MAINTAINERS | 10 + hw/acpi/Kconfig | 5 + hw/acpi/aml-build.c | 10 + hw/acpi/generic_event_device.c | 44 ++ hw/acpi/ghes-stub.c | 7 +- hw/acpi/ghes.c | 204 +++-- hw/acpi/ghes_cper.c | 38 + hw/acpi/ghes_cper_stub.c | 19 + hw/acpi/meson.build | 2 + hw/arm/virt-acpi-build.c | 35 +- hw/arm/virt.c | 19 +- hw/core/machine.c | 2 + include/hw/acpi/acpi_dev_interface.h | 1 + include/hw/acpi/aml-build.h | 2 + include/hw/acpi/generic_event_device.h | 1 + include/hw/acpi/ghes.h | 45 +- include/hw/arm/virt.h | 2 + qapi/acpi-hest.json | 35 + qapi/meson.build | 1 + qapi/qapi-schema.json | 1 + scripts/arm_processor_error.py | 377 ++++++++++ scripts/ghes_inject.py | 51 ++ scripts/qmp_helper.py | 702 ++++++++++++++++++ target/arm/kvm.c | 8 +- tests/data/acpi/aarch64/virt/DSDT | Bin 5196 -> 5240 bytes .../data/acpi/aarch64/virt/DSDT.acpihmatvirt | Bin 5282 -> 5326 bytes tests/data/acpi/aarch64/virt/DSDT.memhp | Bin 6557 -> 6601 bytes tests/data/acpi/aarch64/virt/DSDT.pxb | Bin 7679 -> 7723 bytes tests/data/acpi/aarch64/virt/DSDT.topology | Bin 5398 -> 5442 bytes tests/data/acpi/aarch64/virt/HEST | Bin 0 -> 224 bytes 30 files changed, 1550 insertions(+), 71 deletions(-) create mode 100644 hw/acpi/ghes_cper.c create mode 100644 hw/acpi/ghes_cper_stub.c create mode 100644 qapi/acpi-hest.json create mode 100644 scripts/arm_processor_error.py create mode 100755 scripts/ghes_inject.py create mode 100644 scripts/qmp_helper.py create mode 100644 tests/data/acpi/aarch64/virt/HEST
Now that the ghes preparation patches were merged, let's add support
for error injection.
On this series, the first 6 patches chang to the math used to calculate offsets at HEST
table and hardware_error firmware file, together with its migration code. Migration tested
with both latest QEMU released kernel and upstream, on both directions.
The next patches add a new QAPI to allow injecting GHESv2 errors, and a script using such QAPI
to inject ARM Processor Error records.
If I'm counting well, this is the 19th submission of my error inject patches.
---
v2:
- address some nits;
- improved ags cleanup patch and removed ags.present field;
- added some missing le*_to_cpu() calls;
- update date at copyright for new files to 2024-2025;
- qmp command changed to: inject-ghes-v2-error ans since updated to 10.0;
- added HEST and DSDT tables after the changes to make check target happy.
(two patches: first one whitelisting such tables; second one removing from
whitelist and updating/adding such tables to tests/data/acpi)
I'm enclosing a diff from v1 at the end, as it may help check the differences.
Mauro Carvalho Chehab (13):
acpi/ghes: Prepare to support multiple sources on ghes
tests/acpi: virt: allow acpi table changes for a new table: HEST
acpi/ghes: add a firmware file with HEST address
acpi/ghes: Use HEST table offsets when preparing GHES records
acpi/generic_event_device: Update GHES migration to cover hest addr
acpi/generic_event_device: add logic to detect if HEST addr is
available
acpi/ghes: add a notifier to notify when error data is ready
acpi/ghes: Cleanup the code which gets ghes ged state
acpi/generic_event_device: add an APEI error device
arm/virt: Wire up a GED error device for ACPI / GHES
qapi/acpi-hest: add an interface to do generic CPER error injection
tests/acpi: virt: add a HEST table to aarch64 virt and update DSDT
scripts/ghes_inject: add a script to generate GHES error inject
MAINTAINERS | 10 +
hw/acpi/Kconfig | 5 +
hw/acpi/aml-build.c | 10 +
hw/acpi/generic_event_device.c | 44 ++
hw/acpi/ghes-stub.c | 7 +-
hw/acpi/ghes.c | 204 +++--
hw/acpi/ghes_cper.c | 38 +
hw/acpi/ghes_cper_stub.c | 19 +
hw/acpi/meson.build | 2 +
hw/arm/virt-acpi-build.c | 35 +-
hw/arm/virt.c | 19 +-
hw/core/machine.c | 2 +
include/hw/acpi/acpi_dev_interface.h | 1 +
include/hw/acpi/aml-build.h | 2 +
include/hw/acpi/generic_event_device.h | 1 +
include/hw/acpi/ghes.h | 45 +-
include/hw/arm/virt.h | 2 +
qapi/acpi-hest.json | 35 +
qapi/meson.build | 1 +
qapi/qapi-schema.json | 1 +
scripts/arm_processor_error.py | 377 ++++++++++
scripts/ghes_inject.py | 51 ++
scripts/qmp_helper.py | 702 ++++++++++++++++++
target/arm/kvm.c | 8 +-
tests/data/acpi/aarch64/virt/DSDT | Bin 5196 -> 5240 bytes
.../data/acpi/aarch64/virt/DSDT.acpihmatvirt | Bin 5282 -> 5326 bytes
tests/data/acpi/aarch64/virt/DSDT.memhp | Bin 6557 -> 6601 bytes
tests/data/acpi/aarch64/virt/DSDT.pxb | Bin 7679 -> 7723 bytes
tests/data/acpi/aarch64/virt/DSDT.topology | Bin 5398 -> 5442 bytes
tests/data/acpi/aarch64/virt/HEST | Bin 0 -> 224 bytes
30 files changed, 1550 insertions(+), 71 deletions(-)
create mode 100644 hw/acpi/ghes_cper.c
create mode 100644 hw/acpi/ghes_cper_stub.c
create mode 100644 qapi/acpi-hest.json
create mode 100644 scripts/arm_processor_error.py
create mode 100755 scripts/ghes_inject.py
create mode 100644 scripts/qmp_helper.py
create mode 100644 tests/data/acpi/aarch64/virt/HEST
----
Diff against previous version:
Instead of placing a v2 here, it is probably more useful to add the diffs
against the past version:
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index ce00c80054f4..50313ed7ee96 100644
--- a/hw/acpi/generic_event_device.c
+++ b/hw/acpi/generic_event_device.c
@@ -29,6 +29,12 @@ static const uint32_t ged_supported_events[] = {
ACPI_GED_ERROR_EVT,
};
+/*
+ * ACPI 5.0b: 5.6.6 Device Object Notifications
+ * Table 5-135 Error Device Notification Values
+ */
+#define ERROR_DEVICE_NOTIFICATION 0x80
+
/*
* The ACPI Generic Event Device (GED) is a hardware-reduced specific
* device[ACPI v6.1 Section 5.6.9] that handles all platform events,
@@ -120,7 +126,7 @@ void build_ged_aml(Aml *table, const char *name, HotplugHandler *hotplug_dev,
case ACPI_GED_ERROR_EVT:
aml_append(if_ctx,
aml_notify(aml_name(ACPI_APEI_ERROR_DEVICE),
- aml_int(0x80)));
+ aml_int(ERROR_DEVICE_NOTIFICATION)));
break;
case ACPI_GED_NVDIMM_HOTPLUG_EVT:
aml_append(if_ctx,
@@ -326,7 +332,7 @@ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
static const Property acpi_ged_properties[] = {
DEFINE_PROP_UINT32("ged-event", AcpiGedState, ged_event_bitmap, 0),
- DEFINE_PROP_BOOL("x-has-hest-addr", AcpiGedState, ghes_state.hest_lookup, true),
+ DEFINE_PROP_BOOL("x-has-hest-addr", AcpiGedState, ghes_state.use_hest_addr, true),
};
static const VMStateDescription vmstate_memhp_state = {
diff --git a/hw/acpi/ghes-stub.c b/hw/acpi/ghes-stub.c
index fbabf955155a..40f660c246fe 100644
--- a/hw/acpi/ghes-stub.c
+++ b/hw/acpi/ghes-stub.c
@@ -11,7 +11,8 @@
#include "qemu/osdep.h"
#include "hw/acpi/ghes.h"
-int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
+int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
+ uint64_t physical_address)
{
return -1;
}
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 479c465c9554..52e1528aa788 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -67,16 +67,18 @@
* docs/specs/acpi_hest_ghes.rst.
*/
-/* ACPI 6.2: 18.3.2.8 Generic Hardware Error Source version 2
+/*
+ * ACPI 6.2: 18.3.2.8 Generic Hardware Error Source version 2
* Table 18-382 Generic Hardware Error Source version 2 (GHESv2) Structure
*/
#define HEST_GHES_V2_TABLE_SIZE 92
-#define GHES_ACK_OFFSET (64 + GAS_ADDR_OFFSET)
+#define GHES_READ_ACK_ADDR_OFF 64
-/* ACPI 6.2: 18.3.2.7: Generic Hardware Error Source
+/*
+ * ACPI 6.2: 18.3.2.7: Generic Hardware Error Source
* Table 18-380: 'Error Status Address' field
*/
-#define GHES_ERR_ST_ADDR_OFFSET (20 + GAS_ADDR_OFFSET)
+#define GHES_ERR_STATUS_ADDR_OFF 20
/*
* Values for error_severity field
@@ -286,10 +288,10 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
}
/* Build Generic Hardware Error Source version 2 (GHESv2) */
-static void build_ghes_v2(GArray *table_data,
- BIOSLinker *linker,
- const AcpiNotificationSourceId *notif_src,
- uint16_t index, int num_sources)
+static void build_ghes_v2_entry(GArray *table_data,
+ BIOSLinker *linker,
+ const AcpiNotificationSourceId *notif_src,
+ uint16_t index, int num_sources)
{
uint64_t address_offset;
const uint16_t notify = notif_src->notify;
@@ -357,45 +359,38 @@ static void build_ghes_v2(GArray *table_data,
}
/* Build Hardware Error Source Table */
-void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
+void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
+ GArray *hardware_errors,
BIOSLinker *linker,
- const AcpiNotificationSourceId * const notif_source,
+ const AcpiNotificationSourceId *notif_source,
int num_sources,
const char *oem_id, const char *oem_table_id)
{
AcpiTable table = { .sig = "HEST", .rev = 1,
.oem_id = oem_id, .oem_table_id = oem_table_id };
- AcpiGedState *acpi_ged_state;
- AcpiGhesState *ags = NULL;
+ uint32_t hest_offset;
int i;
build_ghes_error_table(hardware_errors, linker, num_sources);
acpi_table_begin(&table, table_data);
- int hest_offset = table_data->len;
+ hest_offset = table_data->len;
/* Error Source Count */
build_append_int_noprefix(table_data, num_sources, 4);
for (i = 0; i < num_sources; i++) {
- build_ghes_v2(table_data, linker, ¬if_source[i], i, num_sources);
+ build_ghes_v2_entry(table_data, linker, ¬if_source[i], i, num_sources);
}
acpi_table_end(linker, &table);
/*
- * tell firmware to write into GPA the address of HEST via fw_cfg,
+ * Tell firmware to write into GPA the address of HEST via fw_cfg,
* once initialized.
*/
- acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
- NULL));
- if (!acpi_ged_state) {
- return;
- }
-
- ags = &acpi_ged_state->ghes_state;
- if (ags->hest_lookup) {
+ if (ags->use_hest_addr) {
bios_linker_loader_write_pointer(linker,
ACPI_HEST_ADDR_FW_CFG_FILE, 0,
sizeof(uint64_t),
@@ -414,12 +409,10 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL,
NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false);
- if (ags && ags->hest_lookup) {
+ if (ags->use_hest_addr) {
fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
}
-
- ags->present = true;
}
static void get_hw_error_offsets(uint64_t ghes_addr,
@@ -444,26 +437,29 @@ static void get_hw_error_offsets(uint64_t ghes_addr,
*read_ack_register_addr = ghes_addr + sizeof(uint64_t);
}
-static void get_ghes_source_offsets(uint16_t source_id, uint64_t hest_addr,
+static void get_ghes_source_offsets(uint16_t source_id,
+ uint64_t hest_entry_addr,
uint64_t *cper_addr,
uint64_t *read_ack_start_addr,
Error **errp)
{
uint64_t hest_err_block_addr, hest_read_ack_addr;
- uint64_t err_source_struct, error_block_addr;
+ uint64_t err_source_entry, error_block_addr;
uint32_t num_sources, i;
- cpu_physical_memory_read(hest_addr, &num_sources, sizeof(num_sources));
+
+ cpu_physical_memory_read(hest_entry_addr, &num_sources,
+ sizeof(num_sources));
num_sources = le32_to_cpu(num_sources);
- err_source_struct = hest_addr + sizeof(num_sources);
+ err_source_entry = hest_entry_addr + sizeof(num_sources);
/*
* Currently, HEST Error source navigates only for GHESv2 tables
*/
for (i = 0; i < num_sources; i++) {
- uint64_t addr = err_source_struct;
+ uint64_t addr = err_source_entry;
uint16_t type, src_id;
cpu_physical_memory_read(addr, &type, sizeof(type));
@@ -479,11 +475,11 @@ static void get_ghes_source_offsets(uint16_t source_id, uint64_t hest_addr,
addr += sizeof(type);
cpu_physical_memory_read(addr, &src_id, sizeof(src_id));
- if (src_id == source_id) {
+ if (le16_to_cpu(src_id) == source_id) {
break;
}
- err_source_struct += HEST_GHES_V2_TABLE_SIZE;
+ err_source_entry += HEST_GHES_V2_TABLE_SIZE;
}
if (i == num_sources) {
error_setg(errp, "HEST: Source %d not found.", source_id);
@@ -491,39 +487,42 @@ static void get_ghes_source_offsets(uint16_t source_id, uint64_t hest_addr,
}
/* Navigate though table address pointers */
- hest_err_block_addr = err_source_struct + GHES_ERR_ST_ADDR_OFFSET;
- hest_read_ack_addr = err_source_struct + GHES_ACK_OFFSET;
+ hest_err_block_addr = err_source_entry + GHES_ERR_STATUS_ADDR_OFF +
+ GAS_ADDR_OFFSET;
cpu_physical_memory_read(hest_err_block_addr, &error_block_addr,
sizeof(error_block_addr));
+ error_block_addr = le64_to_cpu(error_block_addr);
+
cpu_physical_memory_read(error_block_addr, cper_addr,
sizeof(*cper_addr));
+ *cper_addr = le64_to_cpu(*cper_addr);
+
+ hest_read_ack_addr = err_source_entry + GHES_READ_ACK_ADDR_OFF +
+ GAS_ADDR_OFFSET;
+
cpu_physical_memory_read(hest_read_ack_addr, read_ack_start_addr,
sizeof(*read_ack_start_addr));
+
+ *read_ack_start_addr = le64_to_cpu(*read_ack_start_addr);
}
NotifierList acpi_generic_error_notifiers =
NOTIFIER_LIST_INITIALIZER(error_device_notifiers);
-void ghes_record_cper_errors(const void *cper, size_t len,
+void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
uint16_t source_id, Error **errp)
{
uint64_t cper_addr = 0, read_ack_register_addr = 0, read_ack_register;
- AcpiGhesState *ags;
if (len > ACPI_GHES_MAX_RAW_DATA_LENGTH) {
error_setg(errp, "GHES CPER record is too big: %zd", len);
return;
}
- ags = acpi_ghes_get_state();
- if (!ags) {
- return;
- }
-
- if (!ags->hest_lookup) {
+ if (!ags->use_hest_addr) {
fprintf(stderr,"Using old GHES lookup\n");
get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
&cper_addr, &read_ack_register_addr);
@@ -558,7 +557,8 @@ void ghes_record_cper_errors(const void *cper, size_t len,
notifier_list_notify(&acpi_generic_error_notifiers, &source_id);
}
-int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
+int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
+ uint64_t physical_address)
{
/* Memory Error Section Type */
const uint8_t guid[] =
@@ -576,7 +576,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
acpi_ghes_build_append_mem_cper(block, physical_address);
/* Report the error */
- ghes_record_cper_errors(block->data, block->len, source_id, &errp);
+ ghes_record_cper_errors(ags, block->data, block->len, source_id, &errp);
g_array_free(block, true);
@@ -600,9 +600,7 @@ AcpiGhesState *acpi_ghes_get_state(void)
return NULL;
}
ags = &acpi_ged_state->ghes_state;
- if (!ags->present) {
- return NULL;
- }
+
if (!ags->hw_error_le && !ags->hest_addr_le) {
return NULL;
}
diff --git a/hw/acpi/ghes_cper.c b/hw/acpi/ghes_cper.c
index 02c47b41b990..0a2d95dd8b27 100644
--- a/hw/acpi/ghes_cper.c
+++ b/hw/acpi/ghes_cper.c
@@ -1,7 +1,7 @@
/*
* CPER payload parser for error injection
*
- * Copyright(C) 2024 Huawei LTD.
+ * 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.
@@ -16,8 +16,14 @@
#include "qapi/qapi-commands-acpi-hest.h"
#include "hw/acpi/ghes.h"
-void qmp_inject_ghes_error(const char *qmp_cper, Error **errp)
+void qmp_inject_ghes_v2_error(const char *qmp_cper, Error **errp)
{
+ AcpiGhesState *ags;
+
+ ags = acpi_ghes_get_state();
+ if (!ags) {
+ return;
+ }
uint8_t *cper;
size_t len;
@@ -28,5 +34,5 @@ void qmp_inject_ghes_error(const char *qmp_cper, Error **errp)
return;
}
- ghes_record_cper_errors(cper, len, ACPI_HEST_SRC_ID_QMP, errp);
+ ghes_record_cper_errors(ags, cper, len, ACPI_HEST_SRC_ID_QMP, errp);
}
diff --git a/hw/acpi/ghes_cper_stub.c b/hw/acpi/ghes_cper_stub.c
index 8782e2c02fa8..5ebc61970a78 100644
--- a/hw/acpi/ghes_cper_stub.c
+++ b/hw/acpi/ghes_cper_stub.c
@@ -1,7 +1,7 @@
/*
* Stub interface for CPER payload parser for error injection
*
- * Copyright(C) 2024 Huawei LTD.
+ * 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.
@@ -13,7 +13,7 @@
#include "qapi/qapi-commands-acpi-hest.h"
#include "hw/acpi/ghes.h"
-void qmp_inject_ghes_error(const char *cper, Error **errp)
+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/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 0a1f0b62d289..7c7094f46b39 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -966,13 +966,13 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
acpi_add_table(table_offsets, tables_blob);
- if (!ags->hest_lookup) {
- acpi_build_hest(tables_blob, tables->hardware_errors,
+ if (!ags->use_hest_addr) {
+ acpi_build_hest(ags, tables_blob, tables->hardware_errors,
tables->linker, hest_ghes_notify_9_2,
ARRAY_SIZE(hest_ghes_notify_9_2),
vms->oem_id, vms->oem_table_id);
} else {
- acpi_build_hest(tables_blob, tables->hardware_errors,
+ acpi_build_hest(ags, tables_blob, tables->hardware_errors,
tables->linker, hest_ghes_notify,
ARRAY_SIZE(hest_ghes_notify),
vms->oem_id, vms->oem_table_id);
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index 078d78666f91..376933a0024a 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -63,8 +63,7 @@ enum AcpiGhesNotifyType {
typedef struct AcpiGhesState {
uint64_t hest_addr_le;
uint64_t hw_error_le;
- bool present; /* True if GHES is present at all on this board */
- bool hest_lookup; /* True if HEST address is present */
+ bool use_hest_addr; /* True if HEST address is present */
} AcpiGhesState;
/*
@@ -80,15 +79,17 @@ typedef struct AcpiNotificationSourceId {
enum AcpiGhesNotifyType notify;
} AcpiNotificationSourceId;
-void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
+void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
+ GArray *hardware_errors,
BIOSLinker *linker,
const AcpiNotificationSourceId * const notif_source,
int num_sources,
const char *oem_id, const char *oem_table_id);
void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s,
GArray *hardware_errors);
-int acpi_ghes_memory_errors(uint16_t source_id, uint64_t error_physical_addr);
-void ghes_record_cper_errors(const void *cper, size_t len,
+int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
+ uint64_t error_physical_addr);
+void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
uint16_t source_id, Error **errp);
/**
diff --git a/qapi/acpi-hest.json b/qapi/acpi-hest.json
index d58fba485180..fff5018c7ec1 100644
--- a/qapi/acpi-hest.json
+++ b/qapi/acpi-hest.json
@@ -12,7 +12,7 @@
##
-# @inject-ghes-error:
+# @inject-ghes-v2-error:
#
# Inject an error with additional ACPI 6.1 GHESv2 error information
#
@@ -25,9 +25,9 @@
#
# @unstable: This command is experimental.
#
-# Since: 9.2
+# Since: 10.0
##
-{ 'command': 'inject-ghes-error',
+{ 'command': 'inject-ghes-v2-error',
'data': {
'cper': 'str'
},
diff --git a/scripts/arm_processor_error.py b/scripts/arm_processor_error.py
index b4321ff45517..326efc8492dd 100644
--- a/scripts/arm_processor_error.py
+++ b/scripts/arm_processor_error.py
@@ -3,7 +3,7 @@
# pylint: disable=C0301,C0114,R0903,R0912,R0913,R0914,R0915,W0511
# SPDX-License-Identifier: GPL-2.0
#
-# Copyright (C) 2024 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
# Note: currently it lacks a method to fill the ARM Processor Error CPER
# psci field from emulation. On a real hardware, this is filled only
diff --git a/scripts/ghes_inject.py b/scripts/ghes_inject.py
index 67cb6077bec8..5d72bc7f09e1 100755
--- a/scripts/ghes_inject.py
+++ b/scripts/ghes_inject.py
@@ -2,7 +2,7 @@
#
# SPDX-License-Identifier: GPL-2.0
#
-# Copyright (C) 2024 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
"""
Handle ACPI GHESv2 error injection logic QEMU QMP interface.
diff --git a/scripts/qmp_helper.py b/scripts/qmp_helper.py
index 357ebc6e8359..8e375d6a6cab 100644
--- a/scripts/qmp_helper.py
+++ b/scripts/qmp_helper.py
@@ -3,7 +3,7 @@
# # pylint: disable=C0103,E0213,E1135,E1136,E1137,R0902,R0903,R0912,R0913
# SPDX-License-Identifier: GPL-2.0
#
-# Copyright (C) 2024 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
"""
Helper classes to be used by ghes_inject command classes.
@@ -541,7 +541,7 @@ def send_cper_raw(self, cper_data):
self._connect()
- if self.send_cmd("inject-ghes-error", cmd_arg):
+ if self.send_cmd("inject-ghes-v2-error", cmd_arg):
print("Error injected.")
def send_cper(self, notif_type, payload):
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index 0283089713b9..544ff174784d 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -2366,10 +2366,13 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
{
ram_addr_t ram_addr;
hwaddr paddr;
+ AcpiGhesState *ags;
assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
- if (acpi_ghes_get_state() && addr) {
+ ags = acpi_ghes_get_state();
+
+ if (ags && addr) {
ram_addr = qemu_ram_addr_from_host(addr);
if (ram_addr != RAM_ADDR_INVALID &&
kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
@@ -2387,7 +2390,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
*/
if (code == BUS_MCEERR_AR) {
kvm_cpu_synchronize_state(c);
- if (!acpi_ghes_memory_errors(ACPI_HEST_SRC_ID_SEA, paddr)) {
+ if (!acpi_ghes_memory_errors(ags, ACPI_HEST_SRC_ID_SEA,
+ paddr)) {
kvm_inject_arm_sea(c);
} else {
error_report("failed to record the error");
diff --git a/tests/data/acpi/aarch64/virt/DSDT b/tests/data/acpi/aarch64/virt/DSDT
index 36d3e5d5a5e4..a182bd9d7182 100644
Binary files a/tests/data/acpi/aarch64/virt/DSDT and b/tests/data/acpi/aarch64/virt/DSDT differ
diff --git a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt
index e6154d0355f8..af1f2b0eb0b7 100644
Binary files a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt and b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt differ
diff --git a/tests/data/acpi/aarch64/virt/DSDT.memhp b/tests/data/acpi/aarch64/virt/DSDT.memhp
index 33f011d6b635..10436ec87c48 100644
Binary files a/tests/data/acpi/aarch64/virt/DSDT.memhp and b/tests/data/acpi/aarch64/virt/DSDT.memhp differ
diff --git a/tests/data/acpi/aarch64/virt/DSDT.pxb b/tests/data/acpi/aarch64/virt/DSDT.pxb
index c0fdc6e9c139..0524b3cbe00b 100644
Binary files a/tests/data/acpi/aarch64/virt/DSDT.pxb and b/tests/data/acpi/aarch64/virt/DSDT.pxb differ
diff --git a/tests/data/acpi/aarch64/virt/DSDT.topology b/tests/data/acpi/aarch64/virt/DSDT.topology
index 029d03eecc4e..8c0423fe62d6 100644
Binary files a/tests/data/acpi/aarch64/virt/DSDT.topology and b/tests/data/acpi/aarch64/virt/DSDT.topology differ
diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST
new file mode 100644
index 000000000000..8b0cf87700fa
Binary files /dev/null and b/tests/data/acpi/aarch64/virt/HEST differThe current code is actually dependent on having just one error
structure with a single source.
As the number of sources should be arch-dependent, as it will depend on
what kind of notifications will exist, change the logic to dynamically
build the table.
Yet, for a proper support, we need to get the number of sources by
reading the number from the HEST table. However, bios currently doesn't
store a pointer to it.
For now just change the logic at table build time, while enforcing that
it will behave like before with a single source ID.
A future patch will add a HEST table bios pointer and change the logic
at acpi_ghes_record_errors() to dynamically use the new size.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
hw/acpi/ghes.c | 47 +++++++++++++++++++++++++---------------
hw/arm/virt-acpi-build.c | 5 +++++
include/hw/acpi/ghes.h | 21 ++++++++++++------
3 files changed, 49 insertions(+), 24 deletions(-)
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index b709c177cdea..4cabb177ad47 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -206,17 +206,26 @@ ghes_gen_err_data_uncorrectable_recoverable(GArray *block,
* Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs.
* See docs/specs/acpi_hest_ghes.rst for blobs format.
*/
-static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker)
+static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
+ int num_sources)
{
int i, error_status_block_offset;
+ /*
+ * TODO: Current version supports only one source.
+ * A further patch will drop this check, after adding a proper migration
+ * code, as, for the code to work, we need to store a bios pointer to the
+ * HEST table.
+ */
+ assert(num_sources == 1);
+
/* Build error_block_address */
- for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) {
+ for (i = 0; i < num_sources; i++) {
build_append_int_noprefix(hardware_errors, 0, sizeof(uint64_t));
}
/* Build read_ack_register */
- for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) {
+ for (i = 0; i < num_sources; i++) {
/*
* Initialize the value of read_ack_register to 1, so GHES can be
* writable after (re)boot.
@@ -231,13 +240,13 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker)
/* Reserve space for Error Status Data Block */
acpi_data_push(hardware_errors,
- ACPI_GHES_MAX_RAW_DATA_LENGTH * ACPI_GHES_ERROR_SOURCE_COUNT);
+ ACPI_GHES_MAX_RAW_DATA_LENGTH * num_sources);
/* Tell guest firmware to place hardware_errors blob into RAM */
bios_linker_loader_alloc(linker, ACPI_HW_ERROR_FW_CFG_FILE,
hardware_errors, sizeof(uint64_t), false);
- for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) {
+ for (i = 0; i < num_sources; i++) {
/*
* Tell firmware to patch error_block_address entries to point to
* corresponding "Generic Error Status Block"
@@ -261,12 +270,14 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker)
}
/* Build Generic Hardware Error Source version 2 (GHESv2) */
-static void build_ghes_v2(GArray *table_data,
- BIOSLinker *linker,
- enum AcpiGhesNotifyType notify,
- uint16_t source_id)
+static void build_ghes_v2_entry(GArray *table_data,
+ BIOSLinker *linker,
+ const AcpiNotificationSourceId *notif_src,
+ uint16_t index, int num_sources)
{
uint64_t address_offset;
+ const uint16_t notify = notif_src->notify;
+ const uint16_t source_id = notif_src->source_id;
/*
* Type:
@@ -297,7 +308,7 @@ static void build_ghes_v2(GArray *table_data,
address_offset + GAS_ADDR_OFFSET,
sizeof(uint64_t),
ACPI_HW_ERROR_FW_CFG_FILE,
- source_id * sizeof(uint64_t));
+ index * sizeof(uint64_t));
/* Notification Structure */
build_ghes_hw_error_notification(table_data, notify);
@@ -317,8 +328,7 @@ static void build_ghes_v2(GArray *table_data,
address_offset + GAS_ADDR_OFFSET,
sizeof(uint64_t),
ACPI_HW_ERROR_FW_CFG_FILE,
- (ACPI_GHES_ERROR_SOURCE_COUNT + source_id)
- * sizeof(uint64_t));
+ (num_sources + index) * sizeof(uint64_t));
/*
* Read Ack Preserve field
@@ -333,19 +343,23 @@ static void build_ghes_v2(GArray *table_data,
/* Build Hardware Error Source Table */
void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
BIOSLinker *linker,
+ const AcpiNotificationSourceId *notif_source,
+ int num_sources,
const char *oem_id, const char *oem_table_id)
{
AcpiTable table = { .sig = "HEST", .rev = 1,
.oem_id = oem_id, .oem_table_id = oem_table_id };
+ int i;
- build_ghes_error_table(hardware_errors, linker);
+ build_ghes_error_table(hardware_errors, linker, num_sources);
acpi_table_begin(&table, table_data);
/* Error Source Count */
- build_append_int_noprefix(table_data, ACPI_GHES_ERROR_SOURCE_COUNT, 4);
- build_ghes_v2(table_data, linker,
- ACPI_GHES_NOTIFY_SEA, ACPI_HEST_SRC_ID_SEA);
+ build_append_int_noprefix(table_data, num_sources, 4);
+ for (i = 0; i < num_sources; i++) {
+ build_ghes_v2_entry(table_data, linker, ¬if_source[i], i, num_sources);
+ }
acpi_table_end(linker, &table);
}
@@ -410,7 +424,6 @@ void ghes_record_cper_errors(const void *cper, size_t len,
}
ags = &acpi_ged_state->ghes_state;
- assert(ACPI_GHES_ERROR_SOURCE_COUNT == 1);
get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
&cper_addr, &read_ack_register_addr);
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 3ac8f8e17861..3d411787fc37 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -893,6 +893,10 @@ static void acpi_align_size(GArray *blob, unsigned align)
g_array_set_size(blob, ROUND_UP(acpi_data_len(blob), align));
}
+static const AcpiNotificationSourceId hest_ghes_notify[] = {
+ { ACPI_HEST_SRC_ID_SYNC, ACPI_GHES_NOTIFY_SEA },
+};
+
static
void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
{
@@ -948,6 +952,7 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
if (vms->ras) {
acpi_add_table(table_offsets, tables_blob);
acpi_build_hest(tables_blob, tables->hardware_errors, tables->linker,
+ hest_ghes_notify, ARRAY_SIZE(hest_ghes_notify),
vms->oem_id, vms->oem_table_id);
}
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index 39619a2457cb..9f0120d0d596 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -57,20 +57,27 @@ enum AcpiGhesNotifyType {
ACPI_GHES_NOTIFY_RESERVED = 12
};
-enum {
- ACPI_HEST_SRC_ID_SEA = 0,
- /* future ids go here */
-
- ACPI_GHES_ERROR_SOURCE_COUNT
-};
-
typedef struct AcpiGhesState {
uint64_t hw_error_le;
bool present; /* True if GHES is present at all on this board */
} AcpiGhesState;
+/*
+ * ID numbers used to fill HEST source ID field
+ */
+enum AcpiGhesSourceID {
+ ACPI_HEST_SRC_ID_SYNC,
+};
+
+typedef struct AcpiNotificationSourceId {
+ enum AcpiGhesSourceID source_id;
+ enum AcpiGhesNotifyType notify;
+} AcpiNotificationSourceId;
+
void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
BIOSLinker *linker,
+ const AcpiNotificationSourceId * const notif_source,
+ int num_sources,
const char *oem_id, const char *oem_table_id);
void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s,
GArray *hardware_errors);
--
2.48.1On Wed, 29 Jan 2025 09:04:07 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> The current code is actually dependent on having just one error
> structure with a single source.
>
> As the number of sources should be arch-dependent, as it will depend on
> what kind of notifications will exist, change the logic to dynamically
> build the table.
>
> Yet, for a proper support, we need to get the number of sources by
> reading the number from the HEST table. However, bios currently doesn't
> store a pointer to it.
>
> For now just change the logic at table build time, while enforcing that
> it will behave like before with a single source ID.
>
> A future patch will add a HEST table bios pointer and change the logic
> at acpi_ghes_record_errors() to dynamically use the new size.
