From 88f074f4871a8c212b212b725e4dcdcdb09613c1 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 18 Oct 2013 14:28:59 -0700 Subject: ACPI, CPER: Update cper info We have a lot of confusing names of functions and data structures in amongs the the error reporting code. In particular the "apei" prefix has been applied to many objects that are not part of APEI. Since we will be using these routines for extended error log reporting it will be clearer if we fix up the names first. Signed-off-by: Chen, Gong Acked-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Tony Luck --- include/linux/cper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h index c23049496531..09ebe2113641 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -389,6 +389,6 @@ struct cper_sec_pcie { u64 cper_next_record_id(void); void cper_print_bits(const char *prefix, unsigned int bits, - const char *strs[], unsigned int strs_size); + const char * const strs[], unsigned int strs_size); #endif -- cgit v1.2.3 From 10ef6b0dffe404bcc54e94cb2ca1a5b18445a66b Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 18 Oct 2013 14:29:07 -0700 Subject: bitops: Introduce a more generic BITMASK macro GENMASK is used to create a contiguous bitmask([hi:lo]). It is implemented twice in current kernel. One is in EDAC driver, the other is in SiS/XGI FB driver. Move it to a more generic place for other usage. Signed-off-by: Chen, Gong Cc: Borislav Petkov Cc: Thomas Winischhofer Cc: Jean-Christophe Plagniol-Villard Cc: Tomi Valkeinen Acked-by: Borislav Petkov Acked-by: Mauro Carvalho Chehab Signed-off-by: Tony Luck --- drivers/edac/amd64_edac.c | 46 ++++++++++++++++++++++++---------------------- drivers/edac/amd64_edac.h | 8 -------- drivers/edac/sb_edac.c | 2 +- drivers/video/sis/init.c | 5 ++--- include/linux/bitops.h | 8 ++++++++ 5 files changed, 35 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 3c9e4e98c651..b53d0de17e15 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -339,8 +339,8 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct, if (pvt->fam == 0xf && pvt->ext_model < K8_REV_F) { csbase = pvt->csels[dct].csbases[csrow]; csmask = pvt->csels[dct].csmasks[csrow]; - base_bits = GENMASK(21, 31) | GENMASK(9, 15); - mask_bits = GENMASK(21, 29) | GENMASK(9, 15); + base_bits = GENMASK_ULL(31, 21) | GENMASK_ULL(15, 9); + mask_bits = GENMASK_ULL(29, 21) | GENMASK_ULL(15, 9); addr_shift = 4; /* @@ -352,16 +352,16 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct, 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; + *base = (csbase & GENMASK_ULL(15, 5)) << 6; + *base |= (csbase & GENMASK_ULL(30, 19)) << 8; *mask = ~0ULL; /* poke holes for the csmask */ - *mask &= ~((GENMASK(5, 15) << 6) | - (GENMASK(19, 30) << 8)); + *mask &= ~((GENMASK_ULL(15, 5) << 6) | + (GENMASK_ULL(30, 19) << 8)); - *mask |= (csmask & GENMASK(5, 15)) << 6; - *mask |= (csmask & GENMASK(19, 30)) << 8; + *mask |= (csmask & GENMASK_ULL(15, 5)) << 6; + *mask |= (csmask & GENMASK_ULL(30, 19)) << 8; return; } else { @@ -370,9 +370,11 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct, addr_shift = 8; if (pvt->fam == 0x15) - base_bits = mask_bits = GENMASK(19,30) | GENMASK(5,13); + base_bits = mask_bits = + GENMASK_ULL(30,19) | GENMASK_ULL(13,5); else - base_bits = mask_bits = GENMASK(19,28) | GENMASK(5,13); + base_bits = mask_bits = + GENMASK_ULL(28,19) | GENMASK_ULL(13,5); } *base = (csbase & base_bits) << addr_shift; @@ -561,7 +563,7 @@ static u64 sys_addr_to_dram_addr(struct mem_ctl_info *mci, u64 sys_addr) * section 3.4.2 of AMD publication 24592: AMD x86-64 Architecture * Programmer's Manual Volume 1 Application Programming. */ - dram_addr = (sys_addr & GENMASK(0, 39)) - dram_base; + dram_addr = (sys_addr & GENMASK_ULL(39, 0)) - dram_base; edac_dbg(2, "using DRAM Base register to translate SysAddr 0x%lx to DramAddr 0x%lx\n", (unsigned long)sys_addr, (unsigned long)dram_addr); @@ -597,7 +599,7 @@ static u64 dram_addr_to_input_addr(struct mem_ctl_info *mci, u64 dram_addr) * concerning translating a DramAddr to an InputAddr. */ intlv_shift = num_node_interleave_bits(dram_intlv_en(pvt, 