
--- a/hw/s390x/meson.build
+++ b/hw/s390x/meson.build
@@ -23,6 +23,7 @@ s390x_ss.add(when: 'CONFIG_KVM', if_true: files(
's390-skeys-kvm.c',
's390-stattrib-kvm.c',
's390-pci-kvm.c',
+ 'cpu-topology.c',
))
s390x_ss.add(when: 'CONFIG_TCG', if_true: files(
'tod-tcg.c',
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 2d75f21..6012165 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -45,6 +45,7 @@
#include "target/s390x/kvm/pv.h"
#include "migration/blocker.h"
#include "qapi/visitor.h"
+#include "hw/s390x/cpu-topology.h"
static Error *pv_mig_blocker;
@@ -123,6 +124,9 @@ static void subsystem_reset(void)
device_cold_reset(dev);
}
}
+ if (s390_has_topology()) {
+ s390_topology_reset();
+ }
}
static int virtio_ccw_hcall_notify(const uint64_t *args)
@@ -309,10 +313,18 @@ static void s390_cpu_plug(HotplugHandler *hotplug_dev,
{
MachineState *ms = MACHINE(hotplug_dev);
S390CPU *cpu = S390_CPU(dev);
+ ERRP_GUARD();
g_assert(!ms->possible_cpus->cpus[cpu->env.core_id].cpu);
ms->possible_cpus->cpus[cpu->env.core_id].cpu = OBJECT(dev);
+ if (s390_has_topology()) {
+ s390_topology_setup_cpu(ms, cpu, errp);
+ if (*errp) {
+ return;
+ }
+ }
+
if (dev->hotplugged) {
raise_irq_cpu_hotplug();
}
@@ -562,11 +574,20 @@ static const CPUArchIdList *s390_possible_cpu_arch_ids(MachineState *ms)
sizeof(CPUArchId) * max_cpus);
ms->possible_cpus->len = max_cpus;
for (i = 0; i < ms->possible_cpus->len; i++) {
+ CpuInstanceProperties *props = &ms->possible_cpus->cpus[i].props;
+
ms->possible_cpus->cpus[i].type = ms->cpu_type;
ms->possible_cpus->cpus[i].vcpus_count = 1;
ms->possible_cpus->cpus[i].arch_id = i;
- ms->possible_cpus->cpus[i].props.has_core_id = true;
- ms->possible_cpus->cpus[i].props.core_id = i;
+
+ props->has_core_id = true;
+ props->core_id = i;
+ props->has_socket_id = true;
+ props->socket_id = s390_std_socket(i, &ms->smp);
+ props->has_book_id = true;
+ props->book_id = s390_std_book(i, &ms->smp);
+ props->has_drawer_id = true;
+ props->drawer_id = s390_std_drawer(i, &ms->smp);
}
return ms->possible_cpus;
@@ -744,6 +765,8 @@ static void ccw_machine_class_init(ObjectClass *oc, void *data)
mc->no_sdcard = 1;
mc->max_cpus = S390_MAX_CPUS;
mc->has_hotpluggable_cpus = true;
+ mc->smp_props.books_supported = true;
+ mc->smp_props.drawers_supported = true;
assert(!mc->get_hotplug_handler);
mc->get_hotplug_handler = s390_get_hotplug_handler;
mc->cpu_index_to_instance_props = s390_cpu_index_to_props;
@@ -853,6 +876,8 @@ static void ccw_machine_8_1_class_options(MachineClass *mc)
{
ccw_machine_8_2_class_options(mc);
compat_props_add(mc->compat_props, hw_compat_8_1, hw_compat_8_1_len);
+ mc->smp_props.drawers_supported = false;
+ mc->smp_props.books_supported = false;
}
DEFINE_CCW_MACHINE(8_1, "8.1", false);
diff --git a/hw/s390x/sclp.c b/hw/s390x/sclp.c
index eff7447..d339cbb 100644
--- a/hw/s390x/sclp.c
+++ b/hw/s390x/sclp.c
@@ -20,6 +20,7 @@
#include "hw/s390x/event-facility.h"
#include "hw/s390x/s390-pci-bus.h"
#include "hw/s390x/ipl.h"
+#include "hw/s390x/cpu-topology.h"
static inline SCLPDevice *get_sclp_device(void)
{
@@ -123,6 +124,10 @@ static void read_SCP_info(SCLPDevice *sclp, SCCB *sccb)
return;
}
+ if (s390_has_topology()) {
+ read_info->stsi_parm = SCLP_READ_SCP_INFO_MNEST;
+ }
+
/* CPU information */
prepare_cpu_entries(machine, entries_start, &cpu_count);
read_info->entries_cpu = cpu_to_be16(cpu_count);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 43a56dc..a735999 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -135,12 +135,16 @@ typedef struct {
* @clusters_supported - whether clusters are supported by the machine
* @has_clusters - whether clusters are explicitly specified in the user
* provided SMP configuration
+ * @books_supported - whether books are supported by the machine
+ * @drawers_supported - whether drawers are supported by the machine
*/
typedef struct {
bool prefer_sockets;
bool dies_supported;
bool clusters_supported;
bool has_clusters;
+ bool books_supported;
+ bool drawers_supported;
} SMPCompatProps;
/**
@@ -323,7 +327,9 @@ typedef struct DeviceMemoryState {
/**
* CpuTopology:
* @cpus: the number of present logical processors on the machine
- * @sockets: the number of sockets on the machine
+ * @drawers: the number of drawers on the machine
+ * @books: the number of books in one drawer
+ * @sockets: the number of sockets in one book
* @dies: the number of dies in one socket
* @clusters: the number of clusters in one die
* @cores: the number of cores in one cluster
@@ -332,6 +338,8 @@ typedef struct DeviceMemoryState {
*/
typedef struct CpuTopology {
unsigned int cpus;
+ unsigned int drawers;
+ unsigned int books;
unsigned int sockets;
unsigned int dies;
unsigned int clusters;
diff --git a/include/hw/qdev-properties-system.h b/include/hw/qdev-properties-system.h
index 0ac327a..e4f8a13 100644
--- a/include/hw/qdev-properties-system.h
+++ b/include/hw/qdev-properties-system.h
@@ -22,6 +22,7 @@ extern const PropertyInfo qdev_prop_audiodev;
extern const PropertyInfo qdev_prop_off_auto_pcibar;
extern const PropertyInfo qdev_prop_pcie_link_speed;
extern const PropertyInfo qdev_prop_pcie_link_width;
+extern const PropertyInfo qdev_prop_cpus390entitlement;
#define DEFINE_PROP_PCI_DEVFN(_n, _s, _f, _d) \
DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_pci_devfn, int32_t)
@@ -73,5 +74,8 @@ extern const PropertyInfo qdev_prop_pcie_link_width;
#define DEFINE_PROP_UUID_NODEFAULT(_name, _state, _field) \
DEFINE_PROP(_name, _state, _field, qdev_prop_uuid, QemuUUID)
+#define DEFINE_PROP_CPUS390ENTITLEMENT(_n, _s, _f, _d) \
+ DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_cpus390entitlement, \
+ CpuS390Entitlement)
#endif
diff --git a/include/hw/s390x/cpu-topology.h b/include/hw/s390x/cpu-topology.h
new file mode 100644
index 0000000..c064f42
--- /dev/null
+++ b/include/hw/s390x/cpu-topology.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CPU Topology
+ *
+ * Copyright IBM Corp. 2022, 2023
+ * Author(s): Pierre Morel <pmorel@linux.ibm.com>
+ *
+ */
+#ifndef HW_S390X_CPU_TOPOLOGY_H
+#define HW_S390X_CPU_TOPOLOGY_H
+
+#ifndef CONFIG_USER_ONLY
+
+#include "qemu/queue.h"
+#include "hw/boards.h"
+#include "qapi/qapi-types-machine-target.h"
+
+#define S390_TOPOLOGY_CPU_IFL 0x03
+
+typedef struct S390TopologyId {
+ uint8_t sentinel;
+ uint8_t drawer;
+ uint8_t book;
+ uint8_t socket;
+ uint8_t type;
+ uint8_t vertical:1;
+ uint8_t entitlement:2;
+ uint8_t dedicated;
+ uint8_t origin;
+} S390TopologyId;
+
+typedef struct S390TopologyEntry {
+ QTAILQ_ENTRY(S390TopologyEntry) next;
+ S390TopologyId id;
+ uint64_t mask;
+} S390TopologyEntry;
+
+typedef struct S390Topology {
+ uint8_t *cores_per_socket;
+ CpuS390Polarization polarization;
+} S390Topology;
+
+typedef QTAILQ_HEAD(, S390TopologyEntry) S390TopologyList;
+
+#ifdef CONFIG_KVM
+bool s390_has_topology(void);
+void s390_topology_setup_cpu(MachineState *ms, S390CPU *cpu, Error **errp);
+void s390_topology_reset(void);
+#else
+static inline bool s390_has_topology(void)
+{
+ return false;
+}