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/ghes.c | 47 +++++++++++++++++++++++++---------------
> hw/arm/virt-acpi-build.c | 5 +++++
> include/hw/acpi/ghes.h | 21 ++++++++++++------
> 3 files changed, 49 insertions(+), 24 deletions(-)
>
> diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> index b709c177cdea..4cabb177ad47 100644
> --- a/hw/acpi/ghes.c
> +++ b/hw/acpi/ghes.c
> @@ -206,17 +206,26 @@ ghes_gen_err_data_uncorrectable_recoverable(GArray *block,
> * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs.
> * See docs/specs/acpi_hest_ghes.rst for blobs format.
> */
> -static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker)
> +static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
> + int num_sources)
> {
> int i, error_status_block_offset;
>
> + /*
> + * TODO: Current version supports only one source.
> + * A further patch will drop this check, after adding a proper migration
> + * code, as, for the code to work, we need to store a bios pointer to the
> + * HEST table.
> + */
> + assert(num_sources == 1);
> +
> /* Build error_block_address */
> - for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) {
> + for (i = 0; i < num_sources; i++) {
> build_append_int_noprefix(hardware_errors, 0, sizeof(uint64_t));
> }
>
> /* Build read_ack_register */
> - for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) {
> + for (i = 0; i < num_sources; i++) {
> /*
> * Initialize the value of read_ack_register to 1, so GHES can be
> * writable after (re)boot.
> @@ -231,13 +240,13 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker)
>
> /* Reserve space for Error Status Data Block */
> acpi_data_push(hardware_errors,
> - ACPI_GHES_MAX_RAW_DATA_LENGTH * ACPI_GHES_ERROR_SOURCE_COUNT);
> + ACPI_GHES_MAX_RAW_DATA_LENGTH * num_sources);
>
> /* Tell guest firmware to place hardware_errors blob into RAM */
> bios_linker_loader_alloc(linker, ACPI_HW_ERROR_FW_CFG_FILE,
> hardware_errors, sizeof(uint64_t), false);
>
> - for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) {
> + for (i = 0; i < num_sources; i++) {
> /*
> * Tell firmware to patch error_block_address entries to point to
> * corresponding "Generic Error Status Block"
> @@ -261,12 +270,14 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker)
> }
>
> /* Build Generic Hardware Error Source version 2 (GHESv2) */
> -static void build_ghes_v2(GArray *table_data,
> - BIOSLinker *linker,
> - enum AcpiGhesNotifyType notify,
> - uint16_t source_id)
> +static void build_ghes_v2_entry(GArray *table_data,
> + BIOSLinker *linker,
> + const AcpiNotificationSourceId *notif_src,
> + uint16_t index, int num_sources)
> {
> uint64_t address_offset;
> + const uint16_t notify = notif_src->notify;
> + const uint16_t source_id = notif_src->source_id;
>
> /*
> * Type:
> @@ -297,7 +308,7 @@ static void build_ghes_v2(GArray *table_data,
> address_offset + GAS_ADDR_OFFSET,
> sizeof(uint64_t),
> ACPI_HW_ERROR_FW_CFG_FILE,
> - source_id * sizeof(uint64_t));
> + index * sizeof(uint64_t));
>
> /* Notification Structure */
> build_ghes_hw_error_notification(table_data, notify);
> @@ -317,8 +328,7 @@ static void build_ghes_v2(GArray *table_data,
> address_offset + GAS_ADDR_OFFSET,
> sizeof(uint64_t),
> ACPI_HW_ERROR_FW_CFG_FILE,
> - (ACPI_GHES_ERROR_SOURCE_COUNT + source_id)
> - * sizeof(uint64_t));
> + (num_sources + index) * sizeof(uint64_t));
>
> /*
> * Read Ack Preserve field
> @@ -333,19 +343,23 @@ static void build_ghes_v2(GArray *table_data,
> /* Build Hardware Error Source Table */
> void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
> BIOSLinker *linker,
> + const AcpiNotificationSourceId *notif_source,
> + int num_sources,
> const char *oem_id, const char *oem_table_id)
> {
> AcpiTable table = { .sig = "HEST", .rev = 1,
> .oem_id = oem_id, .oem_table_id = oem_table_id };
> + int i;
>
> - build_ghes_error_table(hardware_errors, linker);
> + build_ghes_error_table(hardware_errors, linker, num_sources);
>
> acpi_table_begin(&table, table_data);
>
> /* Error Source Count */
> - build_append_int_noprefix(table_data, ACPI_GHES_ERROR_SOURCE_COUNT, 4);
> - build_ghes_v2(table_data, linker,
> - ACPI_GHES_NOTIFY_SEA, ACPI_HEST_SRC_ID_SEA);
> + build_append_int_noprefix(table_data, num_sources, 4);
> + for (i = 0; i < num_sources; i++) {
> + build_ghes_v2_entry(table_data, linker, ¬if_source[i], i, num_sources);
> + }
>
> acpi_table_end(linker, &table);
> }
> @@ -410,7 +424,6 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> }
> ags = &acpi_ged_state->ghes_state;
>
> - assert(ACPI_GHES_ERROR_SOURCE_COUNT == 1);
> get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
> &cper_addr, &read_ack_register_addr);
>
> diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
> index 3ac8f8e17861..3d411787fc37 100644
> --- a/hw/arm/virt-acpi-build.c
> +++ b/hw/arm/virt-acpi-build.c
> @@ -893,6 +893,10 @@ static void acpi_align_size(GArray *blob, unsigned align)
> g_array_set_size(blob, ROUND_UP(acpi_data_len(blob), align));
> }
>
> +static const AcpiNotificationSourceId hest_ghes_notify[] = {
> + { ACPI_HEST_SRC_ID_SYNC, ACPI_GHES_NOTIFY_SEA },
> +};
> +
> static
> void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
> {
> @@ -948,6 +952,7 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
> if (vms->ras) {
> acpi_add_table(table_offsets, tables_blob);
> acpi_build_hest(tables_blob, tables->hardware_errors, tables->linker,
> + hest_ghes_notify, ARRAY_SIZE(hest_ghes_notify),
> vms->oem_id, vms->oem_table_id);
> }
>
> diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
> index 39619a2457cb..9f0120d0d596 100644
> --- a/include/hw/acpi/ghes.h
> +++ b/include/hw/acpi/ghes.h
> @@ -57,20 +57,27 @@ enum AcpiGhesNotifyType {
> ACPI_GHES_NOTIFY_RESERVED = 12
> };
>
> -enum {
> - ACPI_HEST_SRC_ID_SEA = 0,
> - /* future ids go here */
> -
> - ACPI_GHES_ERROR_SOURCE_COUNT
> -};
> -
> typedef struct AcpiGhesState {
> uint64_t hw_error_le;
> bool present; /* True if GHES is present at all on this board */
> } AcpiGhesState;
>
> +/*
> + * ID numbers used to fill HEST source ID field
> + */
> +enum AcpiGhesSourceID {
> + ACPI_HEST_SRC_ID_SYNC,
> +};
> +
> +typedef struct AcpiNotificationSourceId {
> + enum AcpiGhesSourceID source_id;
> + enum AcpiGhesNotifyType notify;
> +} AcpiNotificationSourceId;
> +
> void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
> BIOSLinker *linker,
> + const AcpiNotificationSourceId * const notif_source,
> + int num_sources,
> const char *oem_id, const char *oem_table_id);
> void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s,
> GArray *hardware_errors);
The DSDT table will also be affected by such change.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
tests/data/acpi/aarch64/virt/HEST | 0
tests/qtest/bios-tables-test-allowed-diff.h | 2 ++
2 files changed, 2 insertions(+)
create mode 100644 tests/data/acpi/aarch64/virt/HEST
diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST
new file mode 100644
index 000000000000..e69de29bb2d1
diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h
index dfb8523c8bf4..46298e38e7b8 100644
--- a/tests/qtest/bios-tables-test-allowed-diff.h
+++ b/tests/qtest/bios-tables-test-allowed-diff.h
@@ -1 +1,3 @@
/* List of comma-separated changed AML files to ignore */
+"tests/data/acpi/aarch64/virt/HEST",
+"tests/data/acpi/aarch64/virt/DSDT",
--
2.48.1On Wed, 29 Jan 2025 09:04:08 +0100 Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote: > The DSDT table will also be affected by such change. > > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> move it right before the patch that would actually make changes to tables (10/13) > --- > tests/data/acpi/aarch64/virt/HEST | 0 > tests/qtest/bios-tables-test-allowed-diff.h | 2 ++ > 2 files changed, 2 insertions(+) > create mode 100644 tests/data/acpi/aarch64/virt/HEST > > diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST > new file mode 100644 > index 000000000000..e69de29bb2d1 > diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h > index dfb8523c8bf4..46298e38e7b8 100644 > --- a/tests/qtest/bios-tables-test-allowed-diff.h > +++ b/tests/qtest/bios-tables-test-allowed-diff.h > @@ -1 +1,3 @@ > /* List of comma-separated changed AML files to ignore */ > +"tests/data/acpi/aarch64/virt/HEST", > +"tests/data/acpi/aarch64/virt/DSDT", the list in not complete so 'make check-qtest' still fails [12/13] has complete list of changed files
Em Wed, 29 Jan 2025 16:03:28 +0100 Igor Mammedov <imammedo@redhat.com> escreveu: > On Wed, 29 Jan 2025 09:04:08 +0100 > Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote: > > > The DSDT table will also be affected by such change. > > > > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> > > move it right before the patch that would actually make changes to tables (10/13) Table changes happens on two patches: - patch 03/13: acpi/ghes: add a firmware file with HEST address HEST table was added here - patch 10/13: arm/virt: Wire up a GED error device for ACPI / GHES DSDT changes happen here. If the idea is to avoid make check to fail between those two patches, we need either to split them on 4 patches (one before/one after each change) or do like I did on this series: whitelist before patch 3, update after patch 10. Regards, Mauro > > > > --- > > tests/data/acpi/aarch64/virt/HEST | 0 > > tests/qtest/bios-tables-test-allowed-diff.h | 2 ++ > > 2 files changed, 2 insertions(+) > > create mode 100644 tests/data/acpi/aarch64/virt/HEST > > > > diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST > > new file mode 100644 > > index 000000000000..e69de29bb2d1 > > diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h > > index dfb8523c8bf4..46298e38e7b8 100644 > > --- a/tests/qtest/bios-tables-test-allowed-diff.h > > +++ b/tests/qtest/bios-tables-test-allowed-diff.h > > @@ -1 +1,3 @@ > > /* List of comma-separated changed AML files to ignore */ > > +"tests/data/acpi/aarch64/virt/HEST", > > +"tests/data/acpi/aarch64/virt/DSDT", > > the list in not complete so 'make check-qtest' still fails > [12/13] has complete list of changed files > Thanks, Mauro
On Thu, 30 Jan 2025 14:03:24 +0100 Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote: > Em Wed, 29 Jan 2025 16:03:28 +0100 > Igor Mammedov <imammedo@redhat.com> escreveu: > > > On Wed, 29 Jan 2025 09:04:08 +0100 > > Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote: > > > > > The DSDT table will also be affected by such change. > > > > > > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> > > > > move it right before the patch that would actually make changes to tables (10/13) > > Table changes happens on two patches: > > - patch 03/13: acpi/ghes: add a firmware file with HEST address this one shouldn't affect bios tables test as it only checks ACPI and SMBIOS tables, and hest addr file is not either. Do you really see test failing on this patch? > HEST table was added here > > - patch 10/13: arm/virt: Wire up a GED error device for ACPI / GHES > > DSDT changes happen here. > > If the idea is to avoid make check to fail between those two patches, > we need either to split them on 4 patches (one before/one after each > change) or do like I did on this series: whitelist before patch 3, > update after patch 10. It would be better to group patches that should change ACPI tables close together so that a pair of whitelist/update could cover it. However it depends on how many changes are there, i.e. acpi diff should be digestible for a reader. So there is no hard border here, just use common sense. However when the whitelist is covers all series where only few patches actually result in tables change, that miss-leads the reader since whitelist patch basically tells 'watch out for changes since this moment' and 'update' patch declares no more changes should happen. The same applies to bisection, where closer the gap between whitelist/update the better if the test case is the trigger. No need to be fanatical and do it around each patch, just make it observable (i.e. some small range of commits). > > Regards, > Mauro > > > > > > > > --- > > > tests/data/acpi/aarch64/virt/HEST | 0 > > > tests/qtest/bios-tables-test-allowed-diff.h | 2 ++ > > > 2 files changed, 2 insertions(+) > > > create mode 100644 tests/data/acpi/aarch64/virt/HEST > > > > > > diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST > > > new file mode 100644 > > > index 000000000000..e69de29bb2d1 > > > diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h > > > index dfb8523c8bf4..46298e38e7b8 100644 > > > --- a/tests/qtest/bios-tables-test-allowed-diff.h > > > +++ b/tests/qtest/bios-tables-test-allowed-diff.h > > > @@ -1 +1,3 @@ > > > /* List of comma-separated changed AML files to ignore */ > > > +"tests/data/acpi/aarch64/virt/HEST", > > > +"tests/data/acpi/aarch64/virt/DSDT", > > > > the list in not complete so 'make check-qtest' still fails > > [12/13] has complete list of changed files > > > > > > Thanks, > Mauro >
Em Thu, 30 Jan 2025 15:38:30 +0100 Igor Mammedov <imammedo@redhat.com> escreveu: > On Thu, 30 Jan 2025 14:03:24 +0100 > Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote: > > > Em Wed, 29 Jan 2025 16:03:28 +0100 > > Igor Mammedov <imammedo@redhat.com> escreveu: > > > > > On Wed, 29 Jan 2025 09:04:08 +0100 > > > Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote: > > > > > > > The DSDT table will also be affected by such change. > > > > > > > > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> > > > > > > move it right before the patch that would actually make changes to tables (10/13) > > > > Table changes happens on two patches: > > > > - patch 03/13: acpi/ghes: add a firmware file with HEST address > > this one shouldn't affect bios tables test as it only checks ACPI and SMBIOS tables, > and hest addr file is not either. Heh, true. > Do you really see test failing on this patch? No. I just misunderstood the instructions, as it was not clear to me there that I shouldn't be adding there the HEST table. > > HEST table was added here > > > > - patch 10/13: arm/virt: Wire up a GED error device for ACPI / GHES > > > > DSDT changes happen here. > > > > If the idea is to avoid make check to fail between those two patches, > > we need either to split them on 4 patches (one before/one after each > > change) or do like I did on this series: whitelist before patch 3, > > update after patch 10. > > It would be better to group patches that should change ACPI tables > close together so that a pair of whitelist/update could cover it. > However it depends on how many changes are there, i.e. acpi diff > should be digestible for a reader. So there is no hard border here, > just use common sense. > > However when the whitelist is covers all series where only few patches > actually result in tables change, that miss-leads the reader since > whitelist patch basically tells 'watch out for changes since this moment' > and 'update' patch declares no more changes should happen. > The same applies to bisection, where closer the gap between > whitelist/update the better if the test case is the trigger. > No need to be fanatical and do it around each patch, > just make it observable (i.e. some small range of commits). Got it. Yeah, there was just one patch affecting DSDT table: the one adding an AML representation for the GED notification device. I fixed it for the next (hopefully the final) version. Thanks, Mauro
Store HEST table address at GPA, placing its content at
hest_addr_le variable.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
While here, capitalize first letter on a comment about hardware_error
address.
---
Change from v8:
- hest_addr_lr is now pointing to the error source size and data.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
hw/acpi/ghes.c | 18 +++++++++++++++++-
include/hw/acpi/ghes.h | 1 +
2 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 4cabb177ad47..db6bed010eb0 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -30,6 +30,7 @@
#define ACPI_HW_ERROR_FW_CFG_FILE "etc/hardware_errors"
#define ACPI_HW_ERROR_ADDR_FW_CFG_FILE "etc/hardware_errors_addr"
+#define ACPI_HEST_ADDR_FW_CFG_FILE "etc/acpi_table_hest_addr"
/* The max size in bytes for one error block */
#define ACPI_GHES_MAX_RAW_DATA_LENGTH (1 * KiB)
@@ -261,7 +262,7 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
}
/*
- * tell firmware to write hardware_errors GPA into
+ * Tell firmware to write hardware_errors GPA into
* hardware_errors_addr fw_cfg, once the former has been initialized.
*/
bios_linker_loader_write_pointer(linker, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, 0,
@@ -349,12 +350,15 @@ void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
{
AcpiTable table = { .sig = "HEST", .rev = 1,
.oem_id = oem_id, .oem_table_id = oem_table_id };
+ uint32_t hest_offset;
int i;
build_ghes_error_table(hardware_errors, linker, num_sources);
acpi_table_begin(&table, table_data);
+ hest_offset = table_data->len;
+
/* Error Source Count */
build_append_int_noprefix(table_data, num_sources, 4);
for (i = 0; i < num_sources; i++) {
@@ -362,6 +366,15 @@ void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
}
acpi_table_end(linker, &table);
+
+ /*
+ * Tell firmware to write into GPA the address of HEST via fw_cfg,
+ * once initialized.
+ */
+ bios_linker_loader_write_pointer(linker,
+ ACPI_HEST_ADDR_FW_CFG_FILE, 0,
+ sizeof(uint64_t),
+ ACPI_BUILD_TABLE_FILE, hest_offset);
}
void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
@@ -375,6 +388,9 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL,
NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false);
+ fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
+ NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
+
ags->present = true;
}
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index 9f0120d0d596..237721fec0a2 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -58,6 +58,7 @@ enum AcpiGhesNotifyType {
};
typedef struct AcpiGhesState {
+ uint64_t hest_addr_le;
uint64_t hw_error_le;
bool present; /* True if GHES is present at all on this board */
} AcpiGhesState;
--
2.48.1On Wed, 29 Jan 2025 09:04:09 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> Store HEST table address at GPA, placing its content at
> hest_addr_le variable.
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
>
> While here, capitalize first letter on a comment about hardware_error
> address.
>
> ---
>
> Change from v8:
> - hest_addr_lr is now pointing to the error source size and data.
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> ---
> hw/acpi/ghes.c | 18 +++++++++++++++++-
> include/hw/acpi/ghes.h | 1 +
> 2 files changed, 18 insertions(+), 1 deletion(-)
>
> diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> index 4cabb177ad47..db6bed010eb0 100644
> --- a/hw/acpi/ghes.c
> +++ b/hw/acpi/ghes.c
> @@ -30,6 +30,7 @@
>
> #define ACPI_HW_ERROR_FW_CFG_FILE "etc/hardware_errors"
> #define ACPI_HW_ERROR_ADDR_FW_CFG_FILE "etc/hardware_errors_addr"
> +#define ACPI_HEST_ADDR_FW_CFG_FILE "etc/acpi_table_hest_addr"
>
> /* The max size in bytes for one error block */
> #define ACPI_GHES_MAX_RAW_DATA_LENGTH (1 * KiB)
> @@ -261,7 +262,7 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
> }
>
> /*
> - * tell firmware to write hardware_errors GPA into
> + * Tell firmware to write hardware_errors GPA into
> * hardware_errors_addr fw_cfg, once the former has been initialized.
> */
please, drop non relevant hunk, or move it out into a separate path
> bios_linker_loader_write_pointer(linker, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, 0,
> @@ -349,12 +350,15 @@ void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
> {
> AcpiTable table = { .sig = "HEST", .rev = 1,
> .oem_id = oem_id, .oem_table_id = oem_table_id };
> + uint32_t hest_offset;
> int i;
>
> build_ghes_error_table(hardware_errors, linker, num_sources);
>
> acpi_table_begin(&table, table_data);
>
> + hest_offset = table_data->len;
move it before acpi_table_begin() so that name would match with what actually happens
and adjust 4/13 to account for that
> +
> /* Error Source Count */
> build_append_int_noprefix(table_data, num_sources, 4);
> for (i = 0; i < num_sources; i++) {
> @@ -362,6 +366,15 @@ void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
> }
>
> acpi_table_end(linker, &table);
> +
> + /*
> + * Tell firmware to write into GPA the address of HEST via fw_cfg,
> + * once initialized.
> + */
> + bios_linker_loader_write_pointer(linker,
> + ACPI_HEST_ADDR_FW_CFG_FILE, 0,
> + sizeof(uint64_t),
> + ACPI_BUILD_TABLE_FILE, hest_offset);
it's not safe to add this without compat logic, as it changes size of linker
table and possibly layout.
I'd suggest to partially combine this with use_hest_addr patch.
One way to do it cleanly would be to move part introducing
use_hest_addr here and set it to false to start with,
and flip default to true one all hest_addr_le code in place.
see related comment 6/13
> }
>
> void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
> @@ -375,6 +388,9 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
> fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL,
> NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false);
>
> + fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
> + NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
see 6/13 comments
> +
> ags->present = true;
> }
>
> diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
> index 9f0120d0d596..237721fec0a2 100644
> --- a/include/hw/acpi/ghes.h
> +++ b/include/hw/acpi/ghes.h
> @@ -58,6 +58,7 @@ enum AcpiGhesNotifyType {
> };
>
> typedef struct AcpiGhesState {
> + uint64_t hest_addr_le;
> uint64_t hw_error_le;
> bool present; /* True if GHES is present at all on this board */
> } AcpiGhesState;
Em Wed, 29 Jan 2025 16:23:28 +0100
Igor Mammedov <imammedo@redhat.com> escreveu:
> > +
> > + /*
> > + * Tell firmware to write into GPA the address of HEST via fw_cfg,
> > + * once initialized.
> > + */
> > + bios_linker_loader_write_pointer(linker,
> > + ACPI_HEST_ADDR_FW_CFG_FILE, 0,
> > + sizeof(uint64_t),
> > + ACPI_BUILD_TABLE_FILE, hest_offset);
>
> it's not safe to add this without compat logic, as it changes size of linker
> table and possibly layout.
>
> I'd suggest to partially combine this with use_hest_addr patch.
> One way to do it cleanly would be to move part introducing
> use_hest_addr here and set it to false to start with,
> and flip default to true one all hest_addr_le code in place.
> see related comment 6/13
Ok. It also means I need to temporarily get ags there, e. g.:
+ AcpiGedState *acpi_ged_state;
+ AcpiGhesState *ags = NULL;
+
+ acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
+ NULL));
+ if (acpi_ged_state) {
+ ags = &acpi_ged_state->ghes_state;
+ }
...
+ if (ags->use_hest_addr) {
+ bios_linker_loader_write_pointer(linker,
+ ACPI_HEST_ADDR_FW_CFG_FILE, 0,
+ sizeof(uint64_t),
+ ACPI_BUILD_TABLE_FILE, hest_offset);
+ }
The part which gets ags will be dropped on this patch:
ad2dc8716d1f acpi/generic_event_device: add logic to detect if HEST addr is available
which will set use_hest_addr to false, until we have everything in
place.
Thanks,
Mauro
There are two pointers that are needed during error injection:
1. The start address of the CPER block to be stored;
2. The address of the ack.
It is preferable to calculate them from the HEST table. This allows
checking the source ID, the size of the table and the type of the
HEST error block structures.
Yet, keep the old code, as this is needed for migration purposes.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
hw/acpi/ghes.c | 111 ++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 101 insertions(+), 10 deletions(-)
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index db6bed010eb0..adf80945c6db 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -61,6 +61,25 @@
*/
#define ACPI_GHES_GESB_SIZE 20
+/*
+ * Offsets with regards to the start of the HEST table stored at
+ * ags->hest_addr_le, according with the memory layout map at
+ * docs/specs/acpi_hest_ghes.rst.
+ */
+
+/*
+ * ACPI 6.2: 18.3.2.8 Generic Hardware Error Source version 2
+ * Table 18-382 Generic Hardware Error Source version 2 (GHESv2) Structure
+ */
+#define HEST_GHES_V2_TABLE_SIZE 92
+#define GHES_READ_ACK_ADDR_OFF 64
+
+/*
+ * ACPI 6.2: 18.3.2.7: Generic Hardware Error Source
+ * Table 18-380: 'Error Status Address' field
+ */
+#define GHES_ERR_STATUS_ADDR_OFF 20
+
/*
* Values for error_severity field
*/
@@ -212,14 +231,6 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
{
int i, error_status_block_offset;
- /*
- * TODO: Current version supports only one source.
- * A further patch will drop this check, after adding a proper migration
- * code, as, for the code to work, we need to store a bios pointer to the
- * HEST table.
- */
- assert(num_sources == 1);
-
/* Build error_block_address */
for (i = 0; i < num_sources; i++) {
build_append_int_noprefix(hardware_errors, 0, sizeof(uint64_t));
@@ -420,6 +431,81 @@ static void get_hw_error_offsets(uint64_t ghes_addr,
*read_ack_register_addr = ghes_addr + sizeof(uint64_t);
}
+static void get_ghes_source_offsets(uint16_t source_id,
+ uint64_t hest_entry_addr,
+ uint64_t *cper_addr,
+ uint64_t *read_ack_start_addr,
+ Error **errp)
+{
+ uint64_t hest_err_block_addr, hest_read_ack_addr;
+ uint64_t err_source_entry, error_block_addr;
+ uint32_t num_sources, i;
+
+ if (!hest_entry_addr) {
+ return;
+ }
+
+ cpu_physical_memory_read(hest_entry_addr, &num_sources,
+ sizeof(num_sources));
+ num_sources = le32_to_cpu(num_sources);
+
+ err_source_entry = hest_entry_addr + sizeof(num_sources);
+
+ /*
+ * Currently, HEST Error source navigates only for GHESv2 tables
+ */
+
+ for (i = 0; i < num_sources; i++) {
+ uint64_t addr = err_source_entry;
+ uint16_t type, src_id;
+
+ cpu_physical_memory_read(addr, &type, sizeof(type));
+ type = le16_to_cpu(type);
+
+ /* For now, we only know the size of GHESv2 table */
+ if (type != ACPI_GHES_SOURCE_GENERIC_ERROR_V2) {
+ error_setg(errp, "HEST: type %d not supported.", type);
+ return;
+ }
+
+ /* Compare CPER source address at the GHESv2 structure */
+ addr += sizeof(type);
+ cpu_physical_memory_read(addr, &src_id, sizeof(src_id));
+
+ if (le16_to_cpu(src_id) == source_id) {
+ break;
+ }
+
+ err_source_entry += HEST_GHES_V2_TABLE_SIZE;
+ }
+ if (i == num_sources) {
+ error_setg(errp, "HEST: Source %d not found.", source_id);
+ return;
+ }
+
+ /* Navigate though table address pointers */
+ hest_err_block_addr = err_source_entry + GHES_ERR_STATUS_ADDR_OFF +
+ GAS_ADDR_OFFSET;
+
+ cpu_physical_memory_read(hest_err_block_addr, &error_block_addr,
+ sizeof(error_block_addr));
+
+ error_block_addr = le64_to_cpu(error_block_addr);
+
+ cpu_physical_memory_read(error_block_addr, cper_addr,
+ sizeof(*cper_addr));
+
+ *cper_addr = le64_to_cpu(*cper_addr);
+
+ hest_read_ack_addr = err_source_entry + GHES_READ_ACK_ADDR_OFF +
+ GAS_ADDR_OFFSET;
+
+ cpu_physical_memory_read(hest_read_ack_addr, read_ack_start_addr,
+ sizeof(*read_ack_start_addr));
+
+ *read_ack_start_addr = le64_to_cpu(*read_ack_start_addr);
+}
+
void ghes_record_cper_errors(const void *cper, size_t len,
uint16_t source_id, Error **errp)
{
@@ -440,8 +526,13 @@ void ghes_record_cper_errors(const void *cper, size_t len,
}
ags = &acpi_ged_state->ghes_state;
- get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
- &cper_addr, &read_ack_register_addr);
+ if (!ags->hest_addr_le) {
+ get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
+ &cper_addr, &read_ack_register_addr);
+ } else {
+ get_ghes_source_offsets(source_id, le64_to_cpu(ags->hest_addr_le),
+ &cper_addr, &read_ack_register_addr, errp);
+ }
if (!cper_addr) {
error_setg(errp, "can not find Generic Error Status Block");
--
2.48.1On Wed, 29 Jan 2025 09:04:10 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> There are two pointers that are needed during error injection:
>
> 1. The start address of the CPER block to be stored;
> 2. The address of the ack.
>
> It is preferable to calculate them from the HEST table. This allows
> checking the source ID, the size of the table and the type of the
> HEST error block structures.
>
> Yet, keep the old code, as this is needed for migration purposes.
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> ---
> hw/acpi/ghes.c | 111 ++++++++++++++++++++++++++++++++++++++++++++-----
> 1 file changed, 101 insertions(+), 10 deletions(-)
>
> diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> index db6bed010eb0..adf80945c6db 100644
> --- a/hw/acpi/ghes.c
> +++ b/hw/acpi/ghes.c
> @@ -61,6 +61,25 @@
> */
> #define ACPI_GHES_GESB_SIZE 20
>
> +/*
> + * Offsets with regards to the start of the HEST table stored at
> + * ags->hest_addr_le, according with the memory layout map at
> + * docs/specs/acpi_hest_ghes.rst.
> + */
> +
> +/*
> + * ACPI 6.2: 18.3.2.8 Generic Hardware Error Source version 2
> + * Table 18-382 Generic Hardware Error Source version 2 (GHESv2) Structure
> + */
> +#define HEST_GHES_V2_TABLE_SIZE 92
> +#define GHES_READ_ACK_ADDR_OFF 64
> +
> +/*
> + * ACPI 6.2: 18.3.2.7: Generic Hardware Error Source
> + * Table 18-380: 'Error Status Address' field
> + */
> +#define GHES_ERR_STATUS_ADDR_OFF 20
> +
> /*
> * Values for error_severity field
> */
> @@ -212,14 +231,6 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
> {
> int i, error_status_block_offset;
>
> - /*
> - * TODO: Current version supports only one source.
> - * A further patch will drop this check, after adding a proper migration
> - * code, as, for the code to work, we need to store a bios pointer to the
> - * HEST table.
> - */
> - assert(num_sources == 1);
> -
> /* Build error_block_address */
> for (i = 0; i < num_sources; i++) {
> build_append_int_noprefix(hardware_errors, 0, sizeof(uint64_t));
> @@ -420,6 +431,81 @@ static void get_hw_error_offsets(uint64_t ghes_addr,
> *read_ack_register_addr = ghes_addr + sizeof(uint64_t);
> }
>
> +static void get_ghes_source_offsets(uint16_t source_id,
> + uint64_t hest_entry_addr,
now, confusion introduced in 3/13
(hest_addr_le not actually being start of the table but named as such)
continues here
> + uint64_t *cper_addr,
> + uint64_t *read_ack_start_addr,
> + Error **errp)
> +{
> + uint64_t hest_err_block_addr, hest_read_ack_addr;
> + uint64_t err_source_entry, error_block_addr;
> + uint32_t num_sources, i;
> +
> + if (!hest_entry_addr) {
> + return;
> + }
> +
> + cpu_physical_memory_read(hest_entry_addr, &num_sources,
> + sizeof(num_sources));
hest_entry_addr implies to me error source entry, while what
you are reading here is a part of HEST but not a part of error source
suggest s/hest_entry_addr/hest_addr/ and then read from
hest_addr + 'Error Source Count'_offset
> + num_sources = le32_to_cpu(num_sources);
> +
> + err_source_entry = hest_entry_addr + sizeof(num_sources);
and amend this line to point to 1st error source entry
> +
> + /*
> + * Currently, HEST Error source navigates only for GHESv2 tables
> + */
> +
> + for (i = 0; i < num_sources; i++) {
> + uint64_t addr = err_source_entry;
> + uint16_t type, src_id;
> +
> + cpu_physical_memory_read(addr, &type, sizeof(type));
> + type = le16_to_cpu(type);
> +
> + /* For now, we only know the size of GHESv2 table */
> + if (type != ACPI_GHES_SOURCE_GENERIC_ERROR_V2) {
> + error_setg(errp, "HEST: type %d not supported.", type);
> + return;
> + }
> +
> + /* Compare CPER source address at the GHESv2 structure */
> + addr += sizeof(type);
> + cpu_physical_memory_read(addr, &src_id, sizeof(src_id));
> +
I'd drop this new line
> + if (le16_to_cpu(src_id) == source_id) {
> + break;
> + }
> +
> + err_source_entry += HEST_GHES_V2_TABLE_SIZE;
> + }
> + if (i == num_sources) {
> + error_setg(errp, "HEST: Source %d not found.", source_id);
> + return;
> + }
> +
> + /* Navigate though table address pointers */
> + hest_err_block_addr = err_source_entry + GHES_ERR_STATUS_ADDR_OFF +
> + GAS_ADDR_OFFSET;
> +
> + cpu_physical_memory_read(hest_err_block_addr, &error_block_addr,
> + sizeof(error_block_addr));
> +
> + error_block_addr = le64_to_cpu(error_block_addr);
> +
> + cpu_physical_memory_read(error_block_addr, cper_addr,
> + sizeof(*cper_addr));
> +
> + *cper_addr = le64_to_cpu(*cper_addr);
> +
> + hest_read_ack_addr = err_source_entry + GHES_READ_ACK_ADDR_OFF +
> + GAS_ADDR_OFFSET;
> +
> + cpu_physical_memory_read(hest_read_ack_addr, read_ack_start_addr,
> + sizeof(*read_ack_start_addr));
> +
> + *read_ack_start_addr = le64_to_cpu(*read_ack_start_addr);
> +}
> +
> void ghes_record_cper_errors(const void *cper, size_t len,
> uint16_t source_id, Error **errp)
> {
> @@ -440,8 +526,13 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> }
> ags = &acpi_ged_state->ghes_state;
>
> - get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
> - &cper_addr, &read_ack_register_addr);
> + if (!ags->hest_addr_le) {
> + get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
> + &cper_addr, &read_ack_register_addr);
> + } else {
> + get_ghes_source_offsets(source_id, le64_to_cpu(ags->hest_addr_le),
> + &cper_addr, &read_ack_register_addr, errp);
> + }
>
> if (!cper_addr) {
> error_setg(errp, "can not find Generic Error Status Block");
The GHES migration logic at GED should now support HEST table
location too.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
---
hw/acpi/generic_event_device.c | 29 +++++++++++++++++++++++++++++
1 file changed, 29 insertions(+)
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index c85d97ca3776..5346cae573b7 100644
--- a/hw/acpi/generic_event_device.c
+++ b/hw/acpi/generic_event_device.c
@@ -386,6 +386,34 @@ static const VMStateDescription vmstate_ghes_state = {
}
};
+static const VMStateDescription vmstate_hest = {
+ .name = "acpi-hest",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .fields = (const VMStateField[]) {
+ VMSTATE_UINT64(hest_addr_le, AcpiGhesState),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static bool hest_needed(void *opaque)
+{
+ AcpiGedState *s = opaque;
+ return s->ghes_state.hest_addr_le;
+}
+
+static const VMStateDescription vmstate_hest_state = {
+ .name = "acpi-ged/hest",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = hest_needed,
+ .fields = (const VMStateField[]) {
+ VMSTATE_STRUCT(ghes_state, AcpiGedState, 1,
+ vmstate_hest, AcpiGhesState),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
static const VMStateDescription vmstate_acpi_ged = {
.name = "acpi-ged",
.version_id = 1,
@@ -398,6 +426,7 @@ static const VMStateDescription vmstate_acpi_ged = {
&vmstate_memhp_state,
&vmstate_cpuhp_state,
&vmstate_ghes_state,
+ &vmstate_hest_state,
NULL
}
};
--
2.48.1On Wed, 29 Jan 2025 09:04:11 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> The GHES migration logic at GED should now support HEST table
^^
typo?? Should've it been 'as'?
