diff mbox series

[QEMU,v2,1/1] hw/arm: FW first ARM processor error injection

Message ID 20240624153950.350-1-shiju.jose@huawei.com (mailing list archive)
State New, archived
Headers show
Series [QEMU,v2,1/1] hw/arm: FW first ARM processor error injection | expand

Commit Message

Zhijian Li (Fujitsu)" via June 24, 2024, 3:39 p.m. UTC
From: Shiju Jose <shiju.jose@huawei.com>

Add support for QEMU based FW first ARM processor error injection.

Compliance with N.2.4.4 ARM Processor Error Section in
UEFI 2.9A/2.10 specs.

Examples,
{ "execute": "arm-inject-error",
      "arguments": {
        "errortypes": ['cache-error']
      }
}

{ "execute": "arm-inject-error",
      "arguments": {
        "errortypes": ['tlb-error']
      }
}

{ "execute": "arm-inject-error",
      "arguments": {
        "errortypes": ['bus-error']
      }
}

{ "execute": "arm-inject-error",
      "arguments": {
        "errortypes": ['cache-error', 'tlb-error']
      }
}

{ "execute": "arm-inject-error",
      "arguments": {
        "errortypes": ['cache-error', 'tlb-error', 'bus-error', 'micro-arch-error']
      }
}
etc.

The patch is added on top of the FW-first error reporting supporting
in the following Jonathan's repo.
http://gitlab.com/jic23/qemu/ cxl-2024-06-21

Mauro Carvalho added some instructions about how to use it under rasdaemon
page: https://github.com/mchehab/rasdaemon/wiki/Error-injection-testing

Link: https://lore.kernel.org/r/20240621165115.336-1-shiju.jose@huawei.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>

Change History:
v1 -> V2
1. Updated patch header.
2. Fix the issues reported by Peter Maydell. Thanks.
---
 configs/targets/aarch64-softmmu.mak |   1 +
 hw/acpi/ghes.c                      | 170 +++++++++++++++++++++++++++-
 hw/arm/Kconfig                      |   4 +
 hw/arm/arm_error_inject.c           |  35 ++++++
 hw/arm/arm_error_inject_stubs.c     |  22 ++++
 hw/arm/meson.build                  |   4 +
 include/hw/acpi/ghes.h              |   1 +
 qapi/arm-error-inject.json          |  44 +++++++
 qapi/meson.build                    |   1 +
 qapi/qapi-schema.json               |   1 +
 10 files changed, 282 insertions(+), 1 deletion(-)
 create mode 100644 hw/arm/arm_error_inject.c
 create mode 100644 hw/arm/arm_error_inject_stubs.c
 create mode 100644 qapi/arm-error-inject.json

Comments

Peter Maydell June 24, 2024, 3:41 p.m. UTC | #1
On Mon, 24 Jun 2024 at 16:40, <shiju.jose@huawei.com> wrote:
>
> From: Shiju Jose <shiju.jose@huawei.com>
>
> Add support for QEMU based FW first ARM processor error injection.


> +++ b/hw/arm/arm_error_inject_stubs.c
> @@ -0,0 +1,22 @@
> +/*
> + * ARM  Processor errors QMP stubs
> + *
> + * Copyright(C) 2024 Huawei LTD.
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2. See the
> + * COPYING file in the top-level directory.
> + *
> + * SPDX-License-Identifier: GPL-v2-only

You missed an instance of gpl-v2-only (but you don't need to
respin immediately just for this).

