Merge tag 'mem-2024-09-24' of https://github.com/davidhildenbrand/qemu into staging
Hi,
"Host Memory Backends" and "Memory devices" queue ("mem"):
- Kconfig fix for virtio-based memory devices
- virtio-mem support for suspend+wake-up with plugged memory
- hostmem fix when specifying "merge=off"
# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEEG9nKrXNcTDpGDfzKTd4Q9wD/g1oFAmbyikMRHGRhdmlkQHJl
# ZGhhdC5jb20ACgkQTd4Q9wD/g1q6MBAAitNST73Shc+j327WvRLHQDkzkAlIYm+M
# E8NqtDiV11h7A0eNVu+5BkY/ejtY0Fduae3nxIkrHjK20eHHpiNPUp3hBNIhkKs3
# vlSaU8FLGdt58CteMGcLYsP2E32WNNTckaFGwGjDmyUEfk+Gug4r/rJAZXDfuuLV
# 083I0/MuUF+ozPA0c2MrOwhoBPerg3a5aflVpbgPwGNrT9BHMjo62Q5QzG3U7mxr
# HnlLAScSXsYg2z+d5XLXkKLAiZ4C7UN4vfUAOZwqkfs7IFUTtFO/ev6e7VZI747n
# XhAqOAKzLqPu7tBPZJIC6jwZAUIv5yM0/v5qhVvVVdu7H0ZMtSCXyvCVtnT25Rsn
# yiA+XvCOb7yQ3hRbBIi60IzjNYfWbvw+oTVIDfXkG35TeNf4ZdjWtAiUmw9s5U9Q
# z0tINsD7VlSkbh5h3PkFw1+xagIuJAVkp673HHTtQsg+xgYK2ur5jhhWJdJlnpzA
# 77CAu07UaqU39ssnC2zeGG1eNRA4uzjwQtREzqH2jMfkw/7UuUeXMF+v/fEuLn6w
# JneSMq/a0gmD42HNae0Y40cn2Akfj6+wFu1rW3djF8F6TeLUSssQhbQSHCMwGoOg
# qX7O/3SeSRzlnp3Zyx9Tr7s+BkMz0EGGDe17GQwTQUX2t5wR5iXoGqpKZgOBA8En
# 6uUIcjBUckc=
# =PExj
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 24 Sep 2024 10:45:39 BST
# gpg: using RSA key 1BD9CAAD735C4C3A460DFCCA4DDE10F700FF835A
# gpg: issuer "david@redhat.com"
# gpg: Good signature from "David Hildenbrand <david@redhat.com>" [marginal]
# gpg: aka "David Hildenbrand <davidhildenbrand@gmail.com>" [full]
# gpg: aka "David Hildenbrand <hildenbr@in.tum.de>" [unknown]
# Primary key fingerprint: 1BD9 CAAD 735C 4C3A 460D FCCA 4DDE 10F7 00FF 835A
* tag 'mem-2024-09-24' of https://github.com/davidhildenbrand/qemu:
hostmem: Apply merge property after the memory region is initialized
virtio-mem: Add support for suspend+wake-up with plugged memory
virtio-mem: Use new Resettable framework instead of LegacyReset
reset: Add RESET_TYPE_WAKEUP
reset: Use ResetType for qemu_devices_reset() and MachineClass::reset()
virtio: kconfig: memory devices are PCI only
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/backends/hostmem.c b/backends/hostmem.c
index 4e5576a..1814466 100644
--- a/backends/hostmem.c
+++ b/backends/hostmem.c
@@ -178,7 +178,7 @@
return;
}
- if (!host_memory_backend_mr_inited(backend) &&
+ if (host_memory_backend_mr_inited(backend) &&
value != backend->merge) {
void *ptr = memory_region_get_ram_ptr(&backend->mr);
uint64_t sz = memory_region_size(&backend->mr);
diff --git a/docs/devel/reset.rst b/docs/devel/reset.rst
index ed41e09..74c7c01 100644
--- a/docs/devel/reset.rst
+++ b/docs/devel/reset.rst
@@ -44,6 +44,17 @@
value on each cold reset, such as RNG seed information, and which they
must not reinitialize on a snapshot-load reset.