> location too.
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> Reviewed-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/generic_event_device.c | 29 +++++++++++++++++++++++++++++
> 1 file changed, 29 insertions(+)
>
> diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
> index c85d97ca3776..5346cae573b7 100644
> --- a/hw/acpi/generic_event_device.c
> +++ b/hw/acpi/generic_event_device.c
> @@ -386,6 +386,34 @@ static const VMStateDescription vmstate_ghes_state = {
> }
> };
>
> +static const VMStateDescription vmstate_hest = {
> + .name = "acpi-hest",
> + .version_id = 1,
> + .minimum_version_id = 1,
> + .fields = (const VMStateField[]) {
> + VMSTATE_UINT64(hest_addr_le, AcpiGhesState),
> + VMSTATE_END_OF_LIST()
> + },
> +};
> +
> +static bool hest_needed(void *opaque)
> +{
> + AcpiGedState *s = opaque;
> + return s->ghes_state.hest_addr_le;
> +}
> +
> +static const VMStateDescription vmstate_hest_state = {
> + .name = "acpi-ged/hest",
> + .version_id = 1,
> + .minimum_version_id = 1,
> + .needed = hest_needed,
> + .fields = (const VMStateField[]) {
> + VMSTATE_STRUCT(ghes_state, AcpiGedState, 1,
> + vmstate_hest, AcpiGhesState),
> + VMSTATE_END_OF_LIST()
> + }
> +};
> +
> static const VMStateDescription vmstate_acpi_ged = {
> .name = "acpi-ged",
> .version_id = 1,
> @@ -398,6 +426,7 @@ static const VMStateDescription vmstate_acpi_ged = {
> &vmstate_memhp_state,
> &vmstate_cpuhp_state,
> &vmstate_ghes_state,
> + &vmstate_hest_state,
> NULL
> }
> };
Create a new property (x-has-hest-addr) and use it to detect if
the GHES table offsets can be calculated from the HEST address
(qemu 10.0 and upper) or via the legacy way via an offset obtained
from the hardware_errors firmware file.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
hw/acpi/generic_event_device.c | 1 +
hw/acpi/ghes.c | 20 +++++++++++++-------
hw/arm/virt-acpi-build.c | 30 ++++++++++++++++++++++++++----
hw/core/machine.c | 2 ++
include/hw/acpi/ghes.h | 4 +++-
5 files changed, 45 insertions(+), 12 deletions(-)
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index 5346cae573b7..70729b6238a5 100644
--- a/hw/acpi/generic_event_device.c
+++ b/hw/acpi/generic_event_device.c
@@ -318,6 +318,7 @@ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
static const Property acpi_ged_properties[] = {
DEFINE_PROP_UINT32("ged-event", AcpiGedState, ged_event_bitmap, 0),
+ DEFINE_PROP_BOOL("x-has-hest-addr", AcpiGedState, ghes_state.use_hest_addr, true),
};
static const VMStateDescription vmstate_memhp_state = {
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index adf80945c6db..736287766989 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -353,7 +353,8 @@ static void build_ghes_v2_entry(GArray *table_data,
}
/* Build Hardware Error Source Table */
-void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
+void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
+ GArray *hardware_errors,
BIOSLinker *linker,
const AcpiNotificationSourceId *notif_source,
int num_sources,
@@ -382,10 +383,13 @@ void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
* Tell firmware to write into GPA the address of HEST via fw_cfg,
* once initialized.
*/
- bios_linker_loader_write_pointer(linker,
- ACPI_HEST_ADDR_FW_CFG_FILE, 0,
- sizeof(uint64_t),
- ACPI_BUILD_TABLE_FILE, hest_offset);
+
+ if (ags->use_hest_addr) {
+ bios_linker_loader_write_pointer(linker,
+ ACPI_HEST_ADDR_FW_CFG_FILE, 0,
+ sizeof(uint64_t),
+ ACPI_BUILD_TABLE_FILE, hest_offset);
+ }
}
void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
@@ -399,8 +403,10 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL,
NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false);
- fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
- NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
+ if (ags->use_hest_addr) {
+ fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
+ NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
+ }
ags->present = true;
}
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 3d411787fc37..be1e51e0bb29 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -897,6 +897,10 @@ static const AcpiNotificationSourceId hest_ghes_notify[] = {
{ ACPI_HEST_SRC_ID_SYNC, ACPI_GHES_NOTIFY_SEA },
};
+static const AcpiNotificationSourceId hest_ghes_notify_9_2[] = {
+ { ACPI_HEST_SRC_ID_SYNC, ACPI_GHES_NOTIFY_SEA },
+};
+
static
void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
{
@@ -950,10 +954,28 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
build_dbg2(tables_blob, tables->linker, vms);
if (vms->ras) {
- acpi_add_table(table_offsets, tables_blob);
- acpi_build_hest(tables_blob, tables->hardware_errors, tables->linker,
- hest_ghes_notify, ARRAY_SIZE(hest_ghes_notify),
- vms->oem_id, vms->oem_table_id);
+ AcpiGhesState *ags;
+ AcpiGedState *acpi_ged_state;
+
+ acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
+ NULL));
+ if (acpi_ged_state) {
+ ags = &acpi_ged_state->ghes_state;
+
+ acpi_add_table(table_offsets, tables_blob);
+
+ if (!ags->use_hest_addr) {
+ acpi_build_hest(ags, tables_blob, tables->hardware_errors,
+ tables->linker, hest_ghes_notify_9_2,
+ ARRAY_SIZE(hest_ghes_notify_9_2),
+ vms->oem_id, vms->oem_table_id);
+ } else {
+ acpi_build_hest(ags, tables_blob, tables->hardware_errors,
+ tables->linker, hest_ghes_notify,
+ ARRAY_SIZE(hest_ghes_notify),
+ vms->oem_id, vms->oem_table_id);
+ }
+ }
}
if (ms->numa_state->num_nodes > 0) {
diff --git a/hw/core/machine.c b/hw/core/machine.c
index c23b39949649..0d0cde481954 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -34,10 +34,12 @@
#include "hw/virtio/virtio-pci.h"
#include "hw/virtio/virtio-net.h"
#include "hw/virtio/virtio-iommu.h"
+#include "hw/acpi/generic_event_device.h"
#include "audio/audio.h"
GlobalProperty hw_compat_9_2[] = {
{"arm-cpu", "backcompat-pauth-default-use-qarma5", "true"},
+ { TYPE_ACPI_GED, "x-has-hest-addr", "false" },
};
const size_t hw_compat_9_2_len = G_N_ELEMENTS(hw_compat_9_2);
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index 237721fec0a2..bfc8fd851648 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -61,6 +61,7 @@ typedef struct AcpiGhesState {
uint64_t hest_addr_le;
uint64_t hw_error_le;
bool present; /* True if GHES is present at all on this board */
+ bool use_hest_addr; /* True if HEST address is present */
} AcpiGhesState;
/*
@@ -75,7 +76,8 @@ typedef struct AcpiNotificationSourceId {
enum AcpiGhesNotifyType notify;
} AcpiNotificationSourceId;
-void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
+void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
+ GArray *hardware_errors,
BIOSLinker *linker,
const AcpiNotificationSourceId * const notif_source,
int num_sources,
--
2.48.1On Wed, 29 Jan 2025 09:04:12 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> Create a new property (x-has-hest-addr) and use it to detect if
> the GHES table offsets can be calculated from the HEST address
> (qemu 10.0 and upper) or via the legacy way via an offset obtained
^^^
s/via/where/
> from the hardware_errors firmware file.
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> ---
> hw/acpi/generic_event_device.c | 1 +
> hw/acpi/ghes.c | 20 +++++++++++++-------
> hw/arm/virt-acpi-build.c | 30 ++++++++++++++++++++++++++----
> hw/core/machine.c | 2 ++
> include/hw/acpi/ghes.h | 4 +++-
> 5 files changed, 45 insertions(+), 12 deletions(-)
>
> diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
> index 5346cae573b7..70729b6238a5 100644
> --- a/hw/acpi/generic_event_device.c
> +++ b/hw/acpi/generic_event_device.c
> @@ -318,6 +318,7 @@ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
>
> static const Property acpi_ged_properties[] = {
> DEFINE_PROP_UINT32("ged-event", AcpiGedState, ged_event_bitmap, 0),
> + DEFINE_PROP_BOOL("x-has-hest-addr", AcpiGedState, ghes_state.use_hest_addr, true),
> };
>
> static const VMStateDescription vmstate_memhp_state = {
> diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> index adf80945c6db..736287766989 100644
> --- a/hw/acpi/ghes.c
> +++ b/hw/acpi/ghes.c
> @@ -353,7 +353,8 @@ static void build_ghes_v2_entry(GArray *table_data,
> }
>
> /* Build Hardware Error Source Table */
> -void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
> +void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
> + GArray *hardware_errors,
> BIOSLinker *linker,
> const AcpiNotificationSourceId *notif_source,
> int num_sources,
> @@ -382,10 +383,13 @@ void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
> * Tell firmware to write into GPA the address of HEST via fw_cfg,
> * once initialized.
> */
> - bios_linker_loader_write_pointer(linker,
> - ACPI_HEST_ADDR_FW_CFG_FILE, 0,
> - sizeof(uint64_t),
> - ACPI_BUILD_TABLE_FILE, hest_offset);
> +
> + if (ags->use_hest_addr) {
> + bios_linker_loader_write_pointer(linker,
> + ACPI_HEST_ADDR_FW_CFG_FILE, 0,
> + sizeof(uint64_t),
> + ACPI_BUILD_TABLE_FILE, hest_offset);
> + }
if ags->use_hest_addr is true, then we can safely exclude
hardware_errors_addr fw_cfg
it shouldn't be used when use_hest_addr == true,
something along lines:
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 7362877669..a30f65f9f5 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -272,6 +272,7 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
i * ACPI_GHES_MAX_RAW_DATA_LENGTH);
}
+if (!ags->use_hest_addr) {
/*
* Tell firmware to write hardware_errors GPA into
* hardware_errors_addr fw_cfg, once the former has been initialized.
@@ -280,6 +281,7 @@ static void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker,
sizeof(uint64_t),
ACPI_HW_ERROR_FW_CFG_FILE, 0);
}
+}
/* Build Generic Hardware Error Source version 2 (GHESv2) */
static void build_ghes_v2_entry(GArray *table_data,
@@ -399,13 +401,13 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
fw_cfg_add_file(s, ACPI_HW_ERROR_FW_CFG_FILE, hardware_error->data,
hardware_error->len);
- /* Create a read-write fw_cfg file for Address */
- fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL,
- NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false);
-
if (ags->use_hest_addr) {
fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
+ } else {
+ /* Create a read-write fw_cfg file for Address */
+ fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL,
+ NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false);
}
ags->present = true;
> }
>
> void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
> @@ -399,8 +403,10 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
> fw_cfg_add_file_callback(s, ACPI_HW_ERROR_ADDR_FW_CFG_FILE, NULL, NULL,
> NULL, &(ags->hw_error_le), sizeof(ags->hw_error_le), false);
>
> - fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
> - NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
> + if (ags->use_hest_addr) {
> + fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
> + NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
> + }
>
> ags->present = true;
> }
> diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
> index 3d411787fc37..be1e51e0bb29 100644
> --- a/hw/arm/virt-acpi-build.c
> +++ b/hw/arm/virt-acpi-build.c
> @@ -897,6 +897,10 @@ static const AcpiNotificationSourceId hest_ghes_notify[] = {
> { ACPI_HEST_SRC_ID_SYNC, ACPI_GHES_NOTIFY_SEA },
> };
>
> +static const AcpiNotificationSourceId hest_ghes_notify_9_2[] = {
> + { ACPI_HEST_SRC_ID_SYNC, ACPI_GHES_NOTIFY_SEA },
> +};
> +
> static
> void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
> {
> @@ -950,10 +954,28 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
> build_dbg2(tables_blob, tables->linker, vms);
>
> if (vms->ras) {
> - acpi_add_table(table_offsets, tables_blob);
> - acpi_build_hest(tables_blob, tables->hardware_errors, tables->linker,
> - hest_ghes_notify, ARRAY_SIZE(hest_ghes_notify),
> - vms->oem_id, vms->oem_table_id);
> + AcpiGhesState *ags;
> + AcpiGedState *acpi_ged_state;
I'd do something like this, instead of calling acpi_build_hest() twice
notify = hest_ghes_notify_9_2
notify_sz = ...
> +
> + acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
> + NULL));
> + if (acpi_ged_state) {
> + ags = &acpi_ged_state->ghes_state;
> +
> + acpi_add_table(table_offsets, tables_blob);
> +
> + if (!ags->use_hest_addr) {
notify = hest_ghes_notify
notify_sz =
> + }
acpi_build_hest(ags, tables_blob, tables->hardware_errors,
tables->linker, notify,
notify_sz,
vms->oem_id, vms->oem_table_id);
> + }
> }
>
> if (ms->numa_state->num_nodes > 0) {
> diff --git a/hw/core/machine.c b/hw/core/machine.c
> index c23b39949649..0d0cde481954 100644
> --- a/hw/core/machine.c
> +++ b/hw/core/machine.c
> @@ -34,10 +34,12 @@
> #include "hw/virtio/virtio-pci.h"
> #include "hw/virtio/virtio-net.h"
> #include "hw/virtio/virtio-iommu.h"
> +#include "hw/acpi/generic_event_device.h"
> #include "audio/audio.h"
>
> GlobalProperty hw_compat_9_2[] = {
> {"arm-cpu", "backcompat-pauth-default-use-qarma5", "true"},
> + { TYPE_ACPI_GED, "x-has-hest-addr", "false" },
> };
> const size_t hw_compat_9_2_len = G_N_ELEMENTS(hw_compat_9_2);
>
> diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
> index 237721fec0a2..bfc8fd851648 100644
> --- a/include/hw/acpi/ghes.h
> +++ b/include/hw/acpi/ghes.h
> @@ -61,6 +61,7 @@ typedef struct AcpiGhesState {
> uint64_t hest_addr_le;
> uint64_t hw_error_le;
> bool present; /* True if GHES is present at all on this board */
> + bool use_hest_addr; /* True if HEST address is present */
> } AcpiGhesState;
>
> /*
> @@ -75,7 +76,8 @@ typedef struct AcpiNotificationSourceId {
> enum AcpiGhesNotifyType notify;
> } AcpiNotificationSourceId;
>
> -void acpi_build_hest(GArray *table_data, GArray *hardware_errors,
> +void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
> + GArray *hardware_errors,
> BIOSLinker *linker,
> const AcpiNotificationSourceId * const notif_source,
> int num_sources,
Some error injection notify methods are async, like GPIO
notify. Add a notifier to be used when the error record is
ready to be sent to the guest OS.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
hw/acpi/ghes.c | 5 ++++-
include/hw/acpi/ghes.h | 3 +++
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 736287766989..38ff95273706 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -512,6 +512,9 @@ static void get_ghes_source_offsets(uint16_t source_id,
*read_ack_start_addr = le64_to_cpu(*read_ack_start_addr);
}
+NotifierList acpi_generic_error_notifiers =
+ NOTIFIER_LIST_INITIALIZER(error_device_notifiers);
+
void ghes_record_cper_errors(const void *cper, size_t len,
uint16_t source_id, Error **errp)
{
@@ -567,7 +570,7 @@ void ghes_record_cper_errors(const void *cper, size_t len,
/* Write the generic error data entry into guest memory */
cpu_physical_memory_write(cper_addr, cper, len);
- return;
+ notifier_list_notify(&acpi_generic_error_notifiers, NULL);
}
int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index bfc8fd851648..80a0c3fcfaca 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -24,6 +24,9 @@
#include "hw/acpi/bios-linker-loader.h"
#include "qapi/error.h"
+#include "qemu/notify.h"
+
+extern NotifierList acpi_generic_error_notifiers;
/*
* Values for Hardware Error Notification Type field
--
2.48.1Move the check logic into a common function and simplify the
code which checks if GHES is enabled and was properly setup.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
hw/acpi/ghes-stub.c | 7 ++++---
hw/acpi/ghes.c | 43 ++++++++++++------------------------------
include/hw/acpi/ghes.h | 15 ++++++++-------
target/arm/kvm.c | 8 ++++++--
4 files changed, 30 insertions(+), 43 deletions(-)
diff --git a/hw/acpi/ghes-stub.c b/hw/acpi/ghes-stub.c
index 7cec1812dad9..40f660c246fe 100644
--- a/hw/acpi/ghes-stub.c
+++ b/hw/acpi/ghes-stub.c
@@ -11,12 +11,13 @@
#include "qemu/osdep.h"
#include "hw/acpi/ghes.h"
-int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
+int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
+ uint64_t physical_address)
{
return -1;
}
-bool acpi_ghes_present(void)
+AcpiGhesState *acpi_ghes_get_state(void)
{
- return false;
+ return NULL;
}
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 38ff95273706..849abfa12187 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -407,18 +407,12 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
}
-
- ags->present = true;
}
static void get_hw_error_offsets(uint64_t ghes_addr,
uint64_t *cper_addr,
uint64_t *read_ack_register_addr)
{
- if (!ghes_addr) {
- return;
- }
-
/*
* non-HEST version supports only one source, so no need to change
* the start offset based on the source ID. Also, we can't validate
@@ -447,9 +441,6 @@ static void get_ghes_source_offsets(uint16_t source_id,
uint64_t err_source_entry, error_block_addr;
uint32_t num_sources, i;
- if (!hest_entry_addr) {
- return;
- }
cpu_physical_memory_read(hest_entry_addr, &num_sources,
sizeof(num_sources));
@@ -515,27 +506,17 @@ static void get_ghes_source_offsets(uint16_t source_id,
NotifierList acpi_generic_error_notifiers =
NOTIFIER_LIST_INITIALIZER(error_device_notifiers);
-void ghes_record_cper_errors(const void *cper, size_t len,
+void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
uint16_t source_id, Error **errp)
{
uint64_t cper_addr = 0, read_ack_register_addr = 0, read_ack_register;
- AcpiGedState *acpi_ged_state;
- AcpiGhesState *ags;
if (len > ACPI_GHES_MAX_RAW_DATA_LENGTH) {
error_setg(errp, "GHES CPER record is too big: %zd", len);
return;
}
- acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
- NULL));
- if (!acpi_ged_state) {
- error_setg(errp, "Can't find ACPI_GED object");
- return;
- }
- ags = &acpi_ged_state->ghes_state;
-
- if (!ags->hest_addr_le) {
+ if (!ags->use_hest_addr) {
get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
&cper_addr, &read_ack_register_addr);
} else {
@@ -543,11 +524,6 @@ void ghes_record_cper_errors(const void *cper, size_t len,
&cper_addr, &read_ack_register_addr, errp);
}
- if (!cper_addr) {
- error_setg(errp, "can not find Generic Error Status Block");
- return;
- }
-
cpu_physical_memory_read(read_ack_register_addr,
&read_ack_register, sizeof(read_ack_register));
@@ -573,7 +549,8 @@ void ghes_record_cper_errors(const void *cper, size_t len,
notifier_list_notify(&acpi_generic_error_notifiers, NULL);
}
-int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
+int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
+ uint64_t physical_address)
{
/* Memory Error Section Type */
const uint8_t guid[] =
@@ -599,7 +576,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
acpi_ghes_build_append_mem_cper(block, physical_address);
/* Report the error */
- ghes_record_cper_errors(block->data, block->len, source_id, &errp);
+ ghes_record_cper_errors(ags, block->data, block->len, source_id, &errp);
g_array_free(block, true);
@@ -611,7 +588,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
return 0;
}
-bool acpi_ghes_present(void)
+AcpiGhesState *acpi_ghes_get_state(void)
{
AcpiGedState *acpi_ged_state;
AcpiGhesState *ags;
@@ -620,8 +597,12 @@ bool acpi_ghes_present(void)
NULL));
if (!acpi_ged_state) {
- return false;
+ return NULL;
}
ags = &acpi_ged_state->ghes_state;
- return ags->present;
+
+ if (!ags->hw_error_le && !ags->hest_addr_le) {
+ return NULL;
+ }
+ return ags;
}
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index 80a0c3fcfaca..e1b66141d01c 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -63,7 +63,6 @@ enum AcpiGhesNotifyType {
typedef struct AcpiGhesState {
uint64_t hest_addr_le;
uint64_t hw_error_le;
- bool present; /* True if GHES is present at all on this board */
bool use_hest_addr; /* True if HEST address is present */
} AcpiGhesState;
@@ -87,15 +86,17 @@ void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
const char *oem_id, const char *oem_table_id);
void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s,
GArray *hardware_errors);
-int acpi_ghes_memory_errors(uint16_t source_id, uint64_t error_physical_addr);
-void ghes_record_cper_errors(const void *cper, size_t len,
+int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
+ uint64_t error_physical_addr);
+void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
uint16_t source_id, Error **errp);
/**
- * acpi_ghes_present: Report whether ACPI GHES table is present
+ * acpi_ghes_get_state: Get a pointer for ACPI ghes state
*
- * Returns: true if the system has an ACPI GHES table and it is
- * safe to call acpi_ghes_memory_errors() to record a memory error.
+ * Returns: a pointer to ghes state if the system has an ACPI GHES table,
+ * it is enabled and it is safe to call acpi_ghes_memory_errors() to record
+ * a memory error. Returns false, otherwise.
*/
-bool acpi_ghes_present(void);
+AcpiGhesState *acpi_ghes_get_state(void);
#endif
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index da30bdbb2349..544ff174784d 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -2366,10 +2366,13 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
{
ram_addr_t ram_addr;
hwaddr paddr;
+ AcpiGhesState *ags;
assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
- if (acpi_ghes_present() && addr) {
+ ags = acpi_ghes_get_state();
+
+ if (ags && addr) {
ram_addr = qemu_ram_addr_from_host(addr);
if (ram_addr != RAM_ADDR_INVALID &&
kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
@@ -2387,7 +2390,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
*/
if (code == BUS_MCEERR_AR) {
kvm_cpu_synchronize_state(c);
- if (!acpi_ghes_memory_errors(ACPI_HEST_SRC_ID_SEA, paddr)) {
+ if (!acpi_ghes_memory_errors(ags, ACPI_HEST_SRC_ID_SEA,
+ paddr)) {
kvm_inject_arm_sea(c);
} else {
error_report("failed to record the error");
--
2.48.1On Wed, 29 Jan 2025 09:04:14 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> Move the check logic into a common function and simplify the
> code which checks if GHES is enabled and was properly setup.
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
with nits fixed:
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/ghes-stub.c | 7 ++++---
> hw/acpi/ghes.c | 43 ++++++++++++------------------------------
> include/hw/acpi/ghes.h | 15 ++++++++-------
> target/arm/kvm.c | 8 ++++++--
> 4 files changed, 30 insertions(+), 43 deletions(-)
>
> diff --git a/hw/acpi/ghes-stub.c b/hw/acpi/ghes-stub.c
> index 7cec1812dad9..40f660c246fe 100644
> --- a/hw/acpi/ghes-stub.c
> +++ b/hw/acpi/ghes-stub.c
> @@ -11,12 +11,13 @@
> #include "qemu/osdep.h"
> #include "hw/acpi/ghes.h"
>
> -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> + uint64_t physical_address)
> {
> return -1;
> }
>
> -bool acpi_ghes_present(void)
> +AcpiGhesState *acpi_ghes_get_state(void)
> {
> - return false;
> + return NULL;
> }
> diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> index 38ff95273706..849abfa12187 100644
> --- a/hw/acpi/ghes.c
> +++ b/hw/acpi/ghes.c
> @@ -407,18 +407,12 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
> fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
> NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
> }
> -
> - ags->present = true;
> }
>
> static void get_hw_error_offsets(uint64_t ghes_addr,
> uint64_t *cper_addr,
> uint64_t *read_ack_register_addr)
> {
> - if (!ghes_addr) {
> - return;
> - }
> -
> /*
> * non-HEST version supports only one source, so no need to change
> * the start offset based on the source ID. Also, we can't validate
> @@ -447,9 +441,6 @@ static void get_ghes_source_offsets(uint16_t source_id,
> uint64_t err_source_entry, error_block_addr;
> uint32_t num_sources, i;
>
> - if (!hest_entry_addr) {
> - return;
> - }
>
> cpu_physical_memory_read(hest_entry_addr, &num_sources,
> sizeof(num_sources));
> @@ -515,27 +506,17 @@ static void get_ghes_source_offsets(uint16_t source_id,
> NotifierList acpi_generic_error_notifiers =
> NOTIFIER_LIST_INITIALIZER(error_device_notifiers);
>
> -void ghes_record_cper_errors(const void *cper, size_t len,
> +void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
> uint16_t source_id, Error **errp)
> {
> uint64_t cper_addr = 0, read_ack_register_addr = 0, read_ack_register;
> - AcpiGedState *acpi_ged_state;
> - AcpiGhesState *ags;
>
> if (len > ACPI_GHES_MAX_RAW_DATA_LENGTH) {
> error_setg(errp, "GHES CPER record is too big: %zd", len);
> return;
> }
>
> - acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
> - NULL));
> - if (!acpi_ged_state) {
> - error_setg(errp, "Can't find ACPI_GED object");
> - return;
> - }
> - ags = &acpi_ged_state->ghes_state;
> -
> - if (!ags->hest_addr_le) {
> + if (!ags->use_hest_addr) {
> get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
> &cper_addr, &read_ack_register_addr);
> } else {
> @@ -543,11 +524,6 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> &cper_addr, &read_ack_register_addr, errp);
> }
>
> - if (!cper_addr) {
> - error_setg(errp, "can not find Generic Error Status Block");
> - return;
> - }
> -
> cpu_physical_memory_read(read_ack_register_addr,
> &read_ack_register, sizeof(read_ack_register));
>
> @@ -573,7 +549,8 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> notifier_list_notify(&acpi_generic_error_notifiers, NULL);
> }
>
> -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> + uint64_t physical_address)
> {
> /* Memory Error Section Type */
> const uint8_t guid[] =
> @@ -599,7 +576,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> acpi_ghes_build_append_mem_cper(block, physical_address);
>
> /* Report the error */
> - ghes_record_cper_errors(block->data, block->len, source_id, &errp);
> + ghes_record_cper_errors(ags, block->data, block->len, source_id, &errp);
>
> g_array_free(block, true);
>
> @@ -611,7 +588,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> return 0;
> }
>
> -bool acpi_ghes_present(void)
> +AcpiGhesState *acpi_ghes_get_state(void)
> {
> AcpiGedState *acpi_ged_state;
> AcpiGhesState *ags;
> @@ -620,8 +597,12 @@ bool acpi_ghes_present(void)
> NULL));
>
> if (!acpi_ged_state) {
> - return false;
> + return NULL;
> }
> ags = &acpi_ged_state->ghes_state;
> - return ags->present;
> +
> + if (!ags->hw_error_le && !ags->hest_addr_le) {
should we add a warning here?
(consider case where firmware hasn't managed to update pointers for some reason)
> + return NULL;
> + }
> + return ags;
> }
> diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
> index 80a0c3fcfaca..e1b66141d01c 100644
> --- a/include/hw/acpi/ghes.h
> +++ b/include/hw/acpi/ghes.h
> @@ -63,7 +63,6 @@ enum AcpiGhesNotifyType {
> typedef struct AcpiGhesState {
> uint64_t hest_addr_le;
> uint64_t hw_error_le;
> - bool present; /* True if GHES is present at all on this board */
> bool use_hest_addr; /* True if HEST address is present */
> } AcpiGhesState;
>
> @@ -87,15 +86,17 @@ void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
> const char *oem_id, const char *oem_table_id);
> void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s,
> GArray *hardware_errors);
> -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t error_physical_addr);
> -void ghes_record_cper_errors(const void *cper, size_t len,
> +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> + uint64_t error_physical_addr);
> +void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
> uint16_t source_id, Error **errp);
>
> /**
> - * acpi_ghes_present: Report whether ACPI GHES table is present
> + * acpi_ghes_get_state: Get a pointer for ACPI ghes state
> *
> - * Returns: true if the system has an ACPI GHES table and it is
> - * safe to call acpi_ghes_memory_errors() to record a memory error.
> + * Returns: a pointer to ghes state if the system has an ACPI GHES table,
> + * it is enabled and it is safe to call acpi_ghes_memory_errors() to record
> + * a memory error. Returns false, otherwise.
> */
> -bool acpi_ghes_present(void);
> +AcpiGhesState *acpi_ghes_get_state(void);
> #endif
> diff --git a/target/arm/kvm.c b/target/arm/kvm.c
> index da30bdbb2349..544ff174784d 100644
> --- a/target/arm/kvm.c
> +++ b/target/arm/kvm.c
> @@ -2366,10 +2366,13 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
> {
> ram_addr_t ram_addr;
> hwaddr paddr;
> + AcpiGhesState *ags;
>
> assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
>
> - if (acpi_ghes_present() && addr) {
> + ags = acpi_ghes_get_state();
> +
I'd drop this newline
> + if (ags && addr) {
> ram_addr = qemu_ram_addr_from_host(addr);
> if (ram_addr != RAM_ADDR_INVALID &&
> kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
> @@ -2387,7 +2390,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
> */
> if (code == BUS_MCEERR_AR) {
> kvm_cpu_synchronize_state(c);
> - if (!acpi_ghes_memory_errors(ACPI_HEST_SRC_ID_SEA, paddr)) {
> + if (!acpi_ghes_memory_errors(ags, ACPI_HEST_SRC_ID_SEA,
> + paddr)) {
> kvm_inject_arm_sea(c);
> } else {
> error_report("failed to record the error");
Em Wed, 29 Jan 2025 15:55:30 +0100
Igor Mammedov <imammedo@redhat.com> escreveu:
> On Wed, 29 Jan 2025 09:04:14 +0100
> Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
>
> > Move the check logic into a common function and simplify the
> > code which checks if GHES is enabled and was properly setup.
