diff options
Diffstat (limited to 'drivers/edac')
-rw-r--r-- | drivers/edac/e752x_edac.c | 40 | ||||
-rw-r--r-- | drivers/edac/edac_mc.c | 175 | ||||
-rw-r--r-- | drivers/edac/edac_mc.h | 28 |
3 files changed, 222 insertions, 21 deletions
diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c index c82bc0ed7f1..8bcc887692a 100644 --- a/drivers/edac/e752x_edac.c +++ b/drivers/edac/e752x_edac.c @@ -285,8 +285,9 @@ static void do_process_ce(struct mem_ctl_info *mci, u16 error_one, if (!pvt->map_type) row = 7 - row; - edac_mc_handle_ce(mci, page, 0, sec1_syndrome, row, channel, - "e752x CE"); + /* e752x mc reads 34:6 of the DRAM linear address */ + edac_mc_handle_ce(mci, page, offset_in_page(sec1_add << 4), + sec1_syndrome, row, channel, "e752x CE"); } static inline void process_ce(struct mem_ctl_info *mci, u16 error_one, @@ -319,8 +320,10 @@ static void do_process_ue(struct mem_ctl_info *mci, u16 error_one, ((block_page >> 1) & 3) : edac_mc_find_csrow_by_page(mci, block_page); - edac_mc_handle_ue(mci, block_page, 0, row, - "e752x UE from Read"); + /* e752x mc reads 34:6 of the DRAM linear address */ + edac_mc_handle_ue(mci, block_page, + offset_in_page(error_2b << 4), + row, "e752x UE from Read"); } if (error_one & 0x0404) { error_2b = scrb_add; @@ -333,8 +336,10 @@ static void do_process_ue(struct mem_ctl_info *mci, u16 error_one, ((block_page >> 1) & 3) : edac_mc_find_csrow_by_page(mci, block_page); - edac_mc_handle_ue(mci, block_page, 0, row, - "e752x UE from Scruber"); + /* e752x mc reads 34:6 of the DRAM linear address */ + edac_mc_handle_ue(mci, block_page, + offset_in_page(error_2b << 4), + row, "e752x UE from Scruber"); } } @@ -556,17 +561,17 @@ static void e752x_check_sysbus(struct e752x_error_info *info, error32 = (stat32 >> 16) & 0x3ff; stat32 = stat32 & 0x3ff; - if(stat32 & 0x083) - sysbus_error(1, stat32 & 0x083, error_found, handle_error); + if(stat32 & 0x087) + sysbus_error(1, stat32 & 0x087, error_found, handle_error); - if(stat32 & 0x37c) - sysbus_error(0, stat32 & 0x37c, error_found, handle_error); + if(stat32 & 0x378) + sysbus_error(0, stat32 & 0x378, error_found, handle_error); - if(error32 & 0x083) - sysbus_error(1, error32 & 0x083, error_found, handle_error); + if(error32 & 0x087) + sysbus_error(1, error32 & 0x087, error_found, handle_error); - if(error32 & 0x37c) - sysbus_error(0, error32 & 0x37c, error_found, handle_error); + if(error32 & 0x378) + sysbus_error(0, error32 & 0x378, error_found, handle_error); } static void e752x_check_membuf (struct e752x_error_info *info, @@ -782,7 +787,12 @@ static void e752x_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev, u8 value; u32 dra, drc, cumul_size; - pci_read_config_dword(pdev, E752X_DRA, &dra); + dra = 0; + for (index=0; index < 4; index++) { + u8 dra_reg; + pci_read_config_byte(pdev, E752X_DRA+index, &dra_reg); + dra |= dra_reg << (index * 8); + } pci_read_config_dword(pdev, E752X_DRC, &drc); drc_chan = dual_channel_active(ddrcsr); drc_drbg = drc_chan + 1; /* 128 in dual mode, 64 in single */ diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 1b4fc922180..7b622300d0e 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -927,6 +927,57 @@ static ssize_t mci_reset_counters_store(struct mem_ctl_info *mci, return count; } +/* memory scrubbing */ +static ssize_t mci_sdram_scrub_rate_store(struct mem_ctl_info *mci, + const char *data, size_t count) +{ + u32 bandwidth = -1; + + if (mci->set_sdram_scrub_rate) { + + memctrl_int_store(&bandwidth, data, count); + + if (!(*mci->set_sdram_scrub_rate)(mci, &bandwidth)) { + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate set successfully, applied: %d\n", + bandwidth); + } else { + /* FIXME: error codes maybe? */ + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate set FAILED, could not apply: %d\n", + bandwidth); + } + } else { + /* FIXME: produce "not implemented" ERROR for user-side. */ + edac_printk(KERN_WARNING, EDAC_MC, + "Memory scrubbing 'set'control is not implemented!