+static inline void s390_topology_setup_cpu(MachineState *ms,
+ S390CPU *cpu,
+ Error **errp) {}
+static inline void s390_topology_reset(void)
+{
+ /* Unreachable, CPU topology not implemented for TCG */
+ assert(false);
+}
+#endif
+
+extern S390Topology s390_topology;
+
+static inline int s390_std_socket(int n, CpuTopology *smp)
+{
+ return (n / smp->cores) % smp->sockets;
+}
+
+static inline int s390_std_book(int n, CpuTopology *smp)
+{
+ return (n / (smp->cores * smp->sockets)) % smp->books;
+}
+
+static inline int s390_std_drawer(int n, CpuTopology *smp)
+{
+ return (n / (smp->cores * smp->sockets * smp->books)) % smp->drawers;
+}
+
+#endif /* CONFIG_USER_ONLY */
+
+#endif
diff --git a/include/hw/s390x/s390-virtio-ccw.h b/include/hw/s390x/s390-virtio-ccw.h
index 9bba21a..c1d46e7 100644
--- a/include/hw/s390x/s390-virtio-ccw.h
+++ b/include/hw/s390x/s390-virtio-ccw.h
@@ -30,6 +30,12 @@ struct S390CcwMachineState {
uint8_t loadparm[8];
};
+#define S390_PTF_REASON_NONE (0x00 << 8)
+#define S390_PTF_REASON_DONE (0x01 << 8)
+#define S390_PTF_REASON_BUSY (0x02 << 8)
+#define S390_TOPO_FC_MASK 0xffUL
+void s390_handle_ptf(S390CPU *cpu, uint8_t r1, uintptr_t ra);
+
struct S390CcwMachineClass {
/*< private >*/
MachineClass parent_class;
diff --git a/include/hw/s390x/sclp.h b/include/hw/s390x/sclp.h
index cf1f2ef..9aef6d9 100644
--- a/include/hw/s390x/sclp.h
+++ b/include/hw/s390x/sclp.h
@@ -112,11 +112,13 @@ typedef struct CPUEntry {
} QEMU_PACKED CPUEntry;
#define SCLP_READ_SCP_INFO_FIXED_CPU_OFFSET 128
+#define SCLP_READ_SCP_INFO_MNEST 4
typedef struct ReadInfo {
SCCBHeader h;
uint16_t rnmax;
uint8_t rnsize;
- uint8_t _reserved1[16 - 11]; /* 11-15 */
+ uint8_t _reserved1[15 - 11]; /* 11-14 */
+ uint8_t stsi_parm; /* 15-15 */
uint16_t entries_cpu; /* 16-17 */
uint16_t offset_cpu; /* 18-19 */
uint8_t _reserved2[24 - 20]; /* 20-23 */
diff --git a/qapi/machine-common.json b/qapi/machine-common.json
new file mode 100644
index 0000000..fa6bd71
--- /dev/null
+++ b/qapi/machine-common.json
@@ -0,0 +1,21 @@
+# -*- Mode: Python -*-
+# vim: filetype=python
+#
+# This work is licensed under the terms of the GNU GPL, version 2 or later.
+# See the COPYING file in the top-level directory.
+
+##
+# = Machines S390 data types
+##
+
+##
+# @CpuS390Entitlement:
+#
+# An enumeration of CPU entitlements that can be assumed by a virtual
+# S390 CPU
+#
+# Since: 8.2
+##
+{ 'enum': 'CpuS390Entitlement',
+ 'prefix': 'S390_CPU_ENTITLEMENT',
+ 'data': [ 'auto', 'low', 'medium', 'high' ] }
diff --git a/qapi/machine-target.json b/qapi/machine-target.json
index f0a6b72..4e55adb 100644
--- a/qapi/machine-target.json
+++ b/qapi/machine-target.json
@@ -4,6 +4,8 @@
# This work is licensed under the terms of the GNU GPL, version 2 or later.
# See the COPYING file in the top-level directory.
+{ 'include': 'machine-common.json' }
+
##
# @CpuModelInfo:
#
@@ -361,3 +363,122 @@
'TARGET_MIPS',
'TARGET_LOONGARCH64',
'TARGET_RISCV' ] } }
+
+##
+# @CpuS390Polarization:
+#
+# An enumeration of CPU polarization that can be assumed by a virtual
+# S390 CPU
+#
+# Since: 8.2
+##
+{ 'enum': 'CpuS390Polarization',
+ 'prefix': 'S390_CPU_POLARIZATION',
+ 'data': [ 'horizontal', 'vertical' ],
+ 'if': 'TARGET_S390X'
+}
+
+##
+# @set-cpu-topology:
+#
+# Modify the topology by moving the CPU inside the topology tree,
+# or by changing a modifier attribute of a CPU.
+# Absent values will not be modified.
+#
+# @core-id: the vCPU ID to be moved
+#
+# @socket-id: destination socket to move the vCPU to
+#
+# @book-id: destination book to move the vCPU to
+#
+# @drawer-id: destination drawer to move the vCPU to
+#
+# @entitlement: entitlement to set
+#
+# @dedicated: whether the provisioning of real to virtual CPU is dedicated
+#
+# Features:
+#
+# @unstable: This command is experimental.
+#
+# Returns: Nothing on success.
+#
+# Since: 8.2
+##
+{ 'command': 'set-cpu-topology',
+ 'data': {
+ 'core-id': 'uint16',
+ '*socket-id': 'uint16',
+ '*book-id': 'uint16',
+ '*drawer-id': 'uint16',
+ '*entitlement': 'CpuS390Entitlement',
+ '*dedicated': 'bool'
+ },
+ 'features': [ 'unstable' ],
+ 'if': { 'all': [ 'TARGET_S390X' , 'CONFIG_KVM' ] }
+}
+
+##
+# @CPU_POLARIZATION_CHANGE:
+#
+# Emitted when the guest asks to change the polarization.
+#
+# The guest can tell the host (via the PTF instruction) whether the
+# CPUs should be provisioned using horizontal or vertical polarization.
+#
+# On horizontal polarization the host is expected to provision all vCPUs
+# equally.
+#
+# On vertical polarization the host can provision each vCPU differently.
+# The guest will get information on the details of the provisioning
+# the next time it uses the STSI(15) instruction.
+#
+# @polarization: polarization specified by the guest
+#
+# Features:
+#
+# @unstable: This event is experimental.
+#
+# Since: 8.2
+#
+# Example:
+#
+# <- { "event": "CPU_POLARIZATION_CHANGE",
+# "data": { "polarization": "horizontal" },
+# "timestamp": { "seconds": 1401385907, "microseconds": 422329 } }
+##
+{ 'event': 'CPU_POLARIZATION_CHANGE',
+ 'data': { 'polarization': 'CpuS390Polarization' },
+ 'features': [ 'unstable' ],
+ 'if': { 'all': [ 'TARGET_S390X', 'CONFIG_KVM' ] }
+}
+
+##
+# @CpuPolarizationInfo:
+#
+# The result of a CPU polarization query.
+#
+# @polarization: the CPU polarization
+#
+# Since: 8.2
+##
+{ 'struct': 'CpuPolarizationInfo',
+ 'data': { 'polarization': 'CpuS390Polarization' },
+ 'if': { 'all': [ 'TARGET_S390X', 'CONFIG_KVM' ] }
+}
+
+##
+# @query-s390x-cpu-polarization:
+#
+# Features:
+#
+# @unstable: This command is experimental.
+#
+# Returns: the machine's CPU polarization
+#
+# Since: 8.2
+##
+{ 'command': 'query-s390x-cpu-polarization', 'returns': 'CpuPolarizationInfo',
+ 'features': [ 'unstable' ],
+ 'if': { 'all': [ 'TARGET_S390X', 'CONFIG_KVM' ] }
+}
diff --git a/qapi/machine.json b/qapi/machine.json
index a08b657..6c9d2f6 100644
--- a/qapi/machine.json
+++ b/qapi/machine.json
@@ -9,6 +9,7 @@
##
{ 'include': 'common.json' }
+{ 'include': 'machine-common.json' }
##
# @SysEmuTarget:
@@ -56,9 +57,16 @@
#
# @cpu-state: the virtual CPU's state
#
+# @dedicated: the virtual CPU's dedication (since 8.2)
+#
+# @entitlement: the virtual CPU's entitlement (since 8.2)
+#
# Since: 2.12
##
-{ 'struct': 'CpuInfoS390', 'data': { 'cpu-state': 'CpuS390State' } }
+{ 'struct': 'CpuInfoS390',
+ 'data': { 'cpu-state': 'CpuS390State',
+ '*dedicated': 'bool',
+ '*entitlement': 'CpuS390Entitlement' } }
##
# @CpuInfoFast:
@@ -71,8 +79,7 @@
#
# @thread-id: ID of the underlying host thread
#
-# @props: properties describing to which node/socket/core/thread
-# virtual CPU belongs to, provided if supported by board
+# @props: properties associated with a virtual CPU, e.g. the socket id
#
# @target: the QEMU system emulation target, which determines which
# additional fields will be listed (since 3.0)
@@ -899,29 +906,46 @@
# should be passed by management with device_add command when a CPU is
# being hotplugged.
#
+# Which members are optional and which mandatory depends on the
+# architecture and board.