> >
> > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> > Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
>
> with nits fixed:
> Reviewed-by: Igor Mammedov <imammedo@redhat.com>
>
> > ---
> > hw/acpi/ghes-stub.c | 7 ++++---
> > hw/acpi/ghes.c | 43 ++++++++++++------------------------------
> > include/hw/acpi/ghes.h | 15 ++++++++-------
> > target/arm/kvm.c | 8 ++++++--
> > 4 files changed, 30 insertions(+), 43 deletions(-)
> >
> > diff --git a/hw/acpi/ghes-stub.c b/hw/acpi/ghes-stub.c
> > index 7cec1812dad9..40f660c246fe 100644
> > --- a/hw/acpi/ghes-stub.c
> > +++ b/hw/acpi/ghes-stub.c
> > @@ -11,12 +11,13 @@
> > #include "qemu/osdep.h"
> > #include "hw/acpi/ghes.h"
> >
> > -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> > + uint64_t physical_address)
> > {
> > return -1;
> > }
> >
> > -bool acpi_ghes_present(void)
> > +AcpiGhesState *acpi_ghes_get_state(void)
> > {
> > - return false;
> > + return NULL;
> > }
> > diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> > index 38ff95273706..849abfa12187 100644
> > --- a/hw/acpi/ghes.c
> > +++ b/hw/acpi/ghes.c
> > @@ -407,18 +407,12 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
> > fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
> > NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
> > }
> > -
> > - ags->present = true;
> > }
> >
> > static void get_hw_error_offsets(uint64_t ghes_addr,
> > uint64_t *cper_addr,
> > uint64_t *read_ack_register_addr)
> > {
> > - if (!ghes_addr) {
> > - return;
> > - }
> > -
> > /*
> > * non-HEST version supports only one source, so no need to change
> > * the start offset based on the source ID. Also, we can't validate
> > @@ -447,9 +441,6 @@ static void get_ghes_source_offsets(uint16_t source_id,
> > uint64_t err_source_entry, error_block_addr;
> > uint32_t num_sources, i;
> >
> > - if (!hest_entry_addr) {
> > - return;
> > - }
> >
> > cpu_physical_memory_read(hest_entry_addr, &num_sources,
> > sizeof(num_sources));
> > @@ -515,27 +506,17 @@ static void get_ghes_source_offsets(uint16_t source_id,
> > NotifierList acpi_generic_error_notifiers =
> > NOTIFIER_LIST_INITIALIZER(error_device_notifiers);
> >
> > -void ghes_record_cper_errors(const void *cper, size_t len,
> > +void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
> > uint16_t source_id, Error **errp)
> > {
> > uint64_t cper_addr = 0, read_ack_register_addr = 0, read_ack_register;
> > - AcpiGedState *acpi_ged_state;
> > - AcpiGhesState *ags;
> >
> > if (len > ACPI_GHES_MAX_RAW_DATA_LENGTH) {
> > error_setg(errp, "GHES CPER record is too big: %zd", len);
> > return;
> > }
> >
> > - acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
> > - NULL));
> > - if (!acpi_ged_state) {
> > - error_setg(errp, "Can't find ACPI_GED object");
> > - return;
> > - }
> > - ags = &acpi_ged_state->ghes_state;
> > -
> > - if (!ags->hest_addr_le) {
> > + if (!ags->use_hest_addr) {
> > get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
> > &cper_addr, &read_ack_register_addr);
> > } else {
> > @@ -543,11 +524,6 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> > &cper_addr, &read_ack_register_addr, errp);
> > }
> >
> > - if (!cper_addr) {
> > - error_setg(errp, "can not find Generic Error Status Block");
> > - return;
> > - }
> > -
> > cpu_physical_memory_read(read_ack_register_addr,
> > &read_ack_register, sizeof(read_ack_register));
> >
> > @@ -573,7 +549,8 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> > notifier_list_notify(&acpi_generic_error_notifiers, NULL);
> > }
> >
> > -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> > + uint64_t physical_address)
> > {
> > /* Memory Error Section Type */
> > const uint8_t guid[] =
> > @@ -599,7 +576,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > acpi_ghes_build_append_mem_cper(block, physical_address);
> >
> > /* Report the error */
> > - ghes_record_cper_errors(block->data, block->len, source_id, &errp);
> > + ghes_record_cper_errors(ags, block->data, block->len, source_id, &errp);
> >
> > g_array_free(block, true);
> >
> > @@ -611,7 +588,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > return 0;
> > }
> >
> > -bool acpi_ghes_present(void)
> > +AcpiGhesState *acpi_ghes_get_state(void)
> > {
> > AcpiGedState *acpi_ged_state;
> > AcpiGhesState *ags;
> > @@ -620,8 +597,12 @@ bool acpi_ghes_present(void)
> > NULL));
> >
> > if (!acpi_ged_state) {
> > - return false;
> > + return NULL;
> > }
> > ags = &acpi_ged_state->ghes_state;
> > - return ags->present;
> > +
> > + if (!ags->hw_error_le && !ags->hest_addr_le) {
>
> should we add a warning here?
> (consider case where firmware hasn't managed to update pointers for some reason)
I don't think so, as this will also return NULL if ras=off. See, the
original goal of acpi_ghes_present(void) were to avoid needing to check
if ras is enabled outside GHES code, like here at target/arm/kvm.c:
void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
{
ram_addr_t ram_addr;
hwaddr paddr;
AcpiGhesState *ags;
assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
ags = acpi_ghes_get_state();
if (ags && addr) {
...
This new logic repurposed acpi_ghes_present() as acpi_ghes_get_state(),
using it to full two situations:
1) ras=on;
2) either hw_err_addr_le or hest_addr_le exists.
Except if some serious issue takes place, (2) is actually equivalent
to check if ras is on or off.
Besides that, Error **errp is not defined yet, so we can't do this:
error_setg(errp, "HEST/GHES pointer is not available")
> > + return NULL;
> > + }
> > + return ags;
> > }
> > diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
> > index 80a0c3fcfaca..e1b66141d01c 100644
> > --- a/include/hw/acpi/ghes.h
> > +++ b/include/hw/acpi/ghes.h
> > @@ -63,7 +63,6 @@ enum AcpiGhesNotifyType {
> > typedef struct AcpiGhesState {
> > uint64_t hest_addr_le;
> > uint64_t hw_error_le;
> > - bool present; /* True if GHES is present at all on this board */
> > bool use_hest_addr; /* True if HEST address is present */
> > } AcpiGhesState;
> >
> > @@ -87,15 +86,17 @@ void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
> > const char *oem_id, const char *oem_table_id);
> > void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s,
> > GArray *hardware_errors);
> > -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t error_physical_addr);
> > -void ghes_record_cper_errors(const void *cper, size_t len,
> > +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> > + uint64_t error_physical_addr);
> > +void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
> > uint16_t source_id, Error **errp);
> >
> > /**
> > - * acpi_ghes_present: Report whether ACPI GHES table is present
> > + * acpi_ghes_get_state: Get a pointer for ACPI ghes state
> > *
> > - * Returns: true if the system has an ACPI GHES table and it is
> > - * safe to call acpi_ghes_memory_errors() to record a memory error.
> > + * Returns: a pointer to ghes state if the system has an ACPI GHES table,
> > + * it is enabled and it is safe to call acpi_ghes_memory_errors() to record
> > + * a memory error. Returns false, otherwise.
> > */
> > -bool acpi_ghes_present(void);
> > +AcpiGhesState *acpi_ghes_get_state(void);
> > #endif
> > diff --git a/target/arm/kvm.c b/target/arm/kvm.c
> > index da30bdbb2349..544ff174784d 100644
> > --- a/target/arm/kvm.c
> > +++ b/target/arm/kvm.c
> > @@ -2366,10 +2366,13 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
> > {
> > ram_addr_t ram_addr;
> > hwaddr paddr;
> > + AcpiGhesState *ags;
> >
> > assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
> >
> > - if (acpi_ghes_present() && addr) {
> > + ags = acpi_ghes_get_state();
>
> > +
> I'd drop this newline
>
> > + if (ags && addr) {
> > ram_addr = qemu_ram_addr_from_host(addr);
> > if (ram_addr != RAM_ADDR_INVALID &&
> > kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
> > @@ -2387,7 +2390,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
> > */
> > if (code == BUS_MCEERR_AR) {
> > kvm_cpu_synchronize_state(c);
> > - if (!acpi_ghes_memory_errors(ACPI_HEST_SRC_ID_SEA, paddr)) {
> > + if (!acpi_ghes_memory_errors(ags, ACPI_HEST_SRC_ID_SEA,
> > + paddr)) {
> > kvm_inject_arm_sea(c);
> > } else {
> > error_report("failed to record the error");
>
Thanks,
Mauro
On Thu, 30 Jan 2025 14:44:39 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> Em Wed, 29 Jan 2025 15:55:30 +0100
> Igor Mammedov <imammedo@redhat.com> escreveu:
>
> > On Wed, 29 Jan 2025 09:04:14 +0100
> > Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> >
> > > Move the check logic into a common function and simplify the
> > > code which checks if GHES is enabled and was properly setup.
> > >
> > > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> > > Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> >
> > with nits fixed:
> > Reviewed-by: Igor Mammedov <imammedo@redhat.com>
> >
> > > ---
> > > hw/acpi/ghes-stub.c | 7 ++++---
> > > hw/acpi/ghes.c | 43 ++++++++++++------------------------------
> > > include/hw/acpi/ghes.h | 15 ++++++++-------
> > > target/arm/kvm.c | 8 ++++++--
> > > 4 files changed, 30 insertions(+), 43 deletions(-)
> > >
> > > diff --git a/hw/acpi/ghes-stub.c b/hw/acpi/ghes-stub.c
> > > index 7cec1812dad9..40f660c246fe 100644
> > > --- a/hw/acpi/ghes-stub.c
> > > +++ b/hw/acpi/ghes-stub.c
> > > @@ -11,12 +11,13 @@
> > > #include "qemu/osdep.h"
> > > #include "hw/acpi/ghes.h"
> > >
> > > -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > > +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> > > + uint64_t physical_address)
> > > {
> > > return -1;
> > > }
> > >
> > > -bool acpi_ghes_present(void)
> > > +AcpiGhesState *acpi_ghes_get_state(void)
> > > {
> > > - return false;
> > > + return NULL;
> > > }
> > > diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> > > index 38ff95273706..849abfa12187 100644
> > > --- a/hw/acpi/ghes.c
> > > +++ b/hw/acpi/ghes.c
> > > @@ -407,18 +407,12 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s,
> > > fw_cfg_add_file_callback(s, ACPI_HEST_ADDR_FW_CFG_FILE, NULL, NULL,
> > > NULL, &(ags->hest_addr_le), sizeof(ags->hest_addr_le), false);
> > > }
> > > -
> > > - ags->present = true;
> > > }
> > >
> > > static void get_hw_error_offsets(uint64_t ghes_addr,
> > > uint64_t *cper_addr,
> > > uint64_t *read_ack_register_addr)
> > > {
> > > - if (!ghes_addr) {
> > > - return;
> > > - }
> > > -
> > > /*
> > > * non-HEST version supports only one source, so no need to change
> > > * the start offset based on the source ID. Also, we can't validate
> > > @@ -447,9 +441,6 @@ static void get_ghes_source_offsets(uint16_t source_id,
> > > uint64_t err_source_entry, error_block_addr;
> > > uint32_t num_sources, i;
> > >
> > > - if (!hest_entry_addr) {
> > > - return;
> > > - }
> > >
> > > cpu_physical_memory_read(hest_entry_addr, &num_sources,
> > > sizeof(num_sources));
> > > @@ -515,27 +506,17 @@ static void get_ghes_source_offsets(uint16_t source_id,
> > > NotifierList acpi_generic_error_notifiers =
> > > NOTIFIER_LIST_INITIALIZER(error_device_notifiers);
> > >
> > > -void ghes_record_cper_errors(const void *cper, size_t len,
> > > +void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
> > > uint16_t source_id, Error **errp)
> > > {
> > > uint64_t cper_addr = 0, read_ack_register_addr = 0, read_ack_register;
> > > - AcpiGedState *acpi_ged_state;
> > > - AcpiGhesState *ags;
> > >
> > > if (len > ACPI_GHES_MAX_RAW_DATA_LENGTH) {
> > > error_setg(errp, "GHES CPER record is too big: %zd", len);
> > > return;
> > > }
> > >
> > > - acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED,
> > > - NULL));
> > > - if (!acpi_ged_state) {
> > > - error_setg(errp, "Can't find ACPI_GED object");
> > > - return;
> > > - }
> > > - ags = &acpi_ged_state->ghes_state;
> > > -
> > > - if (!ags->hest_addr_le) {
> > > + if (!ags->use_hest_addr) {
> > > get_hw_error_offsets(le64_to_cpu(ags->hw_error_le),
> > > &cper_addr, &read_ack_register_addr);
> > > } else {
> > > @@ -543,11 +524,6 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> > > &cper_addr, &read_ack_register_addr, errp);
> > > }
> > >
> > > - if (!cper_addr) {
> > > - error_setg(errp, "can not find Generic Error Status Block");
> > > - return;
> > > - }
> > > -
> > > cpu_physical_memory_read(read_ack_register_addr,
> > > &read_ack_register, sizeof(read_ack_register));
> > >
> > > @@ -573,7 +549,8 @@ void ghes_record_cper_errors(const void *cper, size_t len,
> > > notifier_list_notify(&acpi_generic_error_notifiers, NULL);
> > > }
> > >
> > > -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > > +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> > > + uint64_t physical_address)
> > > {
> > > /* Memory Error Section Type */
> > > const uint8_t guid[] =
> > > @@ -599,7 +576,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > > acpi_ghes_build_append_mem_cper(block, physical_address);
> > >
> > > /* Report the error */
> > > - ghes_record_cper_errors(block->data, block->len, source_id, &errp);
> > > + ghes_record_cper_errors(ags, block->data, block->len, source_id, &errp);
> > >
> > > g_array_free(block, true);
> > >
> > > @@ -611,7 +588,7 @@ int acpi_ghes_memory_errors(uint16_t source_id, uint64_t physical_address)
> > > return 0;
> > > }
> > >
> > > -bool acpi_ghes_present(void)
> > > +AcpiGhesState *acpi_ghes_get_state(void)
> > > {
> > > AcpiGedState *acpi_ged_state;
> > > AcpiGhesState *ags;
> > > @@ -620,8 +597,12 @@ bool acpi_ghes_present(void)
> > > NULL));
> > >
> > > if (!acpi_ged_state) {
> > > - return false;
> > > + return NULL;
> > > }
> > > ags = &acpi_ged_state->ghes_state;
> > > - return ags->present;
> > > +
> > > + if (!ags->hw_error_le && !ags->hest_addr_le) {
> >
> > should we add a warning here?
> > (consider case where firmware hasn't managed to update pointers for some reason)
>
> I don't think so, as this will also return NULL if ras=off. See, the
> original goal of acpi_ghes_present(void) were to avoid needing to check
> if ras is enabled outside GHES code, like here at target/arm/kvm.c:
>
> void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
> {
> ram_addr_t ram_addr;
> hwaddr paddr;
> AcpiGhesState *ags;
>
> assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
>
> ags = acpi_ghes_get_state();
> if (ags && addr) {
> ...
>
> This new logic repurposed acpi_ghes_present() as acpi_ghes_get_state(),
> using it to full two situations:
>
> 1) ras=on;
> 2) either hw_err_addr_le or hest_addr_le exists.
>
> Except if some serious issue takes place, (2) is actually equivalent
> to check if ras is on or off.
I was thinking about hypothetical case of firmware failure to updating
fwcfg files.
But yep, it's hardly possible (unless dst target on migration is misconfigured),
just ignore this comment.
> Besides that, Error **errp is not defined yet, so we can't do this:
warn_report_once() would've done the job here.
>
> error_setg(errp, "HEST/GHES pointer is not available")
>
> > > + return NULL;
> > > + }
> > > + return ags;
> > > }
> > > diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
> > > index 80a0c3fcfaca..e1b66141d01c 100644
> > > --- a/include/hw/acpi/ghes.h
> > > +++ b/include/hw/acpi/ghes.h
> > > @@ -63,7 +63,6 @@ enum AcpiGhesNotifyType {
> > > typedef struct AcpiGhesState {
> > > uint64_t hest_addr_le;
> > > uint64_t hw_error_le;
> > > - bool present; /* True if GHES is present at all on this board */
> > > bool use_hest_addr; /* True if HEST address is present */
> > > } AcpiGhesState;
> > >
> > > @@ -87,15 +86,17 @@ void acpi_build_hest(AcpiGhesState *ags, GArray *table_data,
> > > const char *oem_id, const char *oem_table_id);
> > > void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s,
> > > GArray *hardware_errors);
> > > -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t error_physical_addr);
> > > -void ghes_record_cper_errors(const void *cper, size_t len,
> > > +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id,
> > > + uint64_t error_physical_addr);
> > > +void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len,
> > > uint16_t source_id, Error **errp);
> > >
> > > /**
> > > - * acpi_ghes_present: Report whether ACPI GHES table is present
> > > + * acpi_ghes_get_state: Get a pointer for ACPI ghes state
> > > *
> > > - * Returns: true if the system has an ACPI GHES table and it is
> > > - * safe to call acpi_ghes_memory_errors() to record a memory error.
> > > + * Returns: a pointer to ghes state if the system has an ACPI GHES table,
> > > + * it is enabled and it is safe to call acpi_ghes_memory_errors() to record
> > > + * a memory error. Returns false, otherwise.
> > > */
> > > -bool acpi_ghes_present(void);
> > > +AcpiGhesState *acpi_ghes_get_state(void);
> > > #endif
> > > diff --git a/target/arm/kvm.c b/target/arm/kvm.c
> > > index da30bdbb2349..544ff174784d 100644
> > > --- a/target/arm/kvm.c
> > > +++ b/target/arm/kvm.c
> > > @@ -2366,10 +2366,13 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
> > > {
> > > ram_addr_t ram_addr;
> > > hwaddr paddr;
> > > + AcpiGhesState *ags;
> > >
> > > assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
> > >
> > > - if (acpi_ghes_present() && addr) {
> > > + ags = acpi_ghes_get_state();
> >
> > > +
> > I'd drop this newline
> >
> > > + if (ags && addr) {
> > > ram_addr = qemu_ram_addr_from_host(addr);
> > > if (ram_addr != RAM_ADDR_INVALID &&
> > > kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
> > > @@ -2387,7 +2390,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
> > > */
> > > if (code == BUS_MCEERR_AR) {
> > > kvm_cpu_synchronize_state(c);
> > > - if (!acpi_ghes_memory_errors(ACPI_HEST_SRC_ID_SEA, paddr)) {
> > > + if (!acpi_ghes_memory_errors(ags, ACPI_HEST_SRC_ID_SEA,
> > > + paddr)) {
> > > kvm_inject_arm_sea(c);
> > > } else {
> > > error_report("failed to record the error");
> >
>
>
>
> Thanks,
> Mauro
>
Adds a generic error device to handle generic hardware error
events as specified at ACPI 6.5 specification at 18.3.2.7.2:
https://uefi.org/specs/ACPI/6.5/18_Platform_Error_Interfaces.html#event-notification-for-generic-error-sources
using HID PNP0C33.
The PNP0C33 device is used to report hardware errors to
the guest via ACPI APEI Generic Hardware Error Source (GHES).
Co-authored-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Co-authored-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
---
hw/acpi/aml-build.c | 10 ++++++++++
hw/acpi/generic_event_device.c | 14 ++++++++++++++
include/hw/acpi/acpi_dev_interface.h | 1 +
include/hw/acpi/aml-build.h | 2 ++
include/hw/acpi/generic_event_device.h | 1 +
5 files changed, 28 insertions(+)
diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
index f8f93a9f66c8..e4bd7b611372 100644
--- a/hw/acpi/aml-build.c
+++ b/hw/acpi/aml-build.c
@@ -2614,3 +2614,13 @@ Aml *aml_i2c_serial_bus_device(uint16_t address, const char *resource_source)
return var;
}
+
+/* ACPI 5.0b: 18.3.2.6.2 Event Notification For Generic Error Sources */
+Aml *aml_error_device(void)
+{
+ Aml *dev = aml_device(ACPI_APEI_ERROR_DEVICE);
+ aml_append(dev, aml_name_decl("_HID", aml_string("PNP0C33")));
+ aml_append(dev, aml_name_decl("_UID", aml_int(0)));
+
+ return dev;
+}
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
index 70729b6238a5..50313ed7ee96 100644
--- a/hw/acpi/generic_event_device.c
+++ b/hw/acpi/generic_event_device.c
@@ -26,8 +26,15 @@ static const uint32_t ged_supported_events[] = {
ACPI_GED_PWR_DOWN_EVT,
ACPI_GED_NVDIMM_HOTPLUG_EVT,
ACPI_GED_CPU_HOTPLUG_EVT,
+ ACPI_GED_ERROR_EVT,
};
+/*
+ * ACPI 5.0b: 5.6.6 Device Object Notifications
+ * Table 5-135 Error Device Notification Values
+ */
+#define ERROR_DEVICE_NOTIFICATION 0x80
+
/*
* The ACPI Generic Event Device (GED) is a hardware-reduced specific
* device[ACPI v6.1 Section 5.6.9] that handles all platform events,
@@ -116,6 +123,11 @@ void build_ged_aml(Aml *table, const char *name, HotplugHandler *hotplug_dev,
aml_notify(aml_name(ACPI_POWER_BUTTON_DEVICE),
aml_int(0x80)));
break;
+ case ACPI_GED_ERROR_EVT:
+ aml_append(if_ctx,
+ aml_notify(aml_name(ACPI_APEI_ERROR_DEVICE),
+ aml_int(ERROR_DEVICE_NOTIFICATION)));
+ break;
case ACPI_GED_NVDIMM_HOTPLUG_EVT:
aml_append(if_ctx,
aml_notify(aml_name("\\_SB.NVDR"),
@@ -295,6 +307,8 @@ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
sel = ACPI_GED_MEM_HOTPLUG_EVT;
} else if (ev & ACPI_POWER_DOWN_STATUS) {
sel = ACPI_GED_PWR_DOWN_EVT;
+ } else if (ev & ACPI_GENERIC_ERROR) {
+ sel = ACPI_GED_ERROR_EVT;
} else if (ev & ACPI_NVDIMM_HOTPLUG_STATUS) {
sel = ACPI_GED_NVDIMM_HOTPLUG_EVT;
} else if (ev & ACPI_CPU_HOTPLUG_STATUS) {
diff --git a/include/hw/acpi/acpi_dev_interface.h b/include/hw/acpi/acpi_dev_interface.h
index 68d9d15f50aa..8294f8f0ccca 100644
--- a/include/hw/acpi/acpi_dev_interface.h
+++ b/include/hw/acpi/acpi_dev_interface.h
@@ -13,6 +13,7 @@ typedef enum {
ACPI_NVDIMM_HOTPLUG_STATUS = 16,
ACPI_VMGENID_CHANGE_STATUS = 32,
ACPI_POWER_DOWN_STATUS = 64,
+ ACPI_GENERIC_ERROR = 128,
} AcpiEventStatusBits;
#define TYPE_ACPI_DEVICE_IF "acpi-device-interface"
diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h
index c18f68134246..f38e12971932 100644
--- a/include/hw/acpi/aml-build.h
+++ b/include/hw/acpi/aml-build.h
@@ -252,6 +252,7 @@ struct CrsRangeSet {
/* Consumer/Producer */
#define AML_SERIAL_BUS_FLAG_CONSUME_ONLY (1 << 1)
+#define ACPI_APEI_ERROR_DEVICE "GEDD"
/**
* init_aml_allocator:
*
@@ -382,6 +383,7 @@ Aml *aml_dma(AmlDmaType typ, AmlDmaBusMaster bm, AmlTransferSize sz,
uint8_t channel);
Aml *aml_sleep(uint64_t msec);
Aml *aml_i2c_serial_bus_device(uint16_t address, const char *resource_source);
+Aml *aml_error_device(void);
/* Block AML object primitives */
Aml *aml_scope(const char *name_format, ...) G_GNUC_PRINTF(1, 2);
diff --git a/include/hw/acpi/generic_event_device.h b/include/hw/acpi/generic_event_device.h
index d2dac87b4a9f..1c18ac296fcb 100644
--- a/include/hw/acpi/generic_event_device.h
+++ b/include/hw/acpi/generic_event_device.h
@@ -101,6 +101,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED)
#define ACPI_GED_PWR_DOWN_EVT 0x2
#define ACPI_GED_NVDIMM_HOTPLUG_EVT 0x4
#define ACPI_GED_CPU_HOTPLUG_EVT 0x8
+#define ACPI_GED_ERROR_EVT 0x10
typedef struct GEDState {
MemoryRegion evt;
--
2.48.1On Wed, 29 Jan 2025 09:04:15 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> Adds a generic error device to handle generic hardware error
> events as specified at ACPI 6.5 specification at 18.3.2.7.2:
> https://uefi.org/specs/ACPI/6.5/18_Platform_Error_Interfaces.html#event-notification-for-generic-error-sources
> using HID PNP0C33.
>
> The PNP0C33 device is used to report hardware errors to
> the guest via ACPI APEI Generic Hardware Error Source (GHES).
>
> Co-authored-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> Co-authored-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> Reviewed-by: Igor Mammedov <imammedo@redhat.com>
> ---
> hw/acpi/aml-build.c | 10 ++++++++++
> hw/acpi/generic_event_device.c | 14 ++++++++++++++
> include/hw/acpi/acpi_dev_interface.h | 1 +
> include/hw/acpi/aml-build.h | 2 ++
> include/hw/acpi/generic_event_device.h | 1 +
> 5 files changed, 28 insertions(+)
>
> diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
> index f8f93a9f66c8..e4bd7b611372 100644
> --- a/hw/acpi/aml-build.c
> +++ b/hw/acpi/aml-build.c
> @@ -2614,3 +2614,13 @@ Aml *aml_i2c_serial_bus_device(uint16_t address, const char *resource_source)
>
> return var;
> }
> +
> +/* ACPI 5.0b: 18.3.2.6.2 Event Notification For Generic Error Sources */
> +Aml *aml_error_device(void)
> +{
> + Aml *dev = aml_device(ACPI_APEI_ERROR_DEVICE);
> + aml_append(dev, aml_name_decl("_HID", aml_string("PNP0C33")));
> + aml_append(dev, aml_name_decl("_UID", aml_int(0)));
> +
> + return dev;
> +}
> diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
> index 70729b6238a5..50313ed7ee96 100644
> --- a/hw/acpi/generic_event_device.c
> +++ b/hw/acpi/generic_event_device.c
> @@ -26,8 +26,15 @@ static const uint32_t ged_supported_events[] = {
> ACPI_GED_PWR_DOWN_EVT,
> ACPI_GED_NVDIMM_HOTPLUG_EVT,
> ACPI_GED_CPU_HOTPLUG_EVT,
> + ACPI_GED_ERROR_EVT,
> };
>
> +/*
> + * ACPI 5.0b: 5.6.6 Device Object Notifications
> + * Table 5-135 Error Device Notification Values
> + */
> +#define ERROR_DEVICE_NOTIFICATION 0x80
drop 1-off macro as Michael suggested, and move value/comment into
the place where it's used
> +
> /*
> * The ACPI Generic Event Device (GED) is a hardware-reduced specific
> * device[ACPI v6.1 Section 5.6.9] that handles all platform events,
> @@ -116,6 +123,11 @@ void build_ged_aml(Aml *table, const char *name, HotplugHandler *hotplug_dev,
> aml_notify(aml_name(ACPI_POWER_BUTTON_DEVICE),
> aml_int(0x80)));
> break;
> + case ACPI_GED_ERROR_EVT:
> + aml_append(if_ctx,
> + aml_notify(aml_name(ACPI_APEI_ERROR_DEVICE),
> + aml_int(ERROR_DEVICE_NOTIFICATION)));
> + break;
> case ACPI_GED_NVDIMM_HOTPLUG_EVT:
> aml_append(if_ctx,
> aml_notify(aml_name("\\_SB.NVDR"),
> @@ -295,6 +307,8 @@ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
> sel = ACPI_GED_MEM_HOTPLUG_EVT;
> } else if (ev & ACPI_POWER_DOWN_STATUS) {
> sel = ACPI_GED_PWR_DOWN_EVT;
> + } else if (ev & ACPI_GENERIC_ERROR) {
> + sel = ACPI_GED_ERROR_EVT;
> } else if (ev & ACPI_NVDIMM_HOTPLUG_STATUS) {
> sel = ACPI_GED_NVDIMM_HOTPLUG_EVT;
> } else if (ev & ACPI_CPU_HOTPLUG_STATUS) {
> diff --git a/include/hw/acpi/acpi_dev_interface.h b/include/hw/acpi/acpi_dev_interface.h
> index 68d9d15f50aa..8294f8f0ccca 100644
> --- a/include/hw/acpi/acpi_dev_interface.h
> +++ b/include/hw/acpi/acpi_dev_interface.h
> @@ -13,6 +13,7 @@ typedef enum {
> ACPI_NVDIMM_HOTPLUG_STATUS = 16,
> ACPI_VMGENID_CHANGE_STATUS = 32,
> ACPI_POWER_DOWN_STATUS = 64,
> + ACPI_GENERIC_ERROR = 128,
> } AcpiEventStatusBits;
>
> #define TYPE_ACPI_DEVICE_IF "acpi-device-interface"
> diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h
> index c18f68134246..f38e12971932 100644
> --- a/include/hw/acpi/aml-build.h
> +++ b/include/hw/acpi/aml-build.h
> @@ -252,6 +252,7 @@ struct CrsRangeSet {
> /* Consumer/Producer */
> #define AML_SERIAL_BUS_FLAG_CONSUME_ONLY (1 << 1)
>
> +#define ACPI_APEI_ERROR_DEVICE "GEDD"
> /**
> * init_aml_allocator:
> *
> @@ -382,6 +383,7 @@ Aml *aml_dma(AmlDmaType typ, AmlDmaBusMaster bm, AmlTransferSize sz,
> uint8_t channel);
> Aml *aml_sleep(uint64_t msec);
> Aml *aml_i2c_serial_bus_device(uint16_t address, const char *resource_source);
> +Aml *aml_error_device(void);
>
> /* Block AML object primitives */
> Aml *aml_scope(const char *name_format, ...) G_GNUC_PRINTF(1, 2);
> diff --git a/include/hw/acpi/generic_event_device.h b/include/hw/acpi/generic_event_device.h
> index d2dac87b4a9f..1c18ac296fcb 100644
> --- a/include/hw/acpi/generic_event_device.h
> +++ b/include/hw/acpi/generic_event_device.h
> @@ -101,6 +101,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED)
> #define ACPI_GED_PWR_DOWN_EVT 0x2
> #define ACPI_GED_NVDIMM_HOTPLUG_EVT 0x4
> #define ACPI_GED_CPU_HOTPLUG_EVT 0x8
> +#define ACPI_GED_ERROR_EVT 0x10
>
> typedef struct GEDState {
> MemoryRegion evt;
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 <mchehab+huawei@kernel.org>
Co-authored-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Acked-by: Igor Mammedov <imammedo@redhat.com>
---
Changes from v8:
- Added a call to the function that produces GHES generic
records, as this is now added earlier in this series.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
hw/arm/virt-acpi-build.c | 1 +
hw/arm/virt.c | 12 +++++++++++-
include/hw/arm/virt.h | 1 +
3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index be1e51e0bb29..af8588330103 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -861,6 +861,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
}
acpi_dsdt_add_power_button(scope);
+ aml_append(scope, aml_error_device());
#ifdef CONFIG_TPM
acpi_dsdt_add_tpm(scope, vms);
#endif
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 99e0a68b6c55..e272b35ea114 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -678,7 +678,7 @@ static inline DeviceState *create_acpi_ged(VirtMachineState *vms)
DeviceState *dev;
MachineState *ms = MACHINE(vms);
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;
if (ms->ram_slots) {
event |= ACPI_GED_MEM_HOTPLUG_EVT;
@@ -1010,6 +1010,13 @@ 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)
{
@@ -2404,6 +2411,9 @@ 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);
}
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index c8e94e6aedc9..f3cf28436770 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -176,6 +176,7 @@ struct VirtMachineState {
DeviceState *gic;
DeviceState *acpi_dev;
Notifier powerdown_notifier;
+ Notifier generic_error_notifier;
PCIBus *bus;
char *oem_id;
char *oem_table_id;
--
2.48.1Creates 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 is 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 <Jonathan.Cameron@huawei.com>
Co-authored-by: Shiju Jose <shiju.jose@huawei.com>
Co-authored-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Acked-by: Igor Mammedov <imammedo@redhat.com>
---
Changes since v9:
- ARM source IDs renamed to reflect SYNC/ASYNC;
- command name changed to better reflect what it does;
- some improvements at JSON documentation;
- add a check for QMP source at the notification logic.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
MAINTAINERS | 7 +++++++
hw/acpi/Kconfig | 5 +++++
hw/acpi/ghes.c | 2 +-
hw/acpi/ghes_cper.c | 38 ++++++++++++++++++++++++++++++++++++++
hw/acpi/ghes_cper_stub.c | 19 +++++++++++++++++++
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 | 35 +++++++++++++++++++++++++++++++++++
qapi/meson.build | 1 +
qapi/qapi-schema.json | 1 +
13 files changed, 119 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
diff --git a/MAINTAINERS b/MAINTAINERS
index 846b81e3ec03..8e1f662fa0e0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2075,6 +2075,13 @@ 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 <mchehab+huawei@kernel.org>
+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 1d4e9f0845c0..daabbe6cd11e 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 849abfa12187..ef57ad14a38b 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -546,7 +546,7 @@ 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 000000000000..0a2d95dd8b27
--- /dev/null
+++ b/hw/acpi/ghes_cper.c
@@ -0,0 +1,38 @@
+/*
+ * 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.
+ *
+ */
+
+#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;
+
+ ags = acpi_ghes_get_state();
+ if (!ags) {
+ return;
+ }
+
+ uint8_t *cper;
+ size_t len;
+
+ 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);
+}
diff --git a/hw/acpi/ghes_cper_stub.c b/hw/acpi/ghes_cper_stub.c
new file mode 100644
index 000000000000..5ebc61970a78
--- /dev/null
+++ b/hw/acpi/ghes_cper_stub.c
@@ -0,0 +1,19 @@
+/*
+ * 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.
