diff options
Diffstat (limited to 'drivers/edac')
-rw-r--r-- | drivers/edac/i5000_edac.c | 196 | ||||
-rw-r--r-- | drivers/edac/i82443bxgx_edac.c | 63 | ||||
-rw-r--r-- | drivers/edac/mpc85xx_edac.c | 33 |
3 files changed, 221 insertions, 71 deletions
diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c index 4a16b5b61cf..f0d9b415db5 100644 --- a/drivers/edac/i5000_edac.c +++ b/drivers/edac/i5000_edac.c @@ -119,6 +119,7 @@ #define FERR_NF_UNCORRECTABLE (FERR_NF_M12ERR | \ FERR_NF_M11ERR | \ FERR_NF_M10ERR | \ + FERR_NF_M9ERR | \ FERR_NF_M8ERR | \ FERR_NF_M7ERR | \ FERR_NF_M6ERR | \ @@ -301,6 +302,9 @@ static char *numcol_toString[] = { }; #endif +/* enables the report of miscellaneous messages as CE errors - default off */ +static int misc_messages; + /* Enumeration of supported devices */ enum i5000_chips { I5000P = 0, @@ -466,7 +470,8 @@ static void i5000_process_fatal_error_info(struct mem_ctl_info *mci, struct i5000_error_info *info, int handle_errors) { - char msg[EDAC_MC_LABEL_LEN + 1 + 90]; + char msg[EDAC_MC_LABEL_LEN + 1 + 160]; + char *specific = NULL; u32 allErrors; int branch; int channel; @@ -480,11 +485,6 @@ static void i5000_process_fatal_error_info(struct mem_ctl_info *mci, if (!allErrors) return; /* if no error, return now */ - /* ONLY ONE of the possible error bits will be set, as per the docs */ - i5000_mc_printk(mci, KERN_ERR, - "FATAL ERRORS Found!!! 1st FATAL Err Reg= 0x%x\n", - allErrors); - branch = EXTRACT_FBDCHAN_INDX(info->ferr_fat_fbd); channel = branch; @@ -501,28 +501,42 @@ static void i5000_process_fatal_error_info(struct mem_ctl_info *mci, rdwr ? "Write" : "Read", ras, cas); /* Only 1 bit will be on */ - if (allErrors & FERR_FAT_M1ERR) { - i5000_mc_printk(mci, KERN_ERR, - "Alert on non-redundant retry or fast " - "reset timeout\n"); - - } else if (allErrors & FERR_FAT_M2ERR) { - i5000_mc_printk(mci, KERN_ERR, - "Northbound CRC error on non-redundant " - "retry\n"); - - } else if (allErrors & FERR_FAT_M3ERR) { - i5000_mc_printk(mci, KERN_ERR, - ">Tmid Thermal event with intelligent " - "throttling disabled\n"); + switch (allErrors) { + case FERR_FAT_M1ERR: + specific = "Alert on non-redundant retry or fast " + "reset timeout"; + break; + case FERR_FAT_M2ERR: + specific = "Northbound CRC error on non-redundant " + "retry"; + break; + case FERR_FAT_M3ERR: + { + static int done; + + /* + * This error is generated to inform that the intelligent + * throttling is disabled and the temperature passed the + * specified middle point. Since this is something the BIOS + * should take care of, we'll warn only once to avoid + * worthlessly flooding the log. + */ + if (done) + return; + done++; + + specific = ">Tmid Thermal event with intelligent " + "throttling disabled"; + } + break; } /* Form out message */ snprintf(msg, sizeof(msg), "(Branch=%d DRAM-Bank=%d RDWR=%s RAS=%d CAS=%d " - "FATAL Err=0x%x)", + "FATAL Err=0x%x (%s))", branch >> 1, bank, rdwr ? "Write" : "Read", ras, cas, - allErrors); + allErrors, specific); /* Call the helper to output message */ edac_mc_handle_fbd_ue(mci, rank, channel, channel + 1, msg); @@ -539,7 +553,8 @@ static void i5000_process_nonfatal_error_info(struct mem_ctl_info *mci, struct i5000_error_info *info, int handle_errors) { - char msg[EDAC_MC_LABEL_LEN + 1 + 90]; + char msg[EDAC_MC_LABEL_LEN + 1 + 170]; + char *specific = NULL; u32 allErrors; u32 ue_errors; u32 ce_errors; @@ -557,10 +572,6 @@ static void i5000_process_nonfatal_error_info(struct mem_ctl_info *mci, return; /* if no error, return now */ /* ONLY ONE of the possible error bits will be set, as per the docs */ - i5000_mc_printk(mci, KERN_WARNING, - "NON-FATAL ERRORS Found!!! 