diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2010-06-04 15:39:54 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-06-04 15:39:54 -0700 |
commit | 9a9620db07b27700a4de9e86985735fffb78e2f8 (patch) | |
tree | 14cf3a384ea0d7afeb759cdaf96de7fec7abc9a7 /drivers/edac | |
parent | e620d1e39aa33b43bed96aa7f2ebbc88914aed58 (diff) | |
parent | 52707f918cca231f8461d45e78a60014795f20d9 (diff) |
Merge branch 'linux_next' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/i7core
* 'linux_next' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/i7core: (83 commits)
i7core_edac: Better describe the supported devices
Add support for Westmere to i7core_edac driver
i7core_edac: don't free on success
i7core_edac: Add support for X5670
Always call i7core_[ur]dimm_check_mc_ecc_err
i7core_edac: fix memory leak of i7core_dev
EDAC: add __init to i7core_xeon_pci_fixup
i7core_edac: Fix wrong device id for channel 1 devices
i7core: add support for Lynnfield alternate address
i7core_edac: Add initial support for Lynnfield
i7core_edac: do not export static functions
edac: fix i7core build
edac: i7core_edac produces undefined behaviour on 32bit
i7core_edac: Use a more generic approach for probing PCI devices
i7core_edac: PCI device is called NONCORE, instead of NOCORE
i7core_edac: Fix ringbuffer maxsize
i7core_edac: First store, then increment
i7core_edac: Better parse "any" addrmask
i7core_edac: Use a lockless ringbuffer
edac: Create an unique instance for each kobj
...
Diffstat (limited to 'drivers/edac')
-rw-r--r-- | drivers/edac/Kconfig | 13 | ||||
-rw-r--r-- | drivers/edac/Makefile | 2 | ||||
-rw-r--r-- | drivers/edac/edac_core.h | 23 | ||||
-rw-r--r-- | drivers/edac/edac_mc_sysfs.c | 175 | ||||
-rw-r--r-- | drivers/edac/edac_mce.c | 61 | ||||
-rw-r--r-- | drivers/edac/i7core_edac.c | 2078 |
6 files changed, 2325 insertions, 27 deletions
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 55c9c59b3f7..aedef7941b2 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -69,6 +69,9 @@ config EDAC_MM_EDAC occurred so that a particular failing memory module can be replaced. If unsure, select 'Y'. +config EDAC_MCE + bool + config EDAC_AMD64 tristate "AMD64 (Opteron, Athlon64) K8, F10h, F11h" depends on EDAC_MM_EDAC && K8_NB && X86_64 && PCI && EDAC_DECODE_MCE @@ -166,6 +169,16 @@ config EDAC_I5400 Support for error detection and correction the Intel i5400 MCH chipset (Seaburg). +config EDAC_I7CORE + tristate "Intel i7 Core (Nehalem) processors" + depends on EDAC_MM_EDAC && PCI && X86 + select EDAC_MCE + help + Support for error detection and correction the Intel + i7 Core (Nehalem) Integrated Memory Controller that exists on + newer processors like i7 Core, i7 Core Extreme, Xeon 35xx + and Xeon 55xx processors. + config EDAC_I82860 tristate "Intel 82860" depends on EDAC_MM_EDAC && PCI && X86_32 diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index bc5dc232a0f..ca6b1bb24cc 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_EDAC) := edac_stub.o obj-$(CONFIG_EDAC_MM_EDAC) += edac_core.o +obj-$(CONFIG_EDAC_MCE) += edac_mce.o