thanks
-- PMM
diff mbox series

Patch

diff --git a/configs/targets/aarch64-softmmu.mak b/configs/targets/aarch64-softmmu.mak
index 84cb32dc2f..b4b3cd9793 100644
--- a/configs/targets/aarch64-softmmu.mak
+++ b/configs/targets/aarch64-softmmu.mak
@@ -5,3 +5,4 @@  TARGET_KVM_HAVE_GUEST_DEBUG=y
 TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/arm-core.xml gdb-xml/arm-vfp.xml gdb-xml/arm-vfp3.xml gdb-xml/arm-vfp-sysregs.xml gdb-xml/arm-neon.xml gdb-xml/arm-m-profile.xml gdb-xml/arm-m-profile-mve.xml gdb-xml/aarch64-pauth.xml
 # needed by boot.c
 TARGET_NEED_FDT=y
+CONFIG_ARM_EINJ=y
diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 34d8b8a518..ba18e849e2 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -31,6 +31,7 @@ 
 #include "qemu/uuid.h"
 #include "hw/cxl/cxl_device.h"
 #include "hw/cxl/cxl.h"
+#include "qapi/qapi-types-arm-error-inject.h"
 
 #define ACPI_GHES_ERRORS_FW_CFG_FILE        "etc/hardware_errors"
 #define ACPI_GHES_DATA_ADDR_FW_CFG_FILE     "etc/hardware_errors_addr"
@@ -57,6 +58,7 @@ 
 /* The memory section CPER size, UEFI 2.6: N.2.5 Memory Error Section */
 #define ACPI_GHES_MEM_CPER_LENGTH           80
 #define ACPI_GHES_PCIE_CPER_LENGTH 208
+#define ACPI_GHES_ARM_CPER_LENGTH (72 + 600)
 
 /* Masks for block_status flags */
 #define ACPI_GEBS_UNCORRECTABLE         1
@@ -189,6 +191,94 @@  static void acpi_ghes_build_append_mem_cper(GArray *table,
     build_append_int_noprefix(table, 0, 7);
 }
 
+/* UEFI 2.9: N.2.4.4 ARM Processor Error Section */
+static void acpi_ghes_build_append_arm_cper(uint8_t error_types, GArray *table)
+{
+    /*
+     * ARM Processor Error Record
+     */
+
+    /* Validation Bits */
+    build_append_int_noprefix(table,
+                              (1ULL << 3) | /* Vendor specific info Valid */
+                              (1ULL << 2) | /* Running status Valid */
+                              (1ULL << 1) | /* Error affinity level Valid */
+                              (1ULL << 0), /* MPIDR Valid */
+                              4);
+    /* Error Info Num */
+    build_append_int_noprefix(table, 1, 2);
+    /* Context Info Num */
+    build_append_int_noprefix(table, 1, 2);
+    /* Section length */
+    build_append_int_noprefix(table, ACPI_GHES_ARM_CPER_LENGTH, 4);
+    /* Error affinity level */
+    build_append_int_noprefix(table, 2, 1);
+    /* Reserved */
+    build_append_int_noprefix(table, 0, 3);
+    /* MPIDR_EL1 */
+    build_append_int_noprefix(table, 0xAB12, 8);
+    /* MIDR_EL1 */
+    build_append_int_noprefix(table, 0xCD24, 8);
+    /* Running state */
+    build_append_int_noprefix(table, 0x1, 4);
+    /* PSCI state */
+    build_append_int_noprefix(table, 0x1234, 4);
+
+    /* ARM Propcessor error information */
+    /* Version */
+    build_append_int_noprefix(table, 0, 1);
+    /*  Length */
+    build_append_int_noprefix(table, 32, 1);
+    /* Validation Bits */
+    build_append_int_noprefix(table,
+                              (1ULL << 4) | /* Physical fault address Valid */
+                             (1ULL << 3) | /* Virtual fault address Valid */
+                             (1ULL << 2) | /* Error information Valid */
+                              (1ULL << 1) | /* Flags Valid */
+                              (1ULL << 0), /* Multiple error count Valid */
+                              2);
+    /* Type */
+    if (error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_CACHE_ERROR) ||
+        error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_TLB_ERROR) ||
+        error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_BUS_ERROR) ||
+        error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_MICRO_ARCH_ERROR)) {
+        build_append_int_noprefix(table, error_types, 1);
+    } else {
+        return;
+    }
+    /* Multiple error count */
+    build_append_int_noprefix(table, 2, 2);
+    /* Flags  */
+    build_append_int_noprefix(table, 0xD, 1);
+    /* Error information  */
+    if (error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_CACHE_ERROR)) {
+        build_append_int_noprefix(table, 0x0091000F, 8);
+    } else if (error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_TLB_ERROR)) {
+        build_append_int_noprefix(table, 0x0054007F, 8);
+    } else if (error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_BUS_ERROR)) {
+        build_append_int_noprefix(table, 0x80D6460FFF, 8);
+    } else if (error_types & BIT(ARM_PROCESSOR_ERROR_TYPE_MICRO_ARCH_ERROR)) {
+        build_append_int_noprefix(table, 0x78DA03FF, 8);
+    } else {
+        return;
+    }
+    /* Virtual fault address  */
+    build_append_int_noprefix(table, 0x67320230, 8);
+    /* Physical fault address  */
+    build_append_int_noprefix(table, 0x5CDFD492, 8);
+
+    /* ARM Propcessor error context information */
+    /* Version */
+    build_append_int_noprefix(table, 0, 2);
+    /* Validation Bits */
+    /* AArch64 EL1 context registers Valid */
+    build_append_int_noprefix(table, 5, 2);
+    /* Register array size */
+    build_append_int_noprefix(table, 592, 4);
+    /* Register array */
+    build_append_int_noprefix(table, 0x12ABDE67, 8);
+}
+
 static void build_append_aer_cper(PCIDevice *dev, GArray *table)
 {
     PCIDeviceClass *pci_class = PCI_DEVICE_GET_CLASS(dev);
@@ -468,7 +558,8 @@  static int acpi_ghes_record_mem_error(uint64_t error_block_address,
           UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \
                   0xED, 0x7C, 0x83, 0xB1);
 
