diff options
Diffstat (limited to 'drivers/edac')
-rw-r--r-- | drivers/edac/Kconfig | 27 | ||||
-rw-r--r-- | drivers/edac/Makefile | 1 | ||||
-rw-r--r-- | drivers/edac/amd64_edac.c | 294 | ||||
-rw-r--r-- | drivers/edac/amd64_edac.h | 16 | ||||
-rw-r--r-- | drivers/edac/amd64_edac_inj.c | 4 | ||||
-rw-r--r-- | drivers/edac/edac_core.h | 5 | ||||
-rw-r--r-- | drivers/edac/edac_mc.c | 158 | ||||
-rw-r--r-- | drivers/edac/edac_mc_sysfs.c | 71 | ||||
-rw-r--r-- | drivers/edac/edac_module.c | 2 | ||||
-rw-r--r-- | drivers/edac/edac_pci_sysfs.c | 2 | ||||
-rw-r--r-- | drivers/edac/ghes_edac.c | 537 | ||||
-rw-r--r-- | drivers/edac/i3200_edac.c | 37 | ||||
-rw-r--r-- | drivers/edac/i5100_edac.c | 178 | ||||
-rw-r--r-- | drivers/edac/i7300_edac.c | 19 | ||||
-rw-r--r-- | drivers/edac/i7core_edac.c | 8 | ||||
-rw-r--r-- | drivers/edac/mce_amd.c | 166 | ||||
-rw-r--r-- | drivers/edac/mce_amd.h | 13 | ||||
-rw-r--r-- | drivers/edac/mpc85xx_edac.c | 4 | ||||
-rw-r--r-- | drivers/edac/sb_edac.c | 55 |
19 files changed, 1220 insertions, 377 deletions
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 71b5635..f303b59 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -80,6 +80,29 @@ config EDAC_MM_EDAC occurred so that a particular failing memory module can be replaced. If unsure, select 'Y'. +config EDAC_GHES + bool "Output ACPI APEI/GHES BIOS detected errors via EDAC" + depends on ACPI_APEI_GHES && (EDAC_MM_EDAC=y) + default y + help + Not all machines support hardware-driven error report. Some of those + provide a BIOS-driven error report mechanism via ACPI, using the + APEI/GHES driver. By enabling this option, the error reports provided + by GHES are sent to userspace via the EDAC API. + + When this option is enabled, it will disable the hardware-driven + mechanisms, if a GHES BIOS is detected, entering into the + "Firmware First" mode. + + It should be noticed that keeping both GHES and a hardware-driven + error mechanism won't work well, as BIOS will race with OS, while + reading the error registers. So, if you want to not use "Firmware + first" GHES error mechanism, you should disable GHES either at + compilation time or by passing "ghes.disable=1" Kernel parameter + at boot time. + + In doubt, say 'Y'. + config EDAC_AMD64 tristate "AMD64 (Opteron, Athlon64) K8, F10h" depends on EDAC_MM_EDAC && AMD_NB && X86_64 && EDAC_DECODE_MCE @@ -158,7 +181,7 @@ config EDAC_I3000 config EDAC_I3200 tristate "Intel 3200" - depends on EDAC_MM_EDAC && PCI && X86 && EXPERIMENTAL + depends on EDAC_MM_EDAC && PCI && X86 help Support for error detection and correction on the Intel 3200 and 3210 server chipsets. @@ -224,7 +247,7 @@ config EDAC_I7300 config EDAC_SBRIDGE tristate "Intel Sandy-Bridge Integrated MC" depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL - depends on PCI_MMCONFIG && EXPERIMENTAL + depends on PCI_MMCONFIG help Support for error detection and correction the Intel Sandy Bridge Integrated Memory Controller. diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 5608a9b..4154ed6 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -16,6 +16,7 @@ ifdef CONFIG_PCI edac_core-y += edac_pci.o edac_pci_sysfs.o endif +obj-$(CONFIG_EDAC_GHES) += ghes_edac.o obj-$(CONFIG_EDAC_MCE_INJ) += mce_amd_inj.o edac_mce_amd-y := mce_amd.o diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index ad8bf2a..8b6a034 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -31,7 +31,7 @@ static struct ecc_settings **ecc_stngs; * *FIXME: Produce a better mapping/linearisation. */ -struct scrubrate { +static const struct scrubrate { u32 scrubval; /* bit pattern for scrub rate */ u32 bandwidth; /* bandwidth consumed (bytes/sec) */ } scrubrates[] = { @@ -98,6 +98,7 @@ int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset, * * F15h: we select which DCT we access using F1x10C[DctCfgSel] * + * F16h: has only 1 DCT */ static int k8_read_dct_pci_cfg(struct amd64_pvt *pvt, int addr, u32 *val, const char *func) @@ -239,7 +240,7 @@ static int amd64_get_scrub_rate(struct mem_ctl_info *mci) * DRAM base/limit associated with node_id */ static bool amd64_base_limit_match(struct amd64_pvt *pvt, u64 sys_addr, - unsigned nid) + u8 nid) { u64 addr; @@ -265,7 +266,7 @@ static struct mem_ctl_info *find_mc_by_sys_addr(struct mem_ctl_info *mci, u64 sys_addr) { struct amd64_pvt *pvt; - unsigned node_id; + u8 node_id; u32 intlv_en, bits; /* @@ -340,6 +341,27 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct, base_bits = GENMASK(21, 31) | GENMASK(9, 15); mask_bits = GENMASK(21, 29) | GENMASK(9, 15); addr_shift = 4; + + /* + * F16h needs two addr_shift values: 8 for high and 6 for low + * (cf. F16h BKDG). + */ + } else if (boot_cpu_data.x86 == 0x16) { + csbase = pvt->csels[dct].csbases[csrow]; + csmask = pvt->csels[dct].csmasks[csrow >> 1]; + + *base = (csbase & GENMASK(5, 15)) << 6; + *base |= (csbase & GENMASK(19, 30)) << 8; + + *mask = ~0ULL; + /* poke holes for the csmask */ + *mask &= ~((GENMASK(5, 15) << 6) | + (GENMASK(19, 30) << 8)); + + *mask |= (csmask & GENMASK(5, 15)) << 6; + *mask |= (csmask & GENMASK(19, 30)) << 8; + + return; } else { csbase = pvt->csels[dct].csbases[csrow]; csmask = pvt->csels[dct].csmasks[csrow >> 1]; @@ -602,111 +624,6 @@ static u64 sys_addr_to_input_addr(struct mem_ctl_info *mci, u64 sys_addr) return input_addr; } - -/* - * @input_addr is an InputAddr associated with the node represented by mci. - * Translate @input_addr to a DramAddr and return the result. - */ -static u64 input_addr_to_dram_addr(struct mem_ctl_info *mci, u64 input_addr) -{ - struct amd64_pvt *pvt; - unsigned node_id, intlv_shift; - u64 bits, dram_addr; - u32 intlv_sel; - - /* - * Near the start of section 3.4.4 (p. 70, BKDG #26094, K8, revA-E) - * shows how to translate a DramAddr to an InputAddr. Here we reverse - * this procedure. When translating from a DramAddr to an InputAddr, the - * bits used for node interleaving are discarded. Here we recover these - * bits from the IntlvSel field of the DRAM Limit register (section - * 3.4.4.2) for the node that input_addr is associated with. - */ - pvt = mci->pvt_info; - node_id = pvt->mc_node_id; - - BUG_ON(node_id > 7); - - intlv_shift = num_node_interleave_bits(dram_intlv_en(pvt, 0)); - if (intlv_shift == 0) { - edac_dbg(1, " InputAddr 0x%lx translates to DramAddr of same value\n", - (unsigned long)input_addr); - - return input_addr; - } - - bits = ((input_addr & GENMASK(12, 35)) << intlv_shift) + - (input_addr & 0xfff); - - intlv_sel = dram_intlv_sel(pvt, node_id) & ((1 << intlv_shift) - 1); - dram_addr = bits + (intlv_sel << 12); - - edac_dbg(1, "InputAddr 0x%lx translates to DramAddr 0x%lx (%d node interleave bits)\n", - (unsigned long)input_addr, - (unsigned long)dram_addr, intlv_shift); - - return dram_addr; -} - -/* - * @dram_addr is a DramAddr that maps to the node represented by mci. Convert - * @dram_addr to a SysAddr. - */ -static u64 dram_addr_to_sys_addr(struct mem_ctl_info *mci, u64 dram_addr) -{ - struct amd64_pvt *pvt = mci->pvt_info; - u64 hole_base, hole_offset, hole_size, base, sys_addr; - int ret = 0; - - ret = amd64_get_dram_hole_info(mci, &hole_base, &hole_offset, - &hole_size); - if (!ret) { - if ((dram_addr >= hole_base) && - (dram_addr < (hole_base + hole_size))) { - sys_addr = dram_addr + hole_offset; - - edac_dbg(1, "using DHAR to translate DramAddr 0x%lx to SysAddr 0x%lx\n", - (unsigned long)dram_addr, - (unsigned long)sys_addr); - - return sys_addr; - } - } - - base = get_dram_base(pvt, pvt->mc_node_id); - sys_addr = dram_addr + base; - - /* - * The sys_addr we have computed up to this point is a 40-bit value - * because the k8 deals with 40-bit values. However, the value we are - * supposed to return is a full 64-bit physical address. The AMD - * x86-64 architecture specifies that the most significant implemented - * address bit through bit 63 of a physical address must be either all - * 0s or all 1s. Therefore we sign-extend the 40-bit sys_addr to a - * 64-bit value below. See section 3.4.2 of AMD publication 24592: - * AMD x86-64 Architecture Programmer's Manual Volume 1 Application - * Programming. - */ - sys_addr |= ~((sys_addr & (1ull << 39)) - 1); - - edac_dbg(1, " Node %d, DramAddr 0x%lx to SysAddr 0x%lx\n", - pvt->mc_node_id, (unsigned long)dram_addr, - (unsigned long)sys_addr); - - return sys_addr; -} - -/* - * @input_addr is an InputAddr associated with the node given by mci. Translate - * @input_addr to a SysAddr. - */ -static inline u64 input_addr_to_sys_addr(struct mem_ctl_info *mci, - u64 input_addr) -{ - return dram_addr_to_sys_addr(mci, - input_addr_to_dram_addr(mci, input_addr)); -} - /* Map the Error address to a PAGE and PAGE OFFSET. */ static inline void error_address_to_page_and_offset(u64 error_address, struct err_info *err) @@ -939,7 +856,8 @@ static u64 get_error_address(struct mce *m) struct amd64_pvt *pvt; u64 cc6_base, tmp_addr; u32 tmp; - u8 mce_nid, intlv_en; + u16 mce_nid; + u8 intlv_en; if ((addr & GENMASK(24, 47)) >> 24 != 0x00fdf7) return addr; @@ -979,10 +897,29 @@ static u64 get_error_address(struct mce *m) return addr; } +static struct pci_dev *pci_get_related_function(unsigned int vendor, + unsigned int device, + struct pci_dev *related) +{ + struct pci_dev *dev = NULL; + + while ((dev = pci_get_device(vendor, device, dev))) { + if (pci_domain_nr(dev->bus) == pci_domain_nr(related->bus) && + (dev->bus->number == related->bus->number) && + (PCI_SLOT(dev->devfn) == PCI_SLOT(related->devfn))) + break; + } + + return dev; +} + static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range) { + struct amd_northbridge *nb; + struct pci_dev *misc, *f1 = NULL; struct cpuinfo_x86 *c = &boot_cpu_data; int off = range << 3; + u32 llim; amd64_read_pci_cfg(pvt->F1, DRAM_BASE_LO + off, &pvt->ranges[range].base.lo); amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_LO + off, &pvt->ranges[range].lim.lo); @@ -996,30 +933,32 @@ static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range) amd64_read_pci_cfg(pvt->F1, DRAM_BASE_HI + off, &pvt->ranges[range].base.hi); amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_HI + off, &pvt->ranges[range].lim.hi); - /* Factor in CC6 save area by reading dst node's limit reg */ - if (c->x86 == 0x15) { - struct pci_dev *f1 = NULL; - u8 nid = dram_dst_node(pvt, range); - u32 llim; + /* F15h: factor in CC6 save area by reading dst node's limit reg */ + if (c->x86 != 0x15) + return; - f1 = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0x18 + nid, 1)); - if (WARN_ON(!f1)) - return; + nb = node_to_amd_nb(dram_dst_node(pvt, range)); + if (WARN_ON(!nb)) + return; + + misc = nb->misc; + f1 = pci_get_related_function(misc->vendor, PCI_DEVICE_ID_AMD_15H_NB_F1, misc); + if (WARN_ON(!f1)) + return; - amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim); + amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim); - pvt->ranges[range].lim.lo &= GENMASK(0, 15); + pvt->ranges[range].lim.lo &= GENMASK(0, 15); - /* {[39:27],111b} */ - pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16; + /* {[39:27],111b} */ + pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16; - pvt->ranges[range].lim.hi &= GENMASK(0, 7); + pvt->ranges[range].lim.hi &= GENMASK(0, 7); - /* [47:40] */ - pvt->ranges[range].lim.hi |= llim >> 13; + /* [47:40] */ + pvt->ranges[range].lim.hi |= llim >> 13; - pci_dev_put(f1); - } + pci_dev_put(f1); } static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr, @@ -1233,6 +1172,21 @@ static int f15_dbam_to_chip_select(struct amd64_pvt *pvt, u8 dct, return ddr3_cs_size(cs_mode, false); } +/* + * F16h has only limited cs_modes + */ +static int f16_dbam_to_chip_select(struct amd64_pvt *pvt, u8 dct, + unsigned cs_mode) +{ + WARN_ON(cs_mode > 12); + + if (cs_mode == 6 || cs_mode == 8 || + cs_mode == 9 || cs_mode == 12) + return -1; + else + return ddr3_cs_size(cs_mode, false); +} + static void read_dram_ctl_register(struct amd64_pvt *pvt) { @@ -1305,7 +1259,7 @@ static u8 f1x_determine_channel(struct amd64_pvt *pvt, u64 sys_addr, } /* Convert the sys_addr to the normalized DCT address */ -static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, unsigned range, +static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range, u64 sys_addr, bool hi_rng, u32 dct_sel_base_addr) { @@ -1381,7 +1335,7 @@ static int f10_process_possible_spare(struct amd64_pvt *pvt, u8 dct, int csrow) * -EINVAL: NOT FOUND * 0..csrow = Chip-Select Row */ -static int f1x_lookup_addr_in_dct(u64 in_addr, u32 nid, u8 dct) +static int f1x_lookup_addr_in_dct(u64 in_addr, u8 nid, u8 dct) { struct mem_ctl_info *mci; struct amd64_pvt *pvt; @@ -1670,25 +1624,19 @@ static struct amd64_family_type amd64_family_types[] = { .read_dct_pci_cfg = f15_read_dct_pci_cfg, } }, + [F16_CPUS] = { + .ctl_name = "F16h", + .f1_id = PCI_DEVICE_ID_AMD_16H_NB_F1, + .f3_id = PCI_DEVICE_ID_AMD_16H_NB_F3, + .ops = { + .early_channel_count = f1x_early_channel_count, + .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, + .dbam_to_cs = f16_dbam_to_chip_select, + .read_dct_pci_cfg = f10_read_dct_pci_cfg, + } + }, }; -static struct pci_dev *pci_get_related_function(unsigned int vendor, - unsigned int device, - struct pci_dev *related) -{ - struct pci_dev *dev = NULL; - - dev = pci_get_device(vendor, device, dev); - while (dev) { - if ((dev->bus->number == related->bus->number) && - (PCI_SLOT(dev->devfn) == PCI_SLOT(related->devfn))) - break; - dev = pci_get_device(vendor, device, dev); - } - - return dev; -} - /* * These are tables of eigenvectors (one per line) which can be used for the * construction of the syndrome tables. The modified syndrome search algorithm @@ -1696,7 +1644,7 @@ static struct pci_dev *pci_get_related_function(unsigned int vendor, * * Algorithm courtesy of Ross LaFetra from AMD. */ -static u16 x4_vectors[] = { +static const u16 x4_vectors[] = { 0x2f57, 0x1afe, 0x66cc, 0xdd88, 0x11eb, 0x3396, 0x7f4c, 0xeac8, 0x0001, 0x0002, 0x0004, 0x0008, @@ -1735,7 +1683,7 @@ static u16 x4_vectors[] = { 0x19a9, 0x2efe, 0xb5cc, 0x6f88, }; -static u16 x8_vectors[] = { +static const u16 x8_vectors[] = { 0x0145, 0x028a, 0x2374, 0x43c8, 0xa1f0, 0x0520, 0x0a40, 0x1480, 0x0211, 0x0422, 0x0844, 0x1088, 0x01b0, 0x44e0, 0x23c0, 0xed80, 0x1011, 0x0116, 0x022c, 0x0458, 0x08b0, 0x8c60, 0x2740, 0x4e80, @@ -1757,7 +1705,7 @@ static u16 x8_vectors[] = { 0x0100, 0x0200, 0x0400, 0x0800, 0x1000, 0x2000, 0x4000, 0x8000, }; -static int decode_syndrome(u16 syndrome, u16 *vectors, unsigned num_vecs, +static int decode_syndrome(u16 syndrome, const u16 *vectors, unsigned num_vecs, unsigned v_dim) { unsigned int i, err_sym; @@ -2039,7 +1987,9 @@ static void read_mc_regs(struct amd64_pvt *pvt) if (c->x86 >= 0x10) { amd64_read_pci_cfg(pvt->F3, EXT_NB_MCA_CFG, &tmp); - amd64_read_dct_pci_cfg(pvt, DBAM1, &pvt->dbam1); + if (c->x86 != 0x16) + /* F16h has only DCT0 */ + amd64_read_dct_pci_cfg(pvt, DBAM1, &pvt->dbam1); /* F10h, revD and later can do x8 ECC too */ if ((c->x86 > 0x10 || c->x86_model > 7) && tmp & BIT(25)) @@ -2148,12 +2098,18 @@ static int init_csrows(struct mem_ctl_info *mci) edac_dbg(1, "MC node: %d, csrow: %d\n", pvt->mc_node_id, i); - if (row_dct0) + if (row_dct0) { nr_pages = amd64_csrow_nr_pages(pvt, 0, i); + csrow->channels[0]->dimm->nr_pages = nr_pages; + } /* K8 has only one DCT */ - if (boot_cpu_data.x86 != 0xf && row_dct1) - nr_pages += amd64_csrow_nr_pages(pvt, 1, i); + if (boot_cpu_data.x86 != 0xf && row_dct1) { + int row_dct1_pages = amd64_csrow_nr_pages(pvt, 1, i); + + csrow->channels[1]->dimm->nr_pages = row_dct1_pages; + nr_pages += row_dct1_pages; + } mtype = amd64_determine_memory_type(pvt, i); @@ -2172,16 +2128,14 @@ static int init_csrows(struct mem_ctl_info *mci) dimm = csrow->channels[j]->dimm; dimm->mtype = mtype; dimm->edac_mode = edac_mode; - dimm->nr_pages = nr_pages; } - csrow->nr_pages = nr_pages; } return empty; } /* get all cores on this DCT */ -static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, unsigned nid) +static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid) { int cpu; @@ -2191,7 +2145,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, unsigned nid) } /* check MCG_CTL on all the cpus on this node */ -static bool amd64_nb_mce_bank_enabled_on_node(unsigned nid) +static bool amd64_nb_mce_bank_enabled_on_node(u16 nid) { cpumask_var_t mask; int cpu, nbe; @@ -2224,7 +2178,7 @@ out: return ret; } -static int toggle_ecc_err_reporting(struct ecc_settings *s, u8 nid, bool on) +static int toggle_ecc_err_reporting(struct ecc_settings *s, u16 nid, bool on) { cpumask_var_t cmask; int cpu; @@ -2262,7 +2216,7 @@ static int toggle_ecc_err_reporting(struct ecc_settings *s, u8 nid, bool on) return 0; } -static bool enable_ecc_error_reporting(struct ecc_settings *s, u8 nid, +static bool enable_ecc_error_reporting(struct ecc_settings *s, u16 nid, struct pci_dev *F3) { bool ret = true; @@ -2314,7 +2268,7 @@ static bool enable_ecc_error_reporting(struct ecc_settings *s, u8 nid, return ret; } -static void restore_ecc_error_reporting(struct ecc_settings *s, u8 nid, +static void restore_ecc_error_reporting(struct ecc_settings *s, u16 nid, struct pci_dev *F3) { u32 value, mask = 0x3; /* UECC/CECC enable */ @@ -2353,7 +2307,7 @@ static const char *ecc_msg = "'ecc_enable_override'.\n" " (Note that use of the override may cause unknown side effects.)\n"; -static bool ecc_enabled(struct pci_dev *F3, u8 nid) +static bool ecc_enabled(struct pci_dev *F3, u16 nid) { u32 value; u8 ecc_en = 0; @@ -2452,6 +2406,11 @@ static struct amd64_family_type *amd64_per_family_init(struct amd64_pvt *pvt) pvt->ops = &amd64_family_types[F15_CPUS].ops; break; + case 0x16: + fam_type = &amd64_family_types[F16_CPUS]; + pvt->ops = &amd64_family_types[F16_CPUS].ops; + break; + default: amd64_err("Unsupported family!\n"); return NULL; @@ -2474,7 +2433,7 @@ static int amd64_init_one_instance(struct pci_dev *F2) struct mem_ctl_info *mci = NULL; struct edac_mc_layer layers[2]; int err = 0, ret; - u8 nid = get_node_id(F2); + u16 nid = amd_get_node_id(F2); ret = -ENOMEM; pvt = kzalloc(sizeof(struct amd64_pvt), GFP_KERNEL); @@ -2519,7 +2478,6 @@ static int amd64_init_one_instance(struct pci_dev *F2) mci->pvt_info = pvt; mci->pdev = &pvt->F2->dev; - mci->csbased = 1; setup_mci_misc_attrs(mci, fam_type); @@ -2566,7 +2524,7 @@ err_ret: static int amd64_probe_one_instance(struct pci_dev *pdev, const struct pci_device_id *mc_type) { - u8 nid = get_node_id(pdev); + u16 nid = amd_get_node_id(pdev); struct pci_dev *F3 = node_to_amd_nb(nid)->misc; struct ecc_settings *s; int ret = 0; @@ -2616,7 +2574,7 @@ static void amd64_remove_one_instance(struct pci_dev *pdev) { struct mem_ctl_info *mci; struct amd64_pvt *pvt; - u8 nid = get_node_id(pdev); + u16 nid = amd_get_node_id(pdev); struct pci_dev *F3 = node_to_amd_nb(nid)->misc; struct ecc_settings *s = ecc_stngs[nid]; @@ -2678,6 +2636,14 @@ static DEFINE_PCI_DEVICE_TABLE(amd64_pci_table) = { .class = 0, .class_mask = 0, }, + { + .vendor = PCI_VENDOR_ID_AMD, + .device = PCI_DEVICE_ID_AMD_16H_NB_F2, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .class = 0, + .class_mask = 0, + }, {0, } }; diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index e864f40..2c6f113 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -172,7 +172,8 @@ */ #define PCI_DEVICE_ID_AMD_15H_NB_F1 0x1601 #define PCI_DEVICE_ID_AMD_15H_NB_F2 0x1602 - +#define PCI_DEVICE_ID_AMD_16H_NB_F1 0x1531 +#define PCI_DEVICE_ID_AMD_16H_NB_F2 0x1532 /* * Function 1 - Address Map @@ -292,16 +293,11 @@ /* MSRs */ #define MSR_MCGCTL_NBE BIT(4) -/* AMD sets the first MC device at device ID 0x18. */ -static inline u8 get_node_id(struct pci_dev *pdev) -{ - return PCI_SLOT(pdev->devfn) - 0x18; -} - enum amd_families { K8_CPUS = 0, F10_CPUS, F15_CPUS, + F16_CPUS, NUM_FAMILIES, }; @@ -340,7 +336,7 @@ struct amd64_pvt { /* pci_device handles which we utilize */ struct pci_dev *F1, *F2, *F3; - unsigned mc_node_id; /* MC index of this MC node */ + u16 mc_node_id; /* MC index of this MC node */ int ext_model; /* extended model value of this node */ int channel_count; @@ -393,7 +389,7 @@ struct err_info { u32 offset; }; -static inline u64 get_dram_base(struct amd64_pvt *pvt, unsigned i) +static inline u64 get_dram_base(struct amd64_pvt *pvt, u8 i) { u64 addr = ((u64)pvt->ranges[i].base.lo & 0xffff0000) << 8; @@ -403,7 +399,7 @@ static inline u64 get_dram_base(struct amd64_pvt *pvt, unsigned i) return (((u64)pvt->ranges[i].base.hi & 0x000000ff) << 40) | addr; } -static inline u64 get_dram_limit(struct amd64_pvt *pvt, unsigned i) +static inline u64 get_dram_limit(struct amd64_pvt *pvt, u8 i) { u64 lim = (((u64)pvt->ranges[i].lim.lo & 0xffff0000) << 8) | 0x00ffffff; diff --git a/drivers/edac/amd64_edac_inj.c b/drivers/edac/amd64_edac_inj.c index 8c171fa..845f047 100644 --- a/drivers/edac/amd64_edac_inj.c +++ b/drivers/edac/amd64_edac_inj.c @@ -202,9 +202,9 @@ static DEVICE_ATTR(inject_word, S_IRUGO | S_IWUSR, amd64_inject_word_show, amd64_inject_word_store); static DEVICE_ATTR(inject_ecc_vector, S_IRUGO | S_IWUSR, amd64_inject_ecc_vector_show, amd64_inject_ecc_vector_store); -static DEVICE_ATTR(inject_write, S_IRUGO | S_IWUSR, +static DEVICE_ATTR(inject_write, S_IWUSR, NULL, amd64_inject_write_store); -static DEVICE_ATTR(inject_read, S_IRUGO | S_IWUSR, +static DEVICE_ATTR(inject_read, S_IWUSR, NULL, amd64_inject_read_store); diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 23bb99f..3c2625e 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -453,6 +453,11 @@ extern struct mem_ctl_info *find_mci_by_dev(struct device *dev); extern struct mem_ctl_info *edac_mc_del_mc(struct device *dev); extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, unsigned long page); + +void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, + struct mem_ctl_info *mci, + struct edac_raw_error_desc *e); + void edac_mc_handle_error(const enum hw_event_mc_err_type type, struct mem_ctl_info *mci, const u16 error_count, diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index d1e9eb1..27e86d9 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -42,6 +42,12 @@ static DEFINE_MUTEX(mem_ctls_mutex); static LIST_HEAD(mc_devices); +/* + * Used to lock EDAC MC to just one module, avoiding two drivers e. g. + * apei/ghes and i7core_edac to be used at the same time. + */ +static void const *edac_mc_owner; + unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf, unsigned len) { @@ -80,7 +86,7 @@ static void edac_mc_dump_dimm(struct dimm_info *dimm, int number) edac_dimm_info_location(dimm, location, sizeof(location)); edac_dbg(4, "%s%i: %smapped as virtual row %d, chan %d\n", - dimm->mci->mem_is_per_rank ? "rank" : "dimm", + dimm->mci->csbased ? "rank" : "dimm", number, location, dimm->csrow, dimm->cschannel); edac_dbg(4, " dimm = %p\n", dimm); edac_dbg(4, " dimm->label = '%s'\n", dimm->label); @@ -335,7 +341,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, memcpy(mci->layers, layers, sizeof(*layer) * n_layers); mci->nr_csrows = tot_csrows; mci->num_cschannel = tot_channels; - mci->mem_is_per_rank = per_rank; + mci->csbased = per_rank; /* * Alocate and fill the csrow/channels structs @@ -441,13 +447,6 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, mci->op_state = OP_ALLOC; - /* at this point, the root kobj is valid, and in order to - * 'free' the object, then the function: - * edac_mc_unregister_sysfs_main_kobj() must be called - * which will perform kobj unregistration and the actual free - * will occur during the kobject callback operation - */ - return mci; error: @@ -666,9 +665,9 @@ fail1: return 1; } -static void del_mc_from_global_list(struct mem_ctl_info *mci) +static int del_mc_from_global_list(struct mem_ctl_info *mci) { - atomic_dec(&edac_handlers); + int handlers = atomic_dec_return(&edac_handlers); list_del_rcu(&mci->link); /* these are for safe removal of devices from global list while @@ -676,6 +675,8 @@ static void del_mc_from_global_list(struct mem_ctl_info *mci) */ synchronize_rcu(); INIT_LIST_HEAD(&mci->link); + + return handlers; } /** @@ -719,6 +720,7 @@ EXPORT_SYMBOL(edac_mc_find); /* FIXME - should a warning be printed if no error detection? correction? */ int edac_mc_add_mc(struct mem_ctl_info *mci) { + int ret = -EINVAL; edac_dbg(0, "\n"); #ifdef CONFIG_EDAC_DEBUG @@ -749,6 +751,11 @@ int edac_mc_add_mc(struct mem_ctl_info *mci) #endif mutex_lock(&mem_ctls_mutex); + if (edac_mc_owner && edac_mc_owner != mci->mod_name) { + ret = -EPERM; + goto fail0; + } + if (add_mc_to_global_list(mci)) goto fail0; @@ -775,6 +782,8 @@ int edac_mc_add_mc(struct mem_ctl_info *mci) edac_mc_printk(mci, KERN_INFO, "Giving out device to '%s' '%s':" " DEV %s\n", mci->mod_name, mci->ctl_name, edac_dev_name(mci)); + edac_mc_owner = mci->mod_name; + mutex_unlock(&mem_ctls_mutex); return 0; @@ -783,7 +792,7 @@ fail1: fail0: mutex_unlock(&mem_ctls_mutex); - return 1; + return ret; } EXPORT_SYMBOL_GPL(edac_mc_add_mc); @@ -809,7 +818,8 @@ struct mem_ctl_info *edac_mc_del_mc(struct device *dev) return NULL; } - del_mc_from_global_list(mci); + if (!del_mc_from_global_list(mci)) + edac_mc_owner = NULL; mutex_unlock(&mem_ctls_mutex); /* flush workq processes */ @@ -907,6 +917,7 @@ const char *edac_layer_name[] = { [EDAC_MC_LAYER_CHANNEL] = "channel", [EDAC_MC_LAYER_SLOT] = "slot", [EDAC_MC_LAYER_CHIP_SELECT] = "csrow", + [EDAC_MC_LAYER_ALL_MEM] = "memory", }; EXPORT_SYMBOL_GPL(edac_layer_name); @@ -1054,7 +1065,46 @@ static void edac_ue_error(struct mem_ctl_info *mci, edac_inc_ue_error(mci, enable_per_layer_report, pos, error_count); } -#define OTHER_LABEL " or " +/** + * edac_raw_mc_handle_error - reports a memory event to userspace without doing + * anything to discover the error location + * + * @type: severity of the error (CE/UE/Fatal) + * @mci: a struct mem_ctl_info pointer + * @e: error description + * + * This raw function is used internally by edac_mc_handle_error(). It should + * only be called directly when the hardware error come directly from BIOS, + * like in the case of APEI GHES driver. + */ +void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, + struct mem_ctl_info *mci, + struct edac_raw_error_desc *e) +{ + char detail[80]; + int pos[EDAC_MAX_LAYERS] = { e->top_layer, e->mid_layer, e->low_layer }; + + /* Memory type dependent details about the error */ + if (type == HW_EVENT_ERR_CORRECTED) { + snprintf(detail, sizeof(detail), + "page:0x%lx offset:0x%lx grain:%ld syndrome:0x%lx", + e->page_frame_number, e->offset_in_page, + e->grain, e->syndrome); + edac_ce_error(mci, e->error_count, pos, e->msg, e->location, e->label, + detail, e->other_detail, e->enable_per_layer_report, + e->page_frame_number, e->offset_in_page, e->grain); + } else { + snprintf(detail, sizeof(detail), + "page:0x%lx offset:0x%lx grain:%ld", + e->page_frame_number, e->offset_in_page, e->grain); + + edac_ue_error(mci, e->error_count, pos, e->msg, e->location, e->label, + detail, e->other_detail, e->enable_per_layer_report); + } + + +} +EXPORT_SYMBOL_GPL(edac_raw_mc_handle_error); /** * edac_mc_handle_error - reports a memory event to userspace @@ -1086,19 +1136,27 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, const char *msg, const char *other_detail) { - /* FIXME: too much for stack: move it to some pre-alocated area */ - char detail[80], location[80]; - char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * mci->tot_dimms]; char *p; int row = -1, chan = -1; int pos[EDAC_MAX_LAYERS] = { top_layer, mid_layer, low_layer }; - int i; - long grain; - bool enable_per_layer_report = false; + int i, n_labels = 0; u8 grain_bits; + struct edac_raw_error_desc *e = &mci->error_desc; edac_dbg(3, "MC%d\n", mci->mc_idx); + /* Fills the error report buffer */ + memset(e, 0, sizeof (*e)); + e->error_count = error_count; + e->top_layer = top_layer; + e->mid_layer = mid_layer; + e->low_layer = low_layer; + e->page_frame_number = page_frame_number; + e->offset_in_page = offset_in_page; + e->syndrome = syndrome; + e->msg = msg; + e->other_detail = other_detail; + /* * Check if the event report is consistent and if the memory * location is known. If it is known, enable_per_layer_report will be @@ -1121,7 +1179,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, pos[i] = -1; } if (pos[i] >= 0) - enable_per_layer_report = true; + e->enable_per_layer_report = true; } /* @@ -1135,8 +1193,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, * where each memory belongs to a separate channel within the same * branch. */ - grain = 0; - p = label; + p = e->label; *p = '\0'; for (i = 0; i < mci->tot_dimms; i++) { @@ -1150,8 +1207,8 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, continue; /* get the max grain, over the error match range */ - if (dimm->grain > grain) - grain = dimm->grain; + if (dimm->grain > e->grain) + e->grain = dimm->grain; /* * If the error is memory-controller wide, there's no need to @@ -1159,8 +1216,13 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, * channel/memory controller/... may be affected. * Also, don't show errors for empty DIMM slots. */ - if (enable_per_layer_report && dimm->nr_pages) { - if (p != label) { + if (e->enable_per_layer_report && dimm->nr_pages) { + if (n_labels >= EDAC_MAX_LABELS) { + e->enable_per_layer_report = false; + break; + } + n_labels++; + if (p != e->label) { strcpy(p, OTHER_LABEL); p += strlen(OTHER_LABEL); } @@ -1173,7 +1235,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, * incrementing the compat API counters */ edac_dbg(4, "%s csrows map: (%d,%d)\n", - mci->mem_is_per_rank ? "rank" : "dimm", + mci->csbased ? "rank" : "dimm", dimm->csrow, dimm->cschannel); if (row == -1) row = dimm->csrow; @@ -1187,12 +1249,12 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, } } - if (!enable_per_layer_report) { - strcpy(label, "any memory"); + if (!e->enable_per_layer_report) { + strcpy(e->label, "any memory"); } else { edac_dbg(4, "csrow/channel to increment: (%d,%d)\n", row, chan); - if (p == label) - strcpy(label, "unknown memory"); + if (p == e->label) + strcpy(e->label, "unknown memory"); if (type == HW_EVENT_ERR_CORRECTED) { if (row >= 0) { mci->csrows[row]->ce_count += error_count; @@ -1205,7 +1267,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, } /* Fill the RAM location data */ - p = location; + p = e->location; for (i = 0; i < mci->n_layers; i++) { if (pos[i] < 0) @@ -1215,32 +1277,16 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, edac_layer_name[mci->layers[i].type], pos[i]); } - if (p > location) + if (p > e->location) *(p - 1) = '\0'; /* Report the error via the trace interface */ - grain_bits = fls_long(grain) + 1; - trace_mc_event(type, msg, label, error_count, - mci->mc_idx, top_layer, mid_layer, low_layer, - PAGES_TO_MiB(page_frame_number) | offset_in_page, - grain_bits, syndrome, other_detail); + grain_bits = fls_long(e->grain) + 1; + trace_mc_event(type, e->msg, e->label, e->error_count, + mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer, + PAGES_TO_MiB(e->page_frame_number) | e->offset_in_page, + grain_bits, e->syndrome, e->other_detail); - /* Memory type dependent details about the error */ - if (type == HW_EVENT_ERR_CORRECTED) { - snprintf(detail, sizeof(detail), - "page:0x%lx offset:0x%lx grain:%ld syndrome:0x%lx", - page_frame_number, offset_in_page, - grain, syndrome); - edac_ce_error(mci, error_count, pos, msg, location, label, - detail, other_detail, enable_per_layer_report, - page_frame_number, offset_in_page, grain); - } else { - snprintf(detail, sizeof(detail), - "page:0x%lx offset:0x%lx grain:%ld", - page_frame_number, offset_in_page, grain); - - edac_ue_error(mci, error_count, pos, msg, location, label, - detail, other_detail, enable_per_layer_report); - } + edac_raw_mc_handle_error(type, mci, e); } EXPORT_SYMBOL_GPL(edac_mc_handle_error); diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 0ca1ca7..67610a6 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -7,7 +7,7 @@ * * Written Doug Thompson <norsk5@xmission.com> www.softwarebitmaker.com * - * (c) 2012 - Mauro Carvalho Chehab <mchehab@redhat.com> + * (c) 2012-2013 - Mauro Carvalho Chehab <mchehab@redhat.com> * The entire API were re-written, and ported to use struct device * */ @@ -87,7 +87,7 @@ static struct device *mci_pdev; /* * various constants for Memory Controllers */ -static const char *mem_types[] = { +static const char * const mem_types[] = { [MEM_EMPTY] = "Empty", [MEM_RESERVED] = "Reserved", [MEM_UNKNOWN] = "Unknown", @@ -107,7 +107,7 @@ static const char *mem_types[] = { [MEM_RDDR3] = "Registered-DDR3" }; -static const char *dev_types[] = { +static const char * const dev_types[] = { [DEV_UNKNOWN] = "Unknown", [DEV_X1] = "x1", [DEV_X2] = "x2", @@ -118,7 +118,7 @@ static const char *dev_types[] = { [DEV_X64] = "x64" }; -static const char *edac_caps[] = { +static const char * const edac_caps[] = { [EDAC_UNKNOWN] = "Unknown", [EDAC_NONE] = "None", [EDAC_RESERVED] = "Reserved", @@ -143,7 +143,7 @@ static const char *edac_caps[] = { * and the per-dimm/per-rank one */ #define DEVICE_ATTR_LEGACY(_name, _mode, _show, _store) \ - struct device_attribute dev_attr_legacy_##_name = __ATTR(_name, _mode, _show, _store) + static struct device_attribute dev_attr_legacy_##_name = __ATTR(_name, _mode, _show, _store) struct dev_ch_attribute { struct device_attribute attr; @@ -180,9 +180,6 @@ static ssize_t csrow_size_show(struct device *dev, int i; u32 nr_pages = 0; - if (csrow->mci->csbased) - return sprintf(data, "%u\n", PAGES_TO_MiB(csrow->nr_pages)); - for (i = 0; i < csrow->nr_channels; i++) nr_pages += csrow->channels[i]->dimm->nr_pages; return sprintf(data, "%u\n", PAGES_TO_MiB(nr_pages)); @@ -330,17 +327,17 @@ static struct device_attribute *dynamic_csrow_dimm_attr[] = { }; /* possible dynamic channel ce_count attribute files */ -DEVICE_CHANNEL(ch0_ce_count, S_IRUGO | S_IWUSR, +DEVICE_CHANNEL(ch0_ce_count, S_IRUGO, channel_ce_count_show, NULL, 0); -DEVICE_CHANNEL(ch1_ce_count, S_IRUGO | S_IWUSR, +DEVICE_CHANNEL(ch1_ce_count, S_IRUGO, channel_ce_count_show, NULL, 1); -DEVICE_CHANNEL(ch2_ce_count, S_IRUGO | S_IWUSR, +DEVICE_CHANNEL(ch2_ce_count, S_IRUGO, channel_ce_count_show, NULL, 2); -DEVICE_CHANNEL(ch3_ce_count, S_IRUGO | S_IWUSR, +DEVICE_CHANNEL(ch3_ce_count, S_IRUGO, channel_ce_count_show, NULL, 3); -DEVICE_CHANNEL(ch4_ce_count, S_IRUGO | S_IWUSR, +DEVICE_CHANNEL(ch4_ce_count, S_IRUGO, channel_ce_count_show, NULL, 4); -DEVICE_CHANNEL(ch5_ce_count, S_IRUGO | S_IWUSR, +DEVICE_CHANNEL(ch5_ce_count, S_IRUGO, channel_ce_count_show, NULL, 5); /* Total possible dynamic ce_count attribute file table */ @@ -429,8 +426,12 @@ static int edac_create_csrow_objects(struct mem_ctl_info *mci) if (!nr_pages_per_csrow(csrow)) continue; err = edac_create_csrow_object(mci, mci->csrows[i], i); - if (err < 0) + if (err < 0) { + edac_dbg(1, + "failure: create csrow objects for csrow %d\n", + i); goto error; + } } return 0; @@ -608,7 +609,7 @@ static int edac_create_dimm_object(struct mem_ctl_info *mci, device_initialize(&dimm->dev); dimm->dev.parent = &mci->dev; - if (mci->mem_is_per_rank) + if (mci->csbased) dev_set_name(&dimm->dev, "rank%d", index); else dev_set_name(&dimm->dev, "dimm%d", index); @@ -677,9 +678,6 @@ static ssize_t mci_sdram_scrub_rate_store(struct device *dev, unsigned long bandwidth = 0; int new_bw = 0; - if (!mci->set_sdram_scrub_rate) - return -ENODEV; - if (strict_strtoul(data, 10, &bandwidth) < 0) return -EINVAL; @@ -703,9 +701,6 @@ static ssize_t mci_sdram_scrub_rate_show(struct device *dev, struct mem_ctl_info *mci = to_mci(dev); int bandwidth = 0; - if (!mci->get_sdram_scrub_rate) - return -ENODEV; - bandwidth = mci->get_sdram_scrub_rate(mci); if (bandwidth < 0) { edac_printk(KERN_DEBUG, EDAC_MC, "Error reading scrub rate\n"); @@ -780,14 +775,10 @@ static ssize_t mci_size_mb_show(struct device *dev, for (csrow_idx = 0; csrow_idx < mci->nr_csrows; csrow_idx++) { struct csrow_info *csrow = mci->csrows[csrow_idx]; - if (csrow->mci->csbased) { - total_pages += csrow->nr_pages; - } else { - for (j = 0; j < csrow->nr_channels; j++) { - struct dimm_info *dimm = csrow->channels[j]->dimm; + for (j = 0; j < csrow->nr_channels; j++) { + struct dimm_info *dimm = csrow->channels[j]->dimm; - total_pages += dimm->nr_pages; - } + total_pages += dimm->nr_pages; } } @@ -866,8 +857,7 @@ DEVICE_ATTR(ce_count, S_IRUGO, mci_ce_count_show, NULL); DEVICE_ATTR(max_location, S_IRUGO, mci_max_location_show, NULL); /* memory scrubber attribute file */ -DEVICE_ATTR(sdram_scrub_rate, S_IRUGO | S_IWUSR, mci_sdram_scrub_rate_show, - mci_sdram_scrub_rate_store); +DEVICE_ATTR(sdram_scrub_rate, 0, NULL, NULL); static struct attribute *mci_attrs[] = { &dev_attr_reset_counters.attr, @@ -878,7 +868,6 @@ static struct attribute *mci_attrs[] = { &dev_attr_ce_noinfo_count.attr, &dev_attr_ue_count.attr, &dev_attr_ce_count.attr, - &dev_attr_sdram_scrub_rate.attr, &dev_attr_max_location.attr, NULL }; @@ -1007,11 +996,28 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) edac_dbg(0, "creating device %s\n", dev_name(&mci->dev)); err = device_add(&mci->dev); if (err < 0) { + edac_dbg(1, "failure: create device %s\n", dev_name(&mci->dev)); bus_unregister(&mci->bus); kfree(mci->bus.name); return err; } + if (mci->set_sdram_scrub_rate || mci->get_sdram_scrub_rate) { + if (mci->get_sdram_scrub_rate) { + dev_attr_sdram_scrub_rate.attr.mode |= S_IRUGO; + dev_attr_sdram_scrub_rate.show = &mci_sdram_scrub_rate_show; + } + if (mci->set_sdram_scrub_rate) { + dev_attr_sdram_scrub_rate.attr.mode |= S_IWUSR; + dev_attr_sdram_scrub_rate.store = &mci_sdram_scrub_rate_store; + } + err = device_create_file(&mci->dev, + &dev_attr_sdram_scrub_rate); + if (err) { + edac_dbg(1, "failure: create sdram_scrub_rate\n"); + goto fail2; + } + } /* * Create the dimm/rank devices */ @@ -1056,6 +1062,7 @@ fail: continue; device_unregister(&dimm->dev); } +fail2: device_unregister(&mci->dev); bus_unregister(&mci->bus); kfree(mci->bus.name); diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c index 12c951a..a66941f 100644 --- a/drivers/edac/edac_module.c +++ b/drivers/edac/edac_module.c @@ -146,7 +146,7 @@ static void __exit edac_exit(void) /* * Inform the kernel of our entry and exit points */ -module_init(edac_init); +subsys_initcall(edac_init); module_exit(edac_exit); MODULE_LICENSE("GPL"); diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index 0056c4d..e8658e4 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -429,8 +429,8 @@ static void edac_pci_main_kobj_teardown(void) if (atomic_dec_return(&edac_pci_sysfs_refcount) == 0) { edac_dbg(0, "called kobject_put on main kobj\n"); kobject_put(edac_pci_top_main_kobj); + edac_put_sysfs_subsys(); } - edac_put_sysfs_subsys(); } /* diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c new file mode 100644 index 0000000..bb53467 --- /dev/null +++ b/drivers/edac/ghes_edac.c @@ -0,0 +1,537 @@ +/* + * GHES/EDAC Linux driver + * + * This file may be distributed under the terms of the GNU General Public + * License version 2. + * + * Copyright (c) 2013 by Mauro Carvalho Chehab <mchehab@redhat.com> + * + * Red Hat Inc. http://www.redhat.com + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <acpi/ghes.h> +#include <linux/edac.h> +#include <linux/dmi.h> +#include "edac_core.h" +#include <ras/ras_event.h> + +#define GHES_EDAC_REVISION " Ver: 1.0.0" + +struct ghes_edac_pvt { + struct list_head list; + struct ghes *ghes; + struct mem_ctl_info *mci; + + /* Buffers for the error