0)); - input_addr = ((dram_addr >> intlv_shift) & GENMASK(12, 35)) + + input_addr = ((dram_addr >> intlv_shift) & GENMASK_ULL(35, 12)) + (dram_addr & 0xfff); edac_dbg(2, " Intlv Shift=%d DramAddr=0x%lx maps to InputAddr=0x%lx\n", @@ -849,7 +851,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m) end_bit = 39; } - addr = m->addr & GENMASK(start_bit, end_bit); + addr = m->addr & GENMASK_ULL(end_bit, start_bit); /* * Erratum 637 workaround @@ -861,7 +863,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m) u16 mce_nid; u8 intlv_en; - if ((addr & GENMASK(24, 47)) >> 24 != 0x00fdf7) + if ((addr & GENMASK_ULL(47, 24)) >> 24 != 0x00fdf7) return addr; mce_nid = amd_get_nb_id(m->extcpu); @@ -871,7 +873,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m) intlv_en = tmp >> 21 & 0x7; /* add [47:27] + 3 trailing bits */ - cc6_base = (tmp & GENMASK(0, 20)) << 3; + cc6_base = (tmp & GENMASK_ULL(20, 0)) << 3; /* reverse and add DramIntlvEn */ cc6_base |= intlv_en ^ 0x7; @@ -880,18 +882,18 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m) cc6_base <<= 24; if (!intlv_en) - return cc6_base | (addr & GENMASK(0, 23)); + return cc6_base | (addr & GENMASK_ULL(23, 0)); amd64_read_pci_cfg(pvt->F1, DRAM_LOCAL_NODE_BASE, &tmp); /* faster log2 */ - tmp_addr = (addr & GENMASK(12, 23)) << __fls(intlv_en + 1); + tmp_addr = (addr & GENMASK_ULL(23, 12)) << __fls(intlv_en + 1); /* OR DramIntlvSel into bits [14:12] */ - tmp_addr |= (tmp & GENMASK(21, 23)) >> 9; + tmp_addr |= (tmp & GENMASK_ULL(23, 21)) >> 9; /* add remaining [11:0] bits from original MC4_ADDR */ - tmp_addr |= addr & GENMASK(0, 11); + tmp_addr |= addr & GENMASK_ULL(11, 0); return cc6_base | tmp_addr; } @@ -952,12 +954,12 @@ static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range) amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim); - pvt->ranges[range].lim.lo &= GENMASK(0, 15); + pvt->ranges[range].lim.lo &= GENMASK_ULL(15, 0); /* {[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_ULL(7, 0); /* [47:40] */ pvt->ranges[range].lim.hi |= llim >> 13; @@ -1330,7 +1332,7 @@ static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range, chan_off = dram_base; } - return (sys_addr & GENMASK(6,47)) - (chan_off & GENMASK(23,47)); + return (sys_addr & GENMASK_ULL(47,6)) - (chan_off & GENMASK_ULL(47,23)); } /* diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index d2443cfa0698..6dc1fcc25afb 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -159,14 +159,6 @@ #define ON true #define OFF false -/* - * Create a contiguous bitmask starting at bit position @lo and ending at - * position @hi. For example - * - * GENMASK(21, 39) gives us the 64bit vector 0x000000ffffe00000. - */ -#define GENMASK(lo, hi) (((1ULL << ((hi) - (lo) + 1)) - 1) << (lo)) - /* * PCI-defined configuration space registers */ diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index e04462b60756..88f60c5fecbc 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -50,7 +50,7 @@ static int probed; * Get a bit field at register value , from bit to bit */ #define GET_BITFIELD(v, lo, hi) \ - (((v) & ((1ULL << ((hi) - (lo) + 1)) - 1) << (lo)) >> (lo)) + (((v) & GENMASK_ULL(hi, lo)) >> (lo)) /* * sbridge Memory Controller Registers diff --git a/drivers/video/sis/init.c b/drivers/video/sis/init.c index f082ae55c0c9..4f26bc28e60b 100644 --- a/drivers/video/sis/init.c +++ b/drivers/video/sis/init.c @@ -3320,9 +3320,8 @@ SiSSetMode(struct SiS_Private *SiS_Pr, unsigned short ModeNo) } #ifndef GETBITSTR -#define BITMASK(h,l) (((unsigned)(1U << ((h)-(l)+1))-1)<<(l)) -#define GENMASK(mask) BITMASK(1?mask,0?mask) -#define GETBITS(var,mask) (((var) & GENMASK(mask)) >> (0?mask)) +#define GENBITSMASK(mask) GENMASK(1?mask,0?mask) +#define GETBITS(var,mask) (((var) & GENBITSMASK(mask)) >> (0?mask)) #define GETBITSTR(val,from,to) ((GETBITS(val,from)) << (0?to)) #endif diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a3b6b82108b9..bd0c4598d03b 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -10,6 +10,14 @@ #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #endif +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) (((U32_C(1) << ((h) - (l) + 1)) - 1) << (l)) +#define GENMASK_ULL(h, l) (((U64_C(1) << ((h) - (l) + 1)) - 1) << (l)) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); -- cgit v1.2.3 From 4b3db708b114fc35ff1e0cd28a2bfb1490dbb5d3 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Mon, 21 Oct 2013 14:29:25 -0700 Subject: ACPI, x86: Extended error log driver for x86 platform This H/W error log driver (a.k.a eMCA driver) is implemented based on http://www.intel.com/content/www/us/en/architecture-and-technology/enhanced-mca-logging-xeon-paper.html After errors are captured, more detailed platform specific information can be got via this new enhanced H/W error log driver. Most notably we can track memory errors back to the DIMM slot silk screen label. Signed-off-by: Chen, Gong Signed-off-by: Tony Luck --- arch/x86/include/asm/mce.h | 1 + drivers/acpi/Kconfig | 19 +++ drivers/acpi/Makefile | 2 + drivers/acpi/acpi_extlog.c | 327 +++++++++++++++++++++++++++++++++++++++++++++ drivers/acpi/bus.c | 3 +- include/linux/acpi.h | 1 + 6 files changed, 352 insertions(+), 1 deletion(-) create mode 100644 drivers/acpi/acpi_extlog.c (limited to 'include/linux') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cbe6b9e404ce..c696a8687567 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -16,6 +16,7 @@ #define MCG_EXT_CNT_SHIFT 16 #define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) #define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */ +#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */ /* MCG_STATUS register defines */ #define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */ diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 6efe2ac6902f..252f0e818a49 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -372,4 +372,23 @@ config ACPI_BGRT source "drivers/acpi/apei/Kconfig" +config ACPI_EXTLOG + tristate "Extended Error Log support" + depends on X86_MCE && ACPI_APEI + default n + help + Certain usages such as Predictive Failure Analysis (PFA) require + more information about the error than what can be described in + processor machine check banks. Most server processors log + additional information about the error in processor uncore + registers. Since the addresses and layout of these registers vary + widely from one processor to another, system software cannot + readily make use of them. To complicate matters further, some of + the additional error information cannot be constructed without + detailed knowledge about platform topology. + + Enhanced MCA Logging allows firmware to provide additional error + information to system software, synchronous with MCE or CMCI. This + driver adds support for that functionality. + endif # ACPI diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index cdaf68b58b00..bce34afadcd0 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -82,3 +82,5 @@ processor-$(CONFIG_CPU_FREQ) += processor_perflib.o obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o obj-$(CONFIG_ACPI_APEI) += apei/ + +obj-$(CONFIG_ACPI_EXTLOG) += acpi_extlog.o diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c new file mode 100644 index 000000000000..a6869e110ce5 --- /dev/null +++ b/drivers/acpi/acpi_extlog.c @@ -0,0 +1,327 @@ +/* + * Extended Error Log driver + * + * Copyright (C) 2013 Intel Corp. + * Author: Chen, Gong + * + * This file is licensed under GPLv2. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "apei/apei-internal.h" + +#define EXT_ELOG_ENTRY_MASK GENMASK_ULL(51, 0) /* elog entry address mask */ + +#define EXTLOG_DSM_REV 0x0 +#define EXTLOG_FN_QUERY 0x0 +#define EXTLOG_FN_ADDR 0x1 + +#define FLAG_OS_OPTIN BIT(0) +#define EXTLOG_QUERY_L1_EXIST BIT(1) +#define ELOG_ENTRY_VALID (1ULL<<63) +#define ELOG_ENTRY_LEN 0x1000 + +#define EMCA_BUG \ + "Can not request iomem region <0x%016llx-0x%016llx> - eMCA disabled\n" + +struct extlog_l1_head { + u32 ver; /* Header Version */ + u32 hdr_len; /* Header Length */ + u64 total_len; /* entire L1 Directory length including this header */ + u64 elog_base; /* MCA Error Log Directory