\n"); + } + return count; +} + +static ssize_t mci_sdram_scrub_rate_show(struct mem_ctl_info *mci, char *data) +{ + u32 bandwidth = -1; + + if (mci->get_sdram_scrub_rate) { + if (!(*mci->get_sdram_scrub_rate)(mci, &bandwidth)) { + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate successfully, fetched: %d\n", + bandwidth); + } else { + /* FIXME: error codes maybe? */ + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate fetch FAILED, got: %d\n", + bandwidth); + } + } else { + /* FIXME: produce "not implemented" ERROR for user-side. */ + edac_printk(KERN_WARNING, EDAC_MC, + "Memory scrubbing 'get' control is not implemented!\n"); + } + return sprintf(data, "%d\n", bandwidth); +} + /* default attribute files for the MCI object */ static ssize_t mci_ue_count_show(struct mem_ctl_info *mci, char *data) { @@ -1033,6 +1084,9 @@ MCIDEV_ATTR(ce_noinfo_count,S_IRUGO,mci_ce_noinfo_show,NULL); MCIDEV_ATTR(ue_count,S_IRUGO,mci_ue_count_show,NULL); MCIDEV_ATTR(ce_count,S_IRUGO,mci_ce_count_show,NULL); +/* memory scrubber attribute file */ +MCIDEV_ATTR(sdram_scrub_rate,S_IRUGO|S_IWUSR,mci_sdram_scrub_rate_show,mci_sdram_scrub_rate_store); + static struct mcidev_attribute *mci_attr[] = { &mci_attr_reset_counters, &mci_attr_mc_name, @@ -1042,6 +1096,7 @@ static struct mcidev_attribute *mci_attr[] = { &mci_attr_ce_noinfo_count, &mci_attr_ue_count, &mci_attr_ce_count, + &mci_attr_sdram_scrub_rate, NULL }; @@ -1442,11 +1497,11 @@ int edac_mc_add_mc(struct mem_ctl_info *mci, int mc_idx) /* set load time so that error rate can be tracked */ mci->start_time = jiffies; - if (edac_create_sysfs_mci_device(mci)) { - edac_mc_printk(mci, KERN_WARNING, + if (edac_create_sysfs_mci_device(mci)) { + edac_mc_printk(mci, KERN_WARNING, "failed to create sysfs device\n"); - goto fail1; - } + goto fail1; + } /* Report action taken */ edac_mc_printk(mci, KERN_INFO, "Giving out device to %s %s: DEV %s\n", @@ -1703,6 +1758,116 @@ void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg) EXPORT_SYMBOL_GPL(edac_mc_handle_ue_no_info); +/************************************************************* + * On Fully Buffered DIMM modules, this help function is + * called to process UE events + */ +void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci, + unsigned int csrow, + unsigned int channela, + unsigned int channelb, + char *msg) +{ + int len = EDAC_MC_LABEL_LEN * 4; + char labels[len + 1]; + char *pos = labels; + int chars; + + if (csrow >= mci->nr_csrows) { + /* something is wrong */ + edac_mc_printk(mci, KERN_ERR, + "INTERNAL ERROR: row out of range (%d >= %d)\n", + csrow, mci->nr_csrows); + edac_mc_handle_ue_no_info(mci, "INTERNAL ERROR"); + return; + } + + if (channela >= mci->csrows[csrow].nr_channels) { + /* something is wrong */ + edac_mc_printk(mci, KERN_ERR, + "INTERNAL ERROR: channel-a out of range " + "(%d >= %d)\n", + channela, mci->csrows[csrow].nr_channels); + edac_mc_handle_ue_no_info(mci, "INTERNAL ERROR"); + return; + } + + if (channelb >= mci->csrows[csrow].nr_channels) { + /* something is wrong */ + edac_mc_printk(mci, KERN_ERR, + "INTERNAL ERROR: channel-b out of range " + "(%d >= %d)\n", + channelb, mci->csrows[csrow].nr_channels); + edac_mc_handle_ue_no_info(mci, "INTERNAL ERROR"); + return; + } + + mci->ue_count++; + mci->csrows[csrow].ue_count++; + + /* Generate the DIMM labels from the specified channels */ + chars = snprintf(pos, len + 1, "%s", + mci->csrows[csrow].channels[channela].label); + len -= chars; pos += chars; + chars = snprintf(pos, len + 1, "-%s", + mci->csrows[csrow].channels[channelb].label); + + if (log_ue) + edac_mc_printk(mci, KERN_EMERG, + "UE row %d, channel-a= %d channel-b= %d " + "labels \"%s\": %s\n", csrow, channela, channelb, + labels, msg); + + if (panic_on_ue) + panic("UE row %d, channel-a= %d channel-b= %d " + "labels \"%s\": %s\n", csrow, channela, + channelb, labels, msg); +} +EXPORT_SYMBOL(edac_mc_handle_fbd_ue); + +/************************************************************* + * On Fully Buffered DIMM modules, this help function is + * called to process CE events + */ +void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci, + unsigned int csrow, + unsigned int channel, + char *msg) +{ + + /* Ensure boundary values */ + if (csrow >= mci->nr_csrows) { + /* something is wrong */ + edac_mc_printk(mci, KERN_ERR, + "INTERNAL ERROR: row out of range (%d >= %d)\n", + csrow, mci->nr_csrows); + edac_mc_handle_ce_no_info(mci, "INTERNAL ERROR"); + return; + } + if (channel >= mci->csrows[csrow].nr_channels) { + /* something is wrong */ + edac_mc_printk(mci, KERN_ERR, + "INTERNAL ERROR: channel out of range (%d >= %d)\n", + channel, mci->csrows[csrow].nr_channels); + edac_mc_handle_ce_no_info(mci, "INTERNAL ERROR"); + return; + } + + if (log_ce) + /* FIXME - put in DIMM location */ + edac_mc_printk(mci, KERN_WARNING, + "CE row %d, channel %d, label \"%s\": %s\n", + csrow, channel, + mci->csrows[csrow].channels[channel].label, + msg); + + mci->ce_count++; + mci->csrows[csrow].ce_count++; + mci->csrows[csrow].channels[channel].ce_count++; +} +EXPORT_SYMBOL(edac_mc_handle_fbd_ce); + + /* * Iterate over all MC instances and check for ECC, et al, errors */ @@ -1806,7 +1971,7 @@ static void __exit edac_mc_exit(void) debugf0("%s()\n", __func__); kthread_stop(edac_thread); - /* tear down the sysfs device */ + /* tear down the sysfs device */ edac_sysfs_memctrl_teardown(); edac_sysfs_pci_teardown(); } diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h index a1cfd4e3c97..713444cc410 100644 --- a/drivers/edac/edac_mc.h +++ b/drivers/edac/edac_mc.h @@ -123,7 +123,9 @@ enum mem_type { MEM_RDR, /* Registered single data rate SDRAM */ MEM_DDR, /* Double data rate SDRAM */ MEM_RDDR, /* Registered Double data rate SDRAM */ - MEM_RMBS /* Rambus DRAM */ + MEM_RMBS, /* Rambus DRAM */ + MEM_DDR2, /* DDR2 RAM */ + MEM_FB_DDR2, /* fully buffered DDR2 */ }; #define MEM_FLAG_EMPTY BIT(MEM_EMPTY) @@ -137,6 +139,8 @@ enum mem_type { #define MEM_FLAG_DDR BIT(MEM_DDR) #define MEM_FLAG_RDDR BIT(MEM_RDDR) #define MEM_FLAG_RMBS BIT(MEM_RMBS) +#define MEM_FLAG_DDR2 BIT(MEM_DDR2) +#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2) /* chipset Error Detection and Correction capabilities and mode */ enum edac_type { @@ -315,8 +319,21 @@ struct mem_ctl_info { unsigned long scrub_cap; /* chipset scrub capabilities */ enum scrub_type scrub_mode; /* current scrub mode */ + /* Translates sdram memory scrub rate given in bytes/sec to the + internal representation and configures whatever else needs + to be configured. + */ + int (*set_sdram_scrub_rate) (struct mem_ctl_info *mci, u32 *bw); + + /* Get the current sdram memory scrub rate from the internal + representation and converts it to the closest matching + bandwith in bytes/sec. + */ + int (*get_sdram_scrub_rate) (struct mem_ctl_info *mci, u32 *bw); + /* pointer to edac checking routine */ void (*edac_check) (struct mem_ctl_info * mci); + /* * Remaps memory pages: controller pages to physical pages. * For most MC's, this will be NULL. @@ -441,6 +458,15 @@ extern void edac_mc_handle_ue(struct mem_ctl_info *mci, int row, const char *msg); extern void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg); +extern void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci, + unsigned int csrow, + unsigned int channel0, + unsigned int channel1, + char *msg); +extern void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci, + unsigned int csrow, + unsigned int channel, + char *msg); /* * This kmalloc's and initializes all the structures. |