handling routine */ + char detail_location[240]; + char other_detail[160]; + char msg[80]; +}; + +static LIST_HEAD(ghes_reglist); +static DEFINE_MUTEX(ghes_edac_lock); +static int ghes_edac_mc_num; + + +/* Memory Device - Type 17 of SMBIOS spec */ +struct memdev_dmi_entry { + u8 type; + u8 length; + u16 handle; + u16 phys_mem_array_handle; + u16 mem_err_info_handle; + u16 total_width; + u16 data_width; + u16 size; + u8 form_factor; + u8 device_set; + u8 device_locator; + u8 bank_locator; + u8 memory_type; + u16 type_detail; + u16 speed; + u8 manufacturer; + u8 serial_number; + u8 asset_tag; + u8 part_number; + u8 attributes; + u32 extended_size; + u16 conf_mem_clk_speed; +} __attribute__((__packed__)); + +struct ghes_edac_dimm_fill { + struct mem_ctl_info *mci; + unsigned count; +}; + +char *memory_type[] = { + [MEM_EMPTY] = "EMPTY", + [MEM_RESERVED] = "RESERVED", + [MEM_UNKNOWN] = "UNKNOWN", + [MEM_FPM] = "FPM", + [MEM_EDO] = "EDO", + [MEM_BEDO] = "BEDO", + [MEM_SDR] = "SDR", + [MEM_RDR] = "RDR", + [MEM_DDR] = "DDR", + [MEM_RDDR] = "RDDR", + [MEM_RMBS] = "RMBS", + [MEM_DDR2] = "DDR2", + [MEM_FB_DDR2] = "FB_DDR2", + [MEM_RDDR2] = "RDDR2", + [MEM_XDR] = "XDR", + [MEM_DDR3] = "DDR3", + [MEM_RDDR3] = "RDDR3", +}; + +static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg) +{ + int *num_dimm = arg; + + if (dh->type == DMI_ENTRY_MEM_DEVICE) + (*num_dimm)++; +} + +static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) +{ + struct ghes_edac_dimm_fill *dimm_fill = arg; + struct mem_ctl_info *mci = dimm_fill->mci; + + if (dh->type == DMI_ENTRY_MEM_DEVICE) { + struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh; + struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, + mci->n_layers, + dimm_fill->count, 0, 0); + + if (entry->size == 0xffff) { + pr_info("Can't get DIMM%i size\n", + dimm_fill->count); + dimm->nr_pages = MiB_TO_PAGES(32);/* Unknown */ + } else if (entry->size == 0x7fff) { + dimm->nr_pages = MiB_TO_PAGES(entry->extended_size); + } else { + if (entry->size & 1 << 15) + dimm->nr_pages = MiB_TO_PAGES((entry->size & + 0x7fff) << 10); + else + dimm->nr_pages = MiB_TO_PAGES(entry->size); + } + + switch (entry->memory_type) { + case 0x12: + if (entry->type_detail & 1 << 13) + dimm->mtype = MEM_RDDR; + else + dimm->mtype = MEM_DDR; + break; + case 0x13: + if (entry->type_detail & 1 << 13) + dimm->mtype = MEM_RDDR2; + else + dimm->mtype = MEM_DDR2; + break; + case 0x14: + dimm->mtype = MEM_FB_DDR2; + break; + case 0x18: + if (entry->type_detail & 1 << 13) + dimm->mtype = MEM_RDDR3; + else + dimm->mtype = MEM_DDR3; + break; + default: + if (entry->type_detail & 1 << 6) + dimm->mtype = MEM_RMBS; + else if ((entry->type_detail & ((1 << 7) | (1 << 13))) + == ((1 << 7) | (1 << 13))) + dimm->mtype = MEM_RDR; + else if (entry->type_detail & 1 << 7) + dimm->mtype = MEM_SDR; + else if (entry->type_detail & 1 << 9) + dimm->mtype = MEM_EDO; + else + dimm->mtype = MEM_UNKNOWN; + } + + /* + * Actually, we can only detect if the memory has bits for + * checksum or not + */ + if (entry->total_width == entry->data_width) + dimm->edac_mode = EDAC_NONE; + else + dimm->edac_mode = EDAC_SECDED; + + dimm->dtype = DEV_UNKNOWN; + dimm->grain = 128; /* Likely, worse case */ + + /* + * FIXME: It shouldn't be hard to also fill the DIMM labels + */ + + if (dimm->nr_pages) { + edac_dbg(1, "DIMM%i: %s size = %d MB%s\n", + dimm_fill->count, memory_type[dimm->mtype], + PAGES_TO_MiB(dimm->nr_pages), + (dimm->edac_mode != EDAC_NONE) ? "(ECC)" : ""); + edac_dbg(2, "\ttype %d, detail 0x%02x, width %d(total %d)\n", + entry->memory_type, entry->type_detail, + entry->total_width, entry->data_width); + } + + dimm_fill->count++; + } +} + +void ghes_edac_report_mem_error(struct ghes *ghes, int sev, + struct cper_sec_mem_err *mem_err) +{ + enum hw_event_mc_err_type type; + struct edac_raw_error_desc *e; + struct mem_ctl_info *mci; + struct ghes_edac_pvt *pvt = NULL; + char *p; + u8 grain_bits; + + list_for_each_entry(pvt, &ghes_reglist, list) { + if (ghes == pvt->ghes) + break; + } + if (!pvt) { + pr_err("Internal error: Can't find EDAC structure\n"); + return; + } + mci = pvt->mci; + e = &mci->error_desc; + + /* Cleans the error report buffer */ + memset(e, 0, sizeof (*e)); + e->error_count = 1; + strcpy(e->label, "unknown label"); + e->msg = pvt->msg; + e->other_detail = pvt->other_detail; + e->top_layer = -1; + e->mid_layer = -1; + e->low_layer = -1; + *pvt->other_detail = '\0'; + *pvt->msg = '\0'; + + switch (sev) { + case GHES_SEV_CORRECTED: + type = HW_EVENT_ERR_CORRECTED; + break; + case GHES_SEV_RECOVERABLE: + type = HW_EVENT_ERR_UNCORRECTED; + break; + case GHES_SEV_PANIC: + type = HW_EVENT_ERR_FATAL; + break; + default: + case GHES_SEV_NO: + type = HW_EVENT_ERR_INFO; + } + + edac_dbg(1, "error validation_bits: 0x%08llx\n", + (long long)mem_err->validation_bits); + + /* Error type, mapped on e->msg */ + if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) { + p = pvt->msg; + switch (mem_err->error_type) { + case 0: + p += sprintf(p, "Unknown"); + break; + case 1: + p += sprintf(p, "No error"); + break; + case 2: + p += sprintf(p, "Single-bit ECC"); + break; + case 3: + p += sprintf(p, "Multi-bit ECC"); + break; + case 4: + p += sprintf(p, "Single-symbol ChipKill ECC"); + break; + case 5: + p += sprintf(p, "Multi-symbol ChipKill ECC"); + break; + case 6: + p += sprintf(p, "Master abort"); + break; + case 7: + p += sprintf(p, "Target abort"); + break; + case 8: + p += sprintf(p, "Parity Error"); + break; + case 9: + p += sprintf(p, "Watchdog timeout"); + break; + case 10: + p += sprintf(p, "Invalid address"); + break; + case 11: + p += sprintf(p, "Mirror Broken"); + break; + case 12: + p += sprintf(p, "Memory Sparing"); + break; + case 13: + p += sprintf(p, "Scrub corrected error"); + break; + case 14: + p += sprintf(p, "Scrub uncorrected error"); + break; + case 15: + p += sprintf(p, "Physical Memory Map-out event"); + break; + default: + p += sprintf(p, "reserved error (%d)", + mem_err->error_type); + } + } else { + strcpy(pvt->msg, "unknown error"); + } + + /* Error address */ + if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) { + e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT; + e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK; + } + + /* Error grain */ + if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) { + e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK); + } + + /* Memory error location, mapped on e->location */ + p = e->location; + if (mem_err->validation_bits & CPER_MEM_VALID_NODE) + p += sprintf(p, "node:%d ", mem_err->node); + if (mem_err->validation_bits & CPER_MEM_VALID_CARD) + p += sprintf(p, "card:%d ", mem_err->card); + if (mem_err->validation_bits & CPER_MEM_VALID_MODULE) + p += sprintf(p, "module:%d ", mem_err->module); + if (mem_err->validation_bits & CPER_MEM_VALID_BANK) + p += sprintf(p, "bank:%d ", mem_err->bank); + if (mem_err->validation_bits & CPER_MEM_VALID_ROW) + p += sprintf(p, "row:%d ", mem_err->row); + if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN) + p += sprintf(p, "col:%d ", mem_err->column); + if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION) + p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos); + if (p > e->location) + *(p - 1) = '\0'; + + /* All other fields are mapped on e->other_detail */ + p = pvt->other_detail; + if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) { + u64 status = mem_err->error_status; + + p += sprintf(p, "status(0x%016llx): ", (long long)status); + switch ((status >> 8) & 0xff) { + case 1: + p += sprintf(p, "Error detected internal to the component "); + break; + case 16: + p += sprintf(p, "Error detected in the bus "); + break; + case 4: + p += sprintf(p, "Storage error in DRAM memory "); + break; + case 5: + p += sprintf(p, "Storage error in TLB "); + break; + case 6: + p += sprintf(p, "Storage error in cache "); + break; + case 7: + p += sprintf(p, "Error in one or more functional units "); + break; + case 8: + p += sprintf(p, "component failed self test "); + break; + case 9: + p += sprintf(p, "Overflow or undervalue of internal queue "); + break; + case 17: + p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR "); + break; + case 18: + p += sprintf(p, "Improper access error "); + break; + case 19: + p += sprintf(p, "Access to a memory address which is not mapped to any component "); + break; + case 20: + p += sprintf(p, "Loss of Lockstep "); + break; + case 21: + p += sprintf(p, "Response not associated with a request "); + break; + case 22: + p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits "); + break; + case 23: + p += sprintf(p, "Detection of a PATH_ERROR "); + break; + case 25: + p += sprintf(p, "Bus operation timeout "); + break; + case 26: + p += sprintf(p, "A read was issued to data that has been poisoned "); + break; + default: + p += sprintf(p, "reserved "); + break; + } + } + if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) + p += sprintf(p, "requestorID: 0x%016llx ", + (long long)mem_err->requestor_id); + if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID) + p += sprintf(p, "responderID: 0x%016llx ", + (long long)mem_err->responder_id); + if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID) + p += sprintf(p, "targetID: 0x%016llx ", + (long long)mem_err->responder_id); + if (p > pvt->other_detail) + *(p - 1) = '\0'; + + /* Generate the trace event */ + grain_bits = fls_long(e->grain); + sprintf(pvt->detail_location, "APEI location: %s %s", + e->location, e->other_detail); + trace_mc_event(type, e->msg, e->label, e->error_count, + mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer, + PAGES_TO_MiB(e->page_frame_number) | e->offset_in_page, + grain_bits, e->syndrome, pvt->detail_location); + + /* Report the error via EDAC API */ + edac_raw_mc_handle_error(type, mci, e); +} +EXPORT_SYMBOL_GPL(ghes_edac_report_mem_error); + +int ghes_edac_register(struct ghes *ghes, struct device *dev) +{ + bool fake = false; + int rc, num_dimm = 0; + struct mem_ctl_info *mci; + struct edac_mc_layer layers[1]; + struct ghes_edac_pvt *pvt; + struct ghes_edac_dimm_fill dimm_fill; + + /* Get the number of DIMMs */ + dmi_walk(ghes_edac_count_dimms, &num_dimm); + + /* Check if we've got a bogus BIOS */ + if (num_dimm == 0) { + fake = true; + num_dimm = 1; + } + + layers[0].type = EDAC_MC_LAYER_ALL_MEM; + layers[0].size = num_dimm; + layers[0].is_virt_csrow = true; + + /* + * We need to serialize edac_mc_alloc() and edac_mc_add_mc(), + * to avoid duplicated memory controller numbers + */ + mutex_lock(&ghes_edac_lock); + mci = edac_mc_alloc(ghes_edac_mc_num, ARRAY_SIZE(layers), layers, + sizeof(*pvt)); + if (!mci) { + pr_info("Can't allocate memory for EDAC data\n"); + mutex_unlock(&ghes_edac_lock); + return -ENOMEM; + } + + pvt = mci->pvt_info; + memset(pvt, 0, sizeof(*pvt)); + list_add_tail(&pvt->list, &ghes_reglist); + pvt->ghes = ghes; + pvt->mci = mci; + mci->pdev = dev; + + mci->mtype_cap = MEM_FLAG_EMPTY; + mci->edac_ctl_cap = EDAC_FLAG_NONE; + mci->edac_cap = EDAC_FLAG_NONE; + mci->mod_name = "ghes_edac.c"; + mci->mod_ver = GHES_EDAC_REVISION; + mci->ctl_name = "ghes_edac"; + mci->dev_name = "ghes"; + + if (!ghes_edac_mc_num) { + if (!fake) { + pr_info("This EDAC driver relies on BIOS to enumerate memory and get error reports.