+#
+# For s390x see :ref:`cpu-topology-s390x`.
+#
+# The ids other than the node-id specify the position of the CPU
+# within the CPU topology (as defined by the machine property "smp",
+# thus see also type @SMPConfiguration)
+#
# @node-id: NUMA node ID the CPU belongs to
#
-# @socket-id: socket number within node/board the CPU belongs to
+# @drawer-id: drawer number within CPU topology the CPU belongs to
+# (since 8.2)
#
-# @die-id: die number within socket the CPU belongs to (since 4.1)
+# @book-id: book number within parent container the CPU belongs to
+# (since 8.2)
#
-# @cluster-id: cluster number within die the CPU belongs to (since
-# 7.1)
+# @socket-id: socket number within parent container the CPU belongs to
#
-# @core-id: core number within cluster the CPU belongs to
+# @die-id: die number within the parent container the CPU belongs to
+# (since 4.1)
#
-# @thread-id: thread number within core the CPU belongs to
+# @cluster-id: cluster number within the parent container the CPU
+# belongs to (since 7.1)
#
-# Note: currently there are 6 properties that could be present but
-# management should be prepared to pass through other properties
-# with device_add command to allow for future interface extension.
-# This also requires the filed names to be kept in sync with the
-# properties passed to -device/device_add.
+# @core-id: core number within the parent container the CPU
+# belongs to
+#
+# @thread-id: thread number within the core the CPU belongs to
+#
+# Note: management should be prepared to pass through additional
+# properties with device_add.
#
# Since: 2.7
##
{ 'struct': 'CpuInstanceProperties',
+ # Keep these in sync with the properties device_add accepts
'data': { '*node-id': 'int',
+ '*drawer-id': 'int',
+ '*book-id': 'int',
'*socket-id': 'int',
'*die-id': 'int',
'*cluster-id': 'int',
@@ -1478,26 +1502,43 @@
# Schema for CPU topology configuration. A missing value lets QEMU
# figure out a suitable value based on the ones that are provided.
#
-# @cpus: number of virtual CPUs in the virtual machine
-#
-# @sockets: number of sockets in the CPU topology
+# The members other than @cpus and @maxcpus define a topology of
+# containers.
#
-# @dies: number of dies per socket in the CPU topology
+# The ordering from highest/coarsest to lowest/finest is:
+# @drawers, @books, @sockets, @dies, @clusters, @cores, @threads.
#
-# @clusters: number of clusters per die in the CPU topology (since
-# 7.0)
+# Different architectures support different subsets of topology
+# containers.
#
-# @cores: number of cores per cluster in the CPU topology
+# For example, s390x does not have clusters and dies, and the socket
+# is the parent container of cores.
#
-# @threads: number of threads per core in the CPU topology
+# @cpus: number of virtual CPUs in the virtual machine
#
# @maxcpus: maximum number of hotpluggable virtual CPUs in the virtual
# machine
#
+# @drawers: number of drawers in the CPU topology (since 8.2)
+#
+# @books: number of books in the CPU topology (since 8.2)
+#
+# @sockets: number of sockets per parent container
+#
+# @dies: number of dies per parent container
+#
+# @clusters: number of clusters per parent container (since 7.0)
+#
+# @cores: number of cores per parent container
+#
+# @threads: number of threads per core
+#
# Since: 6.1
##
{ 'struct': 'SMPConfiguration', 'data': {
'*cpus': 'int',
+ '*drawers': 'int',
+ '*books': 'int',
'*sockets': 'int',
'*dies': 'int',
'*clusters': 'int',
diff --git a/qapi/meson.build b/qapi/meson.build
index 60a668b..f81a375 100644
--- a/qapi/meson.build
+++ b/qapi/meson.build
@@ -36,6 +36,7 @@ qapi_all_modules = [
'error',
'introspect',
'job',
+ 'machine-common',
'machine',
'machine-target',
'migration',
diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json
index 6594afb..c01ec33 100644
--- a/qapi/qapi-schema.json
+++ b/qapi/qapi-schema.json
@@ -66,6 +66,7 @@
{ 'include': 'introspect.json' }
{ 'include': 'qom.json' }
{ 'include': 'qdev.json' }
+{ 'include': 'machine-common.json' }
{ 'include': 'machine.json' }
{ 'include': 'machine-target.json' }
{ 'include': 'replay.json' }
diff --git a/qemu-options.hx b/qemu-options.hx
index 54a7e94..e26230b 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -272,11 +272,14 @@ SRST
ERST
DEF("smp", HAS_ARG, QEMU_OPTION_smp,
- "-smp [[cpus=]n][,maxcpus=maxcpus][,sockets=sockets][,dies=dies][,clusters=clusters][,cores=cores][,threads=threads]\n"
+ "-smp [[cpus=]n][,maxcpus=maxcpus][,drawers=drawers][,books=books][,sockets=sockets]\n"
+ " [,dies=dies][,clusters=clusters][,cores=cores][,threads=threads]\n"
" set the number of initial CPUs to 'n' [default=1]\n"
" maxcpus= maximum number of total CPUs, including\n"
" offline CPUs for hotplug, etc\n"
- " sockets= number of sockets on the machine board\n"
+ " drawers= number of drawers on the machine board\n"
+ " books= number of books in one drawer\n"
+ " sockets= number of sockets in one book\n"
" dies= number of dies in one socket\n"
" clusters= number of clusters in one die\n"
" cores= number of cores in one cluster\n"
diff --git a/system/vl.c b/system/vl.c
index 3100ac0..92d29bf 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -727,6 +727,12 @@ static QemuOptsList qemu_smp_opts = {
.name = "cpus",
.type = QEMU_OPT_NUMBER,
}, {
+ .name = "drawers",
+ .type = QEMU_OPT_NUMBER,
+ }, {
+ .name = "books",
+ .type = QEMU_OPT_NUMBER,
+ }, {
.name = "sockets",
.type = QEMU_OPT_NUMBER,
}, {
diff --git a/target/s390x/cpu-sysemu.c b/target/s390x/cpu-sysemu.c
index 8112561..1cd30c1 100644
--- a/target/s390x/cpu-sysemu.c
+++ b/target/s390x/cpu-sysemu.c
@@ -307,3 +307,16 @@ void s390_do_cpu_set_diag318(CPUState *cs, run_on_cpu_data arg)
kvm_s390_set_diag318(cs, arg.host_ulong);
}
}
+
+void s390_cpu_topology_set_changed(bool changed)
+{
+ int ret;
+
+ if (kvm_enabled()) {
+ ret = kvm_s390_topology_set_mtcr(changed);
+ if (ret) {
+ error_report("Failed to set Modified Topology Change Report: %s",
+ strerror(-ret));
+ }
+ }
+}
diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c
index 6093ab0..6acfa1c 100644
--- a/target/s390x/cpu.c
+++ b/target/s390x/cpu.c
@@ -31,12 +31,14 @@
#include "qapi/qapi-types-machine.h"
#include "sysemu/hw_accel.h"
#include "hw/qdev-properties.h"
+#include "hw/qdev-properties-system.h"
#include "fpu/softfloat-helpers.h"
#include "disas/capstone.h"
#include "sysemu/tcg.h"
#ifndef CONFIG_USER_ONLY
#include "sysemu/reset.h"
#endif
+#include "hw/s390x/cpu-topology.h"
#define CR0_RESET 0xE0UL
#define CR14_RESET 0xC2000000UL;
@@ -145,6 +147,14 @@ static void s390_query_cpu_fast(CPUState *cpu, CpuInfoFast *value)
S390CPU *s390_cpu = S390_CPU(cpu);
value->u.s390x.cpu_state = s390_cpu->env.cpu_state;
+#if !defined(CONFIG_USER_ONLY)
+ if (s390_has_topology()) {
+ value->u.s390x.has_dedicated = true;
+ value->u.s390x.dedicated = s390_cpu->env.dedicated;
+ value->u.s390x.has_entitlement = true;
+ value->u.s390x.entitlement = s390_cpu->env.entitlement;
+ }
+#endif
}
/* S390CPUClass::reset() */
@@ -290,6 +300,12 @@ static const gchar *s390_gdb_arch_name(CPUState *cs)
static Property s390x_cpu_properties[] = {
#if !defined(CONFIG_USER_ONLY)
DEFINE_PROP_UINT32("core-id", S390CPU, env.core_id, 0),
+ DEFINE_PROP_INT32("socket-id", S390CPU, env.socket_id, -1),
+ DEFINE_PROP_INT32("book-id", S390CPU, env.book_id, -1),
+ DEFINE_PROP_INT32("drawer-id", S390CPU, env.drawer_id, -1),
+ DEFINE_PROP_BOOL("dedicated", S390CPU, env.dedicated, false),
+ DEFINE_PROP_CPUS390ENTITLEMENT("entitlement", S390CPU, env.entitlement,
+ S390_CPU_ENTITLEMENT_AUTO),
#endif
DEFINE_PROP_END_OF_LIST()
};
diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h
index 7bea707..40c5ced 100644
--- a/target/s390x/cpu.h
+++ b/target/s390x/cpu.h
@@ -30,6 +30,7 @@
#include "exec/cpu-defs.h"
#include "qemu/cpu-float.h"
#include "tcg/tcg_s390x.h"
+#include "qapi/qapi-types-machine-common.h"
#define ELF_MACHINE_UNAME "S390X"
@@ -132,6 +133,11 @@ struct CPUArchState {
#if !defined(CONFIG_USER_ONLY)
uint32_t core_id; /* PoP "CPU address", same as cpu_index */
+ int32_t socket_id;
+ int32_t book_id;
+ int32_t drawer_id;
+ bool dedicated;
+ CpuS390Entitlement entitlement; /* Used only for vertical polarization */
uint64_t cpuid;
#endif
@@ -564,6 +570,29 @@ typedef struct SysIB_322 {
} SysIB_322;
QEMU_BUILD_BUG_ON(sizeof(SysIB_322) != 4096);
+/*
+ * Topology Magnitude fields (MAG) indicates the maximum number of
+ * topology list entries (TLE) at the corresponding nesting level.