-    /* invalid fru id: ACPI 4.0: 17.3.2.6.1 Generic Error Data,
+    /*
+     * Invalid fru id: ACPI 4.0: 17.3.2.6.1 Generic Error Data,
      * Table 17-13 Generic Error Data Entry
      */
     QemuUUID fru_id = {};
@@ -505,6 +596,54 @@  static int acpi_ghes_record_mem_error(uint64_t error_block_address,
     return 0;
 }
 
+static int acpi_ghes_record_arm_error(uint8_t error_types,
+                                      uint64_t error_block_address)
+{
+    GArray *block;
+
+    /* Memory Error Section Type */
+    const uint8_t uefi_cper_arm_sec[] =
+          UUID_LE(0xE19E3D16, 0xBC11, 0x11E4, 0x9C, 0xAA, 0xC2, 0x05, \
+                  0x1D, 0x5D, 0x46, 0xB0);
+
+    /*
+     * Invalid fru id: ACPI 4.0: 17.3.2.6.1 Generic Error Data,
+     * Table 17-13 Generic Error Data Entry
+     */
+    QemuUUID fru_id = {};
+    uint32_t data_length;
+
+    block = g_array_new(false, true /* clear */, 1);
+
+    /* This is the length if adding a new generic error data entry*/
+    data_length = ACPI_GHES_DATA_LENGTH + ACPI_GHES_ARM_CPER_LENGTH;
+    /*
+     * It should not run out of the preallocated memory if adding a new generic
+     * error data entry
+     */
+    assert((data_length + ACPI_GHES_GESB_SIZE) <=
+            ACPI_GHES_MAX_RAW_DATA_LENGTH);
+
+    /* Build the new generic error status block header */
+    acpi_ghes_generic_error_status(block, ACPI_GEBS_UNCORRECTABLE,
+        0, 0, data_length, ACPI_CPER_SEV_RECOVERABLE);
+
+    /* Build this new generic error data entry header */
+    acpi_ghes_generic_error_data(block, uefi_cper_arm_sec,
+        ACPI_CPER_SEV_RECOVERABLE, 0, 0,
+        ACPI_GHES_ARM_CPER_LENGTH, fru_id, 0);
+
+    /* Build the ARM processor error section CPER */
+    acpi_ghes_build_append_arm_cper(error_types, block);
+
+    /* Write the generic error data entry into guest memory */
+    cpu_physical_memory_write(error_block_address, block->data, block->len);
+
+    g_array_free(block, true);
+
+    return 0;
+}
+
 static int ghes_record_aer_error(PCIDevice *dev, uint64_t error_block_address)
 {
     const uint8_t aer_section_id_le[] = {
@@ -917,6 +1056,35 @@  static bool ghes_get_addr(uint32_t notify, uint64_t *error_block_addr,
     return true;
 }
 