base address */ + u64 elog_len; /* MCA Error Log Directory length */ + u32 flags; /* bit 0 - OS/VMM Opt-in */ + u8 rev0[12]; + u32 entries; /* Valid L1 Directory entries per logical processor */ + u8 rev1[12]; +}; + +static u8 extlog_dsm_uuid[] = "663E35AF-CC10-41A4-88EA-5470AF055295"; + +/* L1 table related physical address */ +static u64 elog_base; +static size_t elog_size; +static u64 l1_dirbase; +static size_t l1_size; + +/* L1 table related virtual address */ +static void __iomem *extlog_l1_addr; +static void __iomem *elog_addr; + +static void *elog_buf; + +static u64 *l1_entry_base; +static u32 l1_percpu_entry; + +#define ELOG_IDX(cpu, bank) \ + (cpu_physical_id(cpu) * l1_percpu_entry + (bank)) + +#define ELOG_ENTRY_DATA(idx) \ + (*(l1_entry_base + (idx))) + +#define ELOG_ENTRY_ADDR(phyaddr) \ + (phyaddr - elog_base + (u8 *)elog_addr) + +static struct acpi_generic_status *extlog_elog_entry_check(int cpu, int bank) +{ + int idx; + u64 data; + struct acpi_generic_status *estatus; + + WARN_ON(cpu < 0); + idx = ELOG_IDX(cpu, bank); + data = ELOG_ENTRY_DATA(idx); + if ((data & ELOG_ENTRY_VALID) == 0) + return NULL; + + data &= EXT_ELOG_ENTRY_MASK; + estatus = (struct acpi_generic_status *)ELOG_ENTRY_ADDR(data); + + /* if no valid data in elog entry, just return */ + if (estatus->block_status == 0) + return NULL; + + return estatus; +} + +static void __print_extlog_rcd(const char *pfx, + struct acpi_generic_status *estatus, int cpu) +{ + static atomic_t seqno; + unsigned int curr_seqno; + char pfx_seq[64]; + + if (!pfx) { + if (estatus->error_severity <= CPER_SEV_CORRECTED) + pfx = KERN_INFO; + else + pfx = KERN_ERR; + } + curr_seqno = atomic_inc_return(&seqno); + snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}", pfx, curr_seqno); + printk("%s""Hardware error detected on CPU%d\n", pfx_seq, cpu); + cper_estatus_print(pfx_seq, estatus); +} + +static int print_extlog_rcd(const char *pfx, + struct acpi_generic_status *estatus, int cpu) +{ + /* Not more than 2 messages every 5 seconds */ + static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2); + static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2); + struct ratelimit_state *ratelimit; + + if (estatus->error_severity == CPER_SEV_CORRECTED || + (estatus->error_severity == CPER_SEV_INFORMATIONAL)) + ratelimit = &ratelimit_corrected; + else + ratelimit = &ratelimit_uncorrected; + if (__ratelimit(ratelimit)) { + __print_extlog_rcd(pfx, estatus, cpu); + return 0; + } + + return 1; +} + +static int extlog_print(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + int bank = mce->bank; + int cpu = mce->extcpu; + struct acpi_generic_status *estatus; + int rc; + + estatus = extlog_elog_entry_check(cpu, bank); + if (estatus == NULL) + return NOTIFY_DONE; + + memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN); + /* clear record status to enable BIOS to update it again */ + estatus->block_status = 0; + + rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu); + + return NOTIFY_DONE; +} + +static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret) +{ + struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL}; + struct acpi_object_list input; + union acpi_object params[4], *obj; + u8 uuid[16]; + int i; + + acpi_str_to_uuid(extlog_dsm_uuid, uuid); + input.count = 4; + input.pointer = params; + params[0].type = ACPI_TYPE_BUFFER; + params[0].buffer.length = 16; + params[0].buffer.pointer = uuid; + params[1].type = ACPI_TYPE_INTEGER; + params[1].integer.value = rev; + params[2].type = ACPI_TYPE_INTEGER; + params[2].integer.value = func; + params[3].type = ACPI_TYPE_PACKAGE; + params[3].package.count = 0; + params[3].package.elements = NULL; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DSM", &input, &buf))) + return -1; + + *ret = 0; + obj = (union acpi_object *)buf.pointer; + if (obj->type == ACPI_TYPE_INTEGER) { + *ret = obj->integer.value; + } else if (obj->type == ACPI_TYPE_BUFFER) { + if (obj->buffer.length <= 8) { + for (i = 0; i < obj->buffer.length; i++) + *ret |= (obj->buffer.pointer[i] << (i * 8)); + } + } + kfree(buf.pointer); + + return 0; +} + +static bool extlog_get_l1addr(void) +{ + acpi_handle handle; + u64 ret; + + if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle))) + return false; + + if (extlog_get_dsm(handle, EXTLOG_DSM_REV, EXTLOG_FN_QUERY, &ret) || + !