diff options
Diffstat (limited to 'drivers/edac')
| -rw-r--r-- | drivers/edac/Kconfig | 15 | ||||
| -rw-r--r-- | drivers/edac/Makefile | 1 | ||||
| -rw-r--r-- | drivers/edac/qcom_edac.c | 414 | ||||
| -rw-r--r-- | drivers/edac/skx_edac.c | 193 |
4 files changed, 610 insertions, 13 deletions
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 57304b2e989f..41c9ccdd20d6 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -234,6 +234,7 @@ config EDAC_SKX depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG depends on ACPI_NFIT || !ACPI_NFIT # if ACPI_NFIT=m, EDAC_SKX can't be y select DMI + select ACPI_ADXL if ACPI help Support for error detection and correction the Intel Skylake server Integrated Memory Controllers. If your @@ -460,4 +461,18 @@ config EDAC_TI Support for error detection and correction on the TI SoCs. +config EDAC_QCOM + tristate "QCOM EDAC Controller" + depends on ARCH_QCOM && QCOM_LLCC + help + Support for error detection and correction on the + Qualcomm Technologies, Inc. SoCs. + + This driver reports Single Bit Errors (SBEs) and Double Bit Errors (DBEs). + As of now, it supports error reporting for Last Level Cache Controller (LLCC) + of Tag RAM and Data RAM. + + For debugging issues having to do with stability and overall system + health, you should probably say 'Y' here. + endif # EDAC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 02b43a7d8c3e..716096d08ea0 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -77,3 +77,4 @@ obj-$(CONFIG_EDAC_ALTERA) += altera_edac.o obj-$(CONFIG_EDAC_SYNOPSYS) += synopsys_edac.o obj-$(CONFIG_EDAC_XGENE) += xgene_edac.o obj-$(CONFIG_EDAC_TI) += ti_edac.o +obj-$(CONFIG_EDAC_QCOM) += qcom_edac.o diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c new file mode 100644 index 000000000000..82bd775124f2 --- /dev/null +++ b/drivers/edac/qcom_edac.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, The Linux Foundation. All rights reserved. + */ + +#include <linux/edac.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/soc/qcom/llcc-qcom.h> + +#include "edac_mc.h" +#include "edac_device.h" + +#define EDAC_LLCC "qcom_llcc" + +#define LLCC_ERP_PANIC_ON_UE 1 + +#define TRP_SYN_REG_CNT 6 +#define DRP_SYN_REG_CNT 8 + +#define LLCC_COMMON_STATUS0 0x0003000c +#define LLCC_LB_CNT_MASK GENMASK(31, 28) +#define LLCC_LB_CNT_SHIFT 28 + +/* Single & double bit syndrome register offsets */ +#define TRP_ECC_SB_ERR_SYN0 0x0002304c +#define TRP_ECC_DB_ERR_SYN0 0x00020370 +#define DRP_ECC_SB_ERR_SYN0 0x0004204c +#define DRP_ECC_DB_ERR_SYN0 0x00042070 + +/* Error register offsets */ +#define TRP_ECC_ERROR_STATUS1 0x00020348 +#define TRP_ECC_ERROR_STATUS0 0x00020344 +#define DRP_ECC_ERROR_STATUS1 0x00042048 +#define DRP_ECC_ERROR_STATUS0 0x00042044 + +/* TRP, DRP interrupt register offsets */ +#define DRP_INTERRUPT_STATUS 0x00041000 +#define TRP_INTERRUPT_0_STATUS 0x00020480 +#define DRP_INTERRUPT_CLEAR 0x00041008 +#define DRP_ECC_ERROR_CNTR_CLEAR 0x00040004 +#define TRP_INTERRUPT_0_CLEAR 0x00020484 +#define TRP_ECC_ERROR_CNTR_CLEAR 0x00020440 + +/* Mask and shift macros */ +#define ECC_DB_ERR_COUNT_MASK GENMASK(4, 0) +#define ECC_DB_ERR_WAYS_MASK GENMASK(31, 16) +#define ECC_DB_ERR_WAYS_SHIFT BIT(4) + +#define