1st NON-FATAL Err " - "Reg= 0x%x\n", allErrors); - ue_errors = allErrors & FERR_NF_UNCORRECTABLE; if (ue_errors) { debugf0("\tUncorrected bits= 0x%x\n", ue_errors); @@ -579,12 +590,47 @@ static void i5000_process_nonfatal_error_info(struct mem_ctl_info *mci, rank, channel, channel + 1, branch >> 1, bank, rdwr ? "Write" : "Read", ras, cas); + switch (ue_errors) { + case FERR_NF_M12ERR: + specific = "Non-Aliased Uncorrectable Patrol Data ECC"; + break; + case FERR_NF_M11ERR: + specific = "Non-Aliased Uncorrectable Spare-Copy " + "Data ECC"; + break; + case FERR_NF_M10ERR: + specific = "Non-Aliased Uncorrectable Mirrored Demand " + "Data ECC"; + break; + case FERR_NF_M9ERR: + specific = "Non-Aliased Uncorrectable Non-Mirrored " + "Demand Data ECC"; + break; + case FERR_NF_M8ERR: + specific = "Aliased Uncorrectable Patrol Data ECC"; + break; + case FERR_NF_M7ERR: + specific = "Aliased Uncorrectable Spare-Copy Data ECC"; + break; + case FERR_NF_M6ERR: + specific = "Aliased Uncorrectable Mirrored Demand " + "Data ECC"; + break; + case FERR_NF_M5ERR: + specific = "Aliased Uncorrectable Non-Mirrored Demand " + "Data ECC"; + break; + case FERR_NF_M4ERR: + specific = "Uncorrectable Data ECC on Replay"; + break; + } + /* Form out message */ snprintf(msg, sizeof(msg), "(Branch=%d DRAM-Bank=%d RDWR=%s RAS=%d " - "CAS=%d, UE Err=0x%x)", + "CAS=%d, UE Err=0x%x (%s))", branch >> 1, bank, rdwr ? "Write" : "Read", ras, cas, - ue_errors); + ue_errors, specific); /* Call the helper to output message */ edac_mc_handle_fbd_ue(mci, rank, channel, channel + 1, msg); @@ -616,51 +662,74 @@ static void i5000_process_nonfatal_error_info(struct mem_ctl_info *mci, rank, channel, branch >> 1, bank, rdwr ? "Write" : "Read", ras, cas); + switch (ce_errors) { + case FERR_NF_M17ERR: + specific = "Correctable Non-Mirrored Demand Data ECC"; + break; + case FERR_NF_M18ERR: + specific = "Correctable Mirrored Demand Data ECC"; + break; + case FERR_NF_M19ERR: + specific = "Correctable Spare-Copy Data ECC"; + break; + case FERR_NF_M20ERR: + specific = "Correctable Patrol Data ECC"; + break; + } + /* Form out message */ snprintf(msg, sizeof(msg), "(Branch=%d DRAM-Bank=%d RDWR=%s RAS=%d " - "CAS=%d, CE Err=0x%x)", branch >> 1, bank, - rdwr ? "Write" : "Read", ras, cas, ce_errors); + "CAS=%d, CE Err=0x%x (%s))", branch >> 1, bank, + rdwr ? "Write" : "Read", ras, cas, ce_errors, + specific); /* Call the helper to output message */ edac_mc_handle_fbd_ce(mci, rank, channel, msg); } - /* See if any of the thermal errors have fired */ - misc_errors = allErrors & FERR_NF_THERMAL; - if (misc_errors) { - i5000_printk(KERN_WARNING, "\tTHERMAL Error, bits= 0x%x\n", - misc_errors); - } - - /* See if any of the thermal errors have fired */ - misc_errors = allErrors & FERR_NF_NON_RETRY; - if (misc_errors) { - i5000_printk(KERN_WARNING, "\tNON-Retry Errors, bits= 0x%x\n", - misc_errors); - } + if (!misc_messages) + return; - /* See if any of the thermal errors have fired */ - misc_errors = allErrors & FERR_NF_NORTH_CRC; + misc_errors = allErrors & (FERR_NF_NON_RETRY | FERR_NF_NORTH_CRC | + FERR_NF_SPD_PROTOCOL | FERR_NF_DIMM_SPARE); if (misc_errors) { - i5000_printk(KERN_WARNING, - "\tNORTHBOUND CRC Error, bits= 0x%x\n", - misc_errors); - } + switch (misc_errors) { + case FERR_NF_M13ERR: + specific = "Non-Retry or Redundant Retry FBD Memory " + "Alert or Redundant Fast Reset Timeout"; + break; + case FERR_NF_M14ERR: + specific = "Non-Retry or Redundant Retry FBD " + "Configuration Alert"; + break; + case FERR_NF_M15ERR: + specific = "Non-Retry or Redundant Retry FBD " + "Northbound CRC error on read data"; + break; + case FERR_NF_M21ERR: + specific = "FBD Northbound CRC error on " + "FBD Sync Status"; + break; + case FERR_NF_M22ERR: + specific = "SPD protocol error"; + break; + case FERR_NF_M27ERR: + specific = "DIMM-spare copy started"; + break; + case FERR_NF_M28ERR: + specific = "DIMM-spare copy completed"; + break; + } + branch = EXTRACT_FBDCHAN_INDX(info->ferr_nf_fbd); - /* See if any of the thermal errors have fired */ - misc_errors = allErrors & FERR_NF_SPD_PROTOCOL; - if (misc_errors) { - i5000_printk(KERN_WARNING, - "\tSPD Protocol Error, bits= 0x%x\n", - misc_errors); - } + /* Form out message */ + snprintf(msg, sizeof(msg), + "(Branch=%d Err=%#x (%s))", branch >> 1, + misc_errors, specific); - /* See if any of the thermal errors have fired */ - misc_errors = allErrors & FERR_NF_DIMM_SPARE; - if (misc_errors) { - i5000_printk(KERN_WARNING, "\tDIMM-Spare Error, bits= 0x%x\n", - misc_errors); + /* Call the helper to output message */ + edac_mc_handle_fbd_ce(mci, 0, 0, msg); } } @@ -1497,3 +1566,6 @@ MODULE_DESCRIPTION("MC Driver for Intel I5000 memory controllers - " module_param(edac_op_state, int, 0444); MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI"); +module_param(misc_messages, int, 0444); +MODULE_PARM_DESC(misc_messages, "Log miscellaneous non fatal messages"); + diff --git a/drivers/edac/i82443bxgx_edac.c b/drivers/edac/i82443bxgx_edac.c index c5305e3ee43..577760a82a0 100644 --- a/drivers/edac/i82443bxgx_edac.c +++ b/drivers/edac/i82443bxgx_edac.c @@ -114,6 +114,12 @@ struct i82443bxgx_edacmc_error_info { static struct edac_pci_ctl_info *i82443bxgx_pci; +static struct pci_dev *mci_pdev; /* init dev: in case that AGP code has + * already registered driver + */ + +static int i82443bxgx_registered = 1; + static void i82443bxgx_edacmc_get_error_info(struct mem_ctl_info *mci, struct i82443bxgx_edacmc_error_info *info) @@ -345,10 +351,17 @@ EXPORT_SYMBOL_GPL(i82443bxgx_edacmc_probe1); static int __devinit i82443bxgx_edacmc_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { + int rc; + debugf0("MC: " __FILE__ ": %s()\n", __func__); /* don't need to call pci_device_enable() */ - return i82443bxgx_edacmc_probe1(pdev, ent->driver_data); + rc = i82443bxgx_edacmc_probe1(pdev, ent->driver_data); + + if (mci_pdev == NULL) + mci_pdev = pci_dev_get(pdev); + + return rc; } static void __devexit i82443bxgx_edacmc_remove_one(struct pci_dev *pdev) @@ -387,15 +400,61 @@ static struct pci_driver i82443bxgx_edacmc_driver = { static int __init i82443bxgx_edacmc_init(void) { + int pci_rc; /* Ensure that the OPSTATE is set correctly for POLL or NMI */ opstate_init(); - return pci_register_driver(&i82443bxgx_edacmc_driver); + pci_rc = pci_register_driver(&i82443bxgx_edacmc_driver); + if (pci_rc < 0) + goto fail0; + + if (mci_pdev == NULL) { + const struct pci_device_id *id = &i82443bxgx_pci_tbl[0]; + int i = 0; + i82443bxgx_registered = 0; + + while (mci_pdev == NULL && id->vendor != 0) { + mci_pdev = pci_get_device(id->vendor, + id->device, NULL); + i++; + id = &i82443bxgx_pci_tbl[i]; + } + if (!mci_pdev) { + debugf0("i82443bxgx pci_get_device fail\n"); + pci_rc = -ENODEV; + goto fail1; + } + + pci_rc = i82443bxgx_edacmc_init_one(mci_pdev, i82443bxgx_pci_tbl); + + if (pci_rc < 0) { + debugf0("i82443bxgx init fail\n"); + pci_rc = -ENODEV; + goto fail1; + } + } + + return 0; + +fail1: + pci_unregister_driver(&i82443bxgx_edacmc_driver); + +fail0: + if (mci_pdev != NULL) + pci_dev_put(mci_pdev); + + return pci_rc; } static void __exit i82443bxgx_edacmc_exit(void) { pci_unregister_driver(&i82443bxgx_edacmc_driver); + + if (!i82443bxgx_registered) + i82443bxgx_edacmc_remove_one(mci_pdev); + + if (mci_pdev) + pci_dev_put(mci_pdev); } module_init(i82443bxgx_edacmc_init); diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 2265d9ca153..0cfcb2d075a 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -17,6 +17,7 @@ #include <linux/io.h> #include <linux/mod_devicetable.h> #include <linux/edac.h> +#include <linux/smp.h> #include <linux/of_platform.h> #include <linux/of_device.h> @@ -40,7 +41,7 @@ static u32 orig_pci_err_en; #endif static u32 orig_l2_err_disable; -static u32 orig_hid1; +static u32 orig_hid1[2]; /************************ MC SYSFS parts ***********************************/ @@ -647,6 +648,9 @@ static struct of_device_id mpc85xx_l2_err_of_match[] = { { .compatible = "fsl,8568-l2-cache-controller", }, + { + .compatible = "fsl,mpc8572-l2-cache-controller", + }, {}, }; @@ -912,7 +916,8 @@ static int __devinit mpc85xx_mc_err_probe(struct of_device *op, /* register interrupts */ pdata->irq = irq_of_parse_and_map(op->node, 0); res = devm_request_irq(&op->dev, pdata->irq, - mpc85xx_mc_isr, IRQF_DISABLED, + mpc85xx_mc_isr, + IRQF_DISABLED | IRQF_SHARED, "[EDAC] MC err", mci); if (res < 0) { printk(KERN_ERR "%s: Unable to request irq %d for " @@ -980,6 +985,9 @@ static struct of_device_id mpc85xx_mc_err_of_match[] = { { .compatible = "fsl,8568-memory-controller", }, + { + .compatible = "fsl,mpc8572-memory-controller", + }, {}, }; @@ -995,6 +1003,14 @@ static struct of_platform_driver mpc85xx_mc_err_driver = { }, }; + +static void __init mpc85xx_mc_clear_rfxe(void *data) +{ + orig_hid1[smp_processor_id()] = mfspr(SPRN_HID1); + mtspr(SPRN_HID1, (orig_hid1[smp_processor_id()] & ~0x20000)); +} + + static int __init mpc85xx_mc_init(void) { int res = 0; @@ -1030,19 +1046,22 @@ static int __init mpc85xx_mc_init(void) * need to clear HID1[RFXE] to disable machine check int * so we can catch it */ - if (edac_op_state == EDAC_OPSTATE_INT) { - orig_hid1 = mfspr(SPRN_HID1); - mtspr(SPRN_HID1, (orig_hid1 & ~0x20000)); - } + if (edac_op_state == EDAC_OPSTATE_INT) + on_each_cpu(mpc85xx_mc_clear_rfxe, NULL, 0); return 0; } module_init(mpc85xx_mc_init); +static void __exit mpc85xx_mc_restore_hid1(void *data) +{ + mtspr(SPRN_HID1, orig_hid1[smp_processor_id()]); +} + static void __exit mpc85xx_mc_exit(void) { - mtspr(SPRN_HID1, orig_hid1); + on_each_cpu(mpc85xx_mc_restore_hid1, NULL, 0); #ifdef CONFIG_PCI of_unregister_platform_driver(&mpc85xx_pci_err_driver); #endif |