+ *
+ */
+
+#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 73f02b96912b..56b5d1ec9691 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 af8588330103..7d3580244179 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -896,6 +896,7 @@ 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_9_2[] = {
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e272b35ea114..9074a540197d 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1012,6 +1012,13 @@ 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 e1b66141d01c..376933a0024a 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -71,6 +71,7 @@ typedef struct AcpiGhesState {
*/
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 f3cf28436770..56f270f61cf5 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 000000000000..fff5018c7ec1
--- /dev/null
+++ b/qapi/acpi-hest.json
@@ -0,0 +1,35 @@
+# -*- Mode: Python -*-
+# vim: filetype=python
+
+##
+# == 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: 10.0
+##
+{ 'command': 'inject-ghes-v2-error',
+ 'data': {
+ 'cper': 'str'
+ },
+ 'features': [ 'unstable' ]
+}
diff --git a/qapi/meson.build b/qapi/meson.build
index e7bc54e5d047..35cea6147262 100644
--- a/qapi/meson.build
+++ b/qapi/meson.build
@@ -59,6 +59,7 @@ qapi_all_modules = [
if have_system
qapi_all_modules += [
'acpi',
+ 'acpi-hest',
'audio',
'cryptodev',
'qdev',
diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json
index b1581988e4eb..baf19ab73afe 100644
--- a/qapi/qapi-schema.json
+++ b/qapi/qapi-schema.json
@@ -75,6 +75,7 @@
{ 'include': 'misc-target.json' }
{ 'include': 'audio.json' }
{ 'include': 'acpi.json' }
+{ 'include': 'acpi-hest.json' }
{ 'include': 'pci.json' }
{ 'include': 'stats.json' }
{ 'include': 'virtio.json' }
--
2.48.1DSDT has gained a GED device to notify errors:
--- a/DSDT.dsl 2025-01-28 09:38:15.155347858 +0100
+++ b/DSDT.dsl 2025-01-28 09:39:01.684836954 +0100
@@ -9,9 +9,9 @@
*
* Original Table Header:
* Signature "DSDT"
- * Length 0x00001516 (5398)
+ * Length 0x00001542 (5442)
* Revision 0x02
- * Checksum 0x0F
+ * Checksum 0xE9
* OEM ID "BOCHS "
* OEM Table ID "BXPC "
* OEM Revision 0x00000001 (1)
@@ -1931,6 +1931,11 @@
{
Notify (PWRB, 0x80) // Status Change
}
+
+ If (((Local0 & 0x10) == 0x10))
+ {
+ Notify (GEDD, 0x80) // Status Change
+ }
}
}
@@ -1939,6 +1944,12 @@
Name (_HID, "PNP0C0C" /* Power Button Device */) // _HID: Hardware ID
Name (_UID, Zero) // _UID: Unique ID
}
+
+ Device (GEDD)
+ {
+ Name (_HID, "PNP0C33" /* Error Device */) // _HID: Hardware ID
+ Name (_UID, Zero) // _UID: Unique ID
+ }
}
}
New HEST table:
/*
* Intel ACPI Component Architecture
* AML/ASL+ Disassembler version 20240927 (64-bit version)
* Copyright (c) 2000 - 2023 Intel Corporation
*
* Disassembly of hest.dat
*
* ACPI Data Table [HEST]
*
* Format: [HexOffset DecimalOffset ByteLength] FieldName : FieldValue (in hex)
*/
[000h 0000 004h] Signature : "HEST" [Hardware Error Source Table]
[004h 0004 004h] Table Length : 000000E0
[008h 0008 001h] Revision : 01
[009h 0009 001h] Checksum : 68
[00Ah 0010 006h] Oem ID : "BOCHS "
[010h 0016 008h] Oem Table ID : "BXPC "
[018h 0024 004h] Oem Revision : 00000001
[01Ch 0028 004h] Asl Compiler ID : "BXPC"
[020h 0032 004h] Asl Compiler Revision : 00000001
[024h 0036 004h] Error Source Count : 00000002
[028h 0040 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
[02Ah 0042 002h] Source Id : 0000
[02Ch 0044 002h] Related Source Id : FFFF
[02Eh 0046 001h] Reserved : 00
[02Fh 0047 001h] Enabled : 01
[030h 0048 004h] Records To Preallocate : 00000001
[034h 0052 004h] Max Sections Per Record : 00000001
[038h 0056 004h] Max Raw Data Length : 00000400
[03Ch 0060 00Ch] Error Status Address : [Generic Address Structure]
[03Ch 0060 001h] Space ID : 00 [SystemMemory]
[03Dh 0061 001h] Bit Width : 40
[03Eh 0062 001h] Bit Offset : 00
[03Fh 0063 001h] Encoded Access Width : 04 [QWord Access:64]
[040h 0064 008h] Address : 0000000139E40000
[048h 0072 01Ch] Notify : [Hardware Error Notification Structure]
[048h 0072 001h] Notify Type : 08 [SEA]
[049h 0073 001h] Notify Length : 1C
[04Ah 0074 002h] Configuration Write Enable : 0000
[04Ch 0076 004h] PollInterval : 00000000
[050h 0080 004h] Vector : 00000000
[054h 0084 004h] Polling Threshold Value : 00000000
[058h 0088 004h] Polling Threshold Window : 00000000
[05Ch 0092 004h] Error Threshold Value : 00000000
[060h 0096 004h] Error Threshold Window : 00000000
[064h 0100 004h] Error Status Block Length : 00000400
[068h 0104 00Ch] Read Ack Register : [Generic Address Structure]
[068h 0104 001h] Space ID : 00 [SystemMemory]
[069h 0105 001h] Bit Width : 40
[06Ah 0106 001h] Bit Offset : 00
[06Bh 0107 001h] Encoded Access Width : 04 [QWord Access:64]
[06Ch 0108 008h] Address : 0000000139E40010
[074h 0116 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
[07Ch 0124 008h] Read Ack Write : 0000000000000001
[084h 0132 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
[086h 0134 002h] Source Id : 0001
[088h 0136 002h] Related Source Id : FFFF
[08Ah 0138 001h] Reserved : 00
[08Bh 0139 001h] Enabled : 01
[08Ch 0140 004h] Records To Preallocate : 00000001
[090h 0144 004h] Max Sections Per Record : 00000001
[094h 0148 004h] Max Raw Data Length : 00000400
[098h 0152 00Ch] Error Status Address : [Generic Address Structure]
[098h 0152 001h] Space ID : 00 [SystemMemory]
[099h 0153 001h] Bit Width : 40
[09Ah 0154 001h] Bit Offset : 00
[09Bh 0155 001h] Encoded Access Width : 04 [QWord Access:64]
[09Ch 0156 008h] Address : 0000000139E40008
[0A4h 0164 01Ch] Notify : [Hardware Error Notification Structure]
[0A4h 0164 001h] Notify Type : 07 [GPIO]
[0A5h 0165 001h] Notify Length : 1C
[0A6h 0166 002h] Configuration Write Enable : 0000
[0A8h 0168 004h] PollInterval : 00000000
[0ACh 0172 004h] Vector : 00000000
[0B0h 0176 004h] Polling Threshold Value : 00000000
[0B4h 0180 004h] Polling Threshold Window : 00000000
[0B8h 0184 004h] Error Threshold Value : 00000000
[0BCh 0188 004h] Error Threshold Window : 00000000
[0C0h 0192 004h] Error Status Block Length : 00000400
[0C4h 0196 00Ch] Read Ack Register : [Generic Address Structure]
[0C4h 0196 001h] Space ID : 00 [SystemMemory]
[0C5h 0197 001h] Bit Width : 40
[0C6h 0198 001h] Bit Offset : 00
[0C7h 0199 001h] Encoded Access Width : 04 [QWord Access:64]
[0C8h 0200 008h] Address : 0000000139E40018
[0D0h 0208 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
[0D8h 0216 008h] Read Ack Write : 0000000000000001
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
tests/data/acpi/aarch64/virt/DSDT | Bin 5196 -> 5240 bytes
.../data/acpi/aarch64/virt/DSDT.acpihmatvirt | Bin 5282 -> 5326 bytes
tests/data/acpi/aarch64/virt/DSDT.memhp | Bin 6557 -> 6601 bytes
tests/data/acpi/aarch64/virt/DSDT.pxb | Bin 7679 -> 7723 bytes
tests/data/acpi/aarch64/virt/DSDT.topology | Bin 5398 -> 5442 bytes
tests/data/acpi/aarch64/virt/HEST | Bin 0 -> 224 bytes
tests/qtest/bios-tables-test-allowed-diff.h | 2 --
7 files changed, 2 deletions(-)
diff --git a/tests/data/acpi/aarch64/virt/DSDT b/tests/data/acpi/aarch64/virt/DSDT
index 36d3e5d5a5e47359b6dcb3706f98b4f225677591..a182bd9d7182dccdf63c650d048c58f18505d001 100644
GIT binary patch
delta 109
zcmX@3@k4{lCD<jTLWF^ViDe>}G*h$dM)euOOwJsW4+;nC=*7E+g>V+Q2D|zsED)Gn
zoxsJ!z{S)S5FX^j)c_F?VBivHb9Z%dnXE4&D;?b=31V}^dw9C=2KWUSI2#)?aKwjt
Hx-b9$X;vI^
delta 64
zcmeyNaYlp7CD<jzM}&caNqQoeG*i3NM)euOOit{R4+;lM%f`Egg>V+Q2D|zsED)Gn
UoxsJ!z{S)S5FX?-*+E1W06%jPR{#J2
diff --git a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt
index e6154d0355f84fdcc51387b4db8f9ee63acae4e9..af1f2b0eb0b77a80c5bd74f201d24f71e486627f 100644
GIT binary patch
delta 110
zcmZ3ac}|ndCD<k8oCpI0)4_>c(oCIR8`a+lGdXii78eO-)SH|wBICY5U~+W=mjDBo
yK%2X(iwjpnbdzL2c#soEyoaX?Z-8HbfwO@#14n$Qrwc=LlO#wDl9aJAR0;r(tsHj%
delta 66
zcmX@7xk!`CCD<iokq83=(~XH-(oDVX8`a+lGdZzO78eO-l%1R{A|oB$BpDDM<irv0
W;pxH~;1^)vY~akm5g+R5!T<noi4jWx
diff --git a/tests/data/acpi/aarch64/virt/DSDT.memhp b/tests/data/acpi/aarch64/virt/DSDT.memhp
index 33f011d6b635035a04c0b39ce9b4e219f7ae74b7..10436ec87c4859fb84b3ecb7bba5788f38112e59 100644
GIT binary patch
delta 88
zcmbPheA1Z9CD<k8q$C3algUIbX{MH08`WnBGdXcjJ}4Z_<jXo)OvH<SfxzVI1TFyv
qE`c_8R~MJfaU%At($P(lAPz^oho=i~fM0-tv#~J)M|`NK3j+W#;TF9B
delta 44
zcmX?UJlB}ZCD<iot|S8klg&gfX{L_p8`WnBGdXfiJ}4Z_<ij#qOvGz*p@=Oj039?8
AE&u=k
diff --git a/tests/data/acpi/aarch64/virt/DSDT.pxb b/tests/data/acpi/aarch64/virt/DSDT.pxb
index c0fdc6e9c1396cc2259dc4bc665ba023adcf4c9b..0524b3cbe00bfe552de824dd1090bd00a208c527 100644
GIT binary patch
delta 110
zcmexwz1oJ$CD<iITaJN&sbC_PG*jDyjq2XAOwJsWOJsu?^(LQ?m2qDnFu6K`OMrn(
ypv~RY#f7UOx=Au1JjjV7-ow*{H^48zz}di=fg?WD(}f|rNfM+6Ny^w5Dg^+WYaFrw
delta 66
zcmZ2&^WU1wCD<k8zbpd-Q^!OuX{N5b8`ZsKnVi@sm&gV)%1%BZD<d7<BpDDM<irv0
W;pxH~;1^)vY~akm5g+R5!T<oNArgiF
diff --git a/tests/data/acpi/aarch64/virt/DSDT.topology b/tests/data/acpi/aarch64/virt/DSDT.topology
index 029d03eecc4efddc001e5377e85ac8e831294362..8c0423fe62d6950f9098983d86bfee256d7d003a 100644
GIT binary patch
delta 86
zcmbQHbx4cLCD<jzNtA(s>E%Q&X{O%5jp|7vOwJsWyG4Q-^(NmJk>Ot;Fu6K`OMrn(
opv~RY#bxqO5n1WzCP@&RBi_T)g*U)2z`)tqn1Lfc)YF9l01l28<p2Nx
delta 42
ycmX@4HBF1lCD<iIOq79viGL!OG*hGhM)f2SCMWjE-6Fw^vXk$N$V}!Dl?DLb(h64q
diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..8b0cf87700fa1799c0f8e48610ce4b7ff751dd1f 100644
GIT binary patch
literal 224
zcmeZp4Gww0z`($m;pFe^5v<@85#X$#prF9Wz`y`vgJ>oO1_mw$28RFt85lu)5N2Ru
tU|?_nkxwi^d=43qAPxXkD*#pd?>_{9%>kRuh}CQksCsrH%$C4mHUOJBAprmY
literal 0
HcmV?d00001
diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h
index 46298e38e7b8..dfb8523c8bf4 100644
--- a/tests/qtest/bios-tables-test-allowed-diff.h
+++ b/tests/qtest/bios-tables-test-allowed-diff.h
@@ -1,3 +1 @@
/* List of comma-separated changed AML files to ignore */
-"tests/data/acpi/aarch64/virt/HEST",
-"tests/data/acpi/aarch64/virt/DSDT",
--
2.48.1On Wed, 29 Jan 2025 09:04:18 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> DSDT has gained a GED device to notify errors:
>
> --- a/DSDT.dsl 2025-01-28 09:38:15.155347858 +0100
> +++ b/DSDT.dsl 2025-01-28 09:39:01.684836954 +0100
> @@ -9,9 +9,9 @@
> *
> * Original Table Header:
> * Signature "DSDT"
> - * Length 0x00001516 (5398)
> + * Length 0x00001542 (5442)
> * Revision 0x02
> - * Checksum 0x0F
> + * Checksum 0xE9
> * OEM ID "BOCHS "
> * OEM Table ID "BXPC "
> * OEM Revision 0x00000001 (1)
> @@ -1931,6 +1931,11 @@
> {
> Notify (PWRB, 0x80) // Status Change
> }
> +
> + If (((Local0 & 0x10) == 0x10))
> + {
> + Notify (GEDD, 0x80) // Status Change
> + }
> }
> }
>
> @@ -1939,6 +1944,12 @@
> Name (_HID, "PNP0C0C" /* Power Button Device */) // _HID: Hardware ID
> Name (_UID, Zero) // _UID: Unique ID
> }
> +
> + Device (GEDD)
> + {
> + Name (_HID, "PNP0C33" /* Error Device */) // _HID: Hardware ID
> + Name (_UID, Zero) // _UID: Unique ID
> + }
> }
> }
>
> New HEST table:
diff might be a better here,
you can have it during make check when expected tables haven't been update yet.
prereq for that is to have 'iasl' installed (usually part of acpica-tools package)
and adding V=1 to env vars, something like this:
V=1 QTEST_QEMU_BINARY=./qemu-system-aarch64 ./tests/qtest/bios-tables-test
>
> /*
> * Intel ACPI Component Architecture
> * AML/ASL+ Disassembler version 20240927 (64-bit version)
> * Copyright (c) 2000 - 2023 Intel Corporation
> *
> * Disassembly of hest.dat
> *
> * ACPI Data Table [HEST]
> *
> * Format: [HexOffset DecimalOffset ByteLength] FieldName : FieldValue (in hex)
> */
>
> [000h 0000 004h] Signature : "HEST" [Hardware Error Source Table]
> [004h 0004 004h] Table Length : 000000E0
> [008h 0008 001h] Revision : 01
> [009h 0009 001h] Checksum : 68
> [00Ah 0010 006h] Oem ID : "BOCHS "
> [010h 0016 008h] Oem Table ID : "BXPC "
> [018h 0024 004h] Oem Revision : 00000001
> [01Ch 0028 004h] Asl Compiler ID : "BXPC"
> [020h 0032 004h] Asl Compiler Revision : 00000001
>
> [024h 0036 004h] Error Source Count : 00000002
>
> [028h 0040 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
> [02Ah 0042 002h] Source Id : 0000
> [02Ch 0044 002h] Related Source Id : FFFF
> [02Eh 0046 001h] Reserved : 00
> [02Fh 0047 001h] Enabled : 01
> [030h 0048 004h] Records To Preallocate : 00000001
> [034h 0052 004h] Max Sections Per Record : 00000001
> [038h 0056 004h] Max Raw Data Length : 00000400
>
> [03Ch 0060 00Ch] Error Status Address : [Generic Address Structure]
> [03Ch 0060 001h] Space ID : 00 [SystemMemory]
> [03Dh 0061 001h] Bit Width : 40
> [03Eh 0062 001h] Bit Offset : 00
> [03Fh 0063 001h] Encoded Access Width : 04 [QWord Access:64]
> [040h 0064 008h] Address : 0000000139E40000
>
> [048h 0072 01Ch] Notify : [Hardware Error Notification Structure]
> [048h 0072 001h] Notify Type : 08 [SEA]
> [049h 0073 001h] Notify Length : 1C
> [04Ah 0074 002h] Configuration Write Enable : 0000
> [04Ch 0076 004h] PollInterval : 00000000
> [050h 0080 004h] Vector : 00000000
> [054h 0084 004h] Polling Threshold Value : 00000000
> [058h 0088 004h] Polling Threshold Window : 00000000
> [05Ch 0092 004h] Error Threshold Value : 00000000
> [060h 0096 004h] Error Threshold Window : 00000000
>
> [064h 0100 004h] Error Status Block Length : 00000400
> [068h 0104 00Ch] Read Ack Register : [Generic Address Structure]
> [068h 0104 001h] Space ID : 00 [SystemMemory]
> [069h 0105 001h] Bit Width : 40
> [06Ah 0106 001h] Bit Offset : 00
> [06Bh 0107 001h] Encoded Access Width : 04 [QWord Access:64]
> [06Ch 0108 008h] Address : 0000000139E40010
>
> [074h 0116 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
> [07Ch 0124 008h] Read Ack Write : 0000000000000001
>
> [084h 0132 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
> [086h 0134 002h] Source Id : 0001
> [088h 0136 002h] Related Source Id : FFFF
> [08Ah 0138 001h] Reserved : 00
> [08Bh 0139 001h] Enabled : 01
> [08Ch 0140 004h] Records To Preallocate : 00000001
> [090h 0144 004h] Max Sections Per Record : 00000001
> [094h 0148 004h] Max Raw Data Length : 00000400
>
> [098h 0152 00Ch] Error Status Address : [Generic Address Structure]
> [098h 0152 001h] Space ID : 00 [SystemMemory]
> [099h 0153 001h] Bit Width : 40
> [09Ah 0154 001h] Bit Offset : 00
> [09Bh 0155 001h] Encoded Access Width : 04 [QWord Access:64]
> [09Ch 0156 008h] Address : 0000000139E40008
>
> [0A4h 0164 01Ch] Notify : [Hardware Error Notification Structure]
> [0A4h 0164 001h] Notify Type : 07 [GPIO]
> [0A5h 0165 001h] Notify Length : 1C
> [0A6h 0166 002h] Configuration Write Enable : 0000
> [0A8h 0168 004h] PollInterval : 00000000
> [0ACh 0172 004h] Vector : 00000000
> [0B0h 0176 004h] Polling Threshold Value : 00000000
> [0B4h 0180 004h] Polling Threshold Window : 00000000
> [0B8h 0184 004h] Error Threshold Value : 00000000
> [0BCh 0188 004h] Error Threshold Window : 00000000
>
> [0C0h 0192 004h] Error Status Block Length : 00000400
> [0C4h 0196 00Ch] Read Ack Register : [Generic Address Structure]
> [0C4h 0196 001h] Space ID : 00 [SystemMemory]
> [0C5h 0197 001h] Bit Width : 40
> [0C6h 0198 001h] Bit Offset : 00
> [0C7h 0199 001h] Encoded Access Width : 04 [QWord Access:64]
> [0C8h 0200 008h] Address : 0000000139E40018
>
> [0D0h 0208 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
> [0D8h 0216 008h] Read Ack Write : 0000000000000001
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> ---
> tests/data/acpi/aarch64/virt/DSDT | Bin 5196 -> 5240 bytes
> .../data/acpi/aarch64/virt/DSDT.acpihmatvirt | Bin 5282 -> 5326 bytes
> tests/data/acpi/aarch64/virt/DSDT.memhp | Bin 6557 -> 6601 bytes
> tests/data/acpi/aarch64/virt/DSDT.pxb | Bin 7679 -> 7723 bytes
> tests/data/acpi/aarch64/virt/DSDT.topology | Bin 5398 -> 5442 bytes
> tests/data/acpi/aarch64/virt/HEST | Bin 0 -> 224 bytes
> tests/qtest/bios-tables-test-allowed-diff.h | 2 --
> 7 files changed, 2 deletions(-)
>
> diff --git a/tests/data/acpi/aarch64/virt/DSDT b/tests/data/acpi/aarch64/virt/DSDT
> index 36d3e5d5a5e47359b6dcb3706f98b4f225677591..a182bd9d7182dccdf63c650d048c58f18505d001 100644
> GIT binary patch
> delta 109
> zcmX@3@k4{lCD<jTLWF^ViDe>}G*h$dM)euOOwJsW4+;nC=*7E+g>V+Q2D|zsED)Gn
> zoxsJ!z{S)S5FX^j)c_F?VBivHb9Z%dnXE4&D;?b=31V}^dw9C=2KWUSI2#)?aKwjt
> Hx-b9$X;vI^
>
> delta 64
> zcmeyNaYlp7CD<jzM}&caNqQoeG*i3NM)euOOit{R4+;lM%f`Egg>V+Q2D|zsED)Gn
> UoxsJ!z{S)S5FX?-*+E1W06%jPR{#J2
>
> diff --git a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt
> index e6154d0355f84fdcc51387b4db8f9ee63acae4e9..af1f2b0eb0b77a80c5bd74f201d24f71e486627f 100644
> GIT binary patch
> delta 110
> zcmZ3ac}|ndCD<k8oCpI0)4_>c(oCIR8`a+lGdXii78eO-)SH|wBICY5U~+W=mjDBo
> yK%2X(iwjpnbdzL2c#soEyoaX?Z-8HbfwO@#14n$Qrwc=LlO#wDl9aJAR0;r(tsHj%
>
> delta 66
> zcmX@7xk!`CCD<iokq83=(~XH-(oDVX8`a+lGdZzO78eO-l%1R{A|oB$BpDDM<irv0
> W;pxH~;1^)vY~akm5g+R5!T<noi4jWx
>
> diff --git a/tests/data/acpi/aarch64/virt/DSDT.memhp b/tests/data/acpi/aarch64/virt/DSDT.memhp
> index 33f011d6b635035a04c0b39ce9b4e219f7ae74b7..10436ec87c4859fb84b3ecb7bba5788f38112e59 100644
> GIT binary patch
> delta 88
> zcmbPheA1Z9CD<k8q$C3algUIbX{MH08`WnBGdXcjJ}4Z_<jXo)OvH<SfxzVI1TFyv
> qE`c_8R~MJfaU%At($P(lAPz^oho=i~fM0-tv#~J)M|`NK3j+W#;TF9B
>
> delta 44
> zcmX?UJlB}ZCD<iot|S8klg&gfX{L_p8`WnBGdXfiJ}4Z_<ij#qOvGz*p@=Oj039?8
> AE&u=k
>
> diff --git a/tests/data/acpi/aarch64/virt/DSDT.pxb b/tests/data/acpi/aarch64/virt/DSDT.pxb
> index c0fdc6e9c1396cc2259dc4bc665ba023adcf4c9b..0524b3cbe00bfe552de824dd1090bd00a208c527 100644
> GIT binary patch
> delta 110
> zcmexwz1oJ$CD<iITaJN&sbC_PG*jDyjq2XAOwJsWOJsu?^(LQ?m2qDnFu6K`OMrn(
> ypv~RY#f7UOx=Au1JjjV7-ow*{H^48zz}di=fg?WD(}f|rNfM+6Ny^w5Dg^+WYaFrw
>
> delta 66
> zcmZ2&^WU1wCD<k8zbpd-Q^!OuX{N5b8`ZsKnVi@sm&gV)%1%BZD<d7<BpDDM<irv0
> W;pxH~;1^)vY~akm5g+R5!T<oNArgiF
>
> diff --git a/tests/data/acpi/aarch64/virt/DSDT.topology b/tests/data/acpi/aarch64/virt/DSDT.topology
> index 029d03eecc4efddc001e5377e85ac8e831294362..8c0423fe62d6950f9098983d86bfee256d7d003a 100644
> GIT binary patch
> delta 86
> zcmbQHbx4cLCD<jzNtA(s>E%Q&X{O%5jp|7vOwJsWyG4Q-^(NmJk>Ot;Fu6K`OMrn(
> opv~RY#bxqO5n1WzCP@&RBi_T)g*U)2z`)tqn1Lfc)YF9l01l28<p2Nx
>
> delta 42
> ycmX@4HBF1lCD<iIOq79viGL!OG*hGhM)f2SCMWjE-6Fw^vXk$N$V}!Dl?DLb(h64q
>
> diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST
> index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..8b0cf87700fa1799c0f8e48610ce4b7ff751dd1f 100644
> GIT binary patch
> literal 224
> zcmeZp4Gww0z`($m;pFe^5v<@85#X$#prF9Wz`y`vgJ>oO1_mw$28RFt85lu)5N2Ru
> tU|?_nkxwi^d=43qAPxXkD*#pd?>_{9%>kRuh}CQksCsrH%$C4mHUOJBAprmY
>
> literal 0
> HcmV?d00001
>
> diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h
> index 46298e38e7b8..dfb8523c8bf4 100644
> --- a/tests/qtest/bios-tables-test-allowed-diff.h
> +++ b/tests/qtest/bios-tables-test-allowed-diff.h
> @@ -1,3 +1 @@
> /* List of comma-separated changed AML files to ignore */
> -"tests/data/acpi/aarch64/virt/HEST",
> -"tests/data/acpi/aarch64/virt/DSDT",
Em Wed, 29 Jan 2025 16:29:53 +0100
Igor Mammedov <imammedo@redhat.com> escreveu:
> On Wed, 29 Jan 2025 09:04:18 +0100
> Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
>
> > DSDT has gained a GED device to notify errors:
> >
> > --- a/DSDT.dsl 2025-01-28 09:38:15.155347858 +0100
> > +++ b/DSDT.dsl 2025-01-28 09:39:01.684836954 +0100
> > @@ -9,9 +9,9 @@
> > *
> > * Original Table Header:
> > * Signature "DSDT"
> > - * Length 0x00001516 (5398)
> > + * Length 0x00001542 (5442)
> > * Revision 0x02
> > - * Checksum 0x0F
> > + * Checksum 0xE9
> > * OEM ID "BOCHS "
> > * OEM Table ID "BXPC "
> > * OEM Revision 0x00000001 (1)
> > @@ -1931,6 +1931,11 @@
> > {
> > Notify (PWRB, 0x80) // Status Change
> > }
> > +
> > + If (((Local0 & 0x10) == 0x10))
> > + {
> > + Notify (GEDD, 0x80) // Status Change
> > + }
> > }
> > }
> >
> > @@ -1939,6 +1944,12 @@
> > Name (_HID, "PNP0C0C" /* Power Button Device */) // _HID: Hardware ID
> > Name (_UID, Zero) // _UID: Unique ID
> > }
> > +
> > + Device (GEDD)
> > + {
> > + Name (_HID, "PNP0C33" /* Error Device */) // _HID: Hardware ID
> > + Name (_UID, Zero) // _UID: Unique ID
> > + }
> > }
> > }
> >
> > New HEST table:
>
> diff might be a better here,
> you can have it during make check when expected tables haven't been update yet.
> prereq for that is to have 'iasl' installed (usually part of acpica-tools package)
> and adding V=1 to env vars, something like this:
>
> V=1 QTEST_QEMU_BINARY=./qemu-system-aarch64 ./tests/qtest/bios-tables-test
Hmm... didn't produce any diff here. I added a diff generated by
hand (calling iasl before/after the GED wire up patch and manually
running diff).
Anyway, as HEST table is not checked, I dropped it file from the tests[1],
and placed on patch 12/13 just the DSDT diff.