+``RESET_TYPE_WAKEUP``
+ If the machine supports waking up from a suspended state and needs to reset
+ its devices during wake-up (from the ``MachineClass::wakeup()`` method), this
+ reset type should be used for such a request. Devices can utilize this reset
+ type to differentiate the reset requested during machine wake-up from other
+ reset requests. For example, RAM content must not be lost during wake-up, and
+ memory devices like virtio-mem that provide additional RAM must not reset
+ such state during wake-ups, but might do so during cold resets. However, this
+ reset type should not be used for wake-up detection, as not every machine
+ type issues a device reset request during wake-up.
+
``RESET_TYPE_S390_CPU_NORMAL``
This is only used for S390 CPU objects; it clears interrupts, stops
processing, and clears the TLB, but does not touch register contents.
@@ -53,7 +64,6 @@
``RESET_TYPE_S390_CPU_NORMAL`` does and also clears the PSW, prefix,
FPC, timer and control registers. It does not touch gprs, fprs or acrs.
-
Devices which implement reset methods must treat any unknown ``ResetType``
as equivalent to ``RESET_TYPE_COLD``; this will reduce the amount of
existing code we need to change if we add more types in future.
diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c
index 3d13b16..cf0c6c5 100644
--- a/hw/arm/aspeed.c
+++ b/hw/arm/aspeed.c
@@ -1529,12 +1529,12 @@
aspeed_machine_class_init_cpus_defaults(mc);
}
-static void fby35_reset(MachineState *state, ShutdownCause reason)
+static void fby35_reset(MachineState *state, ResetType type)
{
AspeedMachineState *bmc = ASPEED_MACHINE(state);
AspeedGPIOState *gpio = &bmc->soc->gpio;
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
/* Board ID: 7 (Class-1, 4 slots) */
object_property_set_bool(OBJECT(gpio), "gpioV4", true, &error_fatal);
diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
index aec57c0..8edf57a 100644
--- a/hw/arm/mps2-tz.c
+++ b/hw/arm/mps2-tz.c
@@ -1254,7 +1254,7 @@
}
}
-static void mps2_machine_reset(MachineState *machine, ShutdownCause reason)
+static void mps2_machine_reset(MachineState *machine, ResetType type)
{
MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine);
@@ -1264,7 +1264,7 @@
* reset see the correct mapping.
*/
remap_memory(mms, mms->remap);
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
}
static void mps2tz_class_init(ObjectClass *oc, void *data)
diff --git a/hw/core/reset.c b/hw/core/reset.c
index 58dfc8d..14a2639 100644
--- a/hw/core/reset.c
+++ b/hw/core/reset.c
@@ -170,11 +170,8 @@
resettable_container_remove(get_root_reset_container(), obj);
}
-void qemu_devices_reset(ShutdownCause reason)
+void qemu_devices_reset(ResetType type)
{
- ResetType type = (reason == SHUTDOWN_CAUSE_SNAPSHOT_LOAD) ?
- RESET_TYPE_SNAPSHOT_LOAD : RESET_TYPE_COLD;
-
/* Reset the simulation */
resettable_reset(OBJECT(get_root_reset_container()), type);
}
diff --git a/hw/hppa/machine.c b/hw/hppa/machine.c
index 5d0a873..8259fe2 100644
--- a/hw/hppa/machine.c
+++ b/hw/hppa/machine.c
@@ -642,12 +642,12 @@
machine_HP_common_init_tail(machine, pci_bus, translate);
}
-static void hppa_machine_reset(MachineState *ms, ShutdownCause reason)
+static void hppa_machine_reset(MachineState *ms, ResetType type)
{
unsigned int smp_cpus = ms->smp.cpus;
int i;
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
/* Start all CPUs at the firmware entry point.
* Monarch CPU will initialize firmware, secondary CPUs
diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c
index 40edcee..8ae4dff 100644
--- a/hw/i386/microvm.c
+++ b/hw/i386/microvm.c
@@ -462,7 +462,7 @@
microvm_devices_init(mms);
}
-static void microvm_machine_reset(MachineState *machine, ShutdownCause reason)
+static void microvm_machine_reset(MachineState *machine, ResetType type)
{
MicrovmMachineState *mms = MICROVM_MACHINE(machine);
CPUState *cs;
@@ -475,7 +475,7 @@
mms->kernel_cmdline_fixed = true;
}
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
CPU_FOREACH(cs) {
cpu = X86_CPU(cs);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 8d84c22..80a65d9 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1712,12 +1712,12 @@
qemu_add_machine_init_done_notifier(&pcms->machine_done);
}
-static void pc_machine_reset(MachineState *machine, ShutdownCause reason)
+static void pc_machine_reset(MachineState *machine, ResetType type)
{
CPUState *cs;
X86CPU *cpu;
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
/* Reset APIC after devices have been reset to cancel
* any changes that qemu_devices_reset() might have done.
