diff mbox series

[v2,3/5] acpi/ghes: Use HEST table offsets when preparing GHES records

Message ID b1a43a91ea70d5972455318f6a00b6e0adb89202.1732281080.git.mchehab+huawei@kernel.org (mailing list archive)
State New
Headers show
Series Change ghes driver to use HEST-based offsets | expand

Commit Message

Mauro Carvalho Chehab Nov. 22, 2024, 1:14 p.m. UTC
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, which needs a reset before next error.

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 | 98 ++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 88 insertions(+), 10 deletions(-)

Comments

Jonathan Cameron Nov. 25, 2024, noon UTC | #1
On Fri, 22 Nov 2024 14:14:13 +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, which needs a reset before next error.
> 
> 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>
> ---
Just repeat of the comment I failed to explain properly on previous version
about comment style.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

>  hw/acpi/ghes.c | 98 ++++++++++++++++++++++++++++++++++++++++++++------
>  1 file changed, 88 insertions(+), 10 deletions(-)
> 
> diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
> index 680cada0e487..b5e3e2891445 100644
> --- a/hw/acpi/ghes.c
> +++ b/hw/acpi/ghes.c
> @@ -61,6 +61,23 @@
>   */
>  #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.
> + */
> +
This was the bit I failed to explain in previous review.
I think for consistency it should be.

/*
 * ACPI 6.2: 18.3.2.8 Generic Hardware Error Source version 2
 * Table 18-382 Generic Hardware Error Source version 2 (GHESv2) Structure
 */
> +/* 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)
> +
> +/* ACPI 6.2: 18.3.2.7: Generic Hardware Error Source
Similar here.
> + * Table 18-380: 'Error Status Address' field
> + */
> +#define GHES_ERR_ST_ADDR_OFFSET  (20 + GAS_ADDR_OFFSET)
> +
diff mbox series

Patch

diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c
index 680cada0e487..b5e3e2891445 100644
--- a/hw/acpi/ghes.c
+++ b/hw/acpi/ghes.c
@@ -61,6 +61,23 @@ 
  */
 #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_ACK_OFFSET          (64 + GAS_ADDR_OFFSET)
+
+/* 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)
+
 /*
  * Values for error_severity field
  */
@@ -212,14 +229,6 @@  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));
@@ -419,6 +428,70 @@  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,
+                                    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;
+    uint32_t num_sources, i;
+
+    if (!hest_addr) {
+        return;
+    }
+
+    cpu_physical_memory_read(hest_addr, &num_sources, sizeof(num_sources));
+    num_sources = le32_to_cpu(num_sources);
+
+    err_source_struct = hest_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;
+        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 (src_id == source_id) {
+            break;
+        }
+
+        err_source_struct += 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_struct + GHES_ERR_ST_ADDR_OFFSET;
+    hest_read_ack_addr = err_source_struct + GHES_ACK_OFFSET;
+
+    cpu_physical_memory_read(hest_err_block_addr, &error_block_addr,
+                             sizeof(error_block_addr));
+
+    cpu_physical_memory_read(error_block_addr, cper_addr,
+                             sizeof(*cper_addr));
+
+    cpu_physical_memory_read(hest_read_ack_addr, read_ack_start_addr,
+                             sizeof(*read_ack_start_addr));
+}
+
 void ghes_record_cper_errors(const void *cper, size_t len,
                              uint16_t source_id, Error **errp)
 {
@@ -439,8 +512,13 @@  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);
+    }
 
     cper_addr = le64_to_cpu(cper_addr);
     if (!cper_addr) {