[PATCH v6 06/10] acpi/ghes: add support for generic error injection via QAPI

Mauro Carvalho Chehab posted 10 patches 3 months, 2 weeks ago
There is a newer version of this series
[PATCH v6 06/10] acpi/ghes: add support for generic error injection via QAPI
Posted by Mauro Carvalho Chehab 3 months, 2 weeks ago
Provide a generic interface for error injection via GHESv2.

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>
---
 hw/acpi/ghes.c         | 78 ++++++++++++++++++++++++++++++++++++++++++
 hw/acpi/ghes_cper.c    |  2 +-
 include/hw/acpi/ghes.h |  3 ++
 3 files changed, 82 insertions(+), 1 deletion(-)

diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 26e93dd0f6e2..8525481bb828 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -534,6 +534,84 @@ int acpi_ghes_record_errors(enum AcpiGhesNotifyType notify,
 NotifierList acpi_generic_error_notifiers =
     NOTIFIER_LIST_INITIALIZER(error_device_notifiers);
 
+void ghes_record_cper_errors(AcpiGhesCper *cper, Error **errp,
+                             enum AcpiGhesNotifyType notify)
+{
+    uint64_t cper_addr, read_ack_start_addr;
+    uint64_t read_ack = 0;
+    uint32_t data_length;
+    GArray *block;
+    uint32_t i;
+
+    if (ghes_get_hardware_errors_address(notify, NULL, &read_ack_start_addr,
+                                         &cper_addr, NULL)) {
+        error_setg(errp,
+                   "GHES: Invalid error block/ack address(es) for notify %d",
+                   notify);
+        return;
+    }
+
+    cpu_physical_memory_read(read_ack_start_addr,
+                             &read_ack, sizeof(uint64_t));
+
+    /* zero means OSPM does not acknowledge the error */
+    if (!read_ack) {
+        error_setg(errp,
+                   "Last CPER record was not acknowledged yet");
+        read_ack = 1;
+        cpu_physical_memory_write(read_ack_start_addr,
+                                  &read_ack, sizeof(uint64_t));
+        return;
+    }
+
+    read_ack = cpu_to_le64(0);
+    cpu_physical_memory_write(read_ack_start_addr,
+                              &read_ack, sizeof(uint64_t));
+
+    /* Build CPER record */
+
+    /*
+     * Invalid fru id: ACPI 4.0: 17.3.2.6.1 Generic Error Data,
+     * Table 17-13 Generic Error Data Entry
+     */
+    QemuUUID fru_id = {};
+
+    block = g_array_new(false, true /* clear */, 1);
+    data_length = ACPI_GHES_DATA_LENGTH + cper->data_len;
+
+    /*
+     * It should not run out of the preallocated memory if
+     * adding a new generic error data entry
+     */
+    if ((data_length + ACPI_GHES_GESB_SIZE) >
+        ACPI_GHES_MAX_RAW_DATA_LENGTH) {
+        error_setg(errp, "GHES CPER record is too big: %d",
+                   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, cper->guid,
+                                ACPI_CPER_SEV_RECOVERABLE, 0, 0,
+                                cper->data_len, fru_id, 0);
+
+    /* Add CPER data */
+    for (i = 0; i < cper->data_len; i++) {
+        build_append_int_noprefix(block, cper->data[i], 1);
+    }
+
+    /* Write the generic error data entry into guest memory */
+    cpu_physical_memory_write(cper_addr, block->data, block->len);
+
+    g_array_free(block, true);
+
+    notifier_list_notify(&acpi_generic_error_notifiers, NULL);
+}
+
 bool acpi_ghes_present(void)
 {
     AcpiGedState *acpi_ged_state;
diff --git a/hw/acpi/ghes_cper.c b/hw/acpi/ghes_cper.c
index 7aa7e71e90dc..d7ff7debee74 100644
--- a/hw/acpi/ghes_cper.c
+++ b/hw/acpi/ghes_cper.c
@@ -39,7 +39,7 @@ void qmp_ghes_cper(CommonPlatformErrorRecord *qmp_cper,
         return;
     }
 
-    /* TODO: call a function at ghes */
+    ghes_record_cper_errors(&cper, errp, ACPI_GHES_NOTIFY_GPIO);
 
     g_free(cper.data);
 }
diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h
index 2fcfa1cc8090..5a7bdb08f8e2 100644
--- a/include/hw/acpi/ghes.h
+++ b/include/hw/acpi/ghes.h
@@ -79,6 +79,9 @@ typedef struct AcpiGhesCper {
     size_t data_len;
 } AcpiGhesCper;
 
+void ghes_record_cper_errors(AcpiGhesCper *cper, Error **errp,
+                             enum AcpiGhesNotifyType notify);
+
 /**
  * acpi_ghes_present: Report whether ACPI GHES table is present
  *
-- 
2.45.2