edac_core-objs := edac_mc.o edac_device.o edac_mc_sysfs.o edac_pci_sysfs.o edac_core-objs += edac_module.o edac_device_sysfs.o @@ -23,6 +24,7 @@ obj-$(CONFIG_EDAC_CPC925) += cpc925_edac.o obj-$(CONFIG_EDAC_I5000) += i5000_edac.o obj-$(CONFIG_EDAC_I5100) += i5100_edac.o obj-$(CONFIG_EDAC_I5400) += i5400_edac.o +obj-$(CONFIG_EDAC_I7CORE) += i7core_edac.o obj-$(CONFIG_EDAC_E7XXX) += e7xxx_edac.o obj-$(CONFIG_EDAC_E752X) += e752x_edac.o obj-$(CONFIG_EDAC_I82443BXGX) += i82443bxgx_edac.o diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 001b2e797fb..efca9343d26 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -341,12 +341,30 @@ struct csrow_info { struct channel_info *channels; }; +struct mcidev_sysfs_group { + const char *name; /* group name */ + struct mcidev_sysfs_attribute *mcidev_attr; /* group attributes */ +}; + +struct mcidev_sysfs_group_kobj { + struct list_head list; /* list for all instances within a mc */ + + struct kobject kobj; /* kobj for the group */ + + struct mcidev_sysfs_group *grp; /* group description table */ + struct mem_ctl_info *mci; /* the parent */ +}; + /* mcidev_sysfs_attribute structure * used for driver sysfs attributes and in mem_ctl_info * sysfs top level entries */ struct mcidev_sysfs_attribute { - struct attribute attr; + /* It should use either attr or grp */ + struct attribute attr; + struct mcidev_sysfs_group *grp; /* Points to a group of attributes */ + + /* Ops for show/store values at the attribute - not used on group */ ssize_t (*show)(struct mem_ctl_info *,char *); ssize_t (*store)(struct mem_ctl_info *, const char *,size_t); }; @@ -424,6 +442,9 @@ struct mem_ctl_info { /* edac sysfs device control */ struct kobject edac_mci_kobj; + /* list for all grp instances within a mc */ + struct list_head grp_kobj_list; + /* Additional top controller level attributes, but specified * by the low level driver. * diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 418b65f1a1d..c200c2fd43e 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -557,6 +557,8 @@ static ssize_t mcidev_show(struct kobject *kobj, struct attribute *attr, struct mem_ctl_info *mem_ctl_info = to_mci(kobj); struct mcidev_sysfs_attribute *mcidev_attr = to_mcidev_attr(attr); + debugf1("%s() mem_ctl_info %p\n", __func__, mem_ctl_info); + if (mcidev_attr->show) return mcidev_attr->show(mem_ctl_info, buffer); @@ -569,6 +571,8 @@ static ssize_t mcidev_store(struct kobject *kobj, struct attribute *attr, struct mem_ctl_info *mem_ctl_info = to_mci(kobj); struct mcidev_sysfs_attribute *mcidev_attr = to_mcidev_attr(attr); + debugf1("%s() mem_ctl_info %p\n", __func__, mem_ctl_info); + if (mcidev_attr->store) return mcidev_attr->store(mem_ctl_info, buffer, count); @@ -726,28 +730,118 @@ void edac_mc_unregister_sysfs_main_kobj(struct mem_ctl_info *mci) #define EDAC_DEVICE_SYMLINK "device" +#define grp_to_mci(k) (container_of(k, struct mcidev_sysfs_group_kobj, kobj)->mci) + +/* MCI show/store functions for top most object */ +static ssize_t inst_grp_show(struct kobject *kobj, struct attribute *attr, + char *buffer) +{ + struct mem_ctl_info *mem_ctl_info = grp_to_mci(kobj); + struct mcidev_sysfs_attribute *mcidev_attr = to_mcidev_attr(attr); + + debugf1("%s() mem_ctl_info %p\n", __func__, mem_ctl_info); + + if (mcidev_attr->show) + return mcidev_attr->show(mem_ctl_info, buffer); + + return -EIO; +} + +static ssize_t inst_grp_store(struct kobject *kobj, struct attribute *attr, + const char *buffer, size_t count) +{ + struct mem_ctl_info *mem_ctl_info = grp_to_mci(kobj); + struct mcidev_sysfs_attribute *mcidev_attr = to_mcidev_attr(attr); + + debugf1("%s() mem_ctl_info %p\n", __func__, mem_ctl_info); + + if (mcidev_attr->store) + return mcidev_attr->store(mem_ctl_info, buffer, count); + + return -EIO; +} + +/* No memory to release for this kobj */ +static void edac_inst_grp_release(struct kobject *kobj) +{ + struct mcidev_sysfs_group_kobj *grp; + struct mem_ctl_info *mci; + + debugf1("%s()\n", __func__); + + grp = container_of(kobj, struct mcidev_sysfs_group_kobj, kobj); + mci = grp->mci; + + kobject_put(&mci->edac_mci_kobj); +} + +/* Intermediate show/store table */ +static struct sysfs_ops inst_grp_ops = { + .show = inst_grp_show, + .store = inst_grp_store +}; + +/* the kobj_type instance for a instance group */ +static struct kobj_type ktype_inst_grp = { + .release = edac_inst_grp_release, + .sysfs_ops = &inst_grp_ops, +}; + + /* * edac_create_mci_instance_attributes - * create MC driver specific attributes at the topmost level - * directory of this mci instance. + * create MC driver specific attributes bellow an specified kobj + * This routine calls itself recursively, in order to create an entire + * object tree. */ -static int edac_create_mci_instance_attributes(struct mem_ctl_info *mci) +static int edac_create_mci_instance_attributes(struct mem_ctl_info *mci, + struct mcidev_sysfs_attribute *sysfs_attrib, + struct kobject *kobj) { int err; - struct mcidev_sysfs_attribute *sysfs_attrib; - /* point to the start of the array and iterate over it - * adding each attribute listed to this mci instance's kobject - */ - sysfs_attrib = mci->mc_driver_sysfs_attributes; + debugf1("%s()\n", __func__); + + while (sysfs_attrib) { + if (sysfs_attrib->grp) { + struct mcidev_sysfs_group_kobj *grp_kobj; + + grp_kobj = kzalloc(sizeof(*grp_kobj), GFP_KERNEL); + if (!grp_kobj) + return -ENOMEM; + + list_add_tail(&grp_kobj->list, &mci->grp_kobj_list); + + grp_kobj->grp = sysfs_attrib->grp; + grp_kobj->mci = mci; + + debugf0("%s() grp %s, mci %p\n", __func__, + sysfs_attrib->grp->name, mci); + + err = kobject_init_and_add(&grp_kobj->kobj, + &ktype_inst_grp, + &mci->edac_mci_kobj, + sysfs_attrib->grp->name); + if (err) + return err; + + err = edac_create_mci_instance_attributes(mci, + grp_kobj->grp->mcidev_attr, + &grp_kobj->kobj); + + if (err) + return err; + } else if (sysfs_attrib->attr.name) { + debugf0("%s() file %s\n", __func__, + sysfs_attrib->attr.name); + + err = sysfs_create_file(kobj, &sysfs_attrib->attr); + } else + break; - while (sysfs_attrib && sysfs_attrib->attr.name) { - err = sysfs_create_file(&mci->edac_mci_kobj, - (struct