X-Git-Url: http://pileus.org/git/?a=blobdiff_plain;f=drivers%2Fedac%2Fe7xxx_edac.c;h=9a9c1a5467977ca6bb69042651310b2830275757;hb=37b22400f86e83076c8e540b65e8b7e3f1f63e6b;hp=68dea87b72e639448b2eb75ed0f219be3e6b9d39;hpb=4a1e8ebc5e5918079109cc1cd1c44c2f0fd0e11b;p=~andy%2Flinux diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c index 68dea87b72e..9a9c1a54679 100644 --- a/drivers/edac/e7xxx_edac.c +++ b/drivers/edac/e7xxx_edac.c @@ -10,6 +10,9 @@ * Based on work by Dan Hollis and others. * http://www.anime.net/~goemon/linux-ecc/ * + * Datasheet: + * http://www.intel.com/content/www/us/en/chipsets/e7501-chipset-memory-controller-hub-datasheet.html + * * Contributors: * Eric Biederman (Linux Networx) * Tom Zimmerman (Linux Networx) @@ -71,7 +74,7 @@ #endif /* PCI_DEVICE_ID_INTEL_7505_1_ERR */ #define E7XXX_NR_CSROWS 8 /* number of csrows */ -#define E7XXX_NR_DIMMS 8 /* FIXME - is this correct? */ +#define E7XXX_NR_DIMMS 8 /* 2 channels, 4 dimms/channel */ /* E7XXX register addresses - device 0 function 0 */ #define E7XXX_DRB 0x60 /* DRAM row boundary register (8b) */ @@ -216,13 +219,15 @@ static void process_ce(struct mem_ctl_info *mci, struct e7xxx_error_info *info) row = edac_mc_find_csrow_by_page(mci, page); /* convert syndrome to channel */ channel = e7xxx_find_channel(syndrome); - edac_mc_handle_ce(mci, page, 0, syndrome, row, channel, "e7xxx CE"); + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, page, 0, syndrome, + row, channel, -1, "e7xxx CE", "", NULL); } static void process_ce_no_info(struct mem_ctl_info *mci) { debugf3("%s()\n", __func__); - edac_mc_handle_ce_no_info(mci, "e7xxx CE log register overflow"); + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 0, 0, 0, -1, -1, -1, + "e7xxx CE log register overflow", "", NULL); } static void process_ue(struct mem_ctl_info *mci, struct e7xxx_error_info *info) @@ -236,13 +241,17 @@ static void process_ue(struct mem_ctl_info *mci, struct e7xxx_error_info *info) /* FIXME - should use PAGE_SHIFT */ block_page = error_2b >> 6; /* convert to 4k address */ row = edac_mc_find_csrow_by_page(mci, block_page); - edac_mc_handle_ue(mci, block_page, 0, row, "e7xxx UE"); + + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, block_page, 0, 0, + row, -1, -1, "e7xxx UE", "", NULL); } static void process_ue_no_info(struct mem_ctl_info *mci) { debugf3("%s()\n", __func__); - edac_mc_handle_ue_no_info(mci, "e7xxx UE log register overflow"); + + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 0, 0, 0, -1, -1, -1, + "e7xxx UE log register overflow", "", NULL); } static void e7xxx_get_error_info(struct mem_ctl_info *mci, @@ -347,11 +356,12 @@ static void e7xxx_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev, int dev_idx, u32 drc) { unsigned long last_cumul_size; - int index; + int index, j; u8 value; - u32 dra, cumul_size; + u32 dra, cumul_size, nr_pages; int drc_chan, drc_drbg, drc_ddim, mem_dev; struct csrow_info *csrow; + struct dimm_info *dimm; pci_read_config_dword(pdev, E7XXX_DRA, &dra); drc_chan = dual_channel_active(drc, dev_idx); @@ -379,26 +389,32 @@ static void e7xxx_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev, csrow->first_page = last_cumul_size; csrow->last_page = cumul_size - 1; - csrow->nr_pages = cumul_size - last_cumul_size; + nr_pages = cumul_size - last_cumul_size; last_cumul_size = cumul_size; - csrow->grain = 1 << 12; /* 4KiB - resolution of CELOG */ - csrow->mtype = MEM_RDDR; /* only one type supported */ - csrow->dtype = mem_dev ? DEV_X4 : DEV_X8; - - /* - * if single channel or x8 devices then SECDED - * if dual channel and x4 then S4ECD4ED - */ - if (drc_ddim) { - if (drc_chan && mem_dev) { - csrow->edac_mode = EDAC_S4ECD4ED; - mci->edac_cap |= EDAC_FLAG_S4ECD4ED; - } else { - csrow->edac_mode = EDAC_SECDED; - mci->edac_cap |= EDAC_FLAG_SECDED; - } - } else - csrow->edac_mode = EDAC_NONE; + + for (j = 0; j < drc_chan + 1; j++) { + dimm = csrow->channels[j].dimm; + + dimm->nr_pages = nr_pages / (drc_chan + 1); + dimm->grain = 1 << 12; /* 4KiB - resolution of CELOG */ + dimm->mtype = MEM_RDDR; /* only one type supported */ + dimm->dtype = mem_dev ? DEV_X4 : DEV_X8; + + /* + * if single channel or x8 devices then SECDED + * if dual channel and x4 then S4ECD4ED + */ + if (drc_ddim) { + if (drc_chan && mem_dev) { + dimm->edac_mode = EDAC_S4ECD4ED; + mci->edac_cap |= EDAC_FLAG_S4ECD4ED; + } else { + dimm->edac_mode = EDAC_SECDED; + mci->edac_cap |= EDAC_FLAG_SECDED; + } + } else + dimm->edac_mode = EDAC_NONE; + } } } @@ -406,6 +422,7 @@ static int e7xxx_probe1(struct pci_dev *pdev, int dev_idx) { u16 pci_data; struct mem_ctl_info *mci = NULL; + struct edac_mc_layer layers[2]; struct e7xxx_pvt *pvt = NULL; u32 drc; int drc_chan; @@ -416,8 +433,21 @@ static int e7xxx_probe1(struct pci_dev *pdev, int dev_idx) pci_read_config_dword(pdev, E7XXX_DRC, &drc); drc_chan = dual_channel_active(drc, dev_idx); - mci = edac_mc_alloc(sizeof(*pvt), E7XXX_NR_CSROWS, drc_chan + 1, 0); - + /* + * According with the datasheet, this device has a maximum of + * 4 DIMMS per channel, either single-rank or dual-rank. So, the + * total amount of dimms is 8 (E7XXX_NR_DIMMS). + * That means that the DIMM is mapped as CSROWs, and the channel + * will map the rank. So, an error to either channel should be + * attributed to the same dimm. + */ + layers[0].type = EDAC_MC_LAYER_CHIP_SELECT; + layers[0].size = E7XXX_NR_CSROWS; + layers[0].is_virt_csrow = true; + layers[1].type = EDAC_MC_LAYER_CHANNEL; + layers[1].size = drc_chan + 1; + layers[1].is_virt_csrow = false; + mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(*pvt)); if (mci == NULL) return -ENOMEM;