(Pulling in Tony)
On Tue, 04 Mar, at 04:10:57PM, Adrian Huang12 wrote:
> Some fields might be added to the Error Section in the newer UEFI
> spec. For example, the fields 'Reserved', 'Rank Number',
> 'Card Handle' and 'Module Handle' are added to the Memory Error
> Section started from UEFI spec 2.3. Unfortunately, there will have
> the following warning message if the memory corrected error is
> detected and the field 'revision' in struct acpi_generic_data is
> less then 0x203 (UEFI spec 2.3):
>
> {1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 3
> {1}[Hardware Error]: It has been corrected by h/w and requires no further action
> {1}[Hardware Error]: event severity: corrected
> {1}[Hardware Error]: Error 0, type: corrected
> {1}[Hardware Error]: section_type: memory error
> [Firmware Warn]: error section length is too small
>
> This behavior causes this corrected error cannot be displayed
> correctly. To solve the issue, this patch supports different
> length of the Error Section for different UEFI spec version.
>
> And, this patch employs a pre-defined structure to clean up the
> duplicated codes in function cper_estatus_print_section.
>
> With applying this patch, the memory corrected error could be
> displayed correctly after injecting the error.
>
> Tested on v3.14-rc5 with Grantley platform and Intel RAStool.
>
> Signed-off-by: Adrian Huang <ahuang12@xxxxxxxxxx>
> ---
> drivers/firmware/efi/cper.c | 110 +++++++++++++++++++++++++++++++++-----------
> 1 file changed, 84 insertions(+), 26 deletions(-)
>
> diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
> index 1491dd4..c33f1e3 100644
> --- a/drivers/firmware/efi/cper.c
> +++ b/drivers/firmware/efi/cper.c
> @@ -132,9 +132,11 @@ static const char * const cper_proc_flag_strs[] = {
> "corrected",
> };
>
> -static void cper_print_proc_generic(const char *pfx,
> - const struct cper_sec_proc_generic *proc)
> +static void cper_print_proc_generic(const char *pfx, const void *data)
> {
> + const struct cper_sec_proc_generic *proc =
> + (struct cper_sec_proc_generic *) data;
> +
> if (proc->validation_bits & CPER_PROC_VALID_TYPE)
> printk("%s""processor_type: %d, %s\n", pfx, proc->proc_type,
> proc->proc_type < ARRAY_SIZE(cper_proc_type_strs) ?
> @@ -196,8 +198,10 @@ static const char *cper_mem_err_type_strs[] = {
> "physical memory map-out event",
> };
>
> -static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
> +static void cper_print_mem(const char *pfx, const void *data)
> {
> + const struct cper_sec_mem_err *mem = (struct cper_sec_mem_err *) data;
> +
> if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
> printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
> if (mem->validation_bits & CPER_MEM_VALID_PA)
> @@ -261,9 +265,10 @@ static const char *cper_pcie_port_type_strs[] = {
> "root complex event collector",
> };
>
> -static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
> - const struct acpi_generic_data *gdata)
> +static void cper_print_pcie(const char *pfx, const void *data)
> {
> + struct cper_sec_pcie *pcie = (struct cper_sec_pcie *) data;
> +
> if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
> printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
> pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ?
> @@ -297,12 +302,73 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
> pfx, pcie->bridge.secondary_status, pcie->bridge.control);
> }
>
> +struct cper_section_length {
> + u32 revision;
> + u32 length;
> +};
> +
> +/* Per ACPI spec 4.0/5.0, the referred UEFI revision is 2.1. */
> +static struct cper_section_length proc_generic_section_len[] = {
> + {0x201, sizeof(struct cper_sec_proc_generic)},
> + {}
> +};
> +
> +/*
> + * Per ACPI spec 4.0/5.0, the referred UEFI revision is 2.1.
> + * Some fields are added to Memory Error Section in UEFI 2.3 and later,
> + * so we need to distinguish the difference.
> + */
> +static struct cper_section_length mem_section_len[] = {
> + {0x203, sizeof(struct cper_sec_mem_err)},
> + {0x201, offsetof(struct cper_sec_mem_err, reserved)},
> + {}
> +};
> +
> +/* Per ACPI spec 4.0/5.0, the referred UEFI revision is 2.1. */
> +static struct cper_section_length pcie_section_len[] = {
> + {0x201, sizeof(struct cper_sec_pcie)},
> + {}
> +};
> +
> +struct cper_estatus_section_info {
> + uuid_le type;
> + char *name;
> + struct cper_section_length *section_length;
> + void (*print_fn)(const char *, const void *);
> +};
> +
> +static struct cper_estatus_section_info section_info[] = {
> + {CPER_SEC_PROC_GENERIC, "general processor", proc_generic_section_len,
> + cper_print_proc_generic},
> + {CPER_SEC_PLATFORM_MEM, "memory", mem_section_len, cper_print_mem},
> + {CPER_SEC_PCIE, "PCIe", pcie_section_len, cper_print_pcie},
> + {}
> +};
> +
> +static int cper_estatus_check_section(const struct acpi_generic_data *gdata,
> + struct cper_section_length *len)
> +{
> + struct cper_section_length *sec_length;
> +
> + for (sec_length = len; sec_length->revision; sec_length++) {
> + /* Find the corresponding entry. */
> + if (gdata->revision >= (u16) sec_length->revision)
> + break;
> + }
> +
> + if (!sec_length || !sec_length->revision)
> + return -EINVAL;
> +
> + return gdata->error_data_length >= sec_length->length ? 0 : -EINVAL;
> +}
> +
> static void cper_estatus_print_section(
> const char *pfx, const struct acpi_generic_data *gdata, int sec_no)
> {
> uuid_le *sec_type = (uuid_le *)gdata->section_type;
> __u16 severity;
> char newpfx[64];
> + struct cper_estatus_section_info *s_info;
>
> severity = gdata->error_severity;
> printk("%s""Error %d, type: %s\n", pfx, sec_no,
> @@ -313,28 +379,20 @@ static void cper_estatus_print_section(
> printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
>
> snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
> - if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) {
> - struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1);
> - printk("%s""section_type: general processor error\n", newpfx);
> - if (gdata->error_data_length >= sizeof(*proc_err))
> - cper_print_proc_generic(newpfx, proc_err);
> - else
> - goto err_section_too_small;
> - } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
> - struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
> - printk("%s""section_type: memory error\n", newpfx);
> - if (gdata->error_data_length >= sizeof(*mem_err))
> - cper_print_mem(newpfx, mem_err);
> - else
> - goto err_section_too_small;
> - } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
> - struct cper_sec_pcie *pcie = (void *)(gdata + 1);
> - printk("%s""section_type: PCIe error\n", newpfx);
> - if (gdata->error_data_length >= sizeof(*pcie))
> - cper_print_pcie(newpfx, pcie, gdata);
> - else
> +
> + for (s_info = section_info; s_info->print_fn; s_info++) {
> + if (uuid_le_cmp(*sec_type, s_info->type))
> + continue;
> +
> + if (cper_estatus_check_section(gdata, s_info->section_length))
> goto err_section_too_small;
> - } else
> +
> + printk("%s""section_type: %s\n", newpfx, s_info->name);
> + s_info->print_fn(newpfx, (void *) (gdata + 1));
> + break;
> + }
> +
> + if (!s_info->print_fn)
> printk("%s""section type: unknown, %pUl\n", newpfx, sec_type);
>
> return;
> --
> 1.8.1.2
>
>
--
Matt Fleming, Intel Open Source Technology Center
--
To unsubscribe from this list: send the line "unsubscribe linux-efi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