ECC_SB_ERR_COUNT_MASK GENMASK(23, 16) +#define ECC_SB_ERR_COUNT_SHIFT BIT(4) +#define ECC_SB_ERR_WAYS_MASK GENMASK(15, 0) + +#define SB_ECC_ERROR BIT(0) +#define DB_ECC_ERROR BIT(1) + +#define DRP_TRP_INT_CLEAR GENMASK(1, 0) +#define DRP_TRP_CNT_CLEAR GENMASK(1, 0) + +/* Config registers offsets*/ +#define DRP_ECC_ERROR_CFG 0x00040000 + +/* Tag RAM, Data RAM interrupt register offsets */ +#define CMN_INTERRUPT_0_ENABLE 0x0003001c +#define CMN_INTERRUPT_2_ENABLE 0x0003003c +#define TRP_INTERRUPT_0_ENABLE 0x00020488 +#define DRP_INTERRUPT_ENABLE 0x0004100c + +#define SB_ERROR_THRESHOLD 0x1 +#define SB_ERROR_THRESHOLD_SHIFT 24 +#define SB_DB_TRP_INTERRUPT_ENABLE 0x3 +#define TRP0_INTERRUPT_ENABLE 0x1 +#define DRP0_INTERRUPT_ENABLE BIT(6) +#define SB_DB_DRP_INTERRUPT_ENABLE 0x3 + +enum { + LLCC_DRAM_CE = 0, + LLCC_DRAM_UE, + LLCC_TRAM_CE, + LLCC_TRAM_UE, +}; + +static const struct llcc_edac_reg_data edac_reg_data[] = { + [LLCC_DRAM_CE] = { + .name = "DRAM Single-bit", + .synd_reg = DRP_ECC_SB_ERR_SYN0, + .count_status_reg = DRP_ECC_ERROR_STATUS1, + .ways_status_reg = DRP_ECC_ERROR_STATUS0, + .reg_cnt = DRP_SYN_REG_CNT, + .count_mask = ECC_SB_ERR_COUNT_MASK, + .ways_mask = ECC_SB_ERR_WAYS_MASK, + .count_shift = ECC_SB_ERR_COUNT_SHIFT, + }, + [LLCC_DRAM_UE] = { + .name = "DRAM Double-bit", + .synd_reg = DRP_ECC_DB_ERR_SYN0, + .count_status_reg = DRP_ECC_ERROR_STATUS1, + .ways_status_reg = DRP_ECC_ERROR_STATUS0, + .reg_cnt = DRP_SYN_REG_CNT, + .count_mask = ECC_DB_ERR_COUNT_MASK, + .ways_mask = ECC_DB_ERR_WAYS_MASK, + .ways_shift = ECC_DB_ERR_WAYS_SHIFT, + }, + [LLCC_TRAM_CE] = { + .name = "TRAM Single-bit", + .synd_reg = TRP_ECC_SB_ERR_SYN0, + .count_status_reg = TRP_ECC_ERROR_STATUS1, + .ways_status_reg = TRP_ECC_ERROR_STATUS0, + .reg_cnt = TRP_SYN_REG_CNT, + .count_mask = ECC_SB_ERR_COUNT_MASK, + .ways_mask = ECC_SB_ERR_WAYS_MASK, + .count_shift = ECC_SB_ERR_COUNT_SHIFT, + }, + [LLCC_TRAM_UE] = { + .name = "TRAM Double-bit", + .synd_reg = TRP_ECC_DB_ERR_SYN0, + .count_status_reg = TRP_ECC_ERROR_STATUS1, + .ways_status_reg = TRP_ECC_ERROR_STATUS0, + .reg_cnt = TRP_SYN_REG_CNT, + .count_mask = ECC_DB_ERR_COUNT_MASK, + .ways_mask = ECC_DB_ERR_WAYS_MASK, + .ways_shift = ECC_DB_ERR_WAYS_SHIFT, + }, +}; + +static int qcom_llcc_core_setup(struct regmap *llcc_bcast_regmap) +{ + u32 sb_err_threshold; + int ret; + + /* + * Configure interrupt enable registers such that Tag, Data RAM related + * interrupts are propagated to interrupt controller for servicing + */ + ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE, + TRP0_INTERRUPT_ENABLE, + TRP0_INTERRUPT_ENABLE); + if (ret) + return ret; + + ret = regmap_update_bits(llcc_bcast_regmap, TRP_INTERRUPT_0_ENABLE, + SB_DB_TRP_INTERRUPT_ENABLE, + SB_DB_TRP_INTERRUPT_ENABLE); + if (ret) + return ret; + + sb_err_threshold = (SB_ERROR_THRESHOLD << SB_ERROR_THRESHOLD_SHIFT); + ret = regmap_write(llcc_bcast_regmap, DRP_ECC_ERROR_CFG, + sb_err_threshold); + if (ret) + return ret; + + ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE, + DRP0_INTERRUPT_ENABLE, + DRP0_INTERRUPT_ENABLE); + if (ret) + return ret; + + ret = regmap_write(llcc_bcast_regmap, DRP_INTERRUPT_ENABLE, + SB_DB_DRP_INTERRUPT_ENABLE); + return ret; +} + +/* Clear