+bool ghes_record_arm_errors(uint8_t error_types, uint32_t notify)
+{
+    int read_ack_register = 0;
+    uint64_t read_ack_register_addr = 0;
+    uint64_t error_block_addr = 0;
+
+    if (!ghes_get_addr(notify, &error_block_addr, &read_ack_register_addr)) {
+        return false;
+    }
+
+    cpu_physical_memory_read(read_ack_register_addr,
+                             &read_ack_register, sizeof(uint64_t));
+    /* zero means OSPM does not acknowledge the error */
+    if (!read_ack_register) {
+        error_report("Last time OSPM does not acknowledge the error,"
+                     " record CPER failed this time, set the ack value to"
+                     " avoid blocking next time CPER record! exit");
+        read_ack_register = 1;
+        cpu_physical_memory_write(read_ack_register_addr,
+                                  &read_ack_register, sizeof(uint64_t));
+        return false;
+    }
+
+    read_ack_register = cpu_to_le64(0);
+    cpu_physical_memory_write(read_ack_register_addr,
+                              &read_ack_register, sizeof(uint64_t));
+    return acpi_ghes_record_arm_error(error_types, error_block_addr);
+}
+
 bool ghes_record_aer_errors(PCIDevice *dev, uint32_t notify)
 {
     int read_ack_register = 0;
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index 5279162287..fb31a57c20 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -717,3 +717,7 @@  config ARMSSE
     select UNIMP
     select SSE_COUNTER
     select SSE_TIMER
+
+config CXL_ARM_EINJ
+    bool
+    default y if AARCH64
diff --git a/hw/arm/arm_error_inject.c b/hw/arm/arm_error_inject.c
new file mode 100644
index 0000000000..8a76a31733
--- /dev/null
+++ b/hw/arm/arm_error_inject.c
@@ -0,0 +1,35 @@ 
+/*
+ * ARM Processor error injection 
+ *
+ * Copyright(C) 2024 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/qapi-commands-arm-error-inject.h"
+#include "qapi/error.h"
+#include "hw/boards.h"
+#include "hw/acpi/ghes.h"
+
+/* For ARM processor errors */
+void qmp_arm_inject_error(ArmProcessorErrorTypeList *errortypes, Error **errp)
+{
+    MachineState *machine = MACHINE(qdev_get_machine());
+    MachineClass *mc = MACHINE_GET_CLASS(machine);
+    uint8_t error_types = 0;
+
+    while (errortypes) {
+        error_types |= BIT(errortypes->value);
+        errortypes = errortypes->next;
+    }
+
+    ghes_record_arm_errors(error_types, ACPI_GHES_NOTIFY_GPIO);
+    if (mc->set_error) {
+        mc->set_error();
+    }
+
+    return;
+}
diff --git a/hw/arm/arm_error_inject_stubs.c b/hw/arm/arm_error_inject_stubs.c
new file mode 100644
index 0000000000..065a15cfb4
--- /dev/null
+++ b/hw/arm/arm_error_inject_stubs.c
@@ -0,0 +1,22 @@ 
+/*
+ * ARM  Processor errors QMP stubs
+ *
+ * Copyright(C) 2024 Huawei LTD.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See the
+ * COPYING file in the top-level directory.
+ *
+ * SPDX-License-Identifier: GPL-v2-only
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qapi/qapi-commands-arm-error-inject.h"
+
+
+typedef struct ArmProcessorErrorTypeList ArmProcessorErrorTypeList;
+
+void qmp_arm_inject_error(ArmProcessorErrorTypeList *type, Error **errp)
+{
+    error_setg(errp, "ARM processor error support is not compiled in");
+}
diff --git a/hw/arm/meson.build b/hw/arm/meson.build
index 0c07ab522f..59666b9d4e 100644
--- a/hw/arm/meson.build
+++ b/hw/arm/meson.build
@@ -60,6 +60,10 @@  arm_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmuv3.c'))
 arm_ss.add(when: 'CONFIG_FSL_IMX6UL', if_true: files('fsl-imx6ul.c', 'mcimx6ul-evk.c'))
 arm_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_soc.c'))
 arm_ss.add(when: 'CONFIG_XEN', if_true: files('xen_arm.c'))
+system_ss.add(when: 'CONFIG_ARM_EINJ', if_true: files('arm_error_inject.c'))
+system_ss.add(when: 'CONFIG_ARM_EINJ', if_false: files('arm_error_inject_stubs.c'))
+system_ss.add(when: 'CONFIG_ALL', if_true: files('arm_error_inject_stubs.c'))
+
 