attribute*) sysfs_attrib); if (err) { return err; } - sysfs_attrib++; } @@ -759,21 +853,44 @@ static int edac_create_mci_instance_attributes(struct mem_ctl_info *mci) * remove MC driver specific attributes at the topmost level * directory of this mci instance. */ -static void edac_remove_mci_instance_attributes(struct mem_ctl_info *mci) +static void edac_remove_mci_instance_attributes(struct mem_ctl_info *mci, + struct mcidev_sysfs_attribute *sysfs_attrib, + struct kobject *kobj, int count) { - struct mcidev_sysfs_attribute *sysfs_attrib; + struct mcidev_sysfs_group_kobj *grp_kobj, *tmp; - /* point to the start of the array and iterate over it - * adding each attribute listed to this mci instance's kobject - */ - sysfs_attrib = mci->mc_driver_sysfs_attributes; + debugf1("%s()\n", __func__); - /* loop if there are attributes and until we hit a NULL entry */ - while (sysfs_attrib && sysfs_attrib->attr.name) { - sysfs_remove_file(&mci->edac_mci_kobj, - (struct attribute *) sysfs_attrib); + /* + * loop if there are attributes and until we hit a NULL entry + * Remove first all the atributes + */ + while (sysfs_attrib) { + if (sysfs_attrib->grp) { + list_for_each_entry(grp_kobj, &mci->grp_kobj_list, + list) + if (grp_kobj->grp == sysfs_attrib->grp) + edac_remove_mci_instance_attributes(mci, + grp_kobj->grp->mcidev_attr, + &grp_kobj->kobj, count + 1); + } else if (sysfs_attrib->attr.name) { + debugf0("%s() file %s\n", __func__, + sysfs_attrib->attr.name); + sysfs_remove_file(kobj, &sysfs_attrib->attr); + } else + break; sysfs_attrib++; } + + /* + * Now that all attributes got removed, it is save to remove all groups + */ + if (!count) + list_for_each_entry_safe(grp_kobj, tmp, &mci->grp_kobj_list, + list) { + debugf0("%s() grp %s\n", __func__, grp_kobj->grp->name); + kobject_put(&grp_kobj->kobj); + } } @@ -794,6 +911,8 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) debugf0("%s() idx=%d\n", __func__, mci->mc_idx); + INIT_LIST_HEAD(&mci->grp_kobj_list); + /* create a symlink for the device */ err = sysfs_create_link(kobj_mci, &mci->dev->kobj, EDAC_DEVICE_SYMLINK); @@ -806,7 +925,9 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) * then create them now for the driver. */ if (mci->mc_driver_sysfs_attributes) { - err = edac_create_mci_instance_attributes(mci); + err = edac_create_mci_instance_attributes(mci, + mci->mc_driver_sysfs_attributes, + &mci->edac_mci_kobj); if (err) { debugf1("%s() failure to create mci attributes\n", __func__); @@ -841,7 +962,8 @@ fail1: } /* remove the mci instance's attributes, if any */ - edac_remove_mci_instance_attributes(mci); + edac_remove_mci_instance_attributes(mci, + mci->mc_driver_sysfs_attributes, &mci->edac_mci_kobj, 0); /* remove the symlink */ sysfs_remove_link(kobj_mci, EDAC_DEVICE_SYMLINK); @@ -875,8 +997,9 @@ void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci) debugf0("%s() remove_mci_instance\n", __func__); /* remove this mci instance's attribtes */ - edac_remove_mci_instance_attributes(mci); - + edac_remove_mci_instance_attributes(mci, + mci->mc_driver_sysfs_attributes, + &mci->edac_mci_kobj, 