the error interrupt and counter registers */ +static int +qcom_llcc_clear_error_status(int err_type, struct llcc_drv_data *drv) +{ + int ret = 0; + + switch (err_type) { + case LLCC_DRAM_CE: + case LLCC_DRAM_UE: + ret = regmap_write(drv->bcast_regmap, DRP_INTERRUPT_CLEAR, + DRP_TRP_INT_CLEAR); + if (ret) + return ret; + + ret = regmap_write(drv->bcast_regmap, DRP_ECC_ERROR_CNTR_CLEAR, + DRP_TRP_CNT_CLEAR); + if (ret) + return ret; + break; + case LLCC_TRAM_CE: + case LLCC_TRAM_UE: + ret = regmap_write(drv->bcast_regmap, TRP_INTERRUPT_0_CLEAR, + DRP_TRP_INT_CLEAR); + if (ret) + return ret; + + ret = regmap_write(drv->bcast_regmap, TRP_ECC_ERROR_CNTR_CLEAR, + DRP_TRP_CNT_CLEAR); + if (ret) + return ret; + break; + default: + ret = -EINVAL; + edac_printk(KERN_CRIT, EDAC_LLCC, "Unexpected error type: %d\n", + err_type); + } + return ret; +} + +/* Dump Syndrome registers data for Tag RAM, Data RAM bit errors*/ +static int +dump_syn_reg_values(struct llcc_drv_data *drv, u32 bank, int err_type) +{ + struct llcc_edac_reg_data reg_data = edac_reg_data[err_type]; + int err_cnt, err_ways, ret, i; + u32 synd_reg, synd_val; + + for (i = 0; i < reg_data.reg_cnt; i++) { + synd_reg = reg_data.synd_reg + (i * 4); + ret = regmap_read(drv->regmap, drv->offsets[bank] + synd_reg, + &synd_val); + if (ret) + goto clear; + + edac_printk(KERN_CRIT, EDAC_LLCC, "%s: ECC_SYN%d: 0x%8x\n", + reg_data.name, i, synd_val); + } + + ret = regmap_read(drv->regmap, + drv->offsets[bank] + reg_data.count_status_reg, + &err_cnt); + if (ret) + goto clear; + + err_cnt &= reg_data.count_mask; + err_cnt >>= reg_data.count_shift; + edac_printk(KERN_CRIT, EDAC_LLCC, "%s: Error count: 0x%4x\n", + reg_data.name, err_cnt); + + ret = regmap_read(drv->regmap, + drv->offsets[bank] + reg_data.ways_status_reg, + &err_ways); + if (ret) + goto clear; + + err_ways &= reg_data.ways_mask; + err_ways >>= reg_data.ways_shift; + + edac_printk(KERN_CRIT, EDAC_LLCC, "%s: Error ways: 0x%4x\n", + reg_data.name, err_ways); + +clear: + return qcom_llcc_clear_error_status(err_type, drv); +} + +static int +dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank) +{ + struct llcc_drv_data *drv = edev_ctl->pvt_info; + int ret; + + ret = dump_syn_reg_values(drv, bank, err_type); + if (ret) + return ret; + + switch (err_type) { + case LLCC_DRAM_CE: + edac_device_handle_ce(edev_ctl, 0, bank, + "LLCC Data RAM correctable Error"); + break; + case LLCC_DRAM_UE: + edac_device_handle_ue(edev_ctl, 0, bank, + "LLCC Data RAM uncorrectable Error"); + break; + case LLCC_TRAM_CE: + edac_device_handle_ce(edev_ctl, 0, bank, + "LLCC Tag RAM correctable Error"); + break; + case LLCC_TRAM_UE: + edac_device_handle_ue(edev_ctl, 0, bank, + "LLCC Tag RAM uncorrectable Error"); + break; + default: + ret = -EINVAL; + edac_printk(KERN_CRIT, EDAC_LLCC, "Unexpected error type: %d\n", + err_type); + } + + return ret; +} + +static irqreturn_t +llcc_ecc_irq_handler(int irq, void *edev_ctl) +{ + struct edac_device_ctl_info *edac_dev_ctl = edev_ctl; + struct llcc_drv_data *drv = edac_dev_ctl->pvt_info; + irqreturn_t irq_rc = IRQ_NONE; + u32 drp_error, trp_error, i; + bool irq_handled; + int ret; + + /* Iterate over the banks and look for Tag RAM or Data RAM errors */ + for (i = 0; i < drv->num_banks; i++) { + ret = regmap_read(drv->regmap, + drv->offsets[i] + DRP_INTERRUPT_STATUS, + &drp_error); + + if (!ret && (drp_error & SB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Single Bit Error detected in Data RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_DRAM_CE, i); + } else if (!ret && (drp_error & DB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Double Bit Error detected in Data RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_DRAM_UE, i); + } + if (!ret) + irq_handled = true; + + ret = regmap_read(drv->regmap, + drv->offsets[i] + TRP_INTERRUPT_0_STATUS, + &trp_error); + + if (!ret && (trp_error & SB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Single Bit Error detected in Tag RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_TRAM_CE, i); + } else if (!ret && (trp_error & DB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Double Bit Error detected in Tag RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_TRAM_UE, i); + } + if (!ret) + irq_handled = true; + } + + if (irq_handled) + irq_rc = IRQ_HANDLED; + + return irq_rc; +} + +static int qcom_llcc_edac_probe(struct platform_device *pdev) +{ + struct llcc_drv_data *llcc_driv_data = pdev->dev.platform_data; + struct edac_device_ctl_info *edev_ctl; + struct device *dev = &pdev->dev; + int ecc_irq; + int rc; + + rc = qcom_llcc_core_setup(llcc_driv_data->bcast_regmap); + if (rc) + return rc; + + /* Allocate edac control info */ + edev_ctl = edac_device_alloc_ctl_info(0, "qcom-llcc", 1, "bank", + llcc_driv_data->num_banks, 1, + NULL, 0, + edac_device_alloc_index()); + + if (!edev_ctl) + return -ENOMEM; + + edev_ctl->dev = dev; + edev_ctl->mod_name = dev_name(dev); + edev_ctl->dev_name = dev_name(dev); + edev_ctl->ctl_name = "llcc"; + edev_ctl->panic_on_ue = LLCC_ERP_PANIC_ON_UE; + edev_ctl->pvt_info = llcc_driv_data; + + rc = edac_device_add_device(edev_ctl); + if (rc) + goto out_mem; + + platform_set_drvdata(pdev, edev_ctl); + + /* Request for ecc irq */ + ecc_irq = llcc_driv_data->ecc_irq; + if (ecc_irq < 0) { + rc = -ENODEV; + goto out_dev; + } + rc = devm_request_irq(dev, ecc_irq, llcc_ecc_irq_handler, + IRQF_TRIGGER_HIGH, "llcc_ecc", edev_ctl); + if (rc) + goto out_dev; + + return rc; + +out_dev: + edac_device_del_device(edev_ctl->dev); +out_mem: + edac_device_free_ctl_info(edev_ctl); + + return rc; +} + +static int qcom_llcc_edac_remove(struct platform_device *pdev) +{ + struct edac_device_ctl_info *edev_ctl = dev_get_drvdata(&pdev->dev); + + edac_device_del_device(edev_ctl->dev); + edac_device_free_ctl_info(edev_ctl); + + return 0; +} + +static struct platform_driver qcom_llcc_edac_driver = { + .probe = qcom_llcc_edac_probe, + .remove = qcom_llcc_edac_remove, + .driver = { + .name = "qcom_llcc_edac", + }, +}; +module_platform_driver(qcom_llcc_edac_driver); + +MODULE_DESCRIPTION("QCOM EDAC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index dd209e0dd9ab..a99ea61dad32 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -26,6 +26,7 @@ #include <linux/bitmap.h> #include <linux/math64.h> #include <linux/mod_devicetable.h> +#include <linux/adxl.h> #include <acpi/nfit.