From d352e33e1f92e60e12a00be1ea80f47b4e024c88 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 23 Sep 2025 09:04:06 +0200 Subject: arm/virt: Wire up a GED error device for ACPI / GHES Adds support to ARM virtualization to allow handling generic error ACPI Event via GED & error source device. It is aligned with Linux Kernel patch: https://lore.kernel.org/lkml/1272350481-27951-8-git-send-email-ying.huang@intel.com/ Co-authored-by: Mauro Carvalho Chehab Co-authored-by: Jonathan Cameron Signed-off-by: Jonathan Cameron Signed-off-by: Mauro Carvalho Chehab Acked-by: Igor Mammedov Reviewed-by: Jonathan Cameron Reviewed-by: Michael S. Tsirkin Message-ID: <3237a76b1469d669436399495825348bf34122cd.1758610789.git.mchehab+huawei@kernel.org> Signed-off-by: Michael S. Tsirkin --- hw/arm/virt.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'hw/arm/virt.c') diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 02209fadcf..6960f6113f 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -693,7 +693,7 @@ static inline DeviceState *create_acpi_ged(VirtMachineState *vms) MachineState *ms = MACHINE(vms); SysBusDevice *sbdev; int irq = vms->irqmap[VIRT_ACPI_GED]; - uint32_t event = ACPI_GED_PWR_DOWN_EVT; + uint32_t event = ACPI_GED_PWR_DOWN_EVT | ACPI_GED_ERROR_EVT; bool acpi_pcihp; if (ms->ram_slots) { @@ -1050,6 +1050,13 @@ static void virt_powerdown_req(Notifier *n, void *opaque) } } +static void virt_generic_error_req(Notifier *n, void *opaque) +{ + VirtMachineState *s = container_of(n, VirtMachineState, generic_error_notifier); + + acpi_send_event(s->acpi_dev, ACPI_GENERIC_ERROR); +} + static void create_gpio_keys(char *fdt, DeviceState *pl061_dev, uint32_t phandle) { @@ -2500,6 +2507,9 @@ static void machvirt_init(MachineState *machine) if (has_ged && aarch64 && firmware_loaded && virt_is_acpi_enabled(vms)) { vms->acpi_dev = create_acpi_ged(vms); + vms->generic_error_notifier.notify = virt_generic_error_req; + notifier_list_add(&acpi_generic_error_notifiers, + &vms->generic_error_notifier); } else { create_gpio_devices(vms, VIRT_GPIO, sysmem); } -- cgit 1.4.1 From ddd8f3baa27dc05251f52e94d1b643bfb93cbc83 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 23 Sep 2025 09:04:07 +0200 Subject: qapi/acpi-hest: add an interface to do generic CPER error injection Create a QMP command to be used for generic ACPI APEI hardware error injection (HEST) via GHESv2, and add support for it for ARM guests. Error injection uses ACPI_HEST_SRC_ID_QMP source ID to be platform independent. This is mapped at arch virt bindings, depending on the types supported by QEMU and by the BIOS. So, on ARM, this is supported via ACPI_GHES_NOTIFY_GPIO notification type. This patch was co-authored: - original ghes logic to inject a simple ARM record by Shiju Jose; - generic logic to handle block addresses by Jonathan Cameron; - generic GHESv2 error inject by Mauro Carvalho Chehab; Co-authored-by: Jonathan Cameron Co-authored-by: Shiju Jose Co-authored-by: Mauro Carvalho Chehab Signed-off-by: Jonathan Cameron Signed-off-by: Shiju Jose Signed-off-by: Mauro Carvalho Chehab Acked-by: Igor Mammedov Acked-by: Markus Armbruster Reviewed-by: Michael S. Tsirkin Message-ID: <81e2118b3c8b7e5da341817f277d61251655e0db.1758610789.git.mchehab+huawei@kernel.org> Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 7 +++++++ hw/acpi/Kconfig | 5 +++++ hw/acpi/ghes.c | 2 +- hw/acpi/ghes_cper.c | 40 ++++++++++++++++++++++++++++++++++++++++ hw/acpi/ghes_cper_stub.c | 20 ++++++++++++++++++++ hw/acpi/meson.build | 2 ++ hw/arm/virt-acpi-build.c | 1 + hw/arm/virt.c | 7 +++++++ include/hw/acpi/ghes.h | 1 + include/hw/arm/virt.h | 1 + qapi/acpi-hest.json | 36 ++++++++++++++++++++++++++++++++++++ qapi/meson.build | 1 + qapi/qapi-schema.json | 1 + 13 files changed, 123 insertions(+), 1 deletion(-) create mode 100644 hw/acpi/ghes_cper.c create mode 100644 hw/acpi/ghes_cper_stub.c create mode 100644 qapi/acpi-hest.json (limited to 'hw/arm/virt.c') diff --git a/MAINTAINERS b/MAINTAINERS index 406cef88f0..b31ae5193d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2173,6 +2173,13 @@ F: hw/acpi/ghes.c F: include/hw/acpi/ghes.h F: docs/specs/acpi_hest_ghes.rst +ACPI/HEST/GHES/ARM processor CPER +R: Mauro Carvalho Chehab +S: Maintained +F: hw/arm/ghes_cper.c +F: hw/acpi/ghes_cper_stub.c +F: qapi/acpi-hest.json + ppc4xx L: qemu-ppc@nongnu.org S: Orphan diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index 1d4e9f0845..daabbe6cd1 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -51,6 +51,11 @@ config ACPI_APEI bool depends on ACPI +config GHES_CPER + bool + depends on ACPI_APEI + default y + config ACPI_PCI bool depends on ACPI && PCI diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index d666f1b10b..06555905ce 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -553,7 +553,7 @@ void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len, /* Write the generic error data entry into guest memory */ cpu_physical_memory_write(cper_addr, cper, len); - notifier_list_notify(&acpi_generic_error_notifiers, NULL); + notifier_list_notify(&acpi_generic_error_notifiers, &source_id); } int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id, diff --git a/hw/acpi/ghes_cper.c b/hw/acpi/ghes_cper.c new file mode 100644 index 0000000000..31cb2ffabe --- /dev/null +++ b/hw/acpi/ghes_cper.c @@ -0,0 +1,40 @@ +/* + * CPER payload parser for error injection + * + * Copyright(C) 2024-2025 Huawei LTD. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" + +#include "qemu/base64.h" +#include "qemu/error-report.h" +#include "qemu/uuid.h" +#include "qapi/qapi-commands-acpi-hest.h" +#include "hw/acpi/ghes.h" + +void qmp_inject_ghes_v2_error(const char *qmp_cper, Error **errp) +{ + AcpiGhesState *ags; + uint8_t *cper; + size_t len; + + ags = acpi_ghes_get_state(); + if (!ags) { + return; + } + + cper = qbase64_decode(qmp_cper, -1, &len, errp); + if (!cper) { + error_setg(errp, "missing GHES CPER payload"); + return; + } + + ghes_record_cper_errors(ags, cper, len, ACPI_HEST_SRC_ID_QMP, errp); + + g_free(cper); +} diff --git a/hw/acpi/ghes_cper_stub.c b/hw/acpi/ghes_cper_stub.c new file mode 100644 index 0000000000..b16be73502 --- /dev/null +++ b/hw/acpi/ghes_cper_stub.c @@ -0,0 +1,20 @@ +/* + * Stub interface for CPER payload parser for error injection + * + * Copyright(C) 2024-2025 Huawei LTD. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qapi/qapi-commands-acpi-hest.h" +#include "hw/acpi/ghes.h" + +void qmp_inject_ghes_v2_error(const char *cper, Error **errp) +{ + error_setg(errp, "GHES QMP error inject is not compiled in"); +} diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build index 73f02b9691..56b5d1ec96 100644 --- a/hw/acpi/meson.build +++ b/hw/acpi/meson.build @@ -34,4 +34,6 @@ endif system_ss.add(when: 'CONFIG_ACPI', if_false: files('acpi-stub.c', 'aml-build-stub.c', 'ghes-stub.c', 'acpi_interface.c')) system_ss.add(when: 'CONFIG_ACPI_PCI_BRIDGE', if_false: files('pci-bridge-stub.c')) system_ss.add_all(when: 'CONFIG_ACPI', if_true: acpi_ss) +system_ss.add(when: 'CONFIG_GHES_CPER', if_true: files('ghes_cper.c')) +system_ss.add(when: 'CONFIG_GHES_CPER', if_false: files('ghes_cper_stub.c')) system_ss.add(files('acpi-qmp-cmds.c')) diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 2b63008df0..8bb6b60515 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -1128,6 +1128,7 @@ static void acpi_align_size(GArray *blob, unsigned align) static const AcpiNotificationSourceId hest_ghes_notify[] = { { ACPI_HEST_SRC_ID_SYNC, ACPI_GHES_NOTIFY_SEA }, + { ACPI_HEST_SRC_ID_QMP, ACPI_GHES_NOTIFY_GPIO }, }; static const AcpiNotificationSourceId hest_ghes_notify_10_0[] = { diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 6960f6113f..aad557be1a 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -1052,6 +1052,13 @@ static void virt_powerdown_req(Notifier *n, void *opaque) static void virt_generic_error_req(Notifier *n, void *opaque) { + uint16_t *source_id = opaque; + + /* Currently, only QMP source ID is async */ + if (*source_id != ACPI_HEST_SRC_ID_QMP) { + return; + } + VirtMachineState *s = container_of(n, VirtMachineState, generic_error_notifier); acpi_send_event(s->acpi_dev, ACPI_GENERIC_ERROR); diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index 390943e46d..df2ecbf6e4 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -65,6 +65,7 @@ enum AcpiGhesNotifyType { */ enum AcpiGhesSourceID { ACPI_HEST_SRC_ID_SYNC, + ACPI_HEST_SRC_ID_QMP, /* Use it only for QMP injected errors */ }; typedef struct AcpiNotificationSourceId { diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index e14ea0f9d4..04a09af354 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -33,6 +33,7 @@ #include "exec/hwaddr.h" #include "qemu/notify.h" #include "hw/boards.h" +#include "hw/acpi/ghes.h" #include "hw/arm/boot.h" #include "hw/arm/bsa.h" #include "hw/block/flash.h" diff --git a/qapi/acpi-hest.json b/qapi/acpi-hest.json new file mode 100644 index 0000000000..28af1266a7 --- /dev/null +++ b/qapi/acpi-hest.json @@ -0,0 +1,36 @@ +# -*- Mode: Python -*- +# vim: filetype=python +# SPDX-License-Identifier: GPL-2.0-or-later + +## +# == GHESv2 CPER Error Injection +# +# Defined since ACPI Specification 6.1, +# section 18.3.2.8 Generic Hardware Error Source version 2. See: +# +# https://uefi.org/sites/default/files/resources/ACPI_6_1.pdf +## + + +## +# @inject-ghes-v2-error: +# +# Inject an error with additional ACPI 6.1 GHESv2 error information +# +# @cper: contains a base64 encoded string with raw data for a single +# CPER record with Generic Error Status Block, Generic Error Data +# Entry and generic error data payload, as described at +# https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html#format +# +# Features: +# +# @unstable: This command is experimental. +# +# Since: 10.2 +## +{ 'command': 'inject-ghes-v2-error', + 'data': { + 'cper': 'str' + }, + 'features': [ 'unstable' ] +} diff --git a/qapi/meson.build b/qapi/meson.build index ca6b61a608..a46269b5a0 100644 --- a/qapi/meson.build +++ b/qapi/meson.build @@ -59,6 +59,7 @@ if have_system qapi_all_modules += [ 'accelerator', 'acpi', + 'acpi-hest', 'audio', 'cryptodev', 'qdev', diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json index 82f111ba06..b93dd68d94 100644 --- a/qapi/qapi-schema.json +++ b/qapi/qapi-schema.json @@ -68,6 +68,7 @@ { 'include': 'misc-i386.json' } { 'include': 'audio.json' } { 'include': 'acpi.json' } +{ 'include': 'acpi-hest.json' } { 'include': 'pci.json' } { 'include': 'stats.json' } { 'include': 'virtio.json' } -- cgit 1.4.1 From fa82ce2ddee8208c83a5a10bf3ab7348ad3d334a Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Mon, 1 Sep 2025 10:49:15 +0200 Subject: smbios: cap DIMM size to 2Tb as workaround for broken Windows With current limit set to match max spec size (2PTb), Windows fails to parse type 17 records when DIMM size reaches 4Tb+. Failure happens in GetPhysicallyInstalledSystemMemory() function, and fails "Check SMBIOS System Memory Tables" SVVP test. Though not fatal, it