+ */
+#define S390_TOPOLOGY_MAG 6
+#define S390_TOPOLOGY_MAG6 0
+#define S390_TOPOLOGY_MAG5 1
+#define S390_TOPOLOGY_MAG4 2
+#define S390_TOPOLOGY_MAG3 3
+#define S390_TOPOLOGY_MAG2 4
+#define S390_TOPOLOGY_MAG1 5
+/* Configuration topology */
+typedef struct SysIB_151x {
+ uint8_t reserved0[2];
+ uint16_t length;
+ uint8_t mag[S390_TOPOLOGY_MAG];
+ uint8_t reserved1;
+ uint8_t mnest;
+ uint32_t reserved2;
+ char tle[];
+} SysIB_151x;
+QEMU_BUILD_BUG_ON(sizeof(SysIB_151x) != 16);
+
typedef union SysIB {
SysIB_111 sysib_111;
SysIB_121 sysib_121;
@@ -571,9 +600,62 @@ typedef union SysIB {
SysIB_221 sysib_221;
SysIB_222 sysib_222;
SysIB_322 sysib_322;
+ SysIB_151x sysib_151x;
} SysIB;
QEMU_BUILD_BUG_ON(sizeof(SysIB) != 4096);
+/*
+ * CPU Topology List provided by STSI with fc=15 provides a list
+ * of two different Topology List Entries (TLE) types to specify
+ * the topology hierarchy.
+ *
+ * - Container Topology List Entry
+ * Defines a container to contain other Topology List Entries
+ * of any type, nested containers or CPU.
+ * - CPU Topology List Entry
+ * Specifies the CPUs position, type, entitlement and polarization
+ * of the CPUs contained in the last container TLE.
+ *
+ * There can be theoretically up to five levels of containers, QEMU
+ * uses only three levels, the drawer's, book's and socket's level.
+ *
+ * A container with a nesting level (NL) greater than 1 can only
+ * contain another container of nesting level NL-1.
+ *
+ * A container of nesting level 1 (socket), contains as many CPU TLE
+ * as needed to describe the position and qualities of all CPUs inside
+ * the container.
+ * The qualities of a CPU are polarization, entitlement and type.
+ *
+ * The CPU TLE defines the position of the CPUs of identical qualities
+ * using a 64bits mask which first bit has its offset defined by
+ * the CPU address origin field of the CPU TLE like in:
+ * CPU address = origin * 64 + bit position within the mask
+ */
+/* Container type Topology List Entry */
+typedef struct SYSIBContainerListEntry {
+ uint8_t nl;
+ uint8_t reserved[6];
+ uint8_t id;
+} SYSIBContainerListEntry;
+QEMU_BUILD_BUG_ON(sizeof(SYSIBContainerListEntry) != 8);
+
+/* CPU type Topology List Entry */
+typedef struct SysIBCPUListEntry {
+ uint8_t nl;
+ uint8_t reserved0[3];
+#define SYSIB_TLE_POLARITY_MASK 0x03
+#define SYSIB_TLE_DEDICATED 0x04
+ uint8_t flags;
+ uint8_t type;
+ uint16_t origin;
+ uint64_t mask;
+} SysIBCPUListEntry;
+QEMU_BUILD_BUG_ON(sizeof(SysIBCPUListEntry) != 16);
+
+void insert_stsi_15_1_x(S390CPU *cpu, int sel2, uint64_t addr, uint8_t ar, uintptr_t ra);
+void s390_cpu_topology_set_changed(bool changed);
+
/* MMU defines */
#define ASCE_ORIGIN (~0xfffULL) /* segment table origin */
#define ASCE_SUBSPACE 0x200 /* subspace group control */
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index 98f14c0..4dead48 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -255,6 +255,7 @@ bool s390_has_feat(S390Feat feat)
case S390_FEAT_SIE_CMMA:
case S390_FEAT_SIE_PFMFI:
case S390_FEAT_SIE_IBS:
+ case S390_FEAT_CONFIGURATION_TOPOLOGY:
return false;
break;
default:
diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
index bc5c56a..0f0e784 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -86,6 +86,7 @@
#define PRIV_B9_EQBS 0x9c
#define PRIV_B9_CLP 0xa0
+#define PRIV_B9_PTF 0xa2
#define PRIV_B9_PCISTG 0xd0
#define PRIV_B9_PCILG 0xd2
#define PRIV_B9_RPCIT 0xd3
@@ -138,7 +139,6 @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
KVM_CAP_LAST_INFO
};
-static int cap_sync_regs;
static int cap_async_pf;
static int cap_mem_op;
static int cap_mem_op_extension;
@@ -337,21 +337,28 @@ int kvm_arch_get_default_type(MachineState *ms)
int kvm_arch_init(MachineState *ms, KVMState *s)
{
+ int required_caps[] = {
+ KVM_CAP_DEVICE_CTRL,
+ KVM_CAP_SYNC_REGS,
+ };
+
+ for (int i = 0; i < ARRAY_SIZE(required_caps); i++) {
+ if (!kvm_check_extension(s, required_caps[i])) {
+ error_report("KVM is missing capability #%d - "
+ "please use kernel 3.15 or newer", required_caps[i]);
+ return -1;
+ }
+ }
+
object_class_foreach(ccw_machine_class_foreach, TYPE_S390_CCW_MACHINE,
false, NULL);
- if (!kvm_check_extension(kvm_state, KVM_CAP_DEVICE_CTRL)) {
- error_report("KVM is missing capability KVM_CAP_DEVICE_CTRL - "
- "please use kernel 3.15 or newer");
- return -1;
- }
if (!kvm_check_extension(s, KVM_CAP_S390_COW)) {
error_report("KVM is missing capability KVM_CAP_S390_COW - "
"unsupported environment");
return -1;
}
- cap_sync_regs = kvm_check_extension(s, KVM_CAP_SYNC_REGS);
cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF);
cap_mem_op = kvm_check_extension(s, KVM_CAP_S390_MEM_OP);
cap_mem_op_extension = kvm_check_extension(s, KVM_CAP_S390_MEM_OP_EXTENSION);
@@ -365,6 +372,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
kvm_vm_enable_cap(s, KVM_CAP_S390_USER_SIGP, 0);
kvm_vm_enable_cap(s, KVM_CAP_S390_VECTOR_REGISTERS, 0);
kvm_vm_enable_cap(s, KVM_CAP_S390_USER_STSI, 0);
+ kvm_vm_enable_cap(s, KVM_CAP_S390_CPU_TOPOLOGY, 0);
if (ri_allowed()) {
if (kvm_vm_enable_cap(s, KVM_CAP_S390_RI, 0) == 0) {
cap_ri = 1;
@@ -458,37 +466,28 @@ void kvm_s390_reset_vcpu_normal(S390CPU *cpu)
static int can_sync_regs(CPUState *cs, int regs)
{
- return cap_sync_regs && (cs->kvm_run->kvm_valid_regs & regs) == regs;
+ return (cs->kvm_run->kvm_valid_regs & regs) == regs;
}
+#define KVM_SYNC_REQUIRED_REGS (KVM_SYNC_GPRS | KVM_SYNC_ACRS | \
+ KVM_SYNC_CRS | KVM_SYNC_PREFIX)
+
int kvm_arch_put_registers(CPUState *cs, int level)
{
S390CPU *cpu = S390_CPU(cs);
CPUS390XState *env = &cpu->env;
- struct kvm_sregs sregs;
- struct kvm_regs regs;
