EDAC, ghes: Use CPER module handles to locate DIMMs

Use SMBIOS module handle type 17, on platforms which provide valid
ones, to locate the corresponding DIMM and thus have per-DIMM error
counter updates.

Signed-off-by: Fan Wu <wufan@codeaurora.org>
[ Massage commit message. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tyler Baicar <baicar.tyler@gmail.com>
Reviewed-by: James Morse <james.morse@arm.com>
Tested-by: Toshi Kani <toshi.kani@hpe.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: baicar.tyler@gmail.com
Cc: john.garry@huawei.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: shiju.jose@huawei.com
Cc: tanxiaofei@huawei.com
Cc: wanghuiqiang@huawei.com
Link: http://lkml.kernel.org/r/1537322340-1860-1-git-send-email-wufan@codeaurora.org

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 473aeec4b1da44ec4c069d1225db85c67ea691a8..49396bf6ad88f7a2b988a63fdf4183dff96719c3 100644 (file)
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -81,6 +81,18 @@ static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg)
                (*num_dimm)++;
 }
 
+static int get_dimm_smbios_index(u16 handle)
+{
+       struct mem_ctl_info *mci = ghes_pvt->mci;
+       int i;
+
+       for (i = 0; i < mci->tot_dimms; i++) {
+               if (mci->dimms[i]->smbios_handle == handle)
+                       return i;
+       }
+       return -1;
+}
+
 static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
 {
        struct ghes_edac_dimm_fill *dimm_fill = arg;
@@ -177,6 +189,8 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg)
                                entry->total_width, entry->data_width);
                }
 
+               dimm->smbios_handle = entry->handle;
+
                dimm_fill->count++;
        }
 }
@@ -327,12 +341,21 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
                p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos);
        if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {
                const char *bank = NULL, *device = NULL;
+               int index = -1;
+
                dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device);
                if (bank != NULL && device != NULL)
                        p += sprintf(p, "DIMM location:%s %s ", bank, device);
                else
                        p += sprintf(p, "DIMM DMI handle: 0x%.4x ",
                                     mem_err->mem_dev_handle);
+
+               index = get_dimm_smbios_index(mem_err->mem_dev_handle);
+               if (index >= 0) {
+                       e->top_layer = index;
+                       e->enable_per_layer_report = true;
+               }
+
        }
        if (p > e->location)
                *(p - 1) = '\0';

diff --git a/include/linux/edac.h b/include/linux/edac.h
index bffb97828ed67711dffb24099c26f4580e4e654e..a45ce1f84bfc00deaf1d0d602da43fbe0c7b8e2d 100644 (file)
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -451,6 +451,8 @@ struct dimm_info {
        u32 nr_pages;                   /* number of pages on this dimm */
 
        unsigned csrow, cschannel;      /* Points to the old API data */
+
+       u16 smbios_handle;              /* Handle for SMBIOS type 17 */
 };
 
 /**