might cause issues for userspace apps, something like [1]. Lets cap default DIMM size to 2Tb for now, until MS fixes it. 1) https://issues.redhat.com/browse/RHEL-81999?focusedId=27731200&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-27731200 PS: It's obvious 32 int overflow math somewhere in Windows, MS admitted that it's Windows bug and in a process of fixing it. However it's unclear if W10 and earlier would get the fix. So however I dislike changing defaults, we heed to work around the issue (it looks like QEMU regression while not being it). Hopefully 2Tb/DIMM split will last longer until VM memory size will become large enough to cause to many type 17 records issue again. PPS: Alternatively, instead of messing with defaults, we can create a dedicated knob to ask for desired DIMM size cap explicitly on CLI. That will let users to enable workaround when they hit this corner case. Downside is that knob has to be propagated up all mgmt stack, which might be not desirable. PPPS: Yet alternatively, users can configure initial RAM to be less than 4Tb and all additional RAM add as DIMMs on QEMU CLI. (however it's the job to be done by mgmt which could know Windows version and total amount of RAM) Signed-off-by: Igor Mammedov Fixes: 62f182c97b ("smbios: make memory device size configurable per Machine") Reviewed-by: Michael S. Tsirkin Message-ID: <20250901084915.2607632-1-imammedo@redhat.com> Signed-off-by: Michael S. Tsirkin --- hw/arm/virt.c | 1 + hw/core/machine.c | 5 ++++- hw/i386/pc_piix.c | 1 + hw/i386/pc_q35.c | 1 + 4 files changed, 7 insertions(+), 1 deletion(-) (limited to 'hw/arm/virt.c') diff --git a/hw/arm/virt.c b/hw/arm/virt.c index aad557be1a..175023897a 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -3537,6 +3537,7 @@ DEFINE_VIRT_MACHINE_AS_LATEST(10, 2) static void virt_machine_10_1_options(MachineClass *mc) { virt_machine_10_2_options(mc); + mc->smbios_memory_device_size = 2047 * TiB; compat_props_add(mc->compat_props, hw_compat_10_1, hw_compat_10_1_len); } DEFINE_VIRT_MACHINE(10, 1) diff --git a/hw/core/machine.c b/hw/core/machine.c index 7b7a381b0a..681adbb7ac 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -1118,8 +1118,11 @@ static void machine_class_init(ObjectClass *oc, const void *data) * SMBIOS 3.1.0 7.18.5 Memory Device — Extended Size * use max possible value that could be encoded into * 'Extended Size' field (2047Tb). + * + * Unfortunately (current) Windows Server 2025 and earlier do not handle + * 4Tb+ DIMM size. */ - mc->smbios_memory_device_size = 2047 * TiB; + mc->smbios_memory_device_size = 2 * TiB; /* numa node memory size aligned on 8MB by default. * On Linux, each node's border has to be 8MB aligned diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index caf8bab68e..7b3611e973 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -448,6 +448,7 @@ DEFINE_I440FX_MACHINE_AS_LATEST(10, 2); static void pc_i440fx_machine_10_1_options(MachineClass *m) { pc_i440fx_machine_10_2_options(m); + m->smbios_memory_device_size = 2047 * TiB; compat_props_add(m->compat_props, hw_compat_10_1, hw_compat_10_1_len); compat_props_add(m->compat_props, pc_compat_10_1, pc_compat_10_1_len); } diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index e89951285e..6015e639d7 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -384,6 +384,7 @@ DEFINE_Q35_MACHINE_AS_LATEST(10, 2); static void pc_q35_machine_10_1_options(MachineClass *m) { pc_q35_machine_10_2_options(m); + m->smbios_memory_device_size = 2047 * TiB; compat_props_add(m->compat_props, hw_compat_10_1, hw_compat_10_1_len); compat_props_add(m->compat_props, pc_compat_10_1, pc_compat_10_1_len); } -- cgit 1.4.1