struct kvm_fpu fpu = {};
int r;
int i;
+ g_assert(can_sync_regs(cs, KVM_SYNC_REQUIRED_REGS));
+
/* always save the PSW and the GPRS*/
cs->kvm_run->psw_addr = env->psw.addr;
cs->kvm_run->psw_mask = env->psw.mask;
- if (can_sync_regs(cs, KVM_SYNC_GPRS)) {
- for (i = 0; i < 16; i++) {
- cs->kvm_run->s.regs.gprs[i] = env->regs[i];
- cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_GPRS;
- }
- } else {
- for (i = 0; i < 16; i++) {
- regs.gprs[i] = env->regs[i];
- }
- r = kvm_vcpu_ioctl(cs, KVM_SET_REGS, &regs);
- if (r < 0) {
- return r;
- }
- }
+ memcpy(cs->kvm_run->s.regs.gprs, env->regs, sizeof(cs->kvm_run->s.regs.gprs));
+ cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_GPRS;
if (can_sync_regs(cs, KVM_SYNC_VRS)) {
for (i = 0; i < 32; i++) {
@@ -521,6 +520,15 @@ int kvm_arch_put_registers(CPUState *cs, int level)
return 0;
}
+ /*
+ * Access registers, control registers and the prefix - these are
+ * always available via kvm_sync_regs in the kernels that we support
+ */
+ memcpy(cs->kvm_run->s.regs.acrs, env->aregs, sizeof(cs->kvm_run->s.regs.acrs));
+ memcpy(cs->kvm_run->s.regs.crs, env->cregs, sizeof(cs->kvm_run->s.regs.crs));
+ cs->kvm_run->s.regs.prefix = env->psa;
+ cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_ACRS | KVM_SYNC_CRS | KVM_SYNC_PREFIX;
+
if (can_sync_regs(cs, KVM_SYNC_ARCH0)) {
cs->kvm_run->s.regs.cputm = env->cputm;
cs->kvm_run->s.regs.ckc = env->ckc;
@@ -567,25 +575,6 @@ int kvm_arch_put_registers(CPUState *cs, int level)
}
}
- /* access registers and control registers*/
- if (can_sync_regs(cs, KVM_SYNC_ACRS | KVM_SYNC_CRS)) {
- for (i = 0; i < 16; i++) {
- cs->kvm_run->s.regs.acrs[i] = env->aregs[i];
- cs->kvm_run->s.regs.crs[i] = env->cregs[i];
- }
- cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_ACRS;
- cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_CRS;
- } else {
- for (i = 0; i < 16; i++) {
- sregs.acrs[i] = env->aregs[i];
- sregs.crs[i] = env->cregs[i];
- }
- r = kvm_vcpu_ioctl(cs, KVM_SET_SREGS, &sregs);
- if (r < 0) {
- return r;
- }
- }
-
if (can_sync_regs(cs, KVM_SYNC_GSCB)) {
memcpy(cs->kvm_run->s.regs.gscb, env->gscb, 32);
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_GSCB;
@@ -607,13 +596,6 @@ int kvm_arch_put_registers(CPUState *cs, int level)
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_DIAG318;
}
- /* Finally the prefix */
- if (can_sync_regs(cs, KVM_SYNC_PREFIX)) {
- cs->kvm_run->s.regs.prefix = env->psa;
- cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_PREFIX;
- } else {
- /* prefix is only supported via sync regs */
- }
return 0;
}
@@ -621,8 +603,6 @@ int kvm_arch_get_registers(CPUState *cs)
{
S390CPU *cpu = S390_CPU(cs);
CPUS390XState *env = &cpu->env;
- struct kvm_sregs sregs;
- struct kvm_regs regs;
struct kvm_fpu fpu;
int i, r;
@@ -630,37 +610,14 @@ int kvm_arch_get_registers(CPUState *cs)
env->psw.addr = cs->kvm_run->psw_addr;
env->psw.mask = cs->kvm_run->psw_mask;
- /* the GPRS */
- if (can_sync_regs(cs, KVM_SYNC_GPRS)) {
- for (i = 0; i < 16; i++) {
- env->regs[i] = cs->kvm_run->s.regs.gprs[i];
- }
- } else {
- r = kvm_vcpu_ioctl(cs, KVM_GET_REGS, &regs);
- if (r < 0) {
- return r;
- }
- for (i = 0; i < 16; i++) {
- env->regs[i] = regs.gprs[i];
- }
- }
+ /* the GPRS, ACRS and CRS */
+ g_assert(can_sync_regs(cs, KVM_SYNC_REQUIRED_REGS));
+ memcpy(env->regs, cs->kvm_run->s.regs.gprs, sizeof(env->regs));
+ memcpy(env->aregs, cs->kvm_run->s.regs.acrs, sizeof(env->aregs));
+ memcpy(env->cregs, cs->kvm_run->s.regs.crs, sizeof(env->cregs));
- /* The ACRS and CRS */
- if (can_sync_regs(cs, KVM_SYNC_ACRS | KVM_SYNC_CRS)) {
- for (i = 0; i < 16; i++) {
- env->aregs[i] = cs->kvm_run->s.regs.acrs[i];
- env->cregs[i] = cs->kvm_run->s.regs.crs[i];
- }
- } else {
- r = kvm_vcpu_ioctl(cs, KVM_GET_SREGS, &sregs);
- if (r < 0) {
- return r;
- }
- for (i = 0; i < 16; i++) {
- env->aregs[i] = sregs.acrs[i];
- env->cregs[i] = sregs.crs[i];
- }
- }
+ /* The prefix */
+ env->psa = cs->kvm_run->s.regs.prefix;
/* Floating point and vector registers */
if (can_sync_regs(cs, KVM_SYNC_VRS)) {
@@ -685,11 +642,6 @@ int kvm_arch_get_registers(CPUState *cs)
env->fpc = fpu.fpc;
}
- /* The prefix */
- if (can_sync_regs(cs, KVM_SYNC_PREFIX)) {
- env->psa = cs->kvm_run->s.regs.prefix;
- }
-
if (can_sync_regs(cs, KVM_SYNC_ARCH0)) {
env->cputm = cs->kvm_run->s.regs.cputm;
env->ckc = cs->kvm_run->s.regs.ckc;
@@ -1457,6 +1409,13 @@ static int kvm_mpcifc_service_call(S390CPU *cpu, struct kvm_run *run)
}
}
+static void kvm_handle_ptf(S390CPU *cpu, struct kvm_run *run)
+{
+ uint8_t r1 = (run->s390_sieic.ipb >> 20) & 0x0f;
+
+ s390_handle_ptf(cpu, r1, RA_IGNORED);
+}
+
static int handle_b9(S390CPU *cpu, struct kvm_run *run, uint8_t ipa1)
{
int r = 0;
@@ -1474,6 +1433,9 @@ static int handle_b9(S390CPU *cpu, struct kvm_run *run, uint8_t ipa1)
case PRIV_B9_RPCIT:
r = kvm_rpcit_service_call(cpu, run);
break;
+ case PRIV_B9_PTF:
+ kvm_handle_ptf(cpu, run);
+ break;
case PRIV_B9_EQBS:
/* just inject exception */
r = -1;
@@ -1911,9 +1873,12 @@ static int handle_stsi(S390CPU *cpu)
if (run->s390_stsi.sel1 != 2 || run->s390_stsi.sel2 != 2) {
return 0;
}
- /* Only sysib 3.2.2 needs post-handling for now. */
insert_stsi_3_2_2(cpu, run->s390_stsi.addr, run->s390_stsi.ar);
return 0;
+ case 15:
+ insert_stsi_15_1_x(cpu, run->s390_stsi.sel2, run->s390_stsi.addr,
+ run->s390_stsi.ar, RA_IGNORED);
+ return 0;
default:
return 0;
}
@@ -2495,6 +2460,14 @@ void kvm_s390_get_host_cpu_model(S390CPUModel *model, Error **errp)
set_bit(S390_FEAT_UNPACK, model->features);
}
+ /*
+ * If we have kernel support for CPU Topology indicate the
+ * configuration-topology facility.