[1] tests/data/acpi/aarch64/virt/HEST
>
> >
> > /*
> > * Intel ACPI Component Architecture
> > * AML/ASL+ Disassembler version 20240927 (64-bit version)
> > * Copyright (c) 2000 - 2023 Intel Corporation
> > *
> > * Disassembly of hest.dat
> > *
> > * ACPI Data Table [HEST]
> > *
> > * Format: [HexOffset DecimalOffset ByteLength] FieldName : FieldValue (in hex)
> > */
> >
> > [000h 0000 004h] Signature : "HEST" [Hardware Error Source Table]
> > [004h 0004 004h] Table Length : 000000E0
> > [008h 0008 001h] Revision : 01
> > [009h 0009 001h] Checksum : 68
> > [00Ah 0010 006h] Oem ID : "BOCHS "
> > [010h 0016 008h] Oem Table ID : "BXPC "
> > [018h 0024 004h] Oem Revision : 00000001
> > [01Ch 0028 004h] Asl Compiler ID : "BXPC"
> > [020h 0032 004h] Asl Compiler Revision : 00000001
> >
> > [024h 0036 004h] Error Source Count : 00000002
> >
> > [028h 0040 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
> > [02Ah 0042 002h] Source Id : 0000
> > [02Ch 0044 002h] Related Source Id : FFFF
> > [02Eh 0046 001h] Reserved : 00
> > [02Fh 0047 001h] Enabled : 01
> > [030h 0048 004h] Records To Preallocate : 00000001
> > [034h 0052 004h] Max Sections Per Record : 00000001
> > [038h 0056 004h] Max Raw Data Length : 00000400
> >
> > [03Ch 0060 00Ch] Error Status Address : [Generic Address Structure]
> > [03Ch 0060 001h] Space ID : 00 [SystemMemory]
> > [03Dh 0061 001h] Bit Width : 40
> > [03Eh 0062 001h] Bit Offset : 00
> > [03Fh 0063 001h] Encoded Access Width : 04 [QWord Access:64]
> > [040h 0064 008h] Address : 0000000139E40000
> >
> > [048h 0072 01Ch] Notify : [Hardware Error Notification Structure]
> > [048h 0072 001h] Notify Type : 08 [SEA]
> > [049h 0073 001h] Notify Length : 1C
> > [04Ah 0074 002h] Configuration Write Enable : 0000
> > [04Ch 0076 004h] PollInterval : 00000000
> > [050h 0080 004h] Vector : 00000000
> > [054h 0084 004h] Polling Threshold Value : 00000000
> > [058h 0088 004h] Polling Threshold Window : 00000000
> > [05Ch 0092 004h] Error Threshold Value : 00000000
> > [060h 0096 004h] Error Threshold Window : 00000000
> >
> > [064h 0100 004h] Error Status Block Length : 00000400
> > [068h 0104 00Ch] Read Ack Register : [Generic Address Structure]
> > [068h 0104 001h] Space ID : 00 [SystemMemory]
> > [069h 0105 001h] Bit Width : 40
> > [06Ah 0106 001h] Bit Offset : 00
> > [06Bh 0107 001h] Encoded Access Width : 04 [QWord Access:64]
> > [06Ch 0108 008h] Address : 0000000139E40010
> >
> > [074h 0116 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
> > [07Ch 0124 008h] Read Ack Write : 0000000000000001
> >
> > [084h 0132 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
> > [086h 0134 002h] Source Id : 0001
> > [088h 0136 002h] Related Source Id : FFFF
> > [08Ah 0138 001h] Reserved : 00
> > [08Bh 0139 001h] Enabled : 01
> > [08Ch 0140 004h] Records To Preallocate : 00000001
> > [090h 0144 004h] Max Sections Per Record : 00000001
> > [094h 0148 004h] Max Raw Data Length : 00000400
> >
> > [098h 0152 00Ch] Error Status Address : [Generic Address Structure]
> > [098h 0152 001h] Space ID : 00 [SystemMemory]
> > [099h 0153 001h] Bit Width : 40
> > [09Ah 0154 001h] Bit Offset : 00
> > [09Bh 0155 001h] Encoded Access Width : 04 [QWord Access:64]
> > [09Ch 0156 008h] Address : 0000000139E40008
> >
> > [0A4h 0164 01Ch] Notify : [Hardware Error Notification Structure]
> > [0A4h 0164 001h] Notify Type : 07 [GPIO]
> > [0A5h 0165 001h] Notify Length : 1C
> > [0A6h 0166 002h] Configuration Write Enable : 0000
> > [0A8h 0168 004h] PollInterval : 00000000
> > [0ACh 0172 004h] Vector : 00000000
> > [0B0h 0176 004h] Polling Threshold Value : 00000000
> > [0B4h 0180 004h] Polling Threshold Window : 00000000
> > [0B8h 0184 004h] Error Threshold Value : 00000000
> > [0BCh 0188 004h] Error Threshold Window : 00000000
> >
> > [0C0h 0192 004h] Error Status Block Length : 00000400
> > [0C4h 0196 00Ch] Read Ack Register : [Generic Address Structure]
> > [0C4h 0196 001h] Space ID : 00 [SystemMemory]
> > [0C5h 0197 001h] Bit Width : 40
> > [0C6h 0198 001h] Bit Offset : 00
> > [0C7h 0199 001h] Encoded Access Width : 04 [QWord Access:64]
> > [0C8h 0200 008h] Address : 0000000139E40018
> >
> > [0D0h 0208 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
> > [0D8h 0216 008h] Read Ack Write : 0000000000000001
> >
> > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> > ---
> > tests/data/acpi/aarch64/virt/DSDT | Bin 5196 -> 5240 bytes
> > .../data/acpi/aarch64/virt/DSDT.acpihmatvirt | Bin 5282 -> 5326 bytes
> > tests/data/acpi/aarch64/virt/DSDT.memhp | Bin 6557 -> 6601 bytes
> > tests/data/acpi/aarch64/virt/DSDT.pxb | Bin 7679 -> 7723 bytes
> > tests/data/acpi/aarch64/virt/DSDT.topology | Bin 5398 -> 5442 bytes
> > tests/data/acpi/aarch64/virt/HEST | Bin 0 -> 224 bytes
> > tests/qtest/bios-tables-test-allowed-diff.h | 2 --
> > 7 files changed, 2 deletions(-)
> >
> > diff --git a/tests/data/acpi/aarch64/virt/DSDT b/tests/data/acpi/aarch64/virt/DSDT
> > index 36d3e5d5a5e47359b6dcb3706f98b4f225677591..a182bd9d7182dccdf63c650d048c58f18505d001 100644
> > GIT binary patch
> > delta 109
> > zcmX@3@k4{lCD<jTLWF^ViDe>}G*h$dM)euOOwJsW4+;nC=*7E+g>V+Q2D|zsED)Gn
> > zoxsJ!z{S)S5FX^j)c_F?VBivHb9Z%dnXE4&D;?b=31V}^dw9C=2KWUSI2#)?aKwjt
> > Hx-b9$X;vI^
> >
> > delta 64
> > zcmeyNaYlp7CD<jzM}&caNqQoeG*i3NM)euOOit{R4+;lM%f`Egg>V+Q2D|zsED)Gn
> > UoxsJ!z{S)S5FX?-*+E1W06%jPR{#J2
> >
> > diff --git a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt
> > index e6154d0355f84fdcc51387b4db8f9ee63acae4e9..af1f2b0eb0b77a80c5bd74f201d24f71e486627f 100644
> > GIT binary patch
> > delta 110
> > zcmZ3ac}|ndCD<k8oCpI0)4_>c(oCIR8`a+lGdXii78eO-)SH|wBICY5U~+W=mjDBo
> > yK%2X(iwjpnbdzL2c#soEyoaX?Z-8HbfwO@#14n$Qrwc=LlO#wDl9aJAR0;r(tsHj%
> >
> > delta 66
> > zcmX@7xk!`CCD<iokq83=(~XH-(oDVX8`a+lGdZzO78eO-l%1R{A|oB$BpDDM<irv0
> > W;pxH~;1^)vY~akm5g+R5!T<noi4jWx
> >
> > diff --git a/tests/data/acpi/aarch64/virt/DSDT.memhp b/tests/data/acpi/aarch64/virt/DSDT.memhp
> > index 33f011d6b635035a04c0b39ce9b4e219f7ae74b7..10436ec87c4859fb84b3ecb7bba5788f38112e59 100644
> > GIT binary patch
> > delta 88
> > zcmbPheA1Z9CD<k8q$C3algUIbX{MH08`WnBGdXcjJ}4Z_<jXo)OvH<SfxzVI1TFyv
> > qE`c_8R~MJfaU%At($P(lAPz^oho=i~fM0-tv#~J)M|`NK3j+W#;TF9B
> >
> > delta 44
> > zcmX?UJlB}ZCD<iot|S8klg&gfX{L_p8`WnBGdXfiJ}4Z_<ij#qOvGz*p@=Oj039?8
> > AE&u=k
> >
> > diff --git a/tests/data/acpi/aarch64/virt/DSDT.pxb b/tests/data/acpi/aarch64/virt/DSDT.pxb
> > index c0fdc6e9c1396cc2259dc4bc665ba023adcf4c9b..0524b3cbe00bfe552de824dd1090bd00a208c527 100644
> > GIT binary patch
> > delta 110
> > zcmexwz1oJ$CD<iITaJN&sbC_PG*jDyjq2XAOwJsWOJsu?^(LQ?m2qDnFu6K`OMrn(
> > ypv~RY#f7UOx=Au1JjjV7-ow*{H^48zz}di=fg?WD(}f|rNfM+6Ny^w5Dg^+WYaFrw
> >
> > delta 66
> > zcmZ2&^WU1wCD<k8zbpd-Q^!OuX{N5b8`ZsKnVi@sm&gV)%1%BZD<d7<BpDDM<irv0
> > W;pxH~;1^)vY~akm5g+R5!T<oNArgiF
> >
> > diff --git a/tests/data/acpi/aarch64/virt/DSDT.topology b/tests/data/acpi/aarch64/virt/DSDT.topology
> > index 029d03eecc4efddc001e5377e85ac8e831294362..8c0423fe62d6950f9098983d86bfee256d7d003a 100644
> > GIT binary patch
> > delta 86
> > zcmbQHbx4cLCD<jzNtA(s>E%Q&X{O%5jp|7vOwJsWyG4Q-^(NmJk>Ot;Fu6K`OMrn(
> > opv~RY#bxqO5n1WzCP@&RBi_T)g*U)2z`)tqn1Lfc)YF9l01l28<p2Nx
> >
> > delta 42
> > ycmX@4HBF1lCD<iIOq79viGL!OG*hGhM)f2SCMWjE-6Fw^vXk$N$V}!Dl?DLb(h64q
> >
> > diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST
> > index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..8b0cf87700fa1799c0f8e48610ce4b7ff751dd1f 100644
> > GIT binary patch
> > literal 224
> > zcmeZp4Gww0z`($m;pFe^5v<@85#X$#prF9Wz`y`vgJ>oO1_mw$28RFt85lu)5N2Ru
> > tU|?_nkxwi^d=43qAPxXkD*#pd?>_{9%>kRuh}CQksCsrH%$C4mHUOJBAprmY
> >
> > literal 0
> > HcmV?d00001
> >
> > diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h
> > index 46298e38e7b8..dfb8523c8bf4 100644
> > --- a/tests/qtest/bios-tables-test-allowed-diff.h
> > +++ b/tests/qtest/bios-tables-test-allowed-diff.h
> > @@ -1,3 +1 @@
> > /* List of comma-separated changed AML files to ignore */
> > -"tests/data/acpi/aarch64/virt/HEST",
> > -"tests/data/acpi/aarch64/virt/DSDT",
>
Thanks,
Mauro
On Fri, 31 Jan 2025 16:49:19 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> Em Wed, 29 Jan 2025 16:29:53 +0100
> Igor Mammedov <imammedo@redhat.com> escreveu:
>
> > On Wed, 29 Jan 2025 09:04:18 +0100
> > Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> >
> > > DSDT has gained a GED device to notify errors:
> > >
> > > --- a/DSDT.dsl 2025-01-28 09:38:15.155347858 +0100
> > > +++ b/DSDT.dsl 2025-01-28 09:39:01.684836954 +0100
> > > @@ -9,9 +9,9 @@
> > > *
> > > * Original Table Header:
> > > * Signature "DSDT"
> > > - * Length 0x00001516 (5398)
> > > + * Length 0x00001542 (5442)
> > > * Revision 0x02
> > > - * Checksum 0x0F
> > > + * Checksum 0xE9
> > > * OEM ID "BOCHS "
> > > * OEM Table ID "BXPC "
> > > * OEM Revision 0x00000001 (1)
> > > @@ -1931,6 +1931,11 @@
> > > {
> > > Notify (PWRB, 0x80) // Status Change
> > > }
> > > +
> > > + If (((Local0 & 0x10) == 0x10))
> > > + {
> > > + Notify (GEDD, 0x80) // Status Change
> > > + }
> > > }
> > > }
> > >
> > > @@ -1939,6 +1944,12 @@
> > > Name (_HID, "PNP0C0C" /* Power Button Device */) // _HID: Hardware ID
> > > Name (_UID, Zero) // _UID: Unique ID
> > > }
> > > +
> > > + Device (GEDD)
> > > + {
> > > + Name (_HID, "PNP0C33" /* Error Device */) // _HID: Hardware ID
> > > + Name (_UID, Zero) // _UID: Unique ID
> > > + }
> > > }
> > > }
> > >
> > > New HEST table:
> >
> > diff might be a better here,
> > you can have it during make check when expected tables haven't been update yet.
> > prereq for that is to have 'iasl' installed (usually part of acpica-tools package)
> > and adding V=1 to env vars, something like this:
> >
> > V=1 QTEST_QEMU_BINARY=./qemu-system-aarch64 ./tests/qtest/bios-tables-test
>
> Hmm... didn't produce any diff here. I added a diff generated by
> hand (calling iasl before/after the GED wire up patch and manually
> running diff).
that can happen due to stale files which rebuild-expected-aml.sh creates
(I'd check 'git status' output).
And well, rerun configure after iasl has been installed.
> Anyway, as HEST table is not checked, I dropped it file from the tests[1],
> and placed on patch 12/13 just the DSDT diff.
if it's not checked, then it would be better to add it before changes,
and then update here (with new layout)
>
> [1] tests/data/acpi/aarch64/virt/HEST
>
> >
> > >
> > > /*
> > > * Intel ACPI Component Architecture
> > > * AML/ASL+ Disassembler version 20240927 (64-bit version)
> > > * Copyright (c) 2000 - 2023 Intel Corporation
> > > *
> > > * Disassembly of hest.dat
> > > *
> > > * ACPI Data Table [HEST]
> > > *
> > > * Format: [HexOffset DecimalOffset ByteLength] FieldName : FieldValue (in hex)
> > > */
> > >
> > > [000h 0000 004h] Signature : "HEST" [Hardware Error Source Table]
> > > [004h 0004 004h] Table Length : 000000E0
> > > [008h 0008 001h] Revision : 01
> > > [009h 0009 001h] Checksum : 68
> > > [00Ah 0010 006h] Oem ID : "BOCHS "
> > > [010h 0016 008h] Oem Table ID : "BXPC "
> > > [018h 0024 004h] Oem Revision : 00000001
> > > [01Ch 0028 004h] Asl Compiler ID : "BXPC"
> > > [020h 0032 004h] Asl Compiler Revision : 00000001
> > >
> > > [024h 0036 004h] Error Source Count : 00000002
> > >
> > > [028h 0040 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
> > > [02Ah 0042 002h] Source Id : 0000
> > > [02Ch 0044 002h] Related Source Id : FFFF
> > > [02Eh 0046 001h] Reserved : 00
> > > [02Fh 0047 001h] Enabled : 01
> > > [030h 0048 004h] Records To Preallocate : 00000001
> > > [034h 0052 004h] Max Sections Per Record : 00000001
> > > [038h 0056 004h] Max Raw Data Length : 00000400
> > >
> > > [03Ch 0060 00Ch] Error Status Address : [Generic Address Structure]
> > > [03Ch 0060 001h] Space ID : 00 [SystemMemory]
> > > [03Dh 0061 001h] Bit Width : 40
> > > [03Eh 0062 001h] Bit Offset : 00
> > > [03Fh 0063 001h] Encoded Access Width : 04 [QWord Access:64]
> > > [040h 0064 008h] Address : 0000000139E40000
> > >
> > > [048h 0072 01Ch] Notify : [Hardware Error Notification Structure]
> > > [048h 0072 001h] Notify Type : 08 [SEA]
> > > [049h 0073 001h] Notify Length : 1C
> > > [04Ah 0074 002h] Configuration Write Enable : 0000
> > > [04Ch 0076 004h] PollInterval : 00000000
> > > [050h 0080 004h] Vector : 00000000
> > > [054h 0084 004h] Polling Threshold Value : 00000000
> > > [058h 0088 004h] Polling Threshold Window : 00000000
> > > [05Ch 0092 004h] Error Threshold Value : 00000000
> > > [060h 0096 004h] Error Threshold Window : 00000000
> > >
> > > [064h 0100 004h] Error Status Block Length : 00000400
> > > [068h 0104 00Ch] Read Ack Register : [Generic Address Structure]
> > > [068h 0104 001h] Space ID : 00 [SystemMemory]
> > > [069h 0105 001h] Bit Width : 40
> > > [06Ah 0106 001h] Bit Offset : 00
> > > [06Bh 0107 001h] Encoded Access Width : 04 [QWord Access:64]
> > > [06Ch 0108 008h] Address : 0000000139E40010
> > >
> > > [074h 0116 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
> > > [07Ch 0124 008h] Read Ack Write : 0000000000000001
> > >
> > > [084h 0132 002h] Subtable Type : 000A [Generic Hardware Error Source V2]
> > > [086h 0134 002h] Source Id : 0001
> > > [088h 0136 002h] Related Source Id : FFFF
> > > [08Ah 0138 001h] Reserved : 00
> > > [08Bh 0139 001h] Enabled : 01
> > > [08Ch 0140 004h] Records To Preallocate : 00000001
> > > [090h 0144 004h] Max Sections Per Record : 00000001
> > > [094h 0148 004h] Max Raw Data Length : 00000400
> > >
> > > [098h 0152 00Ch] Error Status Address : [Generic Address Structure]
> > > [098h 0152 001h] Space ID : 00 [SystemMemory]
> > > [099h 0153 001h] Bit Width : 40
> > > [09Ah 0154 001h] Bit Offset : 00
> > > [09Bh 0155 001h] Encoded Access Width : 04 [QWord Access:64]
> > > [09Ch 0156 008h] Address : 0000000139E40008
> > >
> > > [0A4h 0164 01Ch] Notify : [Hardware Error Notification Structure]
> > > [0A4h 0164 001h] Notify Type : 07 [GPIO]
> > > [0A5h 0165 001h] Notify Length : 1C
> > > [0A6h 0166 002h] Configuration Write Enable : 0000
> > > [0A8h 0168 004h] PollInterval : 00000000
> > > [0ACh 0172 004h] Vector : 00000000
> > > [0B0h 0176 004h] Polling Threshold Value : 00000000
> > > [0B4h 0180 004h] Polling Threshold Window : 00000000
> > > [0B8h 0184 004h] Error Threshold Value : 00000000
> > > [0BCh 0188 004h] Error Threshold Window : 00000000
> > >
> > > [0C0h 0192 004h] Error Status Block Length : 00000400
> > > [0C4h 0196 00Ch] Read Ack Register : [Generic Address Structure]
> > > [0C4h 0196 001h] Space ID : 00 [SystemMemory]
> > > [0C5h 0197 001h] Bit Width : 40
> > > [0C6h 0198 001h] Bit Offset : 00
> > > [0C7h 0199 001h] Encoded Access Width : 04 [QWord Access:64]
> > > [0C8h 0200 008h] Address : 0000000139E40018
> > >
> > > [0D0h 0208 008h] Read Ack Preserve : FFFFFFFFFFFFFFFE
> > > [0D8h 0216 008h] Read Ack Write : 0000000000000001
> > >
> > > Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> > > ---
> > > tests/data/acpi/aarch64/virt/DSDT | Bin 5196 -> 5240 bytes
> > > .../data/acpi/aarch64/virt/DSDT.acpihmatvirt | Bin 5282 -> 5326 bytes
> > > tests/data/acpi/aarch64/virt/DSDT.memhp | Bin 6557 -> 6601 bytes
> > > tests/data/acpi/aarch64/virt/DSDT.pxb | Bin 7679 -> 7723 bytes
> > > tests/data/acpi/aarch64/virt/DSDT.topology | Bin 5398 -> 5442 bytes
> > > tests/data/acpi/aarch64/virt/HEST | Bin 0 -> 224 bytes
> > > tests/qtest/bios-tables-test-allowed-diff.h | 2 --
> > > 7 files changed, 2 deletions(-)
> > >
> > > diff --git a/tests/data/acpi/aarch64/virt/DSDT b/tests/data/acpi/aarch64/virt/DSDT
> > > index 36d3e5d5a5e47359b6dcb3706f98b4f225677591..a182bd9d7182dccdf63c650d048c58f18505d001 100644
> > > GIT binary patch
> > > delta 109
> > > zcmX@3@k4{lCD<jTLWF^ViDe>}G*h$dM)euOOwJsW4+;nC=*7E+g>V+Q2D|zsED)Gn
> > > zoxsJ!z{S)S5FX^j)c_F?VBivHb9Z%dnXE4&D;?b=31V}^dw9C=2KWUSI2#)?aKwjt
> > > Hx-b9$X;vI^
> > >
> > > delta 64
> > > zcmeyNaYlp7CD<jzM}&caNqQoeG*i3NM)euOOit{R4+;lM%f`Egg>V+Q2D|zsED)Gn
> > > UoxsJ!z{S)S5FX?-*+E1W06%jPR{#J2
> > >
> > > diff --git a/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt b/tests/data/acpi/aarch64/virt/DSDT.acpihmatvirt
> > > index e6154d0355f84fdcc51387b4db8f9ee63acae4e9..af1f2b0eb0b77a80c5bd74f201d24f71e486627f 100644
> > > GIT binary patch
> > > delta 110
> > > zcmZ3ac}|ndCD<k8oCpI0)4_>c(oCIR8`a+lGdXii78eO-)SH|wBICY5U~+W=mjDBo
> > > yK%2X(iwjpnbdzL2c#soEyoaX?Z-8HbfwO@#14n$Qrwc=LlO#wDl9aJAR0;r(tsHj%
> > >
> > > delta 66
> > > zcmX@7xk!`CCD<iokq83=(~XH-(oDVX8`a+lGdZzO78eO-l%1R{A|oB$BpDDM<irv0
> > > W;pxH~;1^)vY~akm5g+R5!T<noi4jWx
> > >
> > > diff --git a/tests/data/acpi/aarch64/virt/DSDT.memhp b/tests/data/acpi/aarch64/virt/DSDT.memhp
> > > index 33f011d6b635035a04c0b39ce9b4e219f7ae74b7..10436ec87c4859fb84b3ecb7bba5788f38112e59 100644
> > > GIT binary patch
> > > delta 88
> > > zcmbPheA1Z9CD<k8q$C3algUIbX{MH08`WnBGdXcjJ}4Z_<jXo)OvH<SfxzVI1TFyv
> > > qE`c_8R~MJfaU%At($P(lAPz^oho=i~fM0-tv#~J)M|`NK3j+W#;TF9B
> > >
> > > delta 44
> > > zcmX?UJlB}ZCD<iot|S8klg&gfX{L_p8`WnBGdXfiJ}4Z_<ij#qOvGz*p@=Oj039?8
> > > AE&u=k
> > >
> > > diff --git a/tests/data/acpi/aarch64/virt/DSDT.pxb b/tests/data/acpi/aarch64/virt/DSDT.pxb
> > > index c0fdc6e9c1396cc2259dc4bc665ba023adcf4c9b..0524b3cbe00bfe552de824dd1090bd00a208c527 100644
> > > GIT binary patch
> > > delta 110
> > > zcmexwz1oJ$CD<iITaJN&sbC_PG*jDyjq2XAOwJsWOJsu?^(LQ?m2qDnFu6K`OMrn(
> > > ypv~RY#f7UOx=Au1JjjV7-ow*{H^48zz}di=fg?WD(}f|rNfM+6Ny^w5Dg^+WYaFrw
> > >
> > > delta 66
> > > zcmZ2&^WU1wCD<k8zbpd-Q^!OuX{N5b8`ZsKnVi@sm&gV)%1%BZD<d7<BpDDM<irv0
> > > W;pxH~;1^)vY~akm5g+R5!T<oNArgiF
> > >
> > > diff --git a/tests/data/acpi/aarch64/virt/DSDT.topology b/tests/data/acpi/aarch64/virt/DSDT.topology
> > > index 029d03eecc4efddc001e5377e85ac8e831294362..8c0423fe62d6950f9098983d86bfee256d7d003a 100644
> > > GIT binary patch
> > > delta 86
> > > zcmbQHbx4cLCD<jzNtA(s>E%Q&X{O%5jp|7vOwJsWyG4Q-^(NmJk>Ot;Fu6K`OMrn(
> > > opv~RY#bxqO5n1WzCP@&RBi_T)g*U)2z`)tqn1Lfc)YF9l01l28<p2Nx
> > >
> > > delta 42
> > > ycmX@4HBF1lCD<iIOq79viGL!OG*hGhM)f2SCMWjE-6Fw^vXk$N$V}!Dl?DLb(h64q
> > >
> > > diff --git a/tests/data/acpi/aarch64/virt/HEST b/tests/data/acpi/aarch64/virt/HEST
> > > index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..8b0cf87700fa1799c0f8e48610ce4b7ff751dd1f 100644
> > > GIT binary patch
> > > literal 224
> > > zcmeZp4Gww0z`($m;pFe^5v<@85#X$#prF9Wz`y`vgJ>oO1_mw$28RFt85lu)5N2Ru
> > > tU|?_nkxwi^d=43qAPxXkD*#pd?>_{9%>kRuh}CQksCsrH%$C4mHUOJBAprmY
> > >
> > > literal 0
> > > HcmV?d00001
> > >
> > > diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h
> > > index 46298e38e7b8..dfb8523c8bf4 100644
> > > --- a/tests/qtest/bios-tables-test-allowed-diff.h
> > > +++ b/tests/qtest/bios-tables-test-allowed-diff.h
> > > @@ -1,3 +1 @@
> > > /* List of comma-separated changed AML files to ignore */
> > > -"tests/data/acpi/aarch64/virt/HEST",
> > > -"tests/data/acpi/aarch64/virt/DSDT",
> >
>
>
>
> Thanks,
> Mauro
>
Using the QMP GHESv2 API requires preparing a raw data array
containing a CPER record.
Add a helper script with subcommands to prepare such data.
Currently, only ARM Processor error CPER record is supported.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
MAINTAINERS | 3 +
scripts/arm_processor_error.py | 377 ++++++++++++++++++
scripts/ghes_inject.py | 51 +++
scripts/qmp_helper.py | 702 +++++++++++++++++++++++++++++++++
4 files changed, 1133 insertions(+)
create mode 100644 scripts/arm_processor_error.py
create mode 100755 scripts/ghes_inject.py
create mode 100644 scripts/qmp_helper.py
diff --git a/MAINTAINERS b/MAINTAINERS
index 8e1f662fa0e0..99a9ba5c2ace 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2081,6 +2081,9 @@ S: Maintained
F: hw/arm/ghes_cper.c
F: hw/acpi/ghes_cper_stub.c
F: qapi/acpi-hest.json
+F: scripts/ghes_inject.py
+F: scripts/arm_processor_error.py
+F: scripts/qmp_helper.py
ppc4xx
L: qemu-ppc@nongnu.org
diff --git a/scripts/arm_processor_error.py b/scripts/arm_processor_error.py
new file mode 100644
index 000000000000..4ac04ab08299
--- /dev/null
+++ b/scripts/arm_processor_error.py
@@ -0,0 +1,377 @@
+#!/usr/bin/env python3
+#
+# pylint: disable=C0301,C0114,R0903,R0912,R0913,R0914,R0915,W0511
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+
+# TODO: current implementation has dummy defaults.
+#
+# For a better implementation, a QMP addition/call is needed to
+# retrieve some data for ARM Processor Error injection:
+#
+# - ARM registers: power_state, mpidr.
+
+import argparse
+import re
+
+from qmp_helper import qmp, util, cper_guid
+
+class ArmProcessorEinj:
+ """
+ Implements ARM Processor Error injection via GHES
+ """
+
+ DESC = """
+ Generates an ARM processor error CPER, compatible with
+ UEFI 2.9A Errata.
+ """
+
+ ACPI_GHES_ARM_CPER_LENGTH = 40
+ ACPI_GHES_ARM_CPER_PEI_LENGTH = 32
+
+ # Context types
+ CONTEXT_AARCH32_EL1 = 1
+ CONTEXT_AARCH64_EL1 = 5
+ CONTEXT_MISC_REG = 8
+
+ def __init__(self, subparsers):
+ """Initialize the error injection class and add subparser"""
+
+ # Valid choice values
+ self.arm_valid_bits = {
+ "mpidr": util.bit(0),
+ "affinity": util.bit(1),
+ "running": util.bit(2),
+ "vendor": util.bit(3),
+ }
+
+ self.pei_flags = {
+ "first": util.bit(0),
+ "last": util.bit(1),
+ "propagated": util.bit(2),
+ "overflow": util.bit(3),
+ }
+
+ self.pei_error_types = {
+ "cache": util.bit(1),
+ "tlb": util.bit(2),
+ "bus": util.bit(3),
+ "micro-arch": util.bit(4),
+ }
+
+ self.pei_valid_bits = {
+ "multiple-error": util.bit(0),
+ "flags": util.bit(1),
+ "error-info": util.bit(2),
+ "virt-addr": util.bit(3),
+ "phy-addr": util.bit(4),
+ }
+
+ self.data = bytearray()
+
+ parser = subparsers.add_parser("arm", description=self.DESC)
+
+ arm_valid_bits = ",".join(self.arm_valid_bits.keys())
+ flags = ",".join(self.pei_flags.keys())
+ error_types = ",".join(self.pei_error_types.keys())
+ pei_valid_bits = ",".join(self.pei_valid_bits.keys())
+
+ # UEFI N.16 ARM Validation bits
+ g_arm = parser.add_argument_group("ARM processor")
+ g_arm.add_argument("--arm", "--arm-valid",
+ help=f"ARM valid bits: {arm_valid_bits}")
+ g_arm.add_argument("-a", "--affinity", "--level", "--affinity-level",
+ type=lambda x: int(x, 0),
+ help="Affinity level (when multiple levels apply)")
+ g_arm.add_argument("-l", "--mpidr", type=lambda x: int(x, 0),
+ help="Multiprocessor Affinity Register")
+ g_arm.add_argument("-i", "--midr", type=lambda x: int(x, 0),
+ help="Main ID Register")
+ g_arm.add_argument("-r", "--running",
+ action=argparse.BooleanOptionalAction,
+ default=None,
+ help="Indicates if the processor is running or not")
+ g_arm.add_argument("--psci", "--psci-state",
+ type=lambda x: int(x, 0),
+ help="Power State Coordination Interface - PSCI state")
+
+ # TODO: Add vendor-specific support
+
+ # UEFI N.17 bitmaps (type and flags)
+ g_pei = parser.add_argument_group("ARM Processor Error Info (PEI)")
+ g_pei.add_argument("-t", "--type", nargs="+",
+ help=f"one or more error types: {error_types}")
+ g_pei.add_argument("-f", "--flags", nargs="*",
+ help=f"zero or more error flags: {flags}")
+ g_pei.add_argument("-V", "--pei-valid", "--error-valid", nargs="*",
+ help=f"zero or more PEI valid bits: {pei_valid_bits}")
+
+ # UEFI N.17 Integer values
+ g_pei.add_argument("-m", "--multiple-error", nargs="+",
+ help="Number of errors: 0: Single error, 1: Multiple errors, 2-65535: Error count if known")
+ g_pei.add_argument("-e", "--error-info", nargs="+",
+ help="Error information (UEFI 2.10 tables N.18 to N.20)")
+ g_pei.add_argument("-p", "--physical-address", nargs="+",
+ help="Physical address")
+ g_pei.add_argument("-v", "--virtual-address", nargs="+",
+ help="Virtual address")
+
+ # UEFI N.21 Context
+ g_ctx = parser.add_argument_group("Processor Context")
+ g_ctx.add_argument("--ctx-type", "--context-type", nargs="*",
+ help="Type of the context (0=ARM32 GPR, 5=ARM64 EL1, other values supported)")
+ g_ctx.add_argument("--ctx-size", "--context-size", nargs="*",
+ help="Minimal size of the context")
+ g_ctx.add_argument("--ctx-array", "--context-array", nargs="*",
+ help="Comma-separated arrays for each context")
+
+ # Vendor-specific data
+ g_vendor = parser.add_argument_group("Vendor-specific data")
+ g_vendor.add_argument("--vendor", "--vendor-specific", nargs="+",
+ help="Vendor-specific byte arrays of data")
+
+ # Add arguments for Generic Error Data
+ qmp.argparse(parser)
+
+ parser.set_defaults(func=self.send_cper)
+
+ def send_cper(self, args):
+ """Parse subcommand arguments and send a CPER via QMP"""
+
+ qmp_cmd = qmp(args.host, args.port, args.debug)
+
+ # Handle Generic Error Data arguments if any
+ qmp_cmd.set_args(args)
+
+ is_cpu_type = re.compile(r"^([\w+]+\-)?arm\-cpu$")
+ cpus = qmp_cmd.search_qom("/machine/unattached/device",
+ "type", is_cpu_type)
+
+ cper = {}
+ pei = {}
+ ctx = {}
+ vendor = {}
+
+ arg = vars(args)
+
+ # Handle global parameters
+ if args.arm:
+ arm_valid_init = False
+ cper["valid"] = util.get_choice(name="valid",
+ value=args.arm,
+ choices=self.arm_valid_bits,
+ suffixes=["-error", "-err"])
+ else:
+ cper["valid"] = 0
+ arm_valid_init = True
+
+ if "running" in arg:
+ if args.running:
+ cper["running-state"] = util.bit(0)
+ else:
+ cper["running-state"] = 0
+ else:
+ cper["running-state"] = 0
+
+ if arm_valid_init:
+ if args.affinity:
+ cper["valid"] |= self.arm_valid_bits["affinity"]
+
+ if args.mpidr:
+ cper["valid"] |= self.arm_valid_bits["mpidr"]
+
+ if "running-state" in cper:
+ cper["valid"] |= self.arm_valid_bits["running"]
+
+ if args.psci:
+ cper["valid"] |= self.arm_valid_bits["running"]
+
+ # Handle PEI
+ if not args.type:
+ args.type = ["cache-error"]
+
+ util.get_mult_choices(
+ pei,
+ name="valid",
+ values=args.pei_valid,
+ choices=self.pei_valid_bits,
+ suffixes=["-valid", "--addr"],
+ )
+ util.get_mult_choices(
+ pei,
+ name="type",
+ values=args.type,
+ choices=self.pei_error_types,
+ suffixes=["-error", "-err"],
+ )
+ util.get_mult_choices(
+ pei,
+ name="flags",
+ values=args.flags,
+ choices=self.pei_flags,
+ suffixes=["-error", "-cap"],
+ )
+ util.get_mult_int(pei, "error-info", args.error_info)
+ util.get_mult_int(pei, "multiple-error", args.multiple_error)
+ util.get_mult_int(pei, "phy-addr", args.physical_address)
+ util.get_mult_int(pei, "virt-addr", args.virtual_address)
+
+ # Handle context
+ util.get_mult_int(ctx, "type", args.ctx_type, allow_zero=True)
+ util.get_mult_int(ctx, "minimal-size", args.ctx_size, allow_zero=True)
+ util.get_mult_array(ctx, "register", args.ctx_array, allow_zero=True)
+
+ util.get_mult_array(vendor, "bytes", args.vendor, max_val=255)
+
+ # Store PEI
+ pei_data = bytearray()
+ default_flags = self.pei_flags["first"]
+ default_flags |= self.pei_flags["last"]
+
+ error_info_num = 0
+
+ for i, p in pei.items(): # pylint: disable=W0612
+ error_info_num += 1
+
+ # UEFI 2.10 doesn't define how to encode error information
+ # when multiple types are raised. So, provide a default only
+ # if a single type is there
+ if "error-info" not in p:
+ if p["type"] == util.bit(1):
+ p["error-info"] = 0x0091000F
+ if p["type"] == util.bit(2):
+ p["error-info"] = 0x0054007F
+ if p["type"] == util.bit(3):
+ p["error-info"] = 0x80D6460FFF
+ if p["type"] == util.bit(4):
+ p["error-info"] = 0x78DA03FF
+
+ if "valid" not in p:
+ p["valid"] = 0
+ if "multiple-error" in p:
+ p["valid"] |= self.pei_valid_bits["multiple-error"]
+
+ if "flags" in p:
+ p["valid"] |= self.pei_valid_bits["flags"]
+
+ if "error-info" in p:
+ p["valid"] |= self.pei_valid_bits["error-info"]
+
+ if "phy-addr" in p:
+ p["valid"] |= self.pei_valid_bits["phy-addr"]
+
+ if "virt-addr" in p:
+ p["valid"] |= self.pei_valid_bits["virt-addr"]
+
+ # Version
+ util.data_add(pei_data, 0, 1)
+
+ util.data_add(pei_data,
+ self.ACPI_GHES_ARM_CPER_PEI_LENGTH, 1)
+
+ util.data_add(pei_data, p["valid"], 2)
+ util.data_add(pei_data, p["type"], 1)
+ util.data_add(pei_data, p.get("multiple-error", 1), 2)
+ util.data_add(pei_data, p.get("flags", default_flags), 1)
+ util.data_add(pei_data, p.get("error-info", 0), 8)
+ util.data_add(pei_data, p.get("virt-addr", 0xDEADBEEF), 8)
+ util.data_add(pei_data, p.get("phy-addr", 0xABBA0BAD), 8)
+
+ # Store Context
+ ctx_data = bytearray()
+ context_info_num = 0
+
+ if ctx:
+ ret = qmp_cmd.send_cmd("query-target", may_open=True)
+
+ default_ctx = self.CONTEXT_MISC_REG
+
+ if "arch" in ret:
+ if ret["arch"] == "aarch64":
+ default_ctx = self.CONTEXT_AARCH64_EL1
+ elif ret["arch"] == "arm":
+ default_ctx = self.CONTEXT_AARCH32_EL1
+
+ for k in sorted(ctx.keys()):
+ context_info_num += 1
+
+ if "type" not in ctx[k]:
+ ctx[k]["type"] = default_ctx
+
+ if "register" not in ctx[k]:
+ ctx[k]["register"] = []
+
+ reg_size = len(ctx[k]["register"])
+ size = 0
+
+ if "minimal-size" in ctx:
+ size = ctx[k]["minimal-size"]
+
+ size = max(size, reg_size)
+
+ size = (size + 1) % 0xFFFE
+
+ # Version
+ util.data_add(ctx_data, 0, 2)
+
+ util.data_add(ctx_data, ctx[k]["type"], 2)
+
+ util.data_add(ctx_data, 8 * size, 4)
+
+ for r in ctx[k]["register"]:
+ util.data_add(ctx_data, r, 8)
+
+ for i in range(reg_size, size): # pylint: disable=W0612
+ util.data_add(ctx_data, 0, 8)
+
+ # Vendor-specific bytes are not grouped
+ vendor_data = bytearray()
+ if vendor:
+ for k in sorted(vendor.keys()):
+ for b in vendor[k]["bytes"]:
+ util.data_add(vendor_data, b, 1)
+
+ # Encode ARM Processor Error
+ data = bytearray()
+
+ util.data_add(data, cper["valid"], 4)
+
+ util.data_add(data, error_info_num, 2)
+ util.data_add(data, context_info_num, 2)
+
+ # Calculate the length of the CPER data
+ cper_length = self.ACPI_GHES_ARM_CPER_LENGTH
+ cper_length += len(pei_data)
+ cper_length += len(vendor_data)
+ cper_length += len(ctx_data)
+ util.data_add(data, cper_length, 4)
+
+ util.data_add(data, arg.get("affinity-level", 0), 1)
+
+ # Reserved
+ util.data_add(data, 0, 3)
+
+ if "midr-el1" not in arg:
+ if cpus:
+ cmd_arg = {
+ 'path': cpus[0],
+ 'property': "midr"
+ }
+ ret = qmp_cmd.send_cmd("qom-get", cmd_arg, may_open=True)
+ if isinstance(ret, int):
+ arg["midr-el1"] = ret
+
+ util.data_add(data, arg.get("mpidr-el1", 0), 8)
+ util.data_add(data, arg.get("midr-el1", 0), 8)
+ util.data_add(data, cper["running-state"], 4)
+ util.data_add(data, arg.get("psci-state", 0), 4)
+
+ # Add PEI
+ data.extend(pei_data)
+ data.extend(ctx_data)
+ data.extend(vendor_data)
+
+ self.data = data
+
+ qmp_cmd.send_cper(cper_guid.CPER_PROC_ARM, self.data)
diff --git a/scripts/ghes_inject.py b/scripts/ghes_inject.py
new file mode 100755
index 000000000000..5d72bc7f09e1
--- /dev/null
+++ b/scripts/ghes_inject.py
@@ -0,0 +1,51 @@
+#!/usr/bin/env python3
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+
+"""
+Handle ACPI GHESv2 error injection logic QEMU QMP interface.