(ret & EXTLOG_QUERY_L1_EXIST)) + return false; + + if (extlog_get_dsm(handle, EXTLOG_DSM_REV, EXTLOG_FN_ADDR, &ret)) + return false; + + l1_dirbase = ret; + /* Spec says L1 directory must be 4K aligned, bail out if it isn't */ + if (l1_dirbase & ((1 << 12) - 1)) { + pr_warn(FW_BUG "L1 Directory is invalid at physical %llx\n", + l1_dirbase); + return false; + } + + return true; +} +static struct notifier_block extlog_mce_dec = { + .notifier_call = extlog_print, +}; + +static int __init extlog_init(void) +{ + struct extlog_l1_head *l1_head; + void __iomem *extlog_l1_hdr; + size_t l1_hdr_size; + struct resource *r; + u64 cap; + int rc; + + rc = -ENODEV; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + if (!(cap & MCG_ELOG_P)) + return rc; + + if (!extlog_get_l1addr()) + return rc; + + rc = -EINVAL; + /* get L1 header to fetch necessary information */ + l1_hdr_size = sizeof(struct extlog_l1_head); + r = request_mem_region(l1_dirbase, l1_hdr_size, "L1 DIR HDR"); + if (!r) { + pr_warn(FW_BUG EMCA_BUG, + (unsigned long long)l1_dirbase, + (unsigned long long)l1_dirbase + l1_hdr_size); + goto err; + } + + extlog_l1_hdr = acpi_os_map_memory(l1_dirbase, l1_hdr_size); + l1_head = (struct extlog_l1_head *)extlog_l1_hdr; + l1_size = l1_head->total_len; + l1_percpu_entry = l1_head->entries; + elog_base = l1_head->elog_base; + elog_size = l1_head->elog_len; + acpi_os_unmap_memory(extlog_l1_hdr, l1_hdr_size); + release_mem_region(l1_dirbase, l1_hdr_size); + + /* remap L1 header again based on completed information */ + r = request_mem_region(l1_dirbase, l1_size, "L1 Table"); + if (!r) { + pr_warn(FW_BUG EMCA_BUG, + (unsigned long long)l1_dirbase, + (unsigned long long)l1_dirbase + l1_size); + goto err; + } + extlog_l1_addr = acpi_os_map_memory(l1_dirbase, l1_size); + l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size); + + /* remap elog table */ + r = request_mem_region(elog_base, elog_size, "Elog Table"); + if (!r) { + pr_warn(FW_BUG EMCA_BUG, + (unsigned long long)elog_base, + (unsigned long long)elog_base + elog_size); + goto err_release_l1_dir; + } + elog_addr = acpi_os_map_memory(elog_base, elog_size); + + rc = -ENOMEM; + /* allocate buffer to save elog record */ + elog_buf = kmalloc(ELOG_ENTRY_LEN, GFP_KERNEL); + if (elog_buf == NULL) + goto err_release_elog; + + mce_register_decode_chain(&extlog_mce_dec); + /* enable OS to be involved to take over management from BIOS */ + ((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN; + + return 0; + +err_release_elog: + if (elog_addr) + acpi_os_unmap_memory(elog_addr, elog_size); + release_mem_region(elog_base, elog_size); +err_release_l1_dir: + if (extlog_l1_addr) + acpi_os_unmap_memory(extlog_l1_addr, l1_size); + release_mem_region(l1_dirbase, l1_size); +err: + pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n"); + return rc; +} + +static void __exit extlog_exit(void) +{ + mce_unregister_decode_chain(&extlog_mce_dec); + ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; + if (extlog_l1_addr) + acpi_os_unmap_memory(extlog_l1_addr, l1_size); + if (elog_addr) + acpi_os_unmap_memory(elog_addr, elog_size); + release_mem_region(elog_base, elog_size); + release_mem_region(l1_dirbase, l1_size); + kfree(elog_buf); +} + +module_init(extlog_init); +module_exit(extlog_exit); + +MODULE_AUTHOR("Chen, Gong "); +MODULE_DESCRIPTION("Extended MCA Error Log Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index b587ec8257b2..e1bd9a181117 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -174,7 +174,7 @@ static void acpi_print_osc_error(acpi_handle handle, printk("\n"); } -static acpi_status acpi_str_to_uuid(char *str, u8 *uuid) +acpi_status acpi_str_to_uuid(char *str, u8 *uuid) { int i; static int opc_map_to_uuid[16] = {6, 4, 2, 0, 11, 9, 16, 14, 19, 21, @@ -195,6 +195,7 @@ static acpi_status acpi_str_to_uuid(char *str, u8 *uuid) } return AE_OK; } +EXPORT_SYMBOL_GPL(acpi_str_to_uuid); acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context) { diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a5db4aeefa36..c30bac8503bc 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -311,6 +311,7 @@ struct acpi_osc_context { #define OSC_INVALID_REVISION_ERROR 8 #define OSC_CAPABILITIES_MASK_ERROR 16 +acpi_status acpi_str_to_uuid(char *str, u8 *uuid); acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* platform-wide _OSC bits */ -- cgit v1.2.3 From dd6dad4288cb93e79bd7abfa6c6a338c47454d1a Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 18 Oct 2013 14:29:25 -0700 Subject: DMI: Parse memory device (type 17) in SMBIOS This patch adds a new interface to decode memory device (type 17) to help error reporting on DIMMs. Original-author: Tony Luck Signed-off-by: Chen, Gong Acked-by: Naveen N. Rao Acked-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Tony Luck --- arch/ia64/kernel/setup.c | 1 + arch/x86/kernel/setup.c | 1 + drivers/firmware/dmi_scan.c | 60 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/dmi.h | 5 ++++ 4 files changed, 67 insertions(+) (limited to 'include/linux') diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 4fc2e9569bb2..d86669bcdfb2 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1063,6 +1063,7 @@ check_bugs (void) static int __init run_dmi_scan(void) { dmi_scan_machine(); + dmi_memdev_walk(); dmi_set_dump_stack_arch_desc(); return 0; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f0de6294b955..918d489fa53d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -993,6 +993,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); dmi_scan_machine(); + dmi_memdev_walk(); dmi_set_dump_stack_arch_desc(); /* diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index fa0affb699b4..59579a744d58 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -25,6 +25,13 @@ static int dmi_initialized; /* DMI system identification string used during boot */ static char dmi_ids_string[128] __initdata; +static struct dmi_memdev_info { + const char *device; + const char *bank; + u16 handle; +} *dmi_memdev; +static int dmi_memdev_nr; + static const char * __init dmi_string_nosave(const struct dmi_header *dm, u8 s) { const u8 *bp = ((u8 *) dm) + dm->length; @@ -322,6 +329,42 @@ static void __init dmi_save_extended_devices(const struct dmi_header *dm) dmi_save_one_device(*d & 0x7f, dmi_string_nosave(dm, *(d - 1))); } +static void __init count_mem_devices(const struct dmi_header *dm, void *v) +{ + if (dm->type != DMI_ENTRY_MEM_DEVICE) + return; + dmi_memdev_nr++; +} + +static void __init save_mem_devices(const struct dmi_header *dm, void *v) +{ + const char *d = (const char *)dm; + static int nr; + + if (dm->type != DMI_ENTRY_MEM_DEVICE) + return; + if (nr >= dmi_memdev_nr) { + pr_warn(FW_BUG "Too many DIMM entries in SMBIOS table\n"); + return; + } + dmi_memdev[nr].handle = dm->handle; + dmi_memdev[nr].device = dmi_string(dm, d[0x10]); + dmi_memdev[nr].bank = dmi_string(dm, d[0x11]); + nr++; +} + +void __init dmi_memdev_walk(void) +{ + if (!dmi_available) + return; + + if (dmi_walk_early(count_mem_devices) == 0 && dmi_memdev_nr) { + dmi_memdev = dmi_alloc(sizeof(*dmi_memdev) * dmi_memdev_nr); + if (dmi_memdev) + dmi_walk_early(save_mem_devices); + } +} + /* * Process a DMI table entry. Right now all we care about are the BIOS * and machine entries. For 2.5 we should pull the smbus controller info @@ -815,3 +858,20 @@ bool dmi_match(enum dmi_field f, const char *str) return !strcmp(info, str); } EXPORT_SYMBOL_GPL(dmi_match); + +void dmi_memdev_name(u16 handle, const char **bank, const char **device) +{ + int n; + + if (dmi_memdev == NULL) + return; + + for (n = 0; n < dmi_memdev_nr; n++) { + if (handle == dmi_memdev[n].handle) { + *bank = dmi_memdev[n].bank; + *device = dmi_memdev[n].device; + break; + } + } +} +EXPORT_SYMBOL_GPL(dmi_memdev_name); diff --git a/include/linux/dmi.h b/include/linux/dmi.h index b6eb7a05d58e..f820f0a336c9 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -99,6 +99,7 @@ extern