+ */
+ if (kvm_check_extension(kvm_state, KVM_CAP_S390_CPU_TOPOLOGY)) {
+ set_bit(S390_FEAT_CONFIGURATION_TOPOLOGY, model->features);
+ }
+
/* We emulate a zPCI bus and AEN, therefore we don't need HW support */
set_bit(S390_FEAT_ZPCI, model->features);
set_bit(S390_FEAT_ADAPTER_EVENT_NOTIFICATION, model->features);
@@ -2661,6 +2634,23 @@ int kvm_s390_get_zpci_op(void)
return cap_zpci_op;
}
+int kvm_s390_topology_set_mtcr(uint64_t attr)
+{
+ struct kvm_device_attr attribute = {
+ .group = KVM_S390_VM_CPU_TOPOLOGY,
+ .attr = attr,
+ };
+
+ if (!s390_has_feat(S390_FEAT_CONFIGURATION_TOPOLOGY)) {
+ return 0;
+ }
+ if (!kvm_vm_check_attr(kvm_state, KVM_S390_VM_CPU_TOPOLOGY, attr)) {
+ return -ENOTSUP;
+ }
+
+ return kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attribute);
+}
+
void kvm_arch_accel_class_init(ObjectClass *oc)
{
}
diff --git a/target/s390x/kvm/kvm_s390x.h b/target/s390x/kvm/kvm_s390x.h
index f978556..649dae5 100644
--- a/target/s390x/kvm/kvm_s390x.h
+++ b/target/s390x/kvm/kvm_s390x.h
@@ -47,5 +47,6 @@ void kvm_s390_crypto_reset(void);
void kvm_s390_restart_interrupt(S390CPU *cpu);
void kvm_s390_stop_interrupt(S390CPU *cpu);
void kvm_s390_set_diag318(CPUState *cs, uint64_t diag318_info);
+int kvm_s390_topology_set_mtcr(uint64_t attr);
#endif /* KVM_S390X_H */
diff --git a/target/s390x/kvm/meson.build b/target/s390x/kvm/meson.build
index d6aca59..588a9aa 100644
--- a/target/s390x/kvm/meson.build
+++ b/target/s390x/kvm/meson.build
@@ -1,7 +1,8 @@
s390x_ss.add(when: 'CONFIG_KVM', if_true: files(
'pv.c',
- 'kvm.c'
+ 'kvm.c',
+ 'stsi-topology.c'
), if_false: files(
'stubs.c'
))
diff --git a/target/s390x/kvm/stsi-topology.c b/target/s390x/kvm/stsi-topology.c
new file mode 100644
index 0000000..efd2aa7
--- /dev/null
+++ b/target/s390x/kvm/stsi-topology.c
@@ -0,0 +1,334 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * QEMU S390x CPU Topology
+ *
+ * Copyright IBM Corp. 2022, 2023
+ * Author(s): Pierre Morel <pmorel@linux.ibm.com>
+ *
+ */
+#include "qemu/osdep.h"
+#include "cpu.h"
+#include "hw/s390x/sclp.h"
+#include "hw/s390x/cpu-topology.h"
+
+QEMU_BUILD_BUG_ON(S390_CPU_ENTITLEMENT_LOW != 1);
+QEMU_BUILD_BUG_ON(S390_CPU_ENTITLEMENT_MEDIUM != 2);
+QEMU_BUILD_BUG_ON(S390_CPU_ENTITLEMENT_HIGH != 3);
+
+/**
+ * fill_container:
+ * @p: The address of the container TLE to fill
+ * @level: The level of nesting for this container
+ * @id: The container receives a unique ID inside its own container
+ *
+ * Returns the next free TLE entry.
+ */
+static char *fill_container(char *p, int level, int id)
+{
+ SYSIBContainerListEntry *tle = (SYSIBContainerListEntry *)p;
+
+ tle->nl = level;
+ tle->id = id;
+ return p + sizeof(*tle);
+}
+
+/**
+ * fill_tle_cpu:
+ * @p: The address of the CPU TLE to fill
+ * @entry: a pointer to the S390TopologyEntry defining this
+ * CPU container.
+ *
+ * Returns the next free TLE entry.
+ */
+static char *fill_tle_cpu(char *p, S390TopologyEntry *entry)
+{
+ SysIBCPUListEntry *tle = (SysIBCPUListEntry *)p;
+ S390TopologyId topology_id = entry->id;
+
+ tle->nl = 0;
+ tle->flags = 0;
+ if (topology_id.vertical) {
+ tle->flags |= topology_id.entitlement;
+ }
+ if (topology_id.dedicated) {
+ tle->flags |= SYSIB_TLE_DEDICATED;
+ }
+ tle->type = topology_id.type;
+ tle->origin = cpu_to_be16(topology_id.origin * 64);
+ tle->mask = cpu_to_be64(entry->mask);
+ return p + sizeof(*tle);
+}
+
+/*
+ * Macro to check that the size of data after increment
+ * will not get bigger than the size of the SysIB.
+ */
+#define SYSIB_GUARD(data, x) do { \
+ data += x; \
+ if (data > sizeof(SysIB)) { \
+ return 0; \
+ } \
+ } while (0)
+
+/**
+ * stsi_topology_fill_sysib:
+ * @p: A pointer to the position of the first TLE
+ * @level: The nested level wanted by the guest
+ *
+ * Fill the SYSIB with the topology information as described in
+ * the PoP, nesting containers as appropriate, with the maximum
+ * nesting limited by @level.
+ *
+ * Return value:
+ * On success: the size of the SysIB_15x after being filled with TLE.
+ * On error: 0 in the case we would overrun the end of the SysIB.
+ */
+static int stsi_topology_fill_sysib(S390TopologyList *topology_list,
+ char *p, int level)
+{
+ S390TopologyEntry *entry;
+ int last_drawer = -1;
+ int last_book = -1;
+ int last_socket = -1;
+ int drawer_id = 0;
+ int book_id = 0;
+ int socket_id = 0;
+ int n = sizeof(SysIB_151x);
+
+ QTAILQ_FOREACH(entry, topology_list, next) {
+ bool drawer_change = last_drawer != entry->id.drawer;
+ bool book_change = drawer_change || last_book != entry->id.book;
+ bool socket_change = book_change || last_socket != entry->id.socket;
+
+ if (level > 3 && drawer_change) {
+ SYSIB_GUARD(n, sizeof(SYSIBContainerListEntry));
+ p = fill_container(p, 3, drawer_id++);
+ book_id = 0;
+ }
+ if (level > 2 && book_change) {
+ SYSIB_GUARD(n, sizeof(SYSIBContainerListEntry));
+ p = fill_container(p, 2, book_id++);
+ socket_id = 0;
+ }
+ if (socket_change) {
+ SYSIB_GUARD(n, sizeof(SYSIBContainerListEntry));
+ p = fill_container(p, 1, socket_id++);
+ }
+
+ SYSIB_GUARD(n, sizeof(SysIBCPUListEntry));
+ p = fill_tle_cpu(p, entry);
+ last_drawer = entry->id.drawer;
+ last_book = entry->id.book;
+ last_socket = entry->id.socket;
+ }
+
+ return n;
+}
+
+/**
+ * setup_stsi:
+ * @topology_list: ordered list of groups of CPUs with same properties
+ * @sysib: pointer to a SysIB to be filled with SysIB_151x data
+ * @level: Nested level specified by the guest
+ *
+ * Setup the SYSIB for STSI 15.1, the header as well as the description
+ * of the topology.
+ */
+static int setup_stsi(S390TopologyList *topology_list, SysIB_151x *sysib,
+ int level)
+{
+ sysib->mnest = level;
+ switch (level) {
+ case 4:
+ sysib->mag[S390_TOPOLOGY_MAG4] = current_machine->smp.drawers;
+ sysib->mag[S390_TOPOLOGY_MAG3] = current_machine->smp.books;
+ sysib->mag[S390_TOPOLOGY_MAG2] = current_machine->smp.sockets;
+ sysib->mag[S390_TOPOLOGY_MAG1] = current_machine->smp.cores;
+ break;
+ case 3:
+ sysib->mag[S390_TOPOLOGY_MAG3] = current_machine->smp.drawers *
+ current_machine->smp.books;
+ sysib->mag[S390_TOPOLOGY_MAG2] = current_machine->smp.sockets;
+ sysib->mag[S390_TOPOLOGY_MAG1] = current_machine->smp.cores;
+ break;
+ case 2:
+ sysib->mag[S390_TOPOLOGY_MAG2] = current_machine->smp.drawers *
+ current_machine->smp.books *
+ current_machine->smp.sockets;
+ sysib->mag[S390_TOPOLOGY_MAG1] = current_machine->smp.cores;
+ break;
+ }
+
+ return stsi_topology_fill_sysib(topology_list, sysib->tle, level);
+}
+
+/**
+ * s390_topology_add_cpu_to_entry:
+ * @entry: Topology entry to setup
+ * @cpu: the S390CPU to add
+ *
+ * Set the core bit inside the topology mask.
+ */
+static void s390_topology_add_cpu_to_entry(S390TopologyEntry *entry,
+ S390CPU *cpu)
+{
+ set_bit(63 - (cpu->env.core_id % 64), &entry->mask);
+}
+
+/**
+ * s390_topology_from_cpu:
+ * @cpu: S390CPU to calculate the topology id
+ *
+ * Initialize the topology id from the CPU environment.
+ */
+static S390TopologyId s390_topology_from_cpu(S390CPU *cpu)
+{
+ S390TopologyId topology_id = {
+ .drawer = cpu->env.drawer_id,
+ .book = cpu->env.book_id,
+ .socket = cpu->env.socket_id,
+ .type = S390_TOPOLOGY_CPU_IFL,
+ .vertical = s390_topology.polarization == S390_CPU_POLARIZATION_VERTICAL,
+ .entitlement = cpu->env.entitlement,
+ .dedicated = cpu->env.dedicated,
+ .origin = cpu->env.core_id / 64,
+ };
+
+ return topology_id;
+}
+
+/**
+ * s390_topology_id_cmp:
+ * @l: first S390TopologyId
+ * @r: second S390TopologyId
+ *
+ * Compare two topology ids according to the sorting order specified by the PoP.
+ *
+ * Returns a negative number if the first id is less than, 0 if it is equal to
+ * and positive if it is larger than the second id.