@@ -1732,7 +1732,7 @@
static void pc_machine_wakeup(MachineState *machine)
{
cpu_synchronize_all_states();
- pc_machine_reset(machine, SHUTDOWN_CAUSE_NONE);
+ pc_machine_reset(machine, RESET_TYPE_WAKEUP);
cpu_synchronize_all_post_reset();
}
diff --git a/hw/ppc/pegasos2.c b/hw/ppc/pegasos2.c
index 9b0a6b7..8ff4a00 100644
--- a/hw/ppc/pegasos2.c
+++ b/hw/ppc/pegasos2.c
@@ -291,14 +291,14 @@
cpu_physical_memory_write(PCI1_IO_BASE + 0x3f1, &val, 1);
}
-static void pegasos2_machine_reset(MachineState *machine, ShutdownCause reason)
+static void pegasos2_machine_reset(MachineState *machine, ResetType type)
{
Pegasos2MachineState *pm = PEGASOS2_MACHINE(machine);
void *fdt;
uint64_t d[2];
int sz;
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
if (!pm->vof) {
return; /* Firmware should set up machine so nothing to do */
}
diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index 3526852..988fd55 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -709,13 +709,13 @@
}
}
-static void pnv_reset(MachineState *machine, ShutdownCause reason)
+static void pnv_reset(MachineState *machine, ResetType type)
{
PnvMachineState *pnv = PNV_MACHINE(machine);
IPMIBmc *bmc;
void *fdt;
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
/*
* The machine should provide by default an internal BMC simulator.
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 8aa3ce7..2c10a70 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1725,7 +1725,7 @@
}
}
-static void spapr_machine_reset(MachineState *machine, ShutdownCause reason)
+static void spapr_machine_reset(MachineState *machine, ResetType type)
{
SpaprMachineState *spapr = SPAPR_MACHINE(machine);
PowerPCCPU *first_ppc_cpu;
@@ -1733,7 +1733,7 @@
void *fdt;
int rc;
- if (reason != SHUTDOWN_CAUSE_SNAPSHOT_LOAD) {
+ if (type != RESET_TYPE_SNAPSHOT_LOAD) {
/*
* Record-replay snapshot load must not consume random, this was
* already replayed from initial machine reset.
@@ -1762,7 +1762,7 @@
spapr_setup_hpt(spapr);
}
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
spapr_ovec_cleanup(spapr->ov5_cas);
spapr->ov5_cas = spapr_ovec_new();
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 18240a0..5aa8d20 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -440,7 +440,7 @@
s390_pv_prep_reset();
}
-static void s390_machine_reset(MachineState *machine, ShutdownCause reason)
+static void s390_machine_reset(MachineState *machine, ResetType type)
{
S390CcwMachineState *ms = S390_CCW_MACHINE(machine);
enum s390_reset reset_type;
@@ -472,7 +472,7 @@
* Device reset includes CPU clear resets so this has to be
* done AFTER the unprotect call above.
*/
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
s390_crypto_reset();
/* configure and start the ipl CPU only */
diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
index bea5be4..17595ff 100644
--- a/hw/virtio/Kconfig
+++ b/hw/virtio/Kconfig
@@ -16,6 +16,7 @@
default y if PCI_DEVICES
depends on PCI
select VIRTIO
+ select VIRTIO_MD_SUPPORTED
config VIRTIO_MMIO
bool
@@ -35,10 +36,17 @@
default y
depends on VIRTIO
+# not all virtio transports support memory devices; if none does,
+# no need to include the code
+config VIRTIO_MD_SUPPORTED
+ bool
+
config VIRTIO_MD
bool
+ depends on VIRTIO_MD_SUPPORTED
select MEM_DEVICE
+# selected by the board if it has the required support code
config VIRTIO_PMEM_SUPPORTED
bool
@@ -46,9 +54,11 @@
bool
default y
depends on VIRTIO
+ depends on VIRTIO_MD_SUPPORTED
depends on VIRTIO_PMEM_SUPPORTED
select VIRTIO_MD
+# selected by the board if it has the required support code
config VIRTIO_MEM_SUPPORTED
bool
@@ -57,6 +67,7 @@
default y
depends on VIRTIO
depends on LINUX
+ depends on VIRTIO_MD_SUPPORTED
depends on VIRTIO_MEM_SUPPORTED
select VIRTIO_MD
diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index 4075f3d..ae1e81d 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -890,6 +890,9 @@
if (vmem->unplugged_inaccessible == ON_OFF_AUTO_ON) {
virtio_add_feature(&features, VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE);
}
+ if (qemu_wakeup_suspend_enabled()) {
+ virtio_add_feature(&features, VIRTIO_MEM_F_PERSISTENT_SUSPEND);
+ }
return features;
}
@@ -902,18 +905,6 @@
return 0;
}
-static void virtio_mem_system_reset(void *opaque)
-{
- VirtIOMEM *vmem = VIRTIO_MEM(opaque);
-
- /*
- * During usual resets, we will unplug all memory and shrink the usable
- * region size. This is, however, not possible in all scenarios. Then,
- * the guest has to deal with this manually (VIRTIO_MEM_REQ_UNPLUG_ALL).