const char * dmi_get_system_info(int field); extern const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from); extern void dmi_scan_machine(void); +extern void dmi_memdev_walk(void); extern void dmi_set_dump_stack_arch_desc(void); extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp); extern int dmi_name_in_vendors(const char *str); @@ -107,6 +108,7 @@ extern int dmi_available; extern int dmi_walk(void (*decode)(const struct dmi_header *, void *), void *private_data); extern bool dmi_match(enum dmi_field f, const char *str); +extern void dmi_memdev_name(u16 handle, const char **bank, const char **device); #else @@ -115,6 +117,7 @@ static inline const char * dmi_get_system_info(int field) { return NULL; } static inline const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from) { return NULL; } static inline void dmi_scan_machine(void) { return; } +static inline void dmi_memdev_walk(void) { } static inline void dmi_set_dump_stack_arch_desc(void) { } static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp) { @@ -133,6 +136,8 @@ static inline int dmi_walk(void (*decode)(const struct dmi_header *, void *), void *private_data) { return -1; } static inline bool dmi_match(enum dmi_field f, const char *str) { return false; } +static inline void dmi_memdev_name(u16 handle, const char **bank, + const char **device) { } static inline const struct dmi_system_id * dmi_first_match(const struct dmi_system_id *list) { return NULL; } -- cgit v1.2.3 From 147de14772ed897727dba7353916b02d1e0f17f4 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 18 Oct 2013 14:30:13 -0700 Subject: ACPI, APEI, CPER: Add UEFI 2.4 support for memory error In latest UEFI spec(by now it is 2.4) memory error definition for CPER (UEFI 2.4 Appendix N Common Platform Error Record) adds some new fields. These fields help people to locate memory error to an actual DIMM location. Original-author: Tony Luck Signed-off-by: Chen, Gong Reviewed-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Acked-by: Naveen N. Rao Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/mcheck/mce-apei.c | 3 +-- drivers/acpi/apei/cper.c | 7 ++++--- drivers/acpi/apei/ghes.c | 4 ++-- drivers/edac/ghes_edac.c | 5 ++--- include/linux/cper.h | 11 +++++++++-- 5 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index cd8b166a1735..de8b60a53f69 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) struct mce m; /* Only corrected MC is reported */ - if (!corrected || !(mem_err->validation_bits & - CPER_MEM_VALID_PHYSICAL_ADDRESS)) + if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA)) return; mce_setup(&m); diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c index eb5f6d6d7dbc..946ef520186f 100644 --- a/drivers/acpi/apei/cper.c +++ b/drivers/acpi/apei/cper.c @@ -8,7 +8,7 @@ * various tables, such as ERST, BERT and HEST etc. * * For more information about CPER, please refer to Appendix N of UEFI - * Specification version 2.3. + * Specification version 2.4. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License version @@ -191,16 +191,17 @@ static const char *cper_mem_err_type_strs[] = { "memory sparing", "scrub corrected error", "scrub uncorrected error", + "physical memory map-out event", }; static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) { if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); - if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) + if (mem->validation_bits & CPER_MEM_VALID_PA) printk("%s""physical_address: 0x%016llx\n", pfx, mem->physical_addr); - if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) + if (mem->validation_bits & CPER_MEM_VALID_PA_MASK) printk("%s""physical_address_mask: 0x%016llx\n", pfx, mem->physical_addr_mask); if (mem->validation_bits & CPER_MEM_VALID_NODE) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 0db6e4ff6501..a30bc313787b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -419,7 +419,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev) if (sec_sev == GHES_SEV_CORRECTED && (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) && - (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) { + (mem_err->validation_bits & CPER_MEM_VALID_PA)) { pfn = mem_err->physical_addr >> PAGE_SHIFT; if (pfn_valid(pfn)) memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE); @@ -430,7 +430,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev) } if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE && - mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) { + mem_err->validation_bits & CPER_MEM_VALID_PA) { pfn = mem_err->physical_addr >> PAGE_SHIFT; memory_failure_queue(pfn, 0, 0); } diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index bb534670ec02..0ad797b9db65 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -297,15 +297,14 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev, } /* Error address */ - if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) { + if (mem_err->validation_bits & CPER_MEM_VALID_PA) { 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) { + if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK) e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK); - } /* Memory error location, mapped on e->location */ p = e->location; diff --git a/include/linux/cper.h b/include/linux/cper.h index 09ebe2113641..2fc0ec3d89cc 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -218,8 +218,8 @@ enum { #define CPER_PROC_VALID_IP 0x1000 #define CPER_MEM_VALID_ERROR_STATUS 0x0001 -#define CPER_MEM_VALID_PHYSICAL_ADDRESS 0x0002 -#define CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK 0x0004 +#define CPER_MEM_VALID_PA 0x0002 +#define CPER_MEM_VALID_PA_MASK 0x0004 #define CPER_MEM_VALID_NODE 0x0008 #define CPER_MEM_VALID_CARD 0x0010 #define CPER_MEM_VALID_MODULE 0x0020 @@ -232,6 +232,9 @@ enum { #define CPER_MEM_VALID_RESPONDER_ID 0x1000 #define CPER_MEM_VALID_TARGET_ID 0x2000 #define CPER_MEM_VALID_ERROR_TYPE 0x4000 +#define CPER_MEM_VALID_RANK_NUMBER 0x8000 +#define CPER_MEM_VALID_CARD_HANDLE 0x10000 +#define CPER_MEM_VALID_MODULE_HANDLE 0x20000 #define CPER_PCIE_VALID_PORT_TYPE 0x0001 #define CPER_PCIE_VALID_VERSION 0x0002 @@ -347,6 +350,10 @@ struct cper_sec_mem_err { __u64 responder_id; __u64 target_id; __u8 error_type; + __u8 reserved; + __u16 rank; + __u16 mem_array_handle; /* card handle in UEFI 2.4 */ + __u16 mem_dev_handle; /* module handle in UEFI 2.4 */ }; struct cper_sec_pcie { -- cgit v1.2.3 From 56507694de3453076d73e0e9813349586ee67e59 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 18 Oct 2013 14:30:38 -0700 Subject: EDAC, GHES: Update ghes error record info In latest UEFI spec(by now it's 2.4) there are some new fields for memory error reporting. Add these new fields for ghes_edac interface. Signed-off-by: Chen, Gong Cc: Mauro Carvalho Chehab Signed-off-by: Tony Luck --- drivers/edac/ghes_edac.c | 11 +++++++++++ include/linux/edac.h | 2 +- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 0ad797b9db65..d5a98a45c062 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -314,6 +314,8 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev, 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_RANK_NUMBER) + p += sprintf(p, "rank:%d ", mem_err->rank); 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) @@ -322,6 +324,15 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev, 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 (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) { + const char *bank = NULL, *device = NULL; + dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device); + if (bank != NULL && device != NULL) + p += sprintf(p, "DIMM location:%s %s ", bank, device); + else + p += sprintf(p, "DIMM DMI handle: 0x%.4x ", + mem_err->mem_dev_handle); + } if (p > e->location) *(p - 1) = '\0'; diff --git a/include/linux/edac.h b/include/linux/edac.h index 5c6d7fbaf89e..dbdffe8d4469 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -51,7 +51,7 @@ static inline void opstate_init(void) #define EDAC_MC_LABEL_LEN 31 /* Maximum size of the location string */ -#define LOCATION_SIZE 80 +#define LOCATION_SIZE 256 /* Defines the maximum number of labels that can be reported */ #define EDAC_MAX_LABELS 8 -- cgit v1.2.3