+ */
+static int s390_topology_id_cmp(const S390TopologyId *l,
+ const S390TopologyId *r)
+{
+ /*
+ * lexical order, compare less significant values only if more significant
+ * ones are equal
+ */
+ return l->sentinel - r->sentinel ?:
+ l->drawer - r->drawer ?:
+ l->book - r->book ?:
+ l->socket - r->socket ?:
+ l->type - r->type ?:
+ /* logic is inverted for the next three */
+ r->vertical - l->vertical ?:
+ r->entitlement - l->entitlement ?:
+ r->dedicated - l->dedicated ?:
+ l->origin - r->origin;
+}
+
+static bool s390_topology_id_eq(const S390TopologyId *l,
+ const S390TopologyId *r)
+{
+ return !s390_topology_id_cmp(l, r);
+}
+
+static bool s390_topology_id_lt(const S390TopologyId *l,
+ const S390TopologyId *r)
+{
+ return s390_topology_id_cmp(l, r) < 0;
+}
+
+/**
+ * s390_topology_fill_list_sorted:
+ * @topology_list: list to fill
+ *
+ * Create S390TopologyEntrys as appropriate from all CPUs and fill the
+ * topology_list with the entries according to the order specified by the PoP.
+ */
+static void s390_topology_fill_list_sorted(S390TopologyList *topology_list)
+{
+ CPUState *cs;
+ S390TopologyEntry sentinel = { .id.sentinel = 1 };
+
+ QTAILQ_INIT(topology_list);
+
+ QTAILQ_INSERT_HEAD(topology_list, &sentinel, next);
+
+ CPU_FOREACH(cs) {
+ S390TopologyId id = s390_topology_from_cpu(S390_CPU(cs));
+ S390TopologyEntry *entry = NULL, *tmp;
+
+ QTAILQ_FOREACH(tmp, topology_list, next) {
+ if (s390_topology_id_eq(&id, &tmp->id)) {
+ entry = tmp;
+ break;
+ } else if (s390_topology_id_lt(&id, &tmp->id)) {
+ entry = g_malloc0(sizeof(*entry));
+ entry->id = id;
+ QTAILQ_INSERT_BEFORE(tmp, entry, next);
+ break;
+ }
+ }
+ assert(entry);
+ s390_topology_add_cpu_to_entry(entry, S390_CPU(cs));
+ }
+
+ QTAILQ_REMOVE(topology_list, &sentinel, next);
+}
+
+/**
+ * s390_topology_empty_list:
+ *
+ * Clear all entries in the S390Topology list.
+ */
+static void s390_topology_empty_list(S390TopologyList *topology_list)
+{
+ S390TopologyEntry *entry = NULL;
+ S390TopologyEntry *tmp = NULL;
+
+ QTAILQ_FOREACH_SAFE(entry, topology_list, next, tmp) {
+ QTAILQ_REMOVE(topology_list, entry, next);
+ g_free(entry);
+ }
+}
+
+/**
+ * insert_stsi_15_1_x:
+ * @cpu: the CPU doing the call for which we set CC
+ * @sel2: the selector 2, containing the nested level
+ * @addr: Guest logical address of the guest SysIB
+ * @ar: the access register number
+ * @ra: the return address
+ *
+ * Emulate STSI 15.1.x, that is, perform all necessary checks and
+ * fill the SYSIB.
+ * In case the topology description is too long to fit into the SYSIB,
+ * set CC=3 and abort without writing the SYSIB.
+ */
+void insert_stsi_15_1_x(S390CPU *cpu, int sel2, uint64_t addr, uint8_t ar, uintptr_t ra)
+{
+ S390TopologyList topology_list;
+ SysIB sysib = {0};
+ int length;
+
+ if (!s390_has_topology() || sel2 < 2 || sel2 > SCLP_READ_SCP_INFO_MNEST) {
+ setcc(cpu, 3);
+ return;
+ }
+
+ s390_topology_fill_list_sorted(&topology_list);
+ length = setup_stsi(&topology_list, &sysib.sysib_151x, sel2);
+ s390_topology_empty_list(&topology_list);
+
+ if (!length) {
+ setcc(cpu, 3);
+ return;
+ }
+
+ sysib.sysib_151x.length = cpu_to_be16(length);
+ if (!s390_cpu_virt_mem_write(cpu, addr, ar, &sysib, length)) {
+ setcc(cpu, 0);
+ } else {
+ s390_cpu_virt_mem_handle_exc(cpu, ra);
+ }
+}
diff --git a/tests/avocado/s390_topology.py b/tests/avocado/s390_topology.py
new file mode 100644
index 0000000..9154ac8
--- /dev/null
+++ b/tests/avocado/s390_topology.py
@@ -0,0 +1,439 @@
+# Functional test that boots a Linux kernel and checks the console
+#
+# Copyright IBM Corp. 2023
+#
+# Author:
+# Pierre Morel <pmorel@linux.ibm.com>
+#
+# This work is licensed under the terms of the GNU GPL, version 2 or
+# later. See the COPYING file in the top-level directory.
+
+import os
+import shutil
+import time
+
+from avocado_qemu import QemuSystemTest
+from avocado_qemu import exec_command
+from avocado_qemu import exec_command_and_wait_for_pattern
+from avocado_qemu import interrupt_interactive_console_until_pattern
+from avocado_qemu import wait_for_console_pattern
+from avocado.utils import process
+from avocado.utils import archive
+
+
+class S390CPUTopology(QemuSystemTest):
+ """
+ S390x CPU topology consists of 4 topology layers, from bottom to top,
+ the cores, sockets, books and drawers and 2 modifiers attributes,
+ the entitlement and the dedication.
+ See: docs/system/s390x/cpu-topology.rst.
+
+ S390x CPU topology is setup in different ways:
+ - implicitly from the '-smp' argument by completing each topology
+ level one after the other beginning with drawer 0, book 0 and
+ socket 0.
+ - explicitly from the '-device' argument on the QEMU command line
+ - explicitly by hotplug of a new CPU using QMP or HMP
+ - it is modified by using QMP 'set-cpu-topology'
+
+ The S390x modifier attribute entitlement depends on the machine
+ polarization, which can be horizontal or vertical.
+ The polarization is changed on a request from the guest.
+ """
+ timeout = 90
+ event_timeout = 10
+
+ KERNEL_COMMON_COMMAND_LINE = ('printk.time=0 '
+ 'root=/dev/ram '
+ 'selinux=0 '
+ 'rdinit=/bin/sh')
+
+ def wait_until_booted(self):
+ wait_for_console_pattern(self, 'no job control',
+ failure_message='Kernel panic - not syncing',
+ vm=None)
+
+ def check_topology(self, c, s, b, d, e, t):
+ res = self.vm.qmp('query-cpus-fast')
+ cpus = res['return']
+ for cpu in cpus:
+ core = cpu['props']['core-id']
+ socket = cpu['props']['socket-id']
+ book = cpu['props']['book-id']
+ drawer = cpu['props']['drawer-id']
+ entitlement = cpu.get('entitlement')
+ dedicated = cpu.get('dedicated')
+ if core == c:
+ self.assertEqual(drawer, d)
+ self.assertEqual(book, b)
+ self.assertEqual(socket, s)
+ self.assertEqual(entitlement, e)
+ self.assertEqual(dedicated, t)
+
+ def kernel_init(self):
+ """
+ We need a VM that supports CPU topology,
+ currently this only the case when using KVM, not TCG.
+ We need a kernel supporting the CPU topology.
+ We need a minimal root filesystem with a shell.