- */
- virtio_mem_unplug_all(vmem);
-}
-
static void virtio_mem_prepare_mr(VirtIOMEM *vmem)
{
const uint64_t region_size = memory_region_size(&vmem->memdev->mr);
@@ -1130,7 +1121,7 @@
vmstate_register_any(VMSTATE_IF(vmem),
&vmstate_virtio_mem_device_early, vmem);
}
- qemu_register_reset(virtio_mem_system_reset, vmem);
+ qemu_register_resettable(OBJECT(vmem));
/*
* Set ourselves as RamDiscardManager before the plug handler maps the
@@ -1150,7 +1141,7 @@
* found via an address space anymore. Unset ourselves.
*/
memory_region_set_ram_discard_manager(&vmem->memdev->mr, NULL);
- qemu_unregister_reset(virtio_mem_system_reset, vmem);
+ qemu_unregister_resettable(OBJECT(vmem));
if (vmem->early_migration) {
vmstate_unregister(VMSTATE_IF(vmem), &vmstate_virtio_mem_device_early,
vmem);
@@ -1850,12 +1841,38 @@
}
}
+static ResettableState *virtio_mem_get_reset_state(Object *obj)
+{
+ VirtIOMEM *vmem = VIRTIO_MEM(obj);
+ return &vmem->reset_state;
+}
+
+static void virtio_mem_system_reset_hold(Object *obj, ResetType type)
+{
+ VirtIOMEM *vmem = VIRTIO_MEM(obj);
+
+ /*
+ * When waking up from standby/suspend-to-ram, do not unplug any memory.
+ */
+ if (type == RESET_TYPE_WAKEUP) {
+ return;
+ }
+
+ /*
+ * During usual resets, we will unplug all memory and shrink the usable
+ * region size. This is, however, not possible in all scenarios. Then,
+ * the guest has to deal with this manually (VIRTIO_MEM_REQ_UNPLUG_ALL).
+ */
+ virtio_mem_unplug_all(vmem);
+}
+
static void virtio_mem_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
VirtIOMEMClass *vmc = VIRTIO_MEM_CLASS(klass);
RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_CLASS(klass);
+ ResettableClass *rc = RESETTABLE_CLASS(klass);
device_class_set_props(dc, virtio_mem_properties);
dc->vmsd = &vmstate_virtio_mem;
@@ -1882,6 +1899,9 @@
rdmc->replay_discarded = virtio_mem_rdm_replay_discarded;
rdmc->register_listener = virtio_mem_rdm_register_listener;
rdmc->unregister_listener = virtio_mem_rdm_unregister_listener;
+
+ rc->get_state = virtio_mem_get_reset_state;
+ rc->phases.hold = virtio_mem_system_reset_hold;
}
static const TypeInfo virtio_mem_info = {
diff --git a/hw/virtio/virtio-qmp.c b/hw/virtio/virtio-qmp.c
index 1dd96ed..cccc6fe 100644
--- a/hw/virtio/virtio-qmp.c
+++ b/hw/virtio/virtio-qmp.c
@@ -450,6 +450,9 @@
FEATURE_ENTRY(VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, \
"VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE: Unplugged memory cannot be "
"accessed"),
+ FEATURE_ENTRY(VIRTIO_MEM_F_PERSISTENT_SUSPEND, \
+ "VIRTIO_MEM_F_PERSISTENT_SUSPND: Plugged memory will remain "
+ "plugged when suspending+resuming"),
{ -1, "" }
};
#endif
diff --git a/include/hw/boards.h b/include/hw/boards.h
index ff25c53..5966069 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -10,6 +10,7 @@
#include "qemu/module.h"
#include "qom/object.h"
#include "hw/core/cpu.h"
+#include "hw/resettable.h"
#define TYPE_MACHINE_SUFFIX "-machine"
@@ -257,7 +258,7 @@
const char *deprecation_reason;
void (*init)(MachineState *state);
- void (*reset)(MachineState *state, ShutdownCause reason);
+ void (*reset)(MachineState *state, ResetType type);
void (*wakeup)(MachineState *state);
int (*kvm_type)(MachineState *machine, const char *arg);
int (*hvf_get_physical_address_range)(MachineState *machine);
diff --git a/include/hw/resettable.h b/include/hw/resettable.h
index 94f6f22..fd862f1 100644
--- a/include/hw/resettable.h
+++ b/include/hw/resettable.h
@@ -29,6 +29,7 @@
* Types of reset.