+"""
+
+import argparse
+import sys
+
+from arm_processor_error import ArmProcessorEinj
+
+EINJ_DESC = """
+Handle ACPI GHESv2 error injection logic QEMU QMP interface.
+
+It allows using UEFI BIOS EINJ features to generate GHES records.
+
+It helps testing CPER and GHES drivers at the guest OS and how
+userspace applications at the guest handle them.
+"""
+
+def main():
+ """Main program"""
+
+ # Main parser - handle generic args like QEMU QMP TCP socket options
+ parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+ usage="%(prog)s [options]",
+ description=EINJ_DESC)
+
+ g_options = parser.add_argument_group("QEMU QMP socket options")
+ g_options.add_argument("-H", "--host", default="localhost", type=str,
+ help="host name")
+ g_options.add_argument("-P", "--port", default=4445, type=int,
+ help="TCP port number")
+ g_options.add_argument('-d', '--debug', action='store_true')
+
+ subparsers = parser.add_subparsers()
+
+ ArmProcessorEinj(subparsers)
+
+ args = parser.parse_args()
+ if "func" in args:
+ args.func(args)
+ else:
+ sys.exit(f"Please specify a valid command for {sys.argv[0]}")
+
+if __name__ == "__main__":
+ main()
diff --git a/scripts/qmp_helper.py b/scripts/qmp_helper.py
new file mode 100644
index 000000000000..4f7ebb31b424
--- /dev/null
+++ b/scripts/qmp_helper.py
@@ -0,0 +1,702 @@
+#!/usr/bin/env python3
+#
+# # pylint: disable=C0103,E0213,E1135,E1136,E1137,R0902,R0903,R0912,R0913
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+
+"""
+Helper classes to be used by ghes_inject command classes.
+"""
+
+import json
+import sys
+
+from datetime import datetime
+from os import path as os_path
+
+try:
+ qemu_dir = os_path.abspath(os_path.dirname(os_path.dirname(__file__)))
+ sys.path.append(os_path.join(qemu_dir, 'python'))
+
+ from qemu.qmp.legacy import QEMUMonitorProtocol
+
+except ModuleNotFoundError as exc:
+ print(f"Module '{exc.name}' not found.")
+ print("Try export PYTHONPATH=top-qemu-dir/python or run from top-qemu-dir")
+ sys.exit(1)
+
+from base64 import b64encode
+
+class util:
+ """
+ Ancillary functions to deal with bitmaps, parse arguments,
+ generate GUID and encode data on a bytearray buffer.
+ """
+
+ #
+ # Helper routines to handle multiple choice arguments
+ #
+ def get_choice(name, value, choices, suffixes=None, bitmask=True):
+ """Produce a list from multiple choice argument"""
+
+ new_values = 0
+
+ if not value:
+ return new_values
+
+ for val in value.split(","):
+ val = val.lower()
+
+ if suffixes:
+ for suffix in suffixes:
+ val = val.removesuffix(suffix)
+
+ if val not in choices.keys():
+ if suffixes:
+ for suffix in suffixes:
+ if val + suffix in choices.keys():
+ val += suffix
+ break
+
+ if val not in choices.keys():
+ sys.exit(f"Error on '{name}': choice '{val}' is invalid.")
+
+ val = choices[val]
+
+ if bitmask:
+ new_values |= val
+ else:
+ if new_values:
+ sys.exit(f"Error on '{name}': only one value is accepted.")
+
+ new_values = val
+
+ return new_values
+
+ def get_array(name, values, max_val=None):
+ """Add numbered hashes from integer lists into an array"""
+
+ array = []
+
+ for value in values:
+ for val in value.split(","):
+ try:
+ val = int(val, 0)
+ except ValueError:
+ sys.exit(f"Error on '{name}': {val} is not an integer")
+
+ if val < 0:
+ sys.exit(f"Error on '{name}': {val} is not unsigned")
+
+ if max_val and val > max_val:
+ sys.exit(f"Error on '{name}': {val} is too little")
+
+ array.append(val)
+
+ return array
+
+ def get_mult_array(mult, name, values, allow_zero=False, max_val=None):
+ """Add numbered hashes from integer lists"""
+
+ if not allow_zero:
+ if not values:
+ return
+ else:
+ if values is None:
+ return
+
+ if not values:
+ i = 0
+ if i not in mult:
+ mult[i] = {}
+
+ mult[i][name] = []
+ return
+
+ i = 0
+ for value in values:
+ for val in value.split(","):
+ try:
+ val = int(val, 0)
+ except ValueError:
+ sys.exit(f"Error on '{name}': {val} is not an integer")
+
+ if val < 0:
+ sys.exit(f"Error on '{name}': {val} is not unsigned")
+
+ if max_val and val > max_val:
+ sys.exit(f"Error on '{name}': {val} is too little")
+
+ if i not in mult:
+ mult[i] = {}
+
+ if name not in mult[i]:
+ mult[i][name] = []
+
+ mult[i][name].append(val)
+
+ i += 1
+
+
+ def get_mult_choices(mult, name, values, choices,
+ suffixes=None, allow_zero=False):
+ """Add numbered hashes from multiple choice arguments"""
+
+ if not allow_zero:
+ if not values:
+ return
+ else:
+ if values is None:
+ return
+
+ i = 0
+ for val in values:
+ new_values = util.get_choice(name, val, choices, suffixes)
+
+ if i not in mult:
+ mult[i] = {}
+
+ mult[i][name] = new_values
+ i += 1
+
+
+ def get_mult_int(mult, name, values, allow_zero=False):
+ """Add numbered hashes from integer arguments"""
+ if not allow_zero:
+ if not values:
+ return
+ else:
+ if values is None:
+ return
+
+ i = 0
+ for val in values:
+ try:
+ val = int(val, 0)
+ except ValueError:
+ sys.exit(f"Error on '{name}': {val} is not an integer")
+
+ if val < 0:
+ sys.exit(f"Error on '{name}': {val} is not unsigned")
+
+ if i not in mult:
+ mult[i] = {}
+
+ mult[i][name] = val
+ i += 1
+
+
+ #
+ # Data encode helper functions
+ #
+ def bit(b):
+ """Simple macro to define a bit on a bitmask"""
+ return 1 << b
+
+
+ def data_add(data, value, num_bytes):
+ """Adds bytes from value inside a bitarray"""
+
+ data.extend(value.to_bytes(num_bytes, byteorder="little")) # pylint: disable=E1101
+
+ def dump_bytearray(name, data):
+ """Does an hexdump of a byte array, grouping in bytes"""
+
+ print(f"{name} ({len(data)} bytes):")
+
+ for ln_start in range(0, len(data), 16):
+ ln_end = min(ln_start + 16, len(data))
+ print(f" {ln_start:08x} ", end="")
+ for i in range(ln_start, ln_end):
+ print(f"{data[i]:02x} ", end="")
+ for i in range(ln_end, ln_start + 16):
+ print(" ", end="")
+ print(" ", end="")
+ for i in range(ln_start, ln_end):
+ if data[i] >= 32 and data[i] < 127:
+ print(chr(data[i]), end="")
+ else:
+ print(".", end="")
+
+ print()
+ print()
+
+ def time(string):
+ """Handle BCD timestamps used on Generic Error Data Block"""
+
+ time = None
+
+ # Formats to be used when parsing time stamps
+ formats = [
+ "%Y-%m-%d %H:%M:%S",
+ ]
+
+ if string == "now":
+ time = datetime.now()
+
+ if time is None:
+ for fmt in formats:
+ try:
+ time = datetime.strptime(string, fmt)
+ break
+ except ValueError:
+ pass
+
+ if time is None:
+ raise ValueError("Invalid time format")
+
+ return time
+
+class guid:
+ """
+ Simple class to handle GUID fields.
+ """
+
+ def __init__(self, time_low, time_mid, time_high, nodes):
+ """Initialize a GUID value"""
+
+ assert len(nodes) == 8
+
+ self.time_low = time_low
+ self.time_mid = time_mid
+ self.time_high = time_high
+ self.nodes = nodes
+
+ @classmethod
+ def UUID(cls, guid_str):
+ """Initialize a GUID using a string on its standard format"""
+
+ if len(guid_str) != 36:
+ print("Size not 36")
+ raise ValueError('Invalid GUID size')
+
+ # It is easier to parse without separators. So, drop them
+ guid_str = guid_str.replace('-', '')
+
+ if len(guid_str) != 32:
+ print("Size not 32", guid_str, len(guid_str))
+ raise ValueError('Invalid GUID hex size')
+
+ time_low = 0
+ time_mid = 0
+ time_high = 0
+ nodes = []
+
+ for i in reversed(range(16, 32, 2)):
+ h = guid_str[i:i + 2]
+ value = int(h, 16)
+ nodes.insert(0, value)
+
+ time_high = int(guid_str[12:16], 16)
+ time_mid = int(guid_str[8:12], 16)
+ time_low = int(guid_str[0:8], 16)
+
+ return cls(time_low, time_mid, time_high, nodes)
+
+ def __str__(self):
+ """Output a GUID value on its default string representation"""
+
+ clock = self.nodes[0] << 8 | self.nodes[1]
+
+ node = 0
+ for i in range(2, len(self.nodes)):
+ node = node << 8 | self.nodes[i]
+
+ s = f"{self.time_low:08x}-{self.time_mid:04x}-"
+ s += f"{self.time_high:04x}-{clock:04x}-{node:012x}"
+ return s
+
+ def to_bytes(self):
+ """Output a GUID value in bytes"""
+
+ data = bytearray()
+
+ util.data_add(data, self.time_low, 4)
+ util.data_add(data, self.time_mid, 2)
+ util.data_add(data, self.time_high, 2)
+ data.extend(bytearray(self.nodes))
+
+ return data
+
+class qmp:
+ """
+ Opens a connection and send/receive QMP commands.
+ """
+
+ def send_cmd(self, command, args=None, may_open=False, return_error=True):
+ """Send a command to QMP, optinally opening a connection"""
+
+ if may_open:
+ self._connect()
+ elif not self.connected:
+ return False
+
+ msg = { 'execute': command }
+ if args:
+ msg['arguments'] = args
+
+ try:
+ obj = self.qmp_monitor.cmd_obj(msg)
+ # Can we use some other exception class here?
+ except Exception as e: # pylint: disable=W0718
+ print(f"Command: {command}")
+ print(f"Failed to inject error: {e}.")
+ return None
+
+ if "return" in obj:
+ if isinstance(obj.get("return"), dict):
+ if obj["return"]:
+ return obj["return"]
+ return "OK"
+
+ return obj["return"]
+
+ if isinstance(obj.get("error"), dict):
+ error = obj["error"]
+ if return_error:
+ print(f"Command: {msg}")
+ print(f'{error["class"]}: {error["desc"]}')
+ else:
+ print(json.dumps(obj))
+
+ return None
+
+ def _close(self):
+ """Shutdown and close the socket, if opened"""
+ if not self.connected:
+ return
+
+ self.qmp_monitor.close()
+ self.connected = False
+
+ def _connect(self):
+ """Connect to a QMP TCP/IP port, if not connected yet"""
+
+ if self.connected:
+ return True
+
+ try:
+ self.qmp_monitor.connect(negotiate=True)
+ except ConnectionError:
+ sys.exit(f"Can't connect to QMP host {self.host}:{self.port}")
+
+ self.connected = True
+
+ return True
+
+ BLOCK_STATUS_BITS = {
+ "uncorrectable": util.bit(0),
+ "correctable": util.bit(1),
+ "multi-uncorrectable": util.bit(2),
+ "multi-correctable": util.bit(3),
+ }
+
+ ERROR_SEVERITY = {
+ "recoverable": 0,
+ "fatal": 1,
+ "corrected": 2,
+ "none": 3,
+ }
+
+ VALIDATION_BITS = {
+ "fru-id": util.bit(0),
+ "fru-text": util.bit(1),
+ "timestamp": util.bit(2),
+ }
+
+ GEDB_FLAGS_BITS = {
+ "recovered": util.bit(0),
+ "prev-error": util.bit(1),
+ "simulated": util.bit(2),
+ }
+
+ GENERIC_DATA_SIZE = 72
+
+ def argparse(parser):
+ """Prepare a parser group to query generic error data"""
+
+ block_status_bits = ",".join(qmp.BLOCK_STATUS_BITS.keys())
+ error_severity_enum = ",".join(qmp.ERROR_SEVERITY.keys())
+ validation_bits = ",".join(qmp.VALIDATION_BITS.keys())
+ gedb_flags_bits = ",".join(qmp.GEDB_FLAGS_BITS.keys())
+
+ g_gen = parser.add_argument_group("Generic Error Data") # pylint: disable=E1101
+ g_gen.add_argument("--block-status",
+ help=f"block status bits: {block_status_bits}")
+ g_gen.add_argument("--raw-data", nargs="+",
+ help="Raw data inside the Error Status Block")
+ g_gen.add_argument("--error-severity", "--severity",
+ help=f"error severity: {error_severity_enum}")
+ g_gen.add_argument("--gen-err-valid-bits",
+ "--generic-error-validation-bits",
+ help=f"validation bits: {validation_bits}")
+ g_gen.add_argument("--fru-id", type=guid.UUID,
+ help="GUID representing a physical device")
+ g_gen.add_argument("--fru-text",
+ help="ASCII string identifying the FRU hardware")
+ g_gen.add_argument("--timestamp", type=util.time,
+ help="Time when the error info was collected")
+ g_gen.add_argument("--precise", "--precise-timestamp",
+ action='store_true',
+ help="Marks the timestamp as precise if --timestamp is used")
+ g_gen.add_argument("--gedb-flags",
+ help=f"General Error Data Block flags: {gedb_flags_bits}")
+
+ def set_args(self, args):
+ """Set the arguments optionally defined via self.argparse()"""
+
+ if args.block_status:
+ self.block_status = util.get_choice(name="block-status",
+ value=args.block_status,
+ choices=self.BLOCK_STATUS_BITS,
+ bitmask=False)
+ if args.raw_data:
+ self.raw_data = util.get_array("raw-data", args.raw_data,
+ max_val=255)
+ print(self.raw_data)
+
+ if args.error_severity:
+ self.error_severity = util.get_choice(name="error-severity",
+ value=args.error_severity,
+ choices=self.ERROR_SEVERITY,
+ bitmask=False)
+
+ if args.fru_id:
+ self.fru_id = args.fru_id.to_bytes()
+ if not args.gen_err_valid_bits:
+ self.validation_bits |= self.VALIDATION_BITS["fru-id"]
+
+ if args.fru_text:
+ text = bytearray(args.fru_text.encode('ascii'))
+ if len(text) > 20:
+ sys.exit("FRU text is too big to fit")
+
+ self.fru_text = text
+ if not args.gen_err_valid_bits:
+ self.validation_bits |= self.VALIDATION_BITS["fru-text"]
+
+ if args.timestamp:
+ time = args.timestamp
+ century = int(time.year / 100)
+
+ bcd = bytearray()
+ util.data_add(bcd, (time.second // 10) << 4 | (time.second % 10), 1)
+ util.data_add(bcd, (time.minute // 10) << 4 | (time.minute % 10), 1)
+ util.data_add(bcd, (time.hour // 10) << 4 | (time.hour % 10), 1)
+
+ if args.precise:
+ util.data_add(bcd, 1, 1)
+ else:
+ util.data_add(bcd, 0, 1)
+
+ util.data_add(bcd, (time.day // 10) << 4 | (time.day % 10), 1)
+ util.data_add(bcd, (time.month // 10) << 4 | (time.month % 10), 1)
+ util.data_add(bcd,
+ ((time.year % 100) // 10) << 4 | (time.year % 10), 1)
+ util.data_add(bcd, ((century % 100) // 10) << 4 | (century % 10), 1)
+
+ self.timestamp = bcd
+ if not args.gen_err_valid_bits:
+ self.validation_bits |= self.VALIDATION_BITS["timestamp"]
+
+ if args.gen_err_valid_bits:
+ self.validation_bits = util.get_choice(name="validation",
+ value=args.gen_err_valid_bits,
+ choices=self.VALIDATION_BITS)
+
+ def __init__(self, host, port, debug=False):
+ """Initialize variables used by the QMP send logic"""
+
+ self.connected = False
+ self.host = host
+ self.port = port
+ self.debug = debug
+
+ # ACPI 6.1: 18.3.2.7.1 Generic Error Data: Generic Error Status Block
+ self.block_status = self.BLOCK_STATUS_BITS["uncorrectable"]
+ self.raw_data = []
+ self.error_severity = self.ERROR_SEVERITY["recoverable"]
+
+ # ACPI 6.1: 18.3.2.7.1 Generic Error Data: Generic Error Data Entry
+ self.validation_bits = 0
+ self.flags = 0
+ self.fru_id = bytearray(16)
+ self.fru_text = bytearray(20)
+ self.timestamp = bytearray(8)
+
+ self.qmp_monitor = QEMUMonitorProtocol(address=(self.host, self.port))
+
+ #
+ # Socket QMP send command
+ #
+ def send_cper_raw(self, cper_data):
+ """Send a raw CPER data to QEMU though QMP TCP socket"""
+
+ data = b64encode(bytes(cper_data)).decode('ascii')
+
+ cmd_arg = {
+ 'cper': data
+ }
+
+ self._connect()
+
+ if self.send_cmd("inject-ghes-error", cmd_arg):
+ print("Error injected.")
+
+ def send_cper(self, notif_type, payload):
+ """Send commands to QEMU though QMP TCP socket"""
+
+ # Fill CPER record header
+
+ # NOTE: bits 4 to 13 of block status contain the number of
+ # data entries in the data section. This is currently unsupported.
+
+ cper_length = len(payload)
+ data_length = cper_length + len(self.raw_data) + self.GENERIC_DATA_SIZE
+
+ # Generic Error Data Entry
+ gede = bytearray()
+
+ gede.extend(notif_type.to_bytes())
+ util.data_add(gede, self.error_severity, 4)
+ util.data_add(gede, 0x300, 2)
+ util.data_add(gede, self.validation_bits, 1)
+ util.data_add(gede, self.flags, 1)
+ util.data_add(gede, cper_length, 4)
+ gede.extend(self.fru_id)
+ gede.extend(self.fru_text)
+ gede.extend(self.timestamp)
+
+ # Generic Error Status Block
+ gebs = bytearray()
+
+ if self.raw_data:
+ raw_data_offset = len(gebs)
+ else:
+ raw_data_offset = 0
+
+ util.data_add(gebs, self.block_status, 4)
+ util.data_add(gebs, raw_data_offset, 4)
+ util.data_add(gebs, len(self.raw_data), 4)
+ util.data_add(gebs, data_length, 4)
+ util.data_add(gebs, self.error_severity, 4)
+
+ cper_data = bytearray()
+ cper_data.extend(gebs)
+ cper_data.extend(gede)
+ cper_data.extend(bytearray(self.raw_data))
+ cper_data.extend(bytearray(payload))
+
+ if self.debug:
+ print(f"GUID: {notif_type}")
+
+ util.dump_bytearray("Generic Error Status Block", gebs)
+ util.dump_bytearray("Generic Error Data Entry", gede)
+
+ if self.raw_data:
+ util.dump_bytearray("Raw data", bytearray(self.raw_data))
+
+ util.dump_bytearray("Payload", payload)
+
+ self.send_cper_raw(cper_data)
+
+
+ def search_qom(self, path, prop, regex):
+ """
+ Return a list of devices that match path array like:
+
+ /machine/unattached/device
+ /machine/peripheral-anon/device
+ ...
+ """
+
+ found = []
+
+ i = 0
+ while 1:
+ dev = f"{path}[{i}]"
+ args = {
+ 'path': dev,
+ 'property': prop
+ }
+ ret = self.send_cmd("qom-get", args, may_open=True, return_error=False)
+ if not ret:
+ break
+
+ if isinstance(ret, str):
+ if regex.search(ret):
+ found.append(dev)
+
+ i += 1
+ if i > 10000:
+ print("Too many objects returned by qom-get!")
+ break
+
+ return found
+
+class cper_guid:
+ """
+ Contains CPER GUID, as per:
+ https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html
+ """
+
+ CPER_PROC_GENERIC = guid(0x9876CCAD, 0x47B4, 0x4bdb,
+ [0xB6, 0x5E, 0x16, 0xF1,
+ 0x93, 0xC4, 0xF3, 0xDB])
+
+ CPER_PROC_X86 = guid(0xDC3EA0B0, 0xA144, 0x4797,
+ [0xB9, 0x5B, 0x53, 0xFA,
+ 0x24, 0x2B, 0x6E, 0x1D])
+
+ CPER_PROC_ITANIUM = guid(0xe429faf1, 0x3cb7, 0x11d4,
+ [0xbc, 0xa7, 0x00, 0x80,
+ 0xc7, 0x3c, 0x88, 0x81])
+
+ CPER_PROC_ARM = guid(0xE19E3D16, 0xBC11, 0x11E4,
+ [0x9C, 0xAA, 0xC2, 0x05,
+ 0x1D, 0x5D, 0x46, 0xB0])
+
+ CPER_PLATFORM_MEM = guid(0xA5BC1114, 0x6F64, 0x4EDE,
+ [0xB8, 0x63, 0x3E, 0x83,
+ 0xED, 0x7C, 0x83, 0xB1])
+
+ CPER_PLATFORM_MEM2 = guid(0x61EC04FC, 0x48E6, 0xD813,
+ [0x25, 0xC9, 0x8D, 0xAA,
+ 0x44, 0x75, 0x0B, 0x12])
+
+ CPER_PCIE = guid(0xD995E954, 0xBBC1, 0x430F,
+ [0xAD, 0x91, 0xB4, 0x4D,
+ 0xCB, 0x3C, 0x6F, 0x35])
+
+ CPER_PCI_BUS = guid(0xC5753963, 0x3B84, 0x4095,
+ [0xBF, 0x78, 0xED, 0xDA,
+ 0xD3, 0xF9, 0xC9, 0xDD])
+
+ CPER_PCI_DEV = guid(0xEB5E4685, 0xCA66, 0x4769,
+ [0xB6, 0xA2, 0x26, 0x06,
+ 0x8B, 0x00, 0x13, 0x26])
+
+ CPER_FW_ERROR = guid(0x81212A96, 0x09ED, 0x4996,
+ [0x94, 0x71, 0x8D, 0x72,
+ 0x9C, 0x8E, 0x69, 0xED])
+
+ CPER_DMA_GENERIC = guid(0x5B51FEF7, 0xC79D, 0x4434,
+ [0x8F, 0x1B, 0xAA, 0x62,
+ 0xDE, 0x3E, 0x2C, 0x64])
+
+ CPER_DMA_VT = guid(0x71761D37, 0x32B2, 0x45cd,
+ [0xA7, 0xD0, 0xB0, 0xFE,
+ 0xDD, 0x93, 0xE8, 0xCF])
+
+ CPER_DMA_IOMMU = guid(0x036F84E1, 0x7F37, 0x428c,
+ [0xA7, 0x9E, 0x57, 0x5F,
+ 0xDF, 0xAA, 0x84, 0xEC])
+
+ CPER_CCIX_PER = guid(0x91335EF6, 0xEBFB, 0x4478,
+ [0xA6, 0xA6, 0x88, 0xB7,
+ 0x28, 0xCF, 0x75, 0xD7])
+
+ CPER_CXL_PROT_ERR = guid(0x80B9EFB4, 0x52B5, 0x4DE3,
+ [0xA7, 0x77, 0x68, 0x78,
+ 0x4B, 0x77, 0x10, 0x48])
--
2.48.1On Wed, 29 Jan 2025 09:04:19 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> Using the QMP GHESv2 API requires preparing a raw data array
> containing a CPER record.
>
> Add a helper script with subcommands to prepare such data.
>
> Currently, only ARM Processor error CPER record is supported.
perhaps add here examples of possible usage,
and maybe to inject-ghes-v2-error doc section as well
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> ---
> MAINTAINERS | 3 +
> scripts/arm_processor_error.py | 377 ++++++++++++++++++
> scripts/ghes_inject.py | 51 +++
> scripts/qmp_helper.py | 702 +++++++++++++++++++++++++++++++++
> 4 files changed, 1133 insertions(+)
> create mode 100644 scripts/arm_processor_error.py
> create mode 100755 scripts/ghes_inject.py
> create mode 100644 scripts/qmp_helper.py
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 8e1f662fa0e0..99a9ba5c2ace 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -2081,6 +2081,9 @@ S: Maintained
> F: hw/arm/ghes_cper.c
> F: hw/acpi/ghes_cper_stub.c
> F: qapi/acpi-hest.json
> +F: scripts/ghes_inject.py
> +F: scripts/arm_processor_error.py
> +F: scripts/qmp_helper.py
>
> ppc4xx
> L: qemu-ppc@nongnu.org
> diff --git a/scripts/arm_processor_error.py b/scripts/arm_processor_error.py
> new file mode 100644
> index 000000000000..4ac04ab08299
> --- /dev/null
> +++ b/scripts/arm_processor_error.py
> @@ -0,0 +1,377 @@
> +#!/usr/bin/env python3
> +#
> +# pylint: disable=C0301,C0114,R0903,R0912,R0913,R0914,R0915,W0511
> +# SPDX-License-Identifier: GPL-2.0
> +#
> +# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> +
> +# TODO: current implementation has dummy defaults.
> +#
> +# For a better implementation, a QMP addition/call is needed to
> +# retrieve some data for ARM Processor Error injection:
> +#
> +# - ARM registers: power_state, mpidr.
> +
> +import argparse
> +import re
> +
> +from qmp_helper import qmp, util, cper_guid
> +
> +class ArmProcessorEinj:
> + """
> + Implements ARM Processor Error injection via GHES
> + """
> +
> + DESC = """
> + Generates an ARM processor error CPER, compatible with
> + UEFI 2.9A Errata.