 system_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmu-common.c'))
 system_ss.add(when: 'CONFIG_CHEETAH', if_true: files('palm.c'))
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index a12d6a7b22..2ff89edb3c 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -78,6 +78,7 @@  int acpi_ghes_record_errors(uint8_t notify, uint64_t error_physical_addr);
 
 typedef struct PCIDevice PCIDevice;
 bool ghes_record_aer_errors(PCIDevice *dev, uint32_t notify);
+bool ghes_record_arm_errors(uint8_t type, uint32_t notify);
 
 typedef struct CXLError CXLError;
 typedef struct PCIEAERErr PCIEAERErr;
diff --git a/qapi/arm-error-inject.json b/qapi/arm-error-inject.json
new file mode 100644
index 0000000000..ccd94d2987
--- /dev/null
+++ b/qapi/arm-error-inject.json
@@ -0,0 +1,44 @@ 
+# -*- Mode: Python -*-
+# vim: filetype=python
+
+##
+# = ARM Processor Errors
+##
+
+##
+# @ArmProcessorErrorType:
+#
+# Type of ARM processor error to inject
+#
+# @unknown-error: Unknown error
+#
+# @cache-error: Cache error
+#
+# @tlb-error: TLB error
+#
+# @bus-error: Bus error.
+#
+# @micro-arch-error: Micro architectural error.
+#
+# Since: 8.0
+##
+{ 'enum': 'ArmProcessorErrorType',
+  'data': ['unknown-error',
+	   'cache-error',
+           'tlb-error',
+           'bus-error',
+           'micro-arch-error']
+}
+
+##
+# @arm-inject-error:
+#
+# Inject ARM Processor error.
+#
+# @errortypes: ARM processor error types to inject
+#
+# Since: 8.1
+##
+{ 'command': 'arm-inject-error',
+  'data': { 'errortypes': ['ArmProcessorErrorType'] }
+}
diff --git a/qapi/meson.build b/qapi/meson.build
index e7bc54e5d0..5927932c4b 100644
--- a/qapi/meson.build
+++ b/qapi/meson.build
@@ -22,6 +22,7 @@  if have_system or have_tools or have_ga
 endif
 
 qapi_all_modules = [
+  'arm-error-inject',
   'authz',
   'block',
   'block-core',
diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json
index b1581988e4..479a22de7e 100644
--- a/qapi/qapi-schema.json
+++ b/qapi/qapi-schema.json
@@ -81,3 +81,4 @@ 
 { 'include': 'vfio.json' }
 { 'include': 'cryptodev.json' }
 { 'include': 'cxl.json' }
+{ 'include': 'arm-error-inject.json' }