\n"); + pr_info("Unfortunately, not all BIOSes reflect the memory layout correctly.\n"); + pr_info("So, the end result of using this driver varies from vendor to vendor.\n"); + pr_info("If you find incorrect reports, please contact your hardware vendor\n"); + pr_info("to correct its BIOS.\n"); + pr_info("This system has %d DIMM sockets.\n", + num_dimm); + } else { + pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS.\n"); + pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would\n"); + pr_info("work on such system. Use this driver with caution\n"); + } + } + + if (!fake) { + /* + * Fill DIMM info from DMI for the memory controller #0 + * + * Keep it in blank for the other memory controllers, as + * there's no reliable way to properly credit each DIMM to + * the memory controller, as different BIOSes fill the + * DMI bank location fields on different ways + */ + if (!ghes_edac_mc_num) { + dimm_fill.count = 0; + dimm_fill.mci = mci; + dmi_walk(ghes_edac_dmidecode, &dimm_fill); + } + } else { + struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, + mci->n_layers, 0, 0, 0); + + dimm->nr_pages = 1; + dimm->grain = 128; + dimm->mtype = MEM_UNKNOWN; + dimm->dtype = DEV_UNKNOWN; + dimm->edac_mode = EDAC_SECDED; + } + + rc = edac_mc_add_mc(mci); + if (rc < 0) { + pr_info("Can't register at EDAC core\n"); + edac_mc_free(mci); + mutex_unlock(&ghes_edac_lock); + return -ENODEV; + } + + ghes_edac_mc_num++; + mutex_unlock(&ghes_edac_lock); + return 0; +} +EXPORT_SYMBOL_GPL(ghes_edac_register); + +void ghes_edac_unregister(struct ghes *ghes) +{ + struct mem_ctl_info *mci; + struct ghes_edac_pvt *pvt, *tmp; + + list_for_each_entry_safe(pvt, tmp, &ghes_reglist, list) { + if (ghes == pvt->ghes) { + mci = pvt->mci; + edac_mc_del_mc(mci->pdev); + edac_mc_free(mci); + list_del(&pvt->list); + } + } +} +EXPORT_SYMBOL_GPL(ghes_edac_unregister); diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index 4e83376..aa44c17 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -106,16 +106,26 @@ static int nr_channels; static int how_many_channels(struct pci_dev *pdev) { + int n_channels; + unsigned char capid0_8b; /* 8th byte of CAPID0 */ pci_read_config_byte(pdev, I3200_CAPID0 + 8, &capid0_8b); + if (capid0_8b & 0x20) { /* check DCD: Dual Channel Disable */ edac_dbg(0, "In single channel mode\n"); - return 1; + n_channels = 1; } else { edac_dbg(0, "In dual channel mode\n"); - return 2; + n_channels = 2; } + + if (capid0_8b & 0x10) /* check if both channels are filled */ + edac_dbg(0, "2 DIMMS per channel disabled\n"); + else + edac_dbg(0, "2 DIMMS per channel enabled\n"); + + return n_channels; } static unsigned long eccerrlog_syndrome(u64 log) @@ -290,6 +300,8 @@ static void i3200_get_drbs(void __iomem *window, for (i = 0; i < I3200_RANKS_PER_CHANNEL; i++) { drbs[0][i] = readw(window + I3200_C0DRB + 2*i) & I3200_DRB_MASK; drbs[1][i] = readw(window + I3200_C1DRB + 2*i) & I3200_DRB_MASK; + + edac_dbg(0, "drb[0][%d] = %d, drb[1][%d] = %d\n", i, drbs[0][i], i, drbs[1][i]); } } @@ -311,6 +323,9 @@ static unsigned long drb_to_nr_pages( int n; n = drbs[channel][rank]; + if (!n) + return 0; + if (rank > 0) n -= drbs[channel][rank - 1]; if (stacked && (channel == 1) && @@ -377,19 +392,19 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) * cumulative; the last one will contain the total memory * contained in all ranks. */ - for (i = 0; i < mci->nr_csrows; i++) { + for (i = 0; i < I3200_DIMMS; i++) { unsigned long nr_pages; - struct csrow_info *csrow = mci->csrows[i]; - nr_pages = drb_to_nr_pages(drbs, stacked, - i / I3200_RANKS_PER_CHANNEL, - i % I3200_RANKS_PER_CHANNEL); + for (j = 0; j < nr_channels; j++) { + struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, + mci->n_layers, i, j, 0); - if (nr_pages == 0) - continue; + nr_pages = drb_to_nr_pages(drbs, stacked, j, i); + if (nr_pages == 0) + continue; - for (j = 0; j < nr_channels; j++) { - struct dimm_info *dimm = csrow->channels[j]->dimm; + edac_dbg(0, "csrow %d, channel %d%s, size = %ld Mb\n", i, j, + stacked ? " (stacked)" : "", PAGES_TO_MiB(nr_pages)); dimm->nr_pages = nr_pages; dimm->grain = nr_pages << PAGE_SHIFT; diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index d6955b2..1b63517 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -27,6 +27,7 @@ #include <linux/edac.h> #include <linux/delay.h> #include <linux/mmzone.h> +#include <linux/debugfs.h> #include "edac_core.h" @@ -68,6 +69,14 @@ I5100_FERR_NF_MEM_M1ERR_MASK) #define I5100_NERR_NF_MEM 0xa4 /* MC Next Non-Fatal Errors */ #define I5100_EMASK_MEM 0xa8 /* MC Error Mask Register */ +#define I5100_MEM0EINJMSK0 0x200 /* Injection Mask0 Register Channel 0 */ +#define I5100_MEM1EINJMSK0 0x208 /* Injection Mask0 Register Channel 1 */ +#define I5100_MEMXEINJMSK0_EINJEN (1 << 27) +#define I5100_MEM0EINJMSK1 0x204 /* Injection Mask1 Register Channel 0 */ +#define I5100_MEM1EINJMSK1 0x206 /* Injection Mask1 Register Channel 1 */ + +/* Device 19, Function 0 */ +#define I5100_DINJ0 0x9a /* device 21 and 22, func 0 */ #define I5100_MTR_0 0x154 /* Memory Technology Registers 0-3 */ @@ -338,13 +347,26 @@ struct i5100_priv { unsigned ranksperchan; /* number of ranks per channel */ struct pci_dev *mc; /* device 16 func 1 */ + struct pci_dev *einj; /* device 19 func 0 */ struct pci_dev *ch0mm; /* device 21 func 0 */ struct pci_dev *ch1mm; /* device 22 func 0 */ struct delayed_work i5100_scrubbing; int scrub_enable; + + /* Error injection */ + u8 inject_channel; + u8 inject_hlinesel; + u8 inject_deviceptr1; + u8 inject_deviceptr2; + u16 inject_eccmask1; + u16 inject_eccmask2; + + struct dentry *debugfs; }; +static struct dentry *i5100_debugfs; + /* map a rank/chan to a slot number on the mainboard */ static int i5100_rank_to_slot(const struct mem_ctl_info *mci, int chan, int rank) @@ -863,13 +885,126 @@ static void i5100_init_csrows(struct mem_ctl_info *mci) } } +/**************************************************************************** + * Error injection routines + ****************************************************************************/ + +static void i5100_do_inject(struct mem_ctl_info *mci) +{ + struct i5100_priv *priv = mci->pvt_info; + u32 mask0; + u16 mask1; + + /* MEM[1:0]EINJMSK0 + * 31 - ADDRMATCHEN + * 29:28 - HLINESEL + * 00 Reserved + * 01 Lower half of cache line + * 10 Upper half of cache line + * 11 Both upper and lower parts of cache line + * 27 - EINJEN + * 25:19 - XORMASK1 for deviceptr1 + * 9:5 - SEC2RAM for deviceptr2 + * 4:0 - FIR2RAM for deviceptr1 + */ + mask0 = ((priv->inject_hlinesel & 0x3) << 28) | + I5100_MEMXEINJMSK0_EINJEN | + ((priv->inject_eccmask1 & 0xffff) << 10) | + ((priv->inject_deviceptr2 & 0x1f) << 5) | + (priv->inject_deviceptr1 & 0x1f); + + /* MEM[1:0]EINJMSK1 + * 15:0 - XORMASK2 for deviceptr2 + */ + mask1 = priv->inject_eccmask2; + + if (priv->inject_channel == 0) { + pci_write_config_dword(priv->mc, I5100_MEM0EINJMSK0, mask0); + pci_write_config_word(priv->mc, I5100_MEM0EINJMSK1, mask1); + } else { + pci_write_config_dword(priv->mc, I5100_MEM1EINJMSK0, mask0); + pci_write_config_word(priv->mc, I5100_MEM1EINJMSK1, mask1); + } + + /* Error Injection Response Function + * Intel 5100 Memory Controller Hub Chipset (318378) datasheet + * hints about this register but carry no data about them. All + * data regarding device 19 is based on experimentation and the + * Intel 7300 Chipset Memory Controller Hub (318082) datasheet + * which appears to be accurate for the i5100 in this area. + * + * The injection code don't work without setting this register. + * The register needs to be flipped off then on else the hardware + * will only preform the first injection. + * + * Stop condition bits 7:4 + * 1010 - Stop after one injection + * 1011 - Never stop injecting faults + * + * Start condition bits 3:0 + * 1010 - Never start + * 1011 - Start immediately + */ + pci_write_config_byte(priv->einj, I5100_DINJ0, 0xaa); + pci_write_config_byte(priv->einj, I5100_DINJ0, 0xab); +} + +#define to_mci(k) container_of(k, struct mem_ctl_info, dev) +static ssize_t inject_enable_write(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct device *dev = file->private_data; + struct mem_ctl_info *mci = to_mci(dev); + + i5100_do_inject(mci); + + return count; +} + +static const struct file_operations i5100_inject_enable_fops = { + .open = simple_open, + .write = inject_enable_write, + .llseek = generic_file_llseek, +}; + +static int i5100_setup_debugfs(struct mem_ctl_info *mci) +{ + struct i5100_priv *priv = mci->pvt_info; + + if (!i5100_debugfs) + return -ENODEV; + + priv->debugfs = debugfs_create_dir(mci->bus.name, i5100_debugfs); + + if (!priv->debugfs) + return -ENOMEM; + + debugfs_create_x8("inject_channel", S_IRUGO | S_IWUSR, priv->debugfs, + &priv->inject_channel); + debugfs_create_x8("inject_hlinesel", S_IRUGO | S_IWUSR, priv->debugfs, + &priv->inject_hlinesel); + debugfs_create_x8("inject_deviceptr1", S_IRUGO | S_IWUSR, priv->debugfs, + &priv->inject_deviceptr1); + debugfs_create_x8("inject_deviceptr2", S_IRUGO | S_IWUSR, priv->debugfs, + &priv->inject_deviceptr2); + debugfs_create_x16("inject_eccmask1", S_IRUGO | S_IWUSR, priv->debugfs, + &priv->inject_eccmask1); + debugfs_create_x16("inject_eccmask2", S_IRUGO | S_IWUSR, priv->debugfs, + &priv->inject_eccmask2); + debugfs_create_file("inject_enable", S_IWUSR, priv->debugfs, + &mci->dev, &i5100_inject_enable_fops); + + return 0; + +} + static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { int rc; struct mem_ctl_info *mci; struct edac_mc_layer layers[2]; struct i5100_priv *priv; - struct pci_dev *ch0mm, *ch1mm; + struct pci_dev *ch0mm, *ch1mm, *einj; int ret = 0; u32 dw; int ranksperch; @@ -941,6 +1076,22 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto bail_disable_ch1; } + + /* device 19, func 0, Error injection */ + einj = pci_get_device_func(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_5100_19, 0); + if (!einj) { + ret = -ENODEV; + goto bail_einj; + } + + rc = pci_enable_device(einj); + if (rc < 0) { + ret = rc; + goto bail_disable_einj; + } + + mci->pdev = &pdev->dev; priv = mci->pvt_info; @@ -948,6 +1099,7 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id) priv->mc = pdev; priv->ch0mm = ch0mm; priv->ch1mm = ch1mm; + priv->einj = einj; INIT_DELAYED_WORK(&(priv->i5100_scrubbing), i5100_refresh_scrubbing); @@ -975,6 +1127,13 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mci->set_sdram_scrub_rate = i5100_set_scrub_rate; mci->get_sdram_scrub_rate = i5100_get_scrub_rate; + priv->inject_channel = 0; + priv->inject_hlinesel = 0; + priv->inject_deviceptr1 = 0; + priv->inject_deviceptr2 = 0; + priv->inject_eccmask1 = 0; + priv->inject_eccmask2 = 0; + i5100_init_csrows(mci); /* this strange construction seems to be in every driver, dunno why */ @@ -992,6 +1151,8 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto bail_scrub; } + i5100_setup_debugfs(mci); + return ret; bail_scrub: @@ -999,6 +1160,12 @@ bail_scrub: cancel_delayed_work_sync(&(priv->i5100_scrubbing)); edac_mc_free(mci); +bail_disable_einj: + pci_disable_device(einj); + +bail_einj: + pci_dev_put(einj); + bail_disable_ch1: pci_disable_device(ch1mm); @@ -1030,14 +1197,18 @@ static void i5100_remove_one(struct pci_dev *pdev) priv = mci->pvt_info; + debugfs_remove_recursive(priv->debugfs); + priv->scrub_enable = 0; cancel_delayed_work_sync(&(priv->i5100_scrubbing)); pci_disable_device(pdev); pci_disable_device(priv->ch0mm); pci_disable_device(priv->ch1mm); + pci_disable_device(priv->einj); pci_dev_put(priv->ch0mm); pci_dev_put(priv->ch1mm); + pci_dev_put(priv->einj); edac_mc_free(mci); } @@ -1060,13 +1231,16 @@ static int __init i5100_init(void) { int pci_rc; - pci_rc = pci_register_driver(&i5100_driver); + i5100_debugfs = debugfs_create_dir("i5100_edac", NULL); + pci_rc = pci_register_driver(&i5100_driver); return (pci_rc < 0) ? pci_rc : 0; } static void __exit i5100_exit(void) { + debugfs_remove(i5100_debugfs); + pci_unregister_driver(&i5100_driver); } diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index 087c27b..9004c64 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -750,15 +750,23 @@ static int i7300_init_csrows(struct mem_ctl_info *mci) struct i7300_dimm_info *dinfo; int rc = -ENODEV; int mtr; - int ch, branch, slot, channel; + int ch, branch, slot, channel, max_channel, max_branch; struct dimm_info *dimm; pvt = mci->pvt_info; edac_dbg(2, "Memory Technology Registers:\n"); + if (IS_SINGLE_MODE(pvt->mc_settings_a)) { + max_branch = 1; + max_channel = 1; + } else { + max_branch = MAX_BRANCHES; + max_channel = MAX_CH_PER_BRANCH; + } + /* Get the AMB present registers for the four channels */ - for (branch = 0; branch < MAX_BRANCHES; branch++) { + for (branch = 0; branch < max_branch; branch++) { /* Read and dump branch 0's MTRs */ channel = to_channel(0, branch); pci_read_config_word(pvt->pci_dev_2x_0_fbd_branch[branch], @@ -767,6 +775,9 @@ static int i7300_init_csrows(struct mem_ctl_info *mci) edac_dbg(2, "\t\tAMB-present CH%d = 0x%x:\n", channel, pvt->ambpresent[channel]); + if (max_channel == 1) + continue; + channel = to_channel(1, branch); pci_read_config_word(pvt->pci_dev_2x_0_fbd_branch[branch], AMBPRESENT_1, @@ -778,11 +789,11 @@ static int i7300_init_csrows(struct mem_ctl_info *mci) /* Get the set of MTR[0-7] regs by each branch */ for (slot = 0; slot < MAX_SLOTS; slot++) { int where = mtr_regs[slot]; - for (branch = 0; branch < MAX_BRANCHES; branch++) { + for (branch = 0; branch < max_branch; branch++) { pci_read_config_word(pvt->pci_dev_2x_0_fbd_branch[branch], where, &pvt->mtr[slot][branch]); - for (ch = 0; ch < MAX_CH_PER_BRANCH; ch++) { + for (ch = 0; ch < max_channel; ch++) { int channel = to_channel(ch, branch); dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index e213d03..0ec3e95 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -420,21 +420,21 @@ static inline int numdimms(u32 dimms) static inline int numrank(u32 rank) { - static int ranks[4] = { 1, 2, 4, -EINVAL }; + static const int ranks[] = { 1, 2, 4, -EINVAL }; return ranks[rank & 0x3]; } static inline int numbank(u32 bank) { - static int banks[4] = { 4, 8, 16, -EINVAL }; + static const int banks[] = { 4, 8, 16, -EINVAL }; return banks[bank & 0x3]; } static inline int numrow(u32 row) { - static int rows[8] = { + static const int rows[] = { 1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, -EINVAL, -EINVAL, -EINVAL, }; @@ -444,7 +444,7 @@ static inline int numrow(u32 row) static inline int numcol(u32 col) { - static int cols[8] = { + static const int cols[] = { 1 << 10, 1 << 11, 1 << 12, -EINVAL, }; return cols[col & 0x3]; diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index ad63757..f3f0c93 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -39,30 +39,28 @@ EXPORT_SYMBOL_GPL(amd_unregister_ecc_decoder); */ /* transaction type */ -const char * const tt_msgs[] = { "INSN", "DATA", "GEN", "RESV" }; -EXPORT_SYMBOL_GPL(tt_msgs); +static const char * const tt_msgs[] = { "INSN", "DATA", "GEN", "RESV" }; /* cache level */ -const char * const ll_msgs[] = { "RESV", "L1", "L2", "L3/GEN" }; -EXPORT_SYMBOL_GPL(ll_msgs); +static const char * const ll_msgs[] = { "RESV", "L1", "L2", "L3/GEN" }; /* memory transaction type */ -const char * const rrrr_msgs[] = { +static const char * const rrrr_msgs[] = { "GEN", "RD", "WR", "DRD", "DWR", "IRD", "PRF", "EV", "SNP" }; -EXPORT_SYMBOL_GPL(rrrr_msgs); /* participating processor */ const char * const pp_msgs[] = { "SRC", "RES", "OBS", "GEN" }; EXPORT_SYMBOL_GPL(pp_msgs); /* request timeout */ -const char * const to_msgs[] = { "no timeout", "timed out" }; -EXPORT_SYMBOL_GPL(to_msgs); +static const char * const to_msgs[] = { "no timeout", "timed out" }; /* memory or i/o */ -const char * const ii_msgs[] = { "MEM", "RESV", "IO", "GEN" }; -EXPORT_SYMBOL_GPL(ii_msgs); +static const char * const ii_msgs[] = { "MEM", "RESV", "IO", "GEN" }; + +/* internal error type */ +static const char * const uu_msgs[] = { "RESV", "RESV", "HWA", "RESV" }; static const char * const f15h_mc1_mce_desc[] = { "UC during a demand linefill from L2", @@ -176,7 +174,7 @@ static bool k8_mc0_mce(u16 ec, u8 xec) return f10h_mc0_mce(ec, xec); } -static bool f14h_mc0_mce(u16 ec, u8 xec) +static bool cat_mc0_mce(u16 ec, u8 xec) { u8 r4 = R4(ec); bool ret = true; @@ -330,22 +328,28 @@ static bool k8_mc1_mce(u16 ec, u8 xec) return ret; } -static bool f14h_mc1_mce(u16 ec, u8 xec) +static bool cat_mc1_mce(u16 ec, u8 xec) { u8 r4 = R4(ec); bool ret = true; - if (MEM_ERROR(ec)) { - if (TT(ec) != 0 || LL(ec) != 1) - ret = false; + if (!MEM_ERROR(ec)) + return false; + + if (TT(ec) != TT_INSTR) + return false; + + if (r4 == R4_IRD) + pr_cont("Data/tag array parity error for a tag hit.\n"); + else if (r4 == R4_SNOOP) + pr_cont("Tag error during snoop/victimization.\n"); + else if (xec == 0x0) + pr_cont("Tag parity error from victim castout.\n"); + else if (xec == 0x2) + pr_cont("Microcode patch RAM parity error.\n"); + else + ret = false; - if (r4 == R4_IRD) - pr_cont("Data/tag array parity error for a tag hit.\n"); - else if (r4 == R4_SNOOP) - pr_cont("Tag error during snoop/victimization.\n"); - else - ret = false; - } return ret; } @@ -399,12 +403,9 @@ static void decode_mc1_mce(struct mce *m) pr_emerg(HW_ERR "Corrupted MC1 MCE info?\n"); } -static void decode_mc2_mce(struct mce *m) +static bool k8_mc2_mce(u16 ec, u8 xec) { - u16 ec = EC(m->status); - u8 xec = XEC(m->status, xec_mask); - - pr_emerg(HW_ERR "MC2 Error"); + bool ret = true; if (xec == 0x1) pr_cont(" in the write data buffers.\n"); @@ -429,24 +430,18 @@ static void decode_mc2_mce(struct mce *m) pr_cont(": %s parity/ECC error during data " "access from L2.\n", R4_MSG(ec)); else - goto wrong_mc2_mce; + ret = false; } else - goto wrong_mc2_mce; + ret = false; } else - goto wrong_mc2_mce; - - return; + ret = false; - wrong_mc2_mce: - pr_emerg(HW_ERR "Corrupted MC2 MCE info?\n"); + return ret; } -static void decode_f15_mc2_mce(struct mce *m) +static bool f15h_mc2_mce(u16 ec, u8 xec) { - u16 ec = EC(m->status); - u8 xec = XEC(m->status, xec_mask); - - pr_emerg(HW_ERR "MC2 Error: "); + bool ret = true; if (TLB_ERROR(ec)) { if (xec == 0x0) @@ -454,10 +449,10 @@ static void decode_f15_mc2_mce(struct mce *m) else if (xec == 0x1) pr_cont("Poison data provided for TLB fill.