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> @@ -35,6 +36,7 @@ #include "edac_module.h" #define EDAC_MOD_STR "skx_edac" +#define MSG_SIZE 1024 /* * Debug macros @@ -54,6 +56,29 @@ static LIST_HEAD(skx_edac_list); static u64 skx_tolm, skx_tohm; +static char *skx_msg; +static unsigned int nvdimm_count; + +enum { + INDEX_SOCKET, + INDEX_MEMCTRL, + INDEX_CHANNEL, + INDEX_DIMM, + INDEX_MAX +}; + +static const char * const component_names[] = { + [INDEX_SOCKET] = "ProcessorSocketId", + [INDEX_MEMCTRL] = "MemoryControllerId", + [INDEX_CHANNEL] = "ChannelId", + [INDEX_DIMM] = "DimmSlotId", +}; + +static int component_indices[ARRAY_SIZE(component_names)]; +static int adxl_component_count; +static const char * const *adxl_component_names; +static u64 *adxl_values; +static char *adxl_msg; #define NUM_IMC 2 /* memory controllers per socket */ #define NUM_CHANNELS 3 /* channels per memory controller */ @@ -393,6 +418,8 @@ static int get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, u16 flags; u64 size = 0; + nvdimm_count++; + dev_handle = ACPI_NFIT_BUILD_DEVICE_HANDLE(dimmno, chan, imc->lmc, imc->src_id, 0); @@ -941,12 +968,46 @@ static void teardown_skx_debug(void) } #endif /*CONFIG_EDAC_DEBUG*/ +static bool skx_adxl_decode(struct decoded_addr *res) + +{ + int i, len = 0; + + if (res->addr >= skx_tohm || (res->addr >= skx_tolm && + res->addr < BIT_ULL(32))) { + edac_dbg(0, "Address 0x%llx out of range\n", res->addr); + return false; + } + + if (adxl_decode(res->addr, adxl_values)) { + edac_dbg(0, "Failed to decode 0x%llx\n", res->addr); + return false; + } + + res->socket = (int)adxl_values[component_indices[INDEX_SOCKET]]; + res->imc = (int)adxl_values[component_indices[INDEX_MEMCTRL]]; + res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]]; + res->dimm = (int)adxl_values[component_indices[INDEX_DIMM]]; + + for (i = 0; i < adxl_component_count; i++) { + if (adxl_values[i] == ~0x0ull) + continue; + + len += snprintf(adxl_msg + len, MSG_SIZE - len, " %s:0x%llx", + adxl_component_names[i], adxl_values[i]); + if (MSG_SIZE - len <= 0) + break; + } + + return true; +} + static void skx_mce_output_error(struct mem_ctl_info *mci, const struct mce *m, struct decoded_addr *res) { enum hw_event_mc_err_type tp_event; - char *type, *optype, msg[256]; + char *type, *optype; bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0); bool overflow = GET_BITFIELD(m->status, 62, 62); bool uncorrected_error = GET_BITFIELD(m->status, 61, 61); @@ -1007,22 +1068,47 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, break; } } + if (adxl_component_count) { + snprintf(skx_msg, MSG_SIZE, "%s%s err_code:%04x:%04x %s", + overflow ? " OVERFLOW" : "", + (uncorrected_error && recoverable) ? " recoverable" : "", + mscod, errcode, adxl_msg); + } else { + snprintf(skx_msg, MSG_SIZE, + "%s%s err_code:%04x:%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:%x col:%x", + overflow ? " OVERFLOW" : "", + (uncorrected_error && recoverable) ? " recoverable" : "", + mscod, errcode, + res->socket, res->imc, res->rank, + res->bank_group, res->bank_address, res->row, res->column); + } - snprintf(msg, sizeof(msg), - "%s%s err_code:%04x:%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:%x col:%x", - overflow ? " OVERFLOW" : "", - (uncorrected_error && recoverable) ? " recoverable" : "", - mscod, errcode, - res->socket, res->imc, res->rank, - res->bank_group, res->bank_address, res->row, res->column); - - edac_dbg(0, "%s\n", msg); + edac_dbg(0, "%s\n", skx_msg); /* Call the helper to output message */ edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, res->channel, res->dimm, -1, - optype, msg); + optype, skx_msg); +} + +static struct mem_ctl_info *get_mci(int src_id, int lmc) +{ + struct skx_dev *d; + + if (lmc > NUM_IMC - 1) { + skx_printk(KERN_ERR, "Bad lmc %d\n", lmc); + return NULL; + } + + list_for_each_entry(d, &skx_edac_list, list) { + if (d->imc[0].src_id == src_id) + return d->imc[lmc].mci; + } + + skx_printk(KERN_ERR, "No mci for src_id %d lmc %d\n", src_id, lmc); + + return NULL; } static int skx_mce_check_error(struct notifier_block *nb, unsigned long val, @@ -1040,10 +1126,23 @@ static int skx_mce_check_error(struct notifier_block *nb, unsigned long val, if ((mce->status & 0xefff) >> 7 != 1 || !(mce->status & MCI_STATUS_ADDRV)) return NOTIFY_DONE; + memset(&res, 0, sizeof(res)); res.addr = mce->addr; - if (!skx_decode(&res)) + + if (adxl_component_count) { + if (!skx_adxl_decode(&res)) + return NOTIFY_DONE; + + mci = get_mci(res.socket, res.imc); + } else { + if (!skx_decode(&res)) + return NOTIFY_DONE; + + mci = res.dev->imc[res.imc].mci; + } + + if (!mci) return NOTIFY_DONE; - mci = res.dev->imc[res.imc].mci; if (mce->mcgstatus & MCG_STATUS_MCIP) type = "Exception"; @@ -1094,6 +1193,62 @@ static void skx_remove(void) } } +static void __init skx_adxl_get(void) +{ + const char * const *names; + int i, j; + + names = adxl_get_component_names(); + if (!names) { + skx_printk(KERN_NOTICE, "No firmware support for address translation."); + skx_printk(KERN_CONT, " Only decoding DDR4 address!\n"); + return; + } + + for (i = 0; i < INDEX_MAX; i++) { + for (j = 0; names[j]; j++) { + if (!strcmp(component_names[i], names[j])) { + component_indices[i] = j; + break; + } + } + + if (!names[j]) + goto err; + } + + adxl_component_names = names; + while (*names++) + adxl_component_count++; + + adxl_values = kcalloc(adxl_component_count, sizeof(*adxl_values), + GFP_KERNEL); + if (!adxl_values) { + adxl_component_count = 0; + return; + } + + adxl_msg = kzalloc(MSG_SIZE, GFP_KERNEL); + if (!adxl_msg) { + adxl_component_count = 0; + kfree(adxl_values); + } + + return; +err: + skx_printk(KERN_ERR, "'%s' is not matched from DSM parameters: ", + component_names[i]); + for (j = 0; names[j]; j++) + skx_printk(KERN_CONT, "%s ", names[j]); + skx_printk(KERN_CONT, "\n"); +} + +static void __exit skx_adxl_put(void) +{ + kfree(adxl_values); + kfree(adxl_msg); +} + /* * skx_init: * make sure we are running on the correct cpu model @@ -1158,6 +1313,15 @@ static int __init skx_init(void) } } + skx_msg = kzalloc(MSG_SIZE, GFP_KERNEL); + if (!skx_msg) { + rc = -ENOMEM; + goto fail; + } + + if (nvdimm_count) + skx_adxl_get(); + /* Ensure that the OPSTATE is set correctly for POLL or NMI */ opstate_init(); @@ -1176,6 +1340,9 @@ static void __exit skx_exit(void) edac_dbg(2, "\n"); mce_unregister_decode_chain(&skx_mce_dec); skx_remove(); + if (nvdimm_count) + skx_adxl_put(); + kfree(skx_msg); teardown_skx_debug(); } |