0); debugf0("%s() unregister this mci kobj\n", __func__); /* unregister this instance's kobject */ diff --git a/drivers/edac/edac_mce.c b/drivers/edac/edac_mce.c new file mode 100644 index 00000000000..9ccdc5b140e --- /dev/null +++ b/drivers/edac/edac_mce.c @@ -0,0 +1,61 @@ +/* Provides edac interface to mcelog events + * + * This file may be distributed under the terms of the + * GNU General Public License version 2. + * + * Copyright (c) 2009 by: + * Mauro Carvalho Chehab <mchehab@redhat.com> + * + * Red Hat Inc. http://www.redhat.com + */ + +#include <linux/module.h> +#include <linux/edac_mce.h> +#include <asm/mce.h> + +int edac_mce_enabled; +EXPORT_SYMBOL_GPL(edac_mce_enabled); + + +/* + * Extension interface + */ + +static LIST_HEAD(edac_mce_list); +static DEFINE_MUTEX(edac_mce_lock); + +int edac_mce_register(struct edac_mce *edac_mce) +{ + mutex_lock(&edac_mce_lock); + list_add_tail(&edac_mce->list, &edac_mce_list); + mutex_unlock(&edac_mce_lock); + return 0; +} +EXPORT_SYMBOL(edac_mce_register); + +void edac_mce_unregister(struct edac_mce *edac_mce) +{ + mutex_lock(&edac_mce_lock); + list_del(&edac_mce->list); + mutex_unlock(&edac_mce_lock); +} +EXPORT_SYMBOL(edac_mce_unregister); + +int edac_mce_parse(struct mce *mce) +{ + struct edac_mce *edac_mce; + + list_for_each_entry(edac_mce, &edac_mce_list, list) { + if (edac_mce->check_error(edac_mce->priv, mce)) + return 1; + } + + /* Nobody queued the error */ + return 0; +} +EXPORT_SYMBOL_GPL(edac_mce_parse); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@redhat.com>"); +MODULE_AUTHOR("Red Hat Inc. (http://www.redhat.com)"); +MODULE_DESCRIPTION("EDAC Driver for mcelog captured errors"); diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c new file mode 100644 index 00000000000..6b8b7b41ec5 --- /dev/null +++ b/drivers/edac/i7core_edac.c @@ -0,0 +1,2078 @@ +/* Intel i7 core/Nehalem Memory Controller kernel module + * + * This driver supports yhe memory controllers found on the Intel + * processor families i7core, i7core 7xx/8xx, i5core, Xeon 35xx, + * Xeon 55xx and Xeon 56xx also known as Nehalem, Nehalem-EP, Lynnfield + * and Westmere-EP. + * + * This file may be distributed under the terms of the + * GNU General Public License version 2 only. + * + * Copyright (c) 2009-2010 by: + * Mauro Carvalho Chehab <mchehab@redhat.com> + * + * Red Hat Inc. http://www.redhat.com + * + * Forked and adapted from the i5400_edac driver + * + * Based on the following public Intel datasheets: + * Intel Core i7 Processor Extreme Edition and Intel Core i7 Processor + * Datasheet, Volume 2: + * http://download.intel.com/design/processor/datashts/320835.pdf + * Intel Xeon Processor 5500 Series Datasheet Volume 2 + * http://www.intel.com/Assets/PDF/datasheet/321322.pdf + * also available at: + * http://www.arrownac.com/manufacturers/intel/s/nehalem/5500-datasheet-v2.pdf + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/edac.h> +#include <linux/mmzone.h> +#include <linux/edac_mce.h> +#include <linux/smp.h> +#include <asm/processor.h> + +#include "edac_core.h" + +/* + * This is used for Nehalem-EP and Nehalem-EX devices, where the non-core + * registers start at bus 255, and are not reported by BIOS. + * We currently find devices with only 2 sockets. In order to support more QPI + * Quick Path Interconnect, just increment this number. + */ +#define MAX_SOCKET_BUSES 2 + + +/* + * Alter this version for the module when modifications are made + */ +#define I7CORE_REVISION " Ver: 1.0.0 " __DATE__ +#define EDAC_MOD_STR "i7core_edac" + +/* + * Debug macros + */ +#define i7core_printk(level, fmt, arg...) \ + edac_printk(level, "i7core", fmt, ##arg) + +#define i7core_mc_printk(mci, level, fmt, arg...) \ + edac_mc_chipset_printk(mci, level, "i7core", fmt, ##arg) + +/* + * i7core Memory Controller Registers + */ + + /* OFFSETS for Device 0 Function 0 */ + +#define MC_CFG_CONTROL 0x90 + + /* OFFSETS for Device 3 Function 0 */ + +#define MC_CONTROL 0x48 +#define MC_STATUS 0x4c +#define MC_MAX_DOD 0x64 + +/* + * OFFSETS for Device 3 Function 4, as inicated on Xeon 5500 datasheet: + * http://www.arrownac.com/manufacturers/intel/s/nehalem/5500-datasheet-v2.pdf + */ + +#define MC_TEST_ERR_RCV1 0x60 + #define DIMM2_COR_ERR(r) ((r) & 0x7fff) + +#define MC_TEST_ERR_RCV0 0x64 + #define DIMM1_COR_ERR(r) (((r) >> 16) & 0x7fff) + #define DIMM0_COR_ERR(r) ((r) & 0x7fff) + +/* OFFSETS for Device 3 Function 2, as inicated on Xeon 5500 datasheet */ +#define MC_COR_ECC_CNT_0 0x80 +#define MC_COR_ECC_CNT_1 0x84 +#define MC_COR_ECC_CNT_2 0x88 +#define MC_COR_ECC_CNT_3 0x8c +#define MC_COR_ECC_CNT_4 0x90 +#define MC_COR_ECC_CNT_5 0x94 + +#define DIMM_TOP_COR_ERR(r) (((r) >> 16) & 0x7fff) +#define DIMM_BOT_COR_ERR(r) ((r) & 0x7fff) + + + /* OFFSETS for Devices 4,5 and 6 Function 0 */ + +#define MC_CHANNEL_DIMM_INIT_PARAMS 0x58 + #define THREE_DIMMS_PRESENT (1 << 24) + #define SINGLE_QUAD_RANK_PRESENT (1 << 23) + #define QUAD_RANK_PRESENT (1 << 22) + #define REGISTERED_DIMM (1 << 15) + +#define MC_CHANNEL_MAPPER 0x60 + #define RDLCH(r, ch) ((((r) >> (3 + (ch * 6))) & 0x07) - 1) + #define WRLCH(r, ch) ((((r) >> (ch * 6)) & 0x07) - 1) + +#define MC_CHANNEL_RANK_PRESENT 0x7c + #define RANK_PRESENT_MASK 0xffff + +#define MC_CHANNEL_ADDR_MATCH 0xf0 +#define MC_CHANNEL_ERROR_MASK 0xf8 +#define MC_CHANNEL_ERROR_INJECT 0xfc + #define INJECT_ADDR_PARITY 0x10 + #define INJECT_ECC 0x08 + #define MASK_CACHELINE 0x06 + #define MASK_FULL_CACHELINE 0x06 + #define MASK_MSB32_CACHELINE 0x04 + #define MASK_LSB32_CACHELINE 0x02 + #define NO_MASK_CACHELINE 0x00 + #define REPEAT_EN 0x01 + + /* OFFSETS for Devices 4,5 and 6 Function 1 */ + +#define MC_DOD_CH_DIMM0 0x48 +#define MC_DOD_CH_DIMM1 0x4c +#define MC_DOD_CH_DIMM2 0x50 + #define RANKOFFSET_MASK ((1 << 12) | (1 << 11) | (1 << 10)) + #define RANKOFFSET(x) ((x & RANKOFFSET_MASK) >> 10) + #define DIMM_PRESENT_MASK (1 << 9) + #define DIMM_PRESENT(x) (((x) & DIMM_PRESENT_MASK) >> 9) + #define MC_DOD_NUMBANK_MASK ((1 << 8) | (1 << 7)) + #define MC_DOD_NUMBANK(x) (((x) & MC_DOD_NUMBANK_MASK) >> 7) + #define MC_DOD_NUMRANK_MASK ((1 << 6) | (1 << 5)) + #define