[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250129151454.0f5293d7@imammedo.users.ipa.redhat.com>
Date: Wed, 29 Jan 2025 15:14:54 +0100
From: Igor Mammedov <imammedo@...hat.com>
To: Mauro Carvalho Chehab <mchehab+huawei@...nel.org>
Cc: "Michael S . Tsirkin" <mst@...hat.com>, Jonathan Cameron
<Jonathan.Cameron@...wei.com>, Shiju Jose <shiju.jose@...wei.com>,
qemu-arm@...gnu.org, qemu-devel@...gnu.org, Ani Sinha
<anisinha@...hat.com>, Dongjiu Geng <gengdongjiu1@...il.com>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 04/13] acpi/ghes: Use HEST table offsets when
preparing GHES records
On Wed, 29 Jan 2025 09:04:10 +0100
Mauro Carvalho Chehab <mchehab+huawei@...nel.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@...nel.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");
Powered by blists - more mailing lists