*
* + Cold: reset resulting from a power cycle of the object.
+ * + Wakeup: reset resulting from a wake-up from a suspended state.
*
* TODO: Support has to be added to handle more types. In particular,
* ResettableState structure needs to be expanded.
@@ -36,6 +37,7 @@
typedef enum ResetType {
RESET_TYPE_COLD,
RESET_TYPE_SNAPSHOT_LOAD,
+ RESET_TYPE_WAKEUP,
RESET_TYPE_S390_CPU_INITIAL,
RESET_TYPE_S390_CPU_NORMAL,
} ResetType;
diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h
index 5f5b02b..a1af144 100644
--- a/include/hw/virtio/virtio-mem.h
+++ b/include/hw/virtio/virtio-mem.h
@@ -14,6 +14,7 @@
#define HW_VIRTIO_MEM_H
#include "standard-headers/linux/virtio_mem.h"
+#include "hw/resettable.h"
#include "hw/virtio/virtio.h"
#include "qapi/qapi-types-misc.h"
#include "sysemu/hostmem.h"
@@ -115,6 +116,9 @@
/* listeners to notify on plug/unplug activity. */
QLIST_HEAD(, RamDiscardListener) rdl_list;
+
+ /* State of the resettable container */
+ ResettableState reset_state;
};
struct VirtIOMEMClass {
diff --git a/include/sysemu/reset.h b/include/sysemu/reset.h
index ae43604..0e297c0 100644
--- a/include/sysemu/reset.h
+++ b/include/sysemu/reset.h
@@ -27,6 +27,7 @@
#ifndef QEMU_SYSEMU_RESET_H
#define QEMU_SYSEMU_RESET_H
+#include "hw/resettable.h"
#include "qapi/qapi-events-run-state.h"
typedef void QEMUResetHandler(void *opaque);
@@ -110,7 +111,7 @@
/**
* qemu_devices_reset: Perform a complete system reset
- * @reason: reason for the reset
+ * @reason: type of the reset
*
* This function performs the low-level work needed to do a complete reset
* of the system (calling all the callbacks registered with
@@ -121,6 +122,6 @@
* If you want to trigger a system reset from, for instance, a device
* model, don't use this function. Use qemu_system_reset_request().
*/
-void qemu_devices_reset(ShutdownCause reason);
+void qemu_devices_reset(ResetType type);
#endif
diff --git a/system/runstate.c b/system/runstate.c
index a0e2a5f..c2c9afa 100644
--- a/system/runstate.c
+++ b/system/runstate.c
@@ -32,6 +32,7 @@
#include "exec/cpu-common.h"
#include "gdbstub/syscalls.h"
#include "hw/boards.h"
+#include "hw/resettable.h"
#include "migration/misc.h"
#include "migration/postcopy-ram.h"
#include "monitor/monitor.h"
@@ -507,15 +508,23 @@
void qemu_system_reset(ShutdownCause reason)
{
MachineClass *mc;
+ ResetType type;
mc = current_machine ? MACHINE_GET_CLASS(current_machine) : NULL;
cpu_synchronize_all_states();
+ switch (reason) {
+ case SHUTDOWN_CAUSE_SNAPSHOT_LOAD:
+ type = RESET_TYPE_SNAPSHOT_LOAD;
+ break;
+ default:
+ type = RESET_TYPE_COLD;
+ }
if (mc && mc->reset) {
- mc->reset(current_machine, reason);
+ mc->reset(current_machine, type);
} else {
- qemu_devices_reset(reason);
+ qemu_devices_reset(type);
}
switch (reason) {
case SHUTDOWN_CAUSE_NONE:
