ghes_edac: do a better job of filling EDAC DIMM info

Instead of just faking a random value for the DIMM data, get
the information that it is available via DMI table.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
This commit is contained in:
Mauro Carvalho Chehab 2013-02-14 09:11:08 -03:00
parent f04c62a703
commit 32fa1f53c2
1 changed files with 180 additions and 12 deletions

View File

@ -11,6 +11,7 @@
#include <acpi/ghes.h>
#include <linux/edac.h>
#include <linux/dmi.h>
#include "edac_core.h"
#define GHES_PFX "ghes_edac: "
@ -26,6 +27,155 @@ static LIST_HEAD(ghes_reglist);
static DEFINE_MUTEX(ghes_edac_lock);
static int ghes_edac_mc_num;
/* Memory Device - Type 17 of SMBIOS spec */
struct memdev_dmi_entry {
u8 type;
u8 length;
u16 handle;
u16 phys_mem_array_handle;
u16 mem_err_info_handle;
u16 total_width;
u16 data_width;
u16 size;
u8 form_factor;
u8 device_set;
u8 device_locator;
u8 bank_locator;
u8 memory_type;
u16 type_detail;
u16 speed;
u8 manufacturer;
u8 serial_number;
u8 asset_tag;
u8 part_number;
u8 attributes;
u32 extended_size;
u16 conf_mem_clk_speed;
} __attribute__((__packed__));
struct ghes_edac_dimm_fill {
struct mem_ctl_info *mci;
unsigned count;
};
char *memory_type[] = {
[MEM_EMPTY] = "EMPTY",
[MEM_RESERVED] = "RESERVED",
[MEM_UNKNOWN] = "UNKNOWN",
[MEM_FPM] = "FPM",
[MEM_EDO] = "EDO",
[MEM_BEDO] = "BEDO",
[MEM_SDR] = "SDR",
[MEM_RDR] = "RDR",
[MEM_DDR] = "DDR",
[MEM_RDDR] = "RDDR",
[MEM_RMBS] = "RMBS",
[MEM_DDR2] = "DDR2",
[MEM_FB_DDR2] = "FB_DDR2",
[MEM_RDDR2] = "RDDR2",
[MEM_XDR] = "XDR",
[MEM_DDR3] = "DDR3",
[MEM_RDDR3] = "RDDR3",
};
static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg)
{
int *num_dimm = arg;
if (dh->type == DMI_ENTRY_MEM_DEVICE)
(*num_dimm)++;
}
static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
{
struct ghes_edac_dimm_fill *dimm_fill = arg;
struct mem_ctl_info *mci = dimm_fill->mci;
if (dh->type == DMI_ENTRY_MEM_DEVICE) {
struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh;
struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
mci->n_layers,
dimm_fill->count, 0, 0);
if (entry->size == 0xffff) {
pr_info(GHES_PFX "Can't get dimm size\n");
dimm->nr_pages = MiB_TO_PAGES(32);/* Unknown */
} else if (entry->size == 0x7fff) {
dimm->nr_pages = MiB_TO_PAGES(entry->extended_size);
} else {
if (entry->size & 1 << 15)
dimm->nr_pages = MiB_TO_PAGES((entry->size &
0x7fff) << 10);
else
dimm->nr_pages = MiB_TO_PAGES(entry->size);
}
switch (entry->memory_type) {
case 0x12:
if (entry->type_detail & 1 << 13)
dimm->mtype = MEM_RDDR;
else
dimm->mtype = MEM_DDR;
break;
case 0x13:
if (entry->type_detail & 1 << 13)
dimm->mtype = MEM_RDDR2;
else
dimm->mtype = MEM_DDR2;
break;
case 0x14:
dimm->mtype = MEM_FB_DDR2;
break;
case 0x18:
if (entry->type_detail & 1 << 13)
dimm->mtype = MEM_RDDR3;
else
dimm->mtype = MEM_DDR3;
break;
default:
if (entry->type_detail & 1 << 6)
dimm->mtype = MEM_RMBS;
else if ((entry->type_detail & ((1 << 7) | (1 << 13)))
== ((1 << 7) | (1 << 13)))
dimm->mtype = MEM_RDR;
else if (entry->type_detail & 1 << 7)
dimm->mtype = MEM_SDR;
else if (entry->type_detail & 1 << 9)
dimm->mtype = MEM_EDO;
else
dimm->mtype = MEM_UNKNOWN;
}
/*
* Actually, we can only detect if the memory has bits for
* checksum or not
*/
if (entry->total_width == entry->data_width)
dimm->edac_mode = EDAC_NONE;
else
dimm->edac_mode = EDAC_SECDED;
dimm->dtype = DEV_UNKNOWN;
dimm->grain = 128; /* Likely, worse case */
/*
* FIXME: It shouldn't be hard to also fill the DIMM labels
*/
if (dimm->nr_pages) {
pr_info(GHES_PFX "DIMM%i: %s size = %d MB%s\n",
dimm_fill->count, memory_type[dimm->mtype],
PAGES_TO_MiB(dimm->nr_pages),
(dimm->edac_mode != EDAC_NONE) ? "(ECC)" : "");
pr_info(GHES_PFX "\ttype %d, detail 0x%02x, width %d(total %d)\n",
entry->memory_type, entry->type_detail,
entry->total_width, entry->data_width);
}
dimm_fill->count++;
}
}
void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
struct cper_sec_mem_err *mem_err)
{
@ -86,15 +236,24 @@ EXPORT_SYMBOL_GPL(ghes_edac_report_mem_error);
int ghes_edac_register(struct ghes *ghes, struct device *dev)
{
int rc;
bool fake = false;
int rc, num_dimm = 0;
struct mem_ctl_info *mci;
struct edac_mc_layer layers[1];
struct csrow_info *csrow;
struct dimm_info *dimm;
struct ghes_edac_pvt *pvt;
struct ghes_edac_dimm_fill dimm_fill;
/* Get the number of DIMMs */
dmi_walk(ghes_edac_count_dimms, &num_dimm);
/* Check if we've got a bogus BIOS */
if (num_dimm == 0) {
fake = true;
num_dimm = 1;
}
layers[0].type = EDAC_MC_LAYER_ALL_MEM;
layers[0].size = 1;
layers[0].size = num_dimm;
layers[0].is_virt_csrow = true;
/*
@ -102,6 +261,8 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
* to avoid duplicated memory controller numbers
*/
mutex_lock(&ghes_edac_lock);
pr_info("ghes_edac#%d: allocating space for %d dimms\n",
ghes_edac_mc_num, num_dimm);
mci = edac_mc_alloc(ghes_edac_mc_num, ARRAY_SIZE(layers), layers,
sizeof(*pvt));
if (!mci) {
@ -125,15 +286,22 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
mci->ctl_name = "ghes_edac";
mci->dev_name = "ghes";
csrow = mci->csrows[0];
dimm = csrow->channels[0]->dimm;
if (!fake) {
/* Fill DIMM info from DMI */
dimm_fill.count = 0;
dimm_fill.mci = mci;
dmi_walk(ghes_edac_dmidecode, &dimm_fill);
} else {
struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
mci->n_layers, 0, 0, 0);
/* FIXME: FAKE DATA */
pr_info(GHES_PFX "Crappy BIOS detected. Faking DIMM EDAC data\n");
dimm->nr_pages = 1000;
dimm->grain = 128;
dimm->mtype = MEM_UNKNOWN;
dimm->dtype = DEV_UNKNOWN;
dimm->edac_mode = EDAC_SECDED;
}
rc = edac_mc_add_mc(mci);
if (rc < 0) {