> + """
> +
> + ACPI_GHES_ARM_CPER_LENGTH = 40
> + ACPI_GHES_ARM_CPER_PEI_LENGTH = 32
> +
> + # Context types
> + CONTEXT_AARCH32_EL1 = 1
> + CONTEXT_AARCH64_EL1 = 5
> + CONTEXT_MISC_REG = 8
> +
> + def __init__(self, subparsers):
> + """Initialize the error injection class and add subparser"""
> +
> + # Valid choice values
> + self.arm_valid_bits = {
> + "mpidr": util.bit(0),
> + "affinity": util.bit(1),
> + "running": util.bit(2),
> + "vendor": util.bit(3),
> + }
> +
> + self.pei_flags = {
> + "first": util.bit(0),
> + "last": util.bit(1),
> + "propagated": util.bit(2),
> + "overflow": util.bit(3),
> + }
> +
> + self.pei_error_types = {
> + "cache": util.bit(1),
> + "tlb": util.bit(2),
> + "bus": util.bit(3),
> + "micro-arch": util.bit(4),
> + }
> +
> + self.pei_valid_bits = {
> + "multiple-error": util.bit(0),
> + "flags": util.bit(1),
> + "error-info": util.bit(2),
> + "virt-addr": util.bit(3),
> + "phy-addr": util.bit(4),
> + }
> +
> + self.data = bytearray()
> +
> + parser = subparsers.add_parser("arm", description=self.DESC)
> +
> + arm_valid_bits = ",".join(self.arm_valid_bits.keys())
> + flags = ",".join(self.pei_flags.keys())
> + error_types = ",".join(self.pei_error_types.keys())
> + pei_valid_bits = ",".join(self.pei_valid_bits.keys())
> +
> + # UEFI N.16 ARM Validation bits
> + g_arm = parser.add_argument_group("ARM processor")
> + g_arm.add_argument("--arm", "--arm-valid",
> + help=f"ARM valid bits: {arm_valid_bits}")
> + g_arm.add_argument("-a", "--affinity", "--level", "--affinity-level",
> + type=lambda x: int(x, 0),
> + help="Affinity level (when multiple levels apply)")
> + g_arm.add_argument("-l", "--mpidr", type=lambda x: int(x, 0),
> + help="Multiprocessor Affinity Register")
> + g_arm.add_argument("-i", "--midr", type=lambda x: int(x, 0),
> + help="Main ID Register")
> + g_arm.add_argument("-r", "--running",
> + action=argparse.BooleanOptionalAction,
> + default=None,
> + help="Indicates if the processor is running or not")
> + g_arm.add_argument("--psci", "--psci-state",
> + type=lambda x: int(x, 0),
> + help="Power State Coordination Interface - PSCI state")
> +
> + # TODO: Add vendor-specific support
> +
> + # UEFI N.17 bitmaps (type and flags)
> + g_pei = parser.add_argument_group("ARM Processor Error Info (PEI)")
> + g_pei.add_argument("-t", "--type", nargs="+",
> + help=f"one or more error types: {error_types}")
> + g_pei.add_argument("-f", "--flags", nargs="*",
> + help=f"zero or more error flags: {flags}")
> + g_pei.add_argument("-V", "--pei-valid", "--error-valid", nargs="*",
> + help=f"zero or more PEI valid bits: {pei_valid_bits}")
> +
> + # UEFI N.17 Integer values
> + g_pei.add_argument("-m", "--multiple-error", nargs="+",
> + help="Number of errors: 0: Single error, 1: Multiple errors, 2-65535: Error count if known")
> + g_pei.add_argument("-e", "--error-info", nargs="+",
> + help="Error information (UEFI 2.10 tables N.18 to N.20)")
> + g_pei.add_argument("-p", "--physical-address", nargs="+",
> + help="Physical address")
> + g_pei.add_argument("-v", "--virtual-address", nargs="+",
> + help="Virtual address")
> +
> + # UEFI N.21 Context
> + g_ctx = parser.add_argument_group("Processor Context")
> + g_ctx.add_argument("--ctx-type", "--context-type", nargs="*",
> + help="Type of the context (0=ARM32 GPR, 5=ARM64 EL1, other values supported)")
> + g_ctx.add_argument("--ctx-size", "--context-size", nargs="*",
> + help="Minimal size of the context")
> + g_ctx.add_argument("--ctx-array", "--context-array", nargs="*",
> + help="Comma-separated arrays for each context")
> +
> + # Vendor-specific data
> + g_vendor = parser.add_argument_group("Vendor-specific data")
> + g_vendor.add_argument("--vendor", "--vendor-specific", nargs="+",
> + help="Vendor-specific byte arrays of data")
> +
> + # Add arguments for Generic Error Data
> + qmp.argparse(parser)
> +
> + parser.set_defaults(func=self.send_cper)
> +
> + def send_cper(self, args):
> + """Parse subcommand arguments and send a CPER via QMP"""
> +
> + qmp_cmd = qmp(args.host, args.port, args.debug)
> +
> + # Handle Generic Error Data arguments if any
> + qmp_cmd.set_args(args)
> +
> + is_cpu_type = re.compile(r"^([\w+]+\-)?arm\-cpu$")
> + cpus = qmp_cmd.search_qom("/machine/unattached/device",
> + "type", is_cpu_type)
> +
> + cper = {}
> + pei = {}
> + ctx = {}
> + vendor = {}
> +
> + arg = vars(args)
> +
> + # Handle global parameters
> + if args.arm:
> + arm_valid_init = False
> + cper["valid"] = util.get_choice(name="valid",
> + value=args.arm,
> + choices=self.arm_valid_bits,
> + suffixes=["-error", "-err"])
> + else:
> + cper["valid"] = 0
> + arm_valid_init = True
> +
> + if "running" in arg:
> + if args.running:
> + cper["running-state"] = util.bit(0)
> + else:
> + cper["running-state"] = 0
> + else:
> + cper["running-state"] = 0
> +
> + if arm_valid_init:
> + if args.affinity:
> + cper["valid"] |= self.arm_valid_bits["affinity"]
> +
> + if args.mpidr:
> + cper["valid"] |= self.arm_valid_bits["mpidr"]
> +
> + if "running-state" in cper:
> + cper["valid"] |= self.arm_valid_bits["running"]
> +
> + if args.psci:
> + cper["valid"] |= self.arm_valid_bits["running"]
> +
> + # Handle PEI
> + if not args.type:
> + args.type = ["cache-error"]
> +
> + util.get_mult_choices(
> + pei,
> + name="valid",
> + values=args.pei_valid,
> + choices=self.pei_valid_bits,
> + suffixes=["-valid", "--addr"],
> + )
> + util.get_mult_choices(
> + pei,
> + name="type",
> + values=args.type,
> + choices=self.pei_error_types,
> + suffixes=["-error", "-err"],
> + )
> + util.get_mult_choices(
> + pei,
> + name="flags",
> + values=args.flags,
> + choices=self.pei_flags,
> + suffixes=["-error", "-cap"],
> + )
> + util.get_mult_int(pei, "error-info", args.error_info)
> + util.get_mult_int(pei, "multiple-error", args.multiple_error)
> + util.get_mult_int(pei, "phy-addr", args.physical_address)
> + util.get_mult_int(pei, "virt-addr", args.virtual_address)
> +
> + # Handle context
> + util.get_mult_int(ctx, "type", args.ctx_type, allow_zero=True)
> + util.get_mult_int(ctx, "minimal-size", args.ctx_size, allow_zero=True)
> + util.get_mult_array(ctx, "register", args.ctx_array, allow_zero=True)
> +
> + util.get_mult_array(vendor, "bytes", args.vendor, max_val=255)
> +
> + # Store PEI
> + pei_data = bytearray()
> + default_flags = self.pei_flags["first"]
> + default_flags |= self.pei_flags["last"]
> +
> + error_info_num = 0
> +
> + for i, p in pei.items(): # pylint: disable=W0612
> + error_info_num += 1
> +
> + # UEFI 2.10 doesn't define how to encode error information
> + # when multiple types are raised. So, provide a default only
> + # if a single type is there
> + if "error-info" not in p:
> + if p["type"] == util.bit(1):
> + p["error-info"] = 0x0091000F
> + if p["type"] == util.bit(2):
> + p["error-info"] = 0x0054007F
> + if p["type"] == util.bit(3):
> + p["error-info"] = 0x80D6460FFF
> + if p["type"] == util.bit(4):
> + p["error-info"] = 0x78DA03FF
> +
> + if "valid" not in p:
> + p["valid"] = 0
> + if "multiple-error" in p:
> + p["valid"] |= self.pei_valid_bits["multiple-error"]
> +
> + if "flags" in p:
> + p["valid"] |= self.pei_valid_bits["flags"]
> +
> + if "error-info" in p:
> + p["valid"] |= self.pei_valid_bits["error-info"]
> +
> + if "phy-addr" in p:
> + p["valid"] |= self.pei_valid_bits["phy-addr"]
> +
> + if "virt-addr" in p:
> + p["valid"] |= self.pei_valid_bits["virt-addr"]
> +
> + # Version
> + util.data_add(pei_data, 0, 1)
> +
> + util.data_add(pei_data,
> + self.ACPI_GHES_ARM_CPER_PEI_LENGTH, 1)
> +
> + util.data_add(pei_data, p["valid"], 2)
> + util.data_add(pei_data, p["type"], 1)
> + util.data_add(pei_data, p.get("multiple-error", 1), 2)
> + util.data_add(pei_data, p.get("flags", default_flags), 1)
> + util.data_add(pei_data, p.get("error-info", 0), 8)
> + util.data_add(pei_data, p.get("virt-addr", 0xDEADBEEF), 8)
> + util.data_add(pei_data, p.get("phy-addr", 0xABBA0BAD), 8)
> +
> + # Store Context
> + ctx_data = bytearray()
> + context_info_num = 0
> +
> + if ctx:
> + ret = qmp_cmd.send_cmd("query-target", may_open=True)
> +
> + default_ctx = self.CONTEXT_MISC_REG
> +
> + if "arch" in ret:
> + if ret["arch"] == "aarch64":
> + default_ctx = self.CONTEXT_AARCH64_EL1
> + elif ret["arch"] == "arm":
> + default_ctx = self.CONTEXT_AARCH32_EL1
> +
> + for k in sorted(ctx.keys()):
> + context_info_num += 1
> +
> + if "type" not in ctx[k]:
> + ctx[k]["type"] = default_ctx
> +
> + if "register" not in ctx[k]:
> + ctx[k]["register"] = []
> +
> + reg_size = len(ctx[k]["register"])
> + size = 0
> +
> + if "minimal-size" in ctx:
> + size = ctx[k]["minimal-size"]
> +
> + size = max(size, reg_size)
> +
> + size = (size + 1) % 0xFFFE
> +
> + # Version
> + util.data_add(ctx_data, 0, 2)
> +
> + util.data_add(ctx_data, ctx[k]["type"], 2)
> +
> + util.data_add(ctx_data, 8 * size, 4)
> +
> + for r in ctx[k]["register"]:
> + util.data_add(ctx_data, r, 8)
> +
> + for i in range(reg_size, size): # pylint: disable=W0612
> + util.data_add(ctx_data, 0, 8)
> +
> + # Vendor-specific bytes are not grouped
> + vendor_data = bytearray()
> + if vendor:
> + for k in sorted(vendor.keys()):
> + for b in vendor[k]["bytes"]:
> + util.data_add(vendor_data, b, 1)
> +
> + # Encode ARM Processor Error
> + data = bytearray()
> +
> + util.data_add(data, cper["valid"], 4)
> +
> + util.data_add(data, error_info_num, 2)
> + util.data_add(data, context_info_num, 2)
> +
> + # Calculate the length of the CPER data
> + cper_length = self.ACPI_GHES_ARM_CPER_LENGTH
> + cper_length += len(pei_data)
> + cper_length += len(vendor_data)
> + cper_length += len(ctx_data)
> + util.data_add(data, cper_length, 4)
> +
> + util.data_add(data, arg.get("affinity-level", 0), 1)
> +
> + # Reserved
> + util.data_add(data, 0, 3)
> +
> + if "midr-el1" not in arg:
> + if cpus:
> + cmd_arg = {
> + 'path': cpus[0],
> + 'property': "midr"
> + }
> + ret = qmp_cmd.send_cmd("qom-get", cmd_arg, may_open=True)
> + if isinstance(ret, int):
> + arg["midr-el1"] = ret
> +
> + util.data_add(data, arg.get("mpidr-el1", 0), 8)
> + util.data_add(data, arg.get("midr-el1", 0), 8)
> + util.data_add(data, cper["running-state"], 4)
> + util.data_add(data, arg.get("psci-state", 0), 4)
> +
> + # Add PEI
> + data.extend(pei_data)
> + data.extend(ctx_data)
> + data.extend(vendor_data)
> +
> + self.data = data
> +
> + qmp_cmd.send_cper(cper_guid.CPER_PROC_ARM, self.data)
> diff --git a/scripts/ghes_inject.py b/scripts/ghes_inject.py
> new file mode 100755
> index 000000000000..5d72bc7f09e1
> --- /dev/null
> +++ b/scripts/ghes_inject.py
> @@ -0,0 +1,51 @@
> +#!/usr/bin/env python3
> +#
> +# SPDX-License-Identifier: GPL-2.0
> +#
> +# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> +
> +"""
> +Handle ACPI GHESv2 error injection logic QEMU QMP interface.
> +"""
> +
> +import argparse
> +import sys
> +
> +from arm_processor_error import ArmProcessorEinj
> +
> +EINJ_DESC = """
> +Handle ACPI GHESv2 error injection logic QEMU QMP interface.
> +
> +It allows using UEFI BIOS EINJ features to generate GHES records.
> +
> +It helps testing CPER and GHES drivers at the guest OS and how
> +userspace applications at the guest handle them.
> +"""
> +
> +def main():
> + """Main program"""
> +
> + # Main parser - handle generic args like QEMU QMP TCP socket options
> + parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter,
> + usage="%(prog)s [options]",
> + description=EINJ_DESC)
> +
> + g_options = parser.add_argument_group("QEMU QMP socket options")
> + g_options.add_argument("-H", "--host", default="localhost", type=str,
> + help="host name")
> + g_options.add_argument("-P", "--port", default=4445, type=int,
> + help="TCP port number")
> + g_options.add_argument('-d', '--debug', action='store_true')
> +
> + subparsers = parser.add_subparsers()
> +
> + ArmProcessorEinj(subparsers)
> +
> + args = parser.parse_args()
> + if "func" in args:
> + args.func(args)
> + else:
> + sys.exit(f"Please specify a valid command for {sys.argv[0]}")
> +
> +if __name__ == "__main__":
> + main()
> diff --git a/scripts/qmp_helper.py b/scripts/qmp_helper.py
> new file mode 100644
> index 000000000000..4f7ebb31b424
> --- /dev/null
> +++ b/scripts/qmp_helper.py
> @@ -0,0 +1,702 @@
> +#!/usr/bin/env python3
> +#
> +# # pylint: disable=C0103,E0213,E1135,E1136,E1137,R0902,R0903,R0912,R0913
> +# SPDX-License-Identifier: GPL-2.0
> +#
> +# Copyright (C) 2024-2025 Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
> +
> +"""
> +Helper classes to be used by ghes_inject command classes.
> +"""
> +
> +import json
> +import sys
> +
> +from datetime import datetime
> +from os import path as os_path
> +
> +try:
> + qemu_dir = os_path.abspath(os_path.dirname(os_path.dirname(__file__)))
> + sys.path.append(os_path.join(qemu_dir, 'python'))
> +
> + from qemu.qmp.legacy import QEMUMonitorProtocol
> +
> +except ModuleNotFoundError as exc:
> + print(f"Module '{exc.name}' not found.")
> + print("Try export PYTHONPATH=top-qemu-dir/python or run from top-qemu-dir")
> + sys.exit(1)
> +
> +from base64 import b64encode
> +
> +class util:
> + """
> + Ancillary functions to deal with bitmaps, parse arguments,
> + generate GUID and encode data on a bytearray buffer.
> + """
> +
> + #
> + # Helper routines to handle multiple choice arguments
> + #
> + def get_choice(name, value, choices, suffixes=None, bitmask=True):
> + """Produce a list from multiple choice argument"""
> +
> + new_values = 0
> +
> + if not value:
> + return new_values
> +
> + for val in value.split(","):
> + val = val.lower()
> +
> + if suffixes:
> + for suffix in suffixes:
> + val = val.removesuffix(suffix)
> +
> + if val not in choices.keys():
> + if suffixes:
> + for suffix in suffixes:
> + if val + suffix in choices.keys():
> + val += suffix
> + break
> +
> + if val not in choices.keys():
> + sys.exit(f"Error on '{name}': choice '{val}' is invalid.")
> +
> + val = choices[val]
> +
> + if bitmask:
> + new_values |= val
> + else:
> + if new_values:
> + sys.exit(f"Error on '{name}': only one value is accepted.")
> +
> + new_values = val
> +
> + return new_values
> +
> + def get_array(name, values, max_val=None):
> + """Add numbered hashes from integer lists into an array"""
> +
> + array = []
> +
> + for value in values:
> + for val in value.split(","):
> + try:
> + val = int(val, 0)
> + except ValueError:
> + sys.exit(f"Error on '{name}': {val} is not an integer")
> +
> + if val < 0:
> + sys.exit(f"Error on '{name}': {val} is not unsigned")
> +
> + if max_val and val > max_val:
> + sys.exit(f"Error on '{name}': {val} is too little")
> +
> + array.append(val)
> +
> + return array
> +
> + def get_mult_array(mult, name, values, allow_zero=False, max_val=None):
> + """Add numbered hashes from integer lists"""
> +
> + if not allow_zero:
> + if not values:
> + return
> + else:
> + if values is None:
> + return
> +
> + if not values:
> + i = 0
> + if i not in mult:
> + mult[i] = {}
> +
> + mult[i][name] = []
> + return
> +
> + i = 0
> + for value in values:
> + for val in value.split(","):
> + try:
> + val = int(val, 0)
> + except ValueError:
> + sys.exit(f"Error on '{name}': {val} is not an integer")
> +
> + if val < 0:
> + sys.exit(f"Error on '{name}': {val} is not unsigned")
> +
> + if max_val and val > max_val:
> + sys.exit(f"Error on '{name}': {val} is too little")
> +
> + if i not in mult:
> + mult[i] = {}
> +
> + if name not in mult[i]:
> + mult[i][name] = []
> +
> + mult[i][name].append(val)
> +
> + i += 1
> +
> +
> + def get_mult_choices(mult, name, values, choices,
> + suffixes=None, allow_zero=False):
> + """Add numbered hashes from multiple choice arguments"""
> +
> + if not allow_zero:
> + if not values:
> + return
> + else:
> + if values is None:
> + return
> +
> + i = 0
> + for val in values:
> + new_values = util.get_choice(name, val, choices, suffixes)
> +
> + if i not in mult:
> + mult[i] = {}
> +
> + mult[i][name] = new_values
> + i += 1
> +
> +
> + def get_mult_int(mult, name, values, allow_zero=False):
> + """Add numbered hashes from integer arguments"""
> + if not allow_zero:
> + if not values:
> + return
> + else:
> + if values is None:
> + return
> +
> + i = 0
> + for val in values:
> + try:
> + val = int(val, 0)
> + except ValueError:
> + sys.exit(f"Error on '{name}': {val} is not an integer")
> +
> + if val < 0:
> + sys.exit(f"Error on '{name}': {val} is not unsigned")
> +
> + if i not in mult:
> + mult[i] = {}
> +
> + mult[i][name] = val
> + i += 1
> +
> +
> + #
> + # Data encode helper functions
> + #
> + def bit(b):
> + """Simple macro to define a bit on a bitmask"""
> + return 1 << b
> +
> +
> + def data_add(data, value, num_bytes):
> + """Adds bytes from value inside a bitarray"""
> +
> + data.extend(value.to_bytes(num_bytes, byteorder="little")) # pylint: disable=E1101
> +
> + def dump_bytearray(name, data):
> + """Does an hexdump of a byte array, grouping in bytes"""
> +
> + print(f"{name} ({len(data)} bytes):")
> +
> + for ln_start in range(0, len(data), 16):
> + ln_end = min(ln_start + 16, len(data))
> + print(f" {ln_start:08x} ", end="")
> + for i in range(ln_start, ln_end):
> + print(f"{data[i]:02x} ", end="")
> + for i in range(ln_end, ln_start + 16):
> + print(" ", end="")
> + print(" ", end="")
> + for i in range(ln_start, ln_end):
> + if data[i] >= 32 and data[i] < 127:
> + print(chr(data[i]), end="")
> + else:
> + print(".", end="")
> +
> + print()
> + print()
> +
> + def time(string):
> + """Handle BCD timestamps used on Generic Error Data Block"""
> +
> + time = None
> +
> + # Formats to be used when parsing time stamps
> + formats = [
> + "%Y-%m-%d %H:%M:%S",
> + ]
> +
> + if string == "now":
> + time = datetime.now()
> +
> + if time is None:
> + for fmt in formats:
> + try:
> + time = datetime.strptime(string, fmt)
> + break
> + except ValueError:
> + pass
> +
> + if time is None:
> + raise ValueError("Invalid time format")
> +
> + return time
> +
> +class guid:
> + """
> + Simple class to handle GUID fields.
> + """
> +
> + def __init__(self, time_low, time_mid, time_high, nodes):
> + """Initialize a GUID value"""
> +
> + assert len(nodes) == 8
> +
> + self.time_low = time_low
> + self.time_mid = time_mid
> + self.time_high = time_high
> + self.nodes = nodes
> +
> + @classmethod
> + def UUID(cls, guid_str):
> + """Initialize a GUID using a string on its standard format"""
> +
> + if len(guid_str) != 36:
> + print("Size not 36")
> + raise ValueError('Invalid GUID size')
> +
> + # It is easier to parse without separators. So, drop them
> + guid_str = guid_str.replace('-', '')
> +
> + if len(guid_str) != 32:
> + print("Size not 32", guid_str, len(guid_str))
> + raise ValueError('Invalid GUID hex size')
> +
> + time_low = 0
> + time_mid = 0
> + time_high = 0
> + nodes = []
> +
> + for i in reversed(range(16, 32, 2)):
> + h = guid_str[i:i + 2]
> + value = int(h, 16)
> + nodes.insert(0, value)
> +
> + time_high = int(guid_str[12:16], 16)
> + time_mid = int(guid_str[8:12], 16)
> + time_low = int(guid_str[0:8], 16)
> +
> + return cls(time_low, time_mid, time_high, nodes)
> +
> + def __str__(self):
> + """Output a GUID value on its default string representation"""
> +
> + clock = self.nodes[0] << 8 | self.nodes[1]
> +
> + node = 0
> + for i in range(2, len(self.nodes)):
> + node = node << 8 | self.nodes[i]
> +
> + s = f"{self.time_low:08x}-{self.time_mid:04x}-"
> + s += f"{self.time_high:04x}-{clock:04x}-{node:012x}"
> + return s
> +
> + def to_bytes(self):
> + """Output a GUID value in bytes"""
> +
> + data = bytearray()
> +
> + util.data_add(data, self.time_low, 4)
> + util.data_add(data, self.time_mid, 2)
> + util.data_add(data, self.time_high, 2)
> + data.extend(bytearray(self.nodes))
> +
> + return data
> +
> +class qmp:
> + """
> + Opens a connection and send/receive QMP commands.
> + """
> +
> + def send_cmd(self, command, args=None, may_open=False, return_error=True):
> + """Send a command to QMP, optinally opening a connection"""
> +
> + if may_open:
> + self._connect()
> + elif not self.connected:
> + return False
> +
> + msg = { 'execute': command }
> + if args:
> + msg['arguments'] = args
> +
> + try:
> + obj = self.qmp_monitor.cmd_obj(msg)
> + # Can we use some other exception class here?
> + except Exception as e: # pylint: disable=W0718
> + print(f"Command: {command}")
> + print(f"Failed to inject error: {e}.")
> + return None
> +
> + if "return" in obj:
> + if isinstance(obj.get("return"), dict):
> + if obj["return"]:
> + return obj["return"]
> + return "OK"
> +
> + return obj["return"]
> +
> + if isinstance(obj.get("error"), dict):
> + error = obj["error"]
> + if return_error:
> + print(f"Command: {msg}")
> + print(f'{error["class"]}: {error["desc"]}')
> + else:
> + print(json.dumps(obj))
> +
> + return None
> +
> + def _close(self):
> + """Shutdown and close the socket, if opened"""
> + if not self.connected:
> + return
> +
> + self.qmp_monitor.close()
> + self.connected = False
> +
> + def _connect(self):
> + """Connect to a QMP TCP/IP port, if not connected yet"""
> +
> + if self.connected:
> + return True
> +
> + try:
> + self.qmp_monitor.connect(negotiate=True)
> + except ConnectionError:
> + sys.exit(f"Can't connect to QMP host {self.host}:{self.port}")
> +
> + self.connected = True
> +
> + return True
> +
> + BLOCK_STATUS_BITS = {
> + "uncorrectable": util.bit(0),
> + "correctable": util.bit(1),
> + "multi-uncorrectable": util.bit(2),
> + "multi-correctable": util.bit(3),
> + }
> +
> + ERROR_SEVERITY = {
> + "recoverable": 0,
> + "fatal": 1,
> + "corrected": 2,
> + "none": 3,
> + }
> +
> + VALIDATION_BITS = {
> + "fru-id": util.bit(0),
> + "fru-text": util.bit(1),
> + "timestamp": util.bit(2),
> + }
> +
> + GEDB_FLAGS_BITS = {
> + "recovered": util.bit(0),
> + "prev-error": util.bit(1),
> + "simulated": util.bit(2),
> + }
> +
> + GENERIC_DATA_SIZE = 72
> +
> + def argparse(parser):
> + """Prepare a parser group to query generic error data"""
> +
> + block_status_bits = ",".join(qmp.BLOCK_STATUS_BITS.keys())
> + error_severity_enum = ",".join(qmp.ERROR_SEVERITY.keys())
> + validation_bits = ",".join(qmp.VALIDATION_BITS.keys())
> + gedb_flags_bits = ",".join(qmp.GEDB_FLAGS_BITS.keys())
> +
> + g_gen = parser.add_argument_group("Generic Error Data") # pylint: disable=E1101
> + g_gen.add_argument("--block-status",
> + help=f"block status bits: {block_status_bits}")
> + g_gen.add_argument("--raw-data", nargs="+",
> + help="Raw data inside the Error Status Block")
> + g_gen.add_argument("--error-severity", "--severity",
> + help=f"error severity: {error_severity_enum}")
> + g_gen.add_argument("--gen-err-valid-bits",
> + "--generic-error-validation-bits",
> + help=f"validation bits: {validation_bits}")
> + g_gen.add_argument("--fru-id", type=guid.UUID,
> + help="GUID representing a physical device")
> + g_gen.add_argument("--fru-text",
> + help="ASCII string identifying the FRU hardware")
> + g_gen.add_argument("--timestamp", type=util.time,
> + help="Time when the error info was collected")
> + g_gen.add_argument("--precise", "--precise-timestamp",
> + action='store_true',
> + help="Marks the timestamp as precise if --timestamp is used")
> + g_gen.add_argument("--gedb-flags",
> + help=f"General Error Data Block flags: {gedb_flags_bits}")
> +
> + def set_args(self, args):
> + """Set the arguments optionally defined via self.argparse()"""
> +
> + if args.block_status:
> + self.block_status = util.get_choice(name="block-status",
> + value=args.block_status,
> + choices=self.BLOCK_STATUS_BITS,
> + bitmask=False)
> + if args.raw_data:
> + self.raw_data = util.get_array("raw-data", args.raw_data,
> + max_val=255)
> + print(self.raw_data)
> +
> + if args.error_severity:
> + self.error_severity = util.get_choice(name="error-severity",
> + value=args.error_severity,
> + choices=self.ERROR_SEVERITY,
> + bitmask=False)
> +
> + if args.fru_id:
> + self.fru_id = args.fru_id.to_bytes()
> + if not args.gen_err_valid_bits:
> + self.validation_bits |= self.VALIDATION_BITS["fru-id"]
> +
> + if args.fru_text:
> + text = bytearray(args.fru_text.encode('ascii'))
> + if len(text) > 20:
> + sys.exit("FRU text is too big to fit")
> +
> + self.fru_text = text
> + if not args.gen_err_valid_bits:
> + self.validation_bits |= self.VALIDATION_BITS["fru-text"]
> +
> + if args.timestamp:
> + time = args.timestamp
> + century = int(time.year / 100)
> +
> + bcd = bytearray()
> + util.data_add(bcd, (time.second // 10) << 4 | (time.second % 10), 1)
> + util.data_add(bcd, (time.minute // 10) << 4 | (time.minute % 10), 1)
> + util.data_add(bcd, (time.hour // 10) << 4 | (time.hour % 10), 1)
> +
> + if args.precise:
> + util.data_add(bcd, 1, 1)
> + else:
> + util.data_add(bcd, 0, 1)
> +
> + util.data_add(bcd, (time.day // 10) << 4 | (time.day % 10), 1)
> + util.data_add(bcd, (time.month // 10) << 4 | (time.month % 10), 1)
> + util.data_add(bcd,
> + ((time.year % 100) // 10) << 4 | (time.year % 10), 1)
> + util.data_add(bcd, ((century % 100) // 10) << 4 | (century % 10), 1)
> +
> + self.timestamp = bcd
> + if not args.gen_err_valid_bits:
> + self.validation_bits |= self.VALIDATION_BITS["timestamp"]
> +
> + if args.gen_err_valid_bits:
> + self.validation_bits = util.get_choice(name="validation",
> + value=args.gen_err_valid_bits,
> + choices=self.VALIDATION_BITS)
> +
> + def __init__(self, host, port, debug=False):
> + """Initialize variables used by the QMP send logic"""
> +
> + self.connected = False
> + self.host = host
> + self.port = port
> + self.debug = debug
> +
> + # ACPI 6.1: 18.3.2.7.1 Generic Error Data: Generic Error Status Block
> + self.block_status = self.BLOCK_STATUS_BITS["uncorrectable"]
> + self.raw_data = []
> + self.error_severity = self.ERROR_SEVERITY["recoverable"]
> +
> + # ACPI 6.1: 18.3.2.7.1 Generic Error Data: Generic Error Data Entry
> + self.validation_bits = 0
> + self.flags = 0
> + self.fru_id = bytearray(16)
> + self.fru_text = bytearray(20)
> + self.timestamp = bytearray(8)
> +
> + self.qmp_monitor = QEMUMonitorProtocol(address=(self.host, self.port))
> +
> + #
> + # Socket QMP send command
> + #
> + def send_cper_raw(self, cper_data):
> + """Send a raw CPER data to QEMU though QMP TCP socket"""
> +
> + data = b64encode(bytes(cper_data)).decode('ascii')
> +
> + cmd_arg = {
> + 'cper': data
> + }
> +
> + self._connect()
> +
> + if self.send_cmd("inject-ghes-error", cmd_arg):
> + print("Error injected.")
> +
> + def send_cper(self, notif_type, payload):
> + """Send commands to QEMU though QMP TCP socket"""
> +
> + # Fill CPER record header
> +
> + # NOTE: bits 4 to 13 of block status contain the number of
> + # data entries in the data section. This is currently unsupported.
> +
> + cper_length = len(payload)
> + data_length = cper_length + len(self.raw_data) + self.GENERIC_DATA_SIZE
> +
> + # Generic Error Data Entry
> + gede = bytearray()
> +
> + gede.extend(notif_type.to_bytes())
> + util.data_add(gede, self.error_severity, 4)
> + util.data_add(gede, 0x300, 2)
> + util.data_add(gede, self.validation_bits, 1)
> + util.data_add(gede, self.flags, 1)
> + util.data_add(gede, cper_length, 4)
> + gede.extend(self.fru_id)
> + gede.extend(self.fru_text)
> + gede.extend(self.timestamp)
> +
> + # Generic Error Status Block
> + gebs = bytearray()
> +
> + if self.raw_data:
> + raw_data_offset = len(gebs)
> + else:
> + raw_data_offset = 0
> +
> + util.data_add(gebs, self.block_status, 4)
> + util.data_add(gebs, raw_data_offset, 4)
> + util.data_add(gebs, len(self.raw_data), 4)
> + util.data_add(gebs, data_length, 4)
> + util.data_add(gebs, self.error_severity, 4)
> +
> + cper_data = bytearray()
> + cper_data.extend(gebs)
> + cper_data.extend(gede)
> + cper_data.extend(bytearray(self.raw_data))
> + cper_data.extend(bytearray(payload))
> +
> + if self.debug:
> + print(f"GUID: {notif_type}")
> +
> + util.dump_bytearray("Generic Error Status Block", gebs)
> + util.dump_bytearray("Generic Error Data Entry", gede)
> +
> + if self.raw_data:
> + util.dump_bytearray("Raw data", bytearray(self.raw_data))
> +
> + util.dump_bytearray("Payload", payload)
> +
> + self.send_cper_raw(cper_data)
> +
> +
> + def search_qom(self, path, prop, regex):
> + """
> + Return a list of devices that match path array like:
> +
> + /machine/unattached/device
> + /machine/peripheral-anon/device
> + ...
> + """
> +
> + found = []
> +
> + i = 0
> + while 1:
> + dev = f"{path}[{i}]"
> + args = {
> + 'path': dev,
> + 'property': prop
> + }
> + ret = self.send_cmd("qom-get", args, may_open=True, return_error=False)
> + if not ret:
> + break
> +
> + if isinstance(ret, str):
> + if regex.search(ret):
> + found.append(dev)
> +
> + i += 1
> + if i > 10000:
> + print("Too many objects returned by qom-get!")
> + break
> +
> + return found
> +
> +class cper_guid:
> + """
> + Contains CPER GUID, as per:
> + https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html
> + """
> +
> + CPER_PROC_GENERIC = guid(0x9876CCAD, 0x47B4, 0x4bdb,
> + [0xB6, 0x5E, 0x16, 0xF1,
> + 0x93, 0xC4, 0xF3, 0xDB])
> +
> + CPER_PROC_X86 = guid(0xDC3EA0B0, 0xA144, 0x4797,
> + [0xB9, 0x5B, 0x53, 0xFA,
> + 0x24, 0x2B, 0x6E, 0x1D])
> +
> + CPER_PROC_ITANIUM = guid(0xe429faf1, 0x3cb7, 0x11d4,
> + [0xbc, 0xa7, 0x00, 0x80,
> + 0xc7, 0x3c, 0x88, 0x81])
> +
> + CPER_PROC_ARM = guid(0xE19E3D16, 0xBC11, 0x11E4,
> + [0x9C, 0xAA, 0xC2, 0x05,
> + 0x1D, 0x5D, 0x46, 0xB0])
> +
> + CPER_PLATFORM_MEM = guid(0xA5BC1114, 0x6F64, 0x4EDE,
> + [0xB8, 0x63, 0x3E, 0x83,
> + 0xED, 0x7C, 0x83, 0xB1])
> +
> + CPER_PLATFORM_MEM2 = guid(0x61EC04FC, 0x48E6, 0xD813,
> + [0x25, 0xC9, 0x8D, 0xAA,
> + 0x44, 0x75, 0x0B, 0x12])
> +
> + CPER_PCIE = guid(0xD995E954, 0xBBC1, 0x430F,
> + [0xAD, 0x91, 0xB4, 0x4D,
> + 0xCB, 0x3C, 0x6F, 0x35])
> +
> + CPER_PCI_BUS = guid(0xC5753963, 0x3B84, 0x4095,
> + [0xBF, 0x78, 0xED, 0xDA,
> + 0xD3, 0xF9, 0xC9, 0xDD])
> +
> + CPER_PCI_DEV = guid(0xEB5E4685, 0xCA66, 0x4769,
> + [0xB6, 0xA2, 0x26, 0x06,
> + 0x8B, 0x00, 0x13, 0x26])
> +
> + CPER_FW_ERROR = guid(0x81212A96, 0x09ED, 0x4996,
> + [0x94, 0x71, 0x8D, 0x72,
> + 0x9C, 0x8E, 0x69, 0xED])
> +
> + CPER_DMA_GENERIC = guid(0x5B51FEF7, 0xC79D, 0x4434,
> + [0x8F, 0x1B, 0xAA, 0x62,
> + 0xDE, 0x3E, 0x2C, 0x64])
> +
> + CPER_DMA_VT = guid(0x71761D37, 0x32B2, 0x45cd,
> + [0xA7, 0xD0, 0xB0, 0xFE,
> + 0xDD, 0x93, 0xE8, 0xCF])
> +
> + CPER_DMA_IOMMU = guid(0x036F84E1, 0x7F37, 0x428c,
> + [0xA7, 0x9E, 0x57, 0x5F,
> + 0xDF, 0xAA, 0x84, 0xEC])
> +
> + CPER_CCIX_PER = guid(0x91335EF6, 0xEBFB, 0x4478,
> + [0xA6, 0xA6, 0x88, 0xB7,
> + 0x28, 0xCF, 0x75, 0xD7])
> +
> + CPER_CXL_PROT_ERR = guid(0x80B9EFB4, 0x52B5, 0x4DE3,
> + [0xA7, 0x77, 0x68, 0x78,
> + 0x4B, 0x77, 0x10, 0x48])
© 2016 - 2025 Red Hat, Inc.