+ """
+ self.require_accelerator("kvm")
+ kernel_url = ('https://archives.fedoraproject.org/pub/archive'
+ '/fedora-secondary/releases/35/Server/s390x/os'
+ '/images/kernel.img')
+ kernel_hash = '0d1aaaf303f07cf0160c8c48e56fe638'
+ kernel_path = self.fetch_asset(kernel_url, algorithm='md5',
+ asset_hash=kernel_hash)
+
+ initrd_url = ('https://archives.fedoraproject.org/pub/archive'
+ '/fedora-secondary/releases/35/Server/s390x/os'
+ '/images/initrd.img')
+ initrd_hash = 'a122057d95725ac030e2ec51df46e172'
+ initrd_path_xz = self.fetch_asset(initrd_url, algorithm='md5',
+ asset_hash=initrd_hash)
+ initrd_path = os.path.join(self.workdir, 'initrd-raw.img')
+ archive.lzma_uncompress(initrd_path_xz, initrd_path)
+
+ self.vm.set_console()
+ kernel_command_line = self.KERNEL_COMMON_COMMAND_LINE
+ self.vm.add_args('-nographic',
+ '-enable-kvm',
+ '-cpu', 'max,ctop=on',
+ '-m', '512',
+ '-kernel', kernel_path,
+ '-initrd', initrd_path,
+ '-append', kernel_command_line)
+
+ def system_init(self):
+ self.log.info("System init")
+ exec_command_and_wait_for_pattern(self,
+ """ mount proc -t proc /proc;
+ mount sys -t sysfs /sys;
+ cat /sys/devices/system/cpu/dispatching """,
+ '0')
+
+ def test_single(self):
+ """
+ This test checks the simplest topology with a single CPU.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.launch()
+ self.wait_until_booted()
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+
+ def test_default(self):
+ """
+ This test checks the implicit topology.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.add_args('-smp',
+ '13,drawers=2,books=2,sockets=3,cores=2,maxcpus=24')
+ self.vm.launch()
+ self.wait_until_booted()
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+ self.check_topology(1, 0, 0, 0, 'medium', False)
+ self.check_topology(2, 1, 0, 0, 'medium', False)
+ self.check_topology(3, 1, 0, 0, 'medium', False)
+ self.check_topology(4, 2, 0, 0, 'medium', False)
+ self.check_topology(5, 2, 0, 0, 'medium', False)
+ self.check_topology(6, 0, 1, 0, 'medium', False)
+ self.check_topology(7, 0, 1, 0, 'medium', False)
+ self.check_topology(8, 1, 1, 0, 'medium', False)
+ self.check_topology(9, 1, 1, 0, 'medium', False)
+ self.check_topology(10, 2, 1, 0, 'medium', False)
+ self.check_topology(11, 2, 1, 0, 'medium', False)
+ self.check_topology(12, 0, 0, 1, 'medium', False)
+
+ def test_move(self):
+ """
+ This test checks the topology modification by moving a CPU
+ to another socket: CPU 0 is moved from socket 0 to socket 2.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.add_args('-smp',
+ '1,drawers=2,books=2,sockets=3,cores=2,maxcpus=24')
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'socket-id': 2, 'entitlement': 'low'})
+ self.assertEqual(res['return'], {})
+ self.check_topology(0, 2, 0, 0, 'low', False)
+
+ def test_dash_device(self):
+ """
+ This test verifies that a CPU defined with the '-device'
+ command line option finds its right place inside the topology.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.add_args('-smp',
+ '1,drawers=2,books=2,sockets=3,cores=2,maxcpus=24')
+ self.vm.add_args('-device', 'max-s390x-cpu,core-id=10')
+ self.vm.add_args('-device',
+ 'max-s390x-cpu,'
+ 'core-id=1,socket-id=0,book-id=1,drawer-id=1,entitlement=low')
+ self.vm.add_args('-device',
+ 'max-s390x-cpu,'
+ 'core-id=2,socket-id=0,book-id=1,drawer-id=1,entitlement=medium')
+ self.vm.add_args('-device',
+ 'max-s390x-cpu,'
+ 'core-id=3,socket-id=1,book-id=1,drawer-id=1,entitlement=high')
+ self.vm.add_args('-device',
+ 'max-s390x-cpu,'
+ 'core-id=4,socket-id=1,book-id=1,drawer-id=1')
+ self.vm.add_args('-device',
+ 'max-s390x-cpu,'
+ 'core-id=5,socket-id=2,book-id=1,drawer-id=1,dedicated=true')
+
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.check_topology(10, 2, 1, 0, 'medium', False)
+ self.check_topology(1, 0, 1, 1, 'low', False)
+ self.check_topology(2, 0, 1, 1, 'medium', False)
+ self.check_topology(3, 1, 1, 1, 'high', False)
+ self.check_topology(4, 1, 1, 1, 'medium', False)
+ self.check_topology(5, 2, 1, 1, 'high', True)
+
+
+ def guest_set_dispatching(self, dispatching):
+ exec_command(self,
+ f'echo {dispatching} > /sys/devices/system/cpu/dispatching')
+ self.vm.event_wait('CPU_POLARIZATION_CHANGE', self.event_timeout)
+ exec_command_and_wait_for_pattern(self,
+ 'cat /sys/devices/system/cpu/dispatching', dispatching)
+
+
+ def test_polarization(self):
+ """
+ This test verifies that QEMU modifies the entitlement change after
+ several guest polarization change requests.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.system_init()
+ res = self.vm.qmp('query-s390x-cpu-polarization')
+ self.assertEqual(res['return']['polarization'], 'horizontal')
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+
+ self.guest_set_dispatching('1');
+ res = self.vm.qmp('query-s390x-cpu-polarization')
+ self.assertEqual(res['return']['polarization'], 'vertical')
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+
+ self.guest_set_dispatching('0');
+ res = self.vm.qmp('query-s390x-cpu-polarization')
+ self.assertEqual(res['return']['polarization'], 'horizontal')
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+
+
+ def check_polarization(self, polarization):
+ #We need to wait for the change to have been propagated to the kernel
+ exec_command_and_wait_for_pattern(self,
+ "\n".join([
+ "timeout 1 sh -c 'while true",
+ 'do',
+ ' syspath="/sys/devices/system/cpu/cpu0/polarization"',
+ ' polarization="$(cat "$syspath")" || exit',
+ f' if [ "$polarization" = "{polarization}" ]; then',
+ ' exit 0',
+ ' fi',
+ ' sleep 0.01',
+ #searched for strings mustn't show up in command, '' to obfuscate
+ "done' && echo succ''ess || echo fail''ure",
+ ]),
+ "success", "failure")
+
+
+ def test_entitlement(self):
+ """
+ This test verifies that QEMU modifies the entitlement
+ after a guest request and that the guest sees the change.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.system_init()
+
+ self.check_polarization('horizontal')
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+
+ self.guest_set_dispatching('1')
+ self.check_polarization('vertical:medium')
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'low'})
+ self.assertEqual(res['return'], {})
+ self.check_polarization('vertical:low')
+ self.check_topology(0, 0, 0, 0, 'low', False)
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'medium'})
+ self.assertEqual(res['return'], {})
+ self.check_polarization('vertical:medium')
+ self.check_topology(0, 0, 0, 0, 'medium', False)
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'high'})
+ self.assertEqual(res['return'], {})
+ self.check_polarization('vertical:high')
+ self.check_topology(0, 0, 0, 0, 'high', False)
+
+ self.guest_set_dispatching('0');
+ self.check_polarization("horizontal")
+ self.check_topology(0, 0, 0, 0, 'high', False)
+
+
+ def test_dedicated(self):
+ """
+ This test verifies that QEMU adjusts the entitlement correctly when a
+ CPU is made dedicated.
+ QEMU retains the entitlement value when horizontal polarization is in effect.
+ For the guest, the field shows the effective value of the entitlement.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.system_init()
+
+ self.check_polarization("horizontal")
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'dedicated': True})
+ self.assertEqual(res['return'], {})
+ self.check_topology(0, 0, 0, 0, 'high', True)
+ self.check_polarization("horizontal")
+
+ self.guest_set_dispatching('1');
+ self.check_topology(0, 0, 0, 0, 'high', True)
+ self.check_polarization("vertical:high")
+
+ self.guest_set_dispatching('0');
+ self.check_topology(0, 0, 0, 0, 'high', True)
+ self.check_polarization("horizontal")
+
+
+ def test_socket_full(self):
+ """
+ This test verifies that QEMU does not accept to overload a socket.
+ The socket-id 0 on book-id 0 already contains CPUs 0 and 1 and can
+ not accept any new CPU while socket-id 0 on book-id 1 is free.
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.add_args('-smp',
+ '3,drawers=2,books=2,sockets=3,cores=2,maxcpus=24')
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.system_init()
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 2, 'socket-id': 0, 'book-id': 0})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 2, 'socket-id': 0, 'book-id': 1})
+ self.assertEqual(res['return'], {})
+
+ def test_dedicated_error(self):
+ """
+ This test verifies that QEMU refuses to lower the entitlement
+ of a dedicated CPU
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.system_init()
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'dedicated': True})
+ self.assertEqual(res['return'], {})
+
+ self.check_topology(0, 0, 0, 0, 'high', True)
+
+ self.guest_set_dispatching('1');
+
+ self.check_topology(0, 0, 0, 0, 'high', True)
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'low', 'dedicated': True})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'low'})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'medium', 'dedicated': True})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'medium'})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'low', 'dedicated': False})
+ self.assertEqual(res['return'], {})
+
+ res = self.vm.qmp('set-cpu-topology',
+ {'core-id': 0, 'entitlement': 'medium', 'dedicated': False})
+ self.assertEqual(res['return'], {})
+
+ def test_move_error(self):
+ """
+ This test verifies that QEMU refuses to move a CPU to an
+ nonexistent location
+
+ :avocado: tags=arch:s390x
+ :avocado: tags=machine:s390-ccw-virtio
+ """
+ self.kernel_init()
+ self.vm.launch()
+ self.wait_until_booted()
+
+ self.system_init()
+
+ res = self.vm.qmp('set-cpu-topology', {'core-id': 0, 'drawer-id': 1})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ res = self.vm.qmp('set-cpu-topology', {'core-id': 0, 'book-id': 1})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ res = self.vm.qmp('set-cpu-topology', {'core-id': 0, 'socket-id': 1})
+ self.assertEqual(res['error']['class'], 'GenericError')
+
+ self.check_topology(0, 0, 0, 0, 'medium', False)
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index e1c1105..241b409 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -3034,7 +3034,9 @@ int main(int argc, char **argv)
qtest_add_func("/migration/bad_dest", test_baddest);
#ifndef _WIN32
- qtest_add_func("/migration/analyze-script", test_analyze_script);
+ if (!g_str_equal(arch, "s390x")) {
+ qtest_add_func("/migration/analyze-script", test_analyze_script);
+ }
#endif
qtest_add_func("/migration/precopy/unix/plain", test_precopy_unix_plain);
qtest_add_func("/migration/precopy/unix/xbzrle", test_precopy_unix_xbzrle);