\n"); else - goto wrong_f15_mc2_mce; + ret = false; } else if (BUS_ERROR(ec)) { if (xec > 2) - goto wrong_f15_mc2_mce; + ret = false; pr_cont("Error during attempted NB data read.\n"); } else if (MEM_ERROR(ec)) { @@ -471,14 +466,63 @@ static void decode_f15_mc2_mce(struct mce *m) break; default: - goto wrong_f15_mc2_mce; + ret = false; } } - return; + return ret; +} - wrong_f15_mc2_mce: - pr_emerg(HW_ERR "Corrupted MC2 MCE info?\n"); +static bool f16h_mc2_mce(u16 ec, u8 xec) +{ + u8 r4 = R4(ec); + + if (!MEM_ERROR(ec)) + return false; + + switch (xec) { + case 0x04 ... 0x05: + pr_cont("%cBUFF parity error.\n", (r4 == R4_RD) ? 'I' : 'O'); + break; + + case 0x09 ... 0x0b: + case 0x0d ... 0x0f: + pr_cont("ECC error in L2 tag (%s).\n", + ((r4 == R4_GEN) ? "BankReq" : + ((r4 == R4_SNOOP) ? "Prb" : "Fill"))); + break; + + case 0x10 ... 0x19: + case 0x1b: + pr_cont("ECC error in L2 data array (%s).\n", + (((r4 == R4_RD) && !(xec & 0x3)) ? "Hit" : + ((r4 == R4_GEN) ? "Attr" : + ((r4 == R4_EVICT) ? "Vict" : "Fill")))); + break; + + case 0x1c ... 0x1d: + case 0x1f: + pr_cont("Parity error in L2 attribute bits (%s).\n", + ((r4 == R4_RD) ? "Hit" : + ((r4 == R4_GEN) ? "Attr" : "Fill"))); + break; + + default: + return false; + } + + return true; +} + +static void decode_mc2_mce(struct mce *m) +{ + u16 ec = EC(m->status); + u8 xec = XEC(m->status, xec_mask); + + pr_emerg(HW_ERR "MC2 Error: "); + + if (!fam_ops->mc2_mce(ec, xec)) + pr_cont(HW_ERR "Corrupted MC2 MCE info?\n"); } static void decode_mc3_mce(struct mce *m) @@ -547,7 +591,7 @@ static void decode_mc4_mce(struct mce *m) return; case 0x19: - if (boot_cpu_data.x86 == 0x15) + if (boot_cpu_data.x86 == 0x15 || boot_cpu_data.x86 == 0x16) pr_cont("Compute Unit Data Error.\n"); else goto wrong_mc4_mce; @@ -633,6 +677,10 @@ static void decode_mc6_mce(struct mce *m) static inline void amd_decode_err_code(u16 ec) { + if (INT_ERROR(ec)) { + pr_emerg(HW_ERR "internal: %s\n", UU_MSG(ec)); + return; + } pr_emerg(HW_ERR "cache level: %s", LL_MSG(ec)); @@ -702,10 +750,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) break; case 2: - if (c->x86 == 0x15) - decode_f15_mc2_mce(m); - else - decode_mc2_mce(m); + decode_mc2_mce(m); break; case 3: @@ -740,7 +785,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) ((m->status & MCI_STATUS_PCC) ? "PCC" : "-"), ((m->status & MCI_STATUS_ADDRV) ? "AddrV" : "-")); - if (c->x86 == 0x15) + if (c->x86 == 0x15 || c->x86 == 0x16) pr_cont("|%s|%s", ((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"), ((m->status & MCI_STATUS_POISON) ? "Poison" : "-")); @@ -772,7 +817,7 @@ static int __init mce_amd_init(void) if (c->x86_vendor != X86_VENDOR_AMD) return 0; - if (c->x86 < 0xf || c->x86 > 0x15) + if (c->x86 < 0xf || c->x86 > 0x16) return 0; fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL); @@ -783,33 +828,46 @@ static int __init mce_amd_init(void) case 0xf: fam_ops->mc0_mce = k8_mc0_mce; fam_ops->mc1_mce = k8_mc1_mce; + fam_ops->mc2_mce = k8_mc2_mce; break; case 0x10: fam_ops->mc0_mce = f10h_mc0_mce; fam_ops->mc1_mce = k8_mc1_mce; + fam_ops->mc2_mce = k8_mc2_mce; break; case 0x11: fam_ops->mc0_mce = k8_mc0_mce; fam_ops->mc1_mce = k8_mc1_mce; + fam_ops->mc2_mce = k8_mc2_mce; break; case 0x12: fam_ops->mc0_mce = f12h_mc0_mce; fam_ops->mc1_mce = k8_mc1_mce; + fam_ops->mc2_mce = k8_mc2_mce; break; case 0x14: nb_err_cpumask = 0x3; - fam_ops->mc0_mce = f14h_mc0_mce; - fam_ops->mc1_mce = f14h_mc1_mce; + fam_ops->mc0_mce = cat_mc0_mce; + fam_ops->mc1_mce = cat_mc1_mce; + fam_ops->mc2_mce = k8_mc2_mce; break; case 0x15: xec_mask = 0x1f; fam_ops->mc0_mce = f15h_mc0_mce; fam_ops->mc1_mce = f15h_mc1_mce; + fam_ops->mc2_mce = f15h_mc2_mce; + break; + + case 0x16: + xec_mask = 0x1f; + fam_ops->mc0_mce = cat_mc0_mce; + fam_ops->mc1_mce = cat_mc1_mce; + fam_ops->mc2_mce = f16h_mc2_mce; break; default: diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h index 6796799..51b7e3a 100644 --- a/drivers/edac/mce_amd.h +++ b/drivers/edac/mce_amd.h @@ -14,6 +14,7 @@ #define TLB_ERROR(x) (((x) & 0xFFF0) == 0x0010) #define MEM_ERROR(x) (((x) & 0xFF00) == 0x0100) #define BUS_ERROR(x) (((x) & 0xF800) == 0x0800) +#define INT_ERROR(x) (((x) & 0xF4FF) == 0x0400) #define TT(x) (((x) >> 2) & 0x3) #define TT_MSG(x) tt_msgs[TT(x)] @@ -25,6 +26,8 @@ #define TO_MSG(x) to_msgs[TO(x)] #define PP(x) (((x) >> 9) & 0x3) #define PP_MSG(x) pp_msgs[PP(x)] +#define UU(x) (((x) >> 8) & 0x3) +#define UU_MSG(x) uu_msgs[UU(x)] #define R4(x) (((x) >> 4) & 0xf) #define R4_MSG(x) ((R4(x) < 9) ? rrrr_msgs[R4(x)] : "Wrong R4!") @@ -32,6 +35,8 @@ #define MCI_STATUS_DEFERRED BIT_64(44) #define MCI_STATUS_POISON BIT_64(43) +extern const char * const pp_msgs[]; + enum tt_ids { TT_INSTR = 0, TT_DATA, @@ -65,19 +70,13 @@ enum rrrr_ids { R4_SNOOP, }; -extern const char * const tt_msgs[]; -extern const char * const ll_msgs[]; -extern const char * const rrrr_msgs[]; -extern const char * const pp_msgs[]; -extern const char * const to_msgs[]; -extern const char * const ii_msgs[]; - /* * per-family decoder ops */ struct amd_decoder_ops { bool (*mc0_mce)(u16, u8); bool (*mc1_mce)(u16, u8); + bool (*mc2_mce)(u16, u8); }; void amd_report_gart_errors(bool); diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 07d1734..939ea18 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -361,7 +361,7 @@ int mpc85xx_pci_err_probe(struct platform_device *op) "[EDAC] PCI err", pci); if (res < 0) { printk(KERN_ERR - "%s: Unable to requiest irq %d for " + "%s: Unable to request irq %d for " "MPC85xx PCI err\n", __func__, pdata->irq); irq_dispose_mapping(pdata->irq); res = -ENODEV; @@ -656,7 +656,7 @@ static int mpc85xx_l2_err_probe(struct platform_device *op) "[EDAC] L2 err", edac_dev); if (res < 0) { printk(KERN_ERR - "%s: Unable to requiest irq %d for " + "%s: Unable to request irq %d for " "MPC85xx L2 err\n", __func__, pdata->irq); irq_dispose_mapping(pdata->irq); res = -ENODEV; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index da7e298..e04462b 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -331,30 +331,31 @@ struct sbridge_pvt { u64 tolm, tohm; }; -#define PCI_DESCR(device, function, device_id) \ - .dev = (device), \ - .func = (function), \ - .dev_id = (device_id) +#define PCI_DESCR(device, function, device_id, opt) \ + .dev = (device), \ + .func = (function), \ + .dev_id = (device_id), \ + .optional = opt static const struct pci_id_descr pci_dev_descr_sbridge[] = { /* Processor Home Agent */ - { PCI_DESCR(14, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0) }, + { PCI_DESCR(14, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0, 0) }, /* Memory controller */ - { PCI_DESCR(15, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA) }, - { PCI_DESCR(15, 1, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS) }, - { PCI_DESCR(15, 2, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0) }, - { PCI_DESCR(15, 3, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1) }, - { PCI_DESCR(15, 4, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2) }, - { PCI_DESCR(15, 5, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3) }, - { PCI_DESCR(17, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO) }, + { PCI_DESCR(15, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA, 0) }, + { PCI_DESCR(15, 1, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS, 0) }, + { PCI_DESCR(15, 2, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0, 0) }, + { PCI_DESCR(15, 3, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1, 0) }, + { PCI_DESCR(15, 4, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2, 0) }, + { PCI_DESCR(15, 5, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3, 0) }, + { PCI_DESCR(17, 0, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO, 1) }, /* System Address Decoder */ - { PCI_DESCR(12, 6, PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0) }, - { PCI_DESCR(12, 7, PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1) }, + { PCI_DESCR(12, 6, PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0, 0) }, + { PCI_DESCR(12, 7, PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1, 0) }, /* Broadcast Registers */ - { PCI_DESCR(13, 6, PCI_DEVICE_ID_INTEL_SBRIDGE_BR) }, + { PCI_DESCR(13, 6, PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0) }, }; #define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) } @@ -556,14 +557,19 @@ static int get_dimm_config(struct mem_ctl_info *mci) pvt->is_close_pg = false; } - pci_read_config_dword(pvt->pci_ddrio, RANK_CFG_A, ®); - if (IS_RDIMM_ENABLED(reg)) { - /* FIXME: Can also be LRDIMM */ - edac_dbg(0, "Memory is registered\n"); - mtype = MEM_RDDR3; + if (pvt->pci_ddrio) { + pci_read_config_dword(pvt->pci_ddrio, RANK_CFG_A, ®); + if (IS_RDIMM_ENABLED(reg)) { + /* FIXME: Can also be LRDIMM */ + edac_dbg(0, "Memory is registered\n"); + mtype = MEM_RDDR3; + } else { + edac_dbg(0, "Memory is unregistered\n"); + mtype = MEM_DDR3; + } } else { - edac_dbg(0, "Memory is unregistered\n"); - mtype = MEM_DDR3; + edac_dbg(0, "Cannot determine memory type\n"); + mtype = MEM_UNKNOWN; } /* On all supported DDR3 DIMM types, there are 8 banks available */ @@ -639,7 +645,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci) tmp_mb = (1 + pvt->tohm) >> 20; mb = div_u64_rem(tmp_mb, 1000, &kb); - edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)", mb, kb, (u64)pvt->tohm); + edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tohm); /* * Step 2) Get SAD range and SAD Interleave list @@ -1303,8 +1309,7 @@ static int mci_bind_devs(struct mem_ctl_info *mci, /* Check if everything were registered */ if (!pvt->pci_sad0 || !pvt->pci_sad1 || !pvt->pci_ha0 || - !pvt-> pci_tad || !pvt->pci_ras || !pvt->pci_ta || - !pvt->pci_ddrio) + !pvt-> pci_tad || !pvt->pci_ras || !pvt->pci_ta) goto enodev; for (i = 0; i < NUM_CHANNELS; i++) { |