MC_DOD_NUMRANK(x) (((x) & MC_DOD_NUMRANK_MASK) >> 5) + #define MC_DOD_NUMROW_MASK ((1 << 4) | (1 << 3) | (1 << 2)) + #define MC_DOD_NUMROW(x) (((x) & MC_DOD_NUMROW_MASK) >> 2) + #define MC_DOD_NUMCOL_MASK 3 + #define MC_DOD_NUMCOL(x) ((x) & MC_DOD_NUMCOL_MASK) + +#define MC_RANK_PRESENT 0x7c + +#define MC_SAG_CH_0 0x80 +#define MC_SAG_CH_1 0x84 +#define MC_SAG_CH_2 0x88 +#define MC_SAG_CH_3 0x8c +#define MC_SAG_CH_4 0x90 +#define MC_SAG_CH_5 0x94 +#define MC_SAG_CH_6 0x98 +#define MC_SAG_CH_7 0x9c + +#define MC_RIR_LIMIT_CH_0 0x40 +#define MC_RIR_LIMIT_CH_1 0x44 +#define MC_RIR_LIMIT_CH_2 0x48 +#define MC_RIR_LIMIT_CH_3 0x4C +#define MC_RIR_LIMIT_CH_4 0x50 +#define MC_RIR_LIMIT_CH_5 0x54 +#define MC_RIR_LIMIT_CH_6 0x58 +#define MC_RIR_LIMIT_CH_7 0x5C +#define MC_RIR_LIMIT_MASK ((1 << 10) - 1) + +#define MC_RIR_WAY_CH 0x80 + #define MC_RIR_WAY_OFFSET_MASK (((1 << 14) - 1) & ~0x7) + #define MC_RIR_WAY_RANK_MASK 0x7 + +/* + * i7core structs + */ + +#define NUM_CHANS 3 +#define MAX_DIMMS 3 /* Max DIMMS per channel */ +#define MAX_MCR_FUNC 4 +#define MAX_CHAN_FUNC 3 + +struct i7core_info { + u32 mc_control; + u32 mc_status; + u32 max_dod; + u32 ch_map; +}; + + +struct i7core_inject { + int enable; + + u32 section; + u32 type; + u32 eccmask; + + /* Error address mask */ + int channel, dimm, rank, bank, page, col; +}; + +struct i7core_channel { + u32 ranks; + u32 dimms; +}; + +struct pci_id_descr { + int dev; + int func; + int dev_id; + int optional; +}; + +struct pci_id_table { + struct pci_id_descr *descr; + int n_devs; +}; + +struct i7core_dev { + struct list_head list; + u8 socket; + struct pci_dev **pdev; + int n_devs; + struct mem_ctl_info *mci; +}; + +struct i7core_pvt { + struct pci_dev *pci_noncore; + struct pci_dev *pci_mcr[MAX_MCR_FUNC + 1]; + struct pci_dev *pci_ch[NUM_CHANS][MAX_CHAN_FUNC + 1]; + + struct i7core_dev *i7core_dev; + + struct i7core_info info; + struct i7core_inject inject; + struct i7core_channel channel[NUM_CHANS]; + + int channels; /* Number of active channels */ + + int ce_count_available; + int csrow_map[NUM_CHANS][MAX_DIMMS]; + + /* ECC corrected errors counts per udimm */ + unsigned long udimm_ce_count[MAX_DIMMS]; + int udimm_last_ce_count[MAX_DIMMS]; + /* ECC corrected errors counts per rdimm */ + unsigned long rdimm_ce_count[NUM_CHANS][MAX_DIMMS]; + int rdimm_last_ce_count[NUM_CHANS][MAX_DIMMS]; + + unsigned int is_registered; + + /* mcelog glue */ + struct edac_mce edac_mce; + + /* Fifo double buffers */ + struct mce mce_entry[MCE_LOG_LEN]; + struct mce mce_outentry[MCE_LOG_LEN]; + + /* Fifo in/out counters */ + unsigned mce_in, mce_out; + + /* Count indicator to show errors not got */ + unsigned mce_overrun; +}; + +/* Static vars */ +static LIST_HEAD(i7core_edac_list); +static DEFINE_MUTEX(i7core_edac_lock); + +#define PCI_DESCR(device, function, device_id) \ + .dev = (device), \ + .func = (function), \ + .dev_id = (device_id) + +struct pci_id_descr pci_dev_descr_i7core_nehalem[] = { + /* Memory controller */ + { PCI_DESCR(3, 0, PCI_DEVICE_ID_INTEL_I7_MCR) }, + { PCI_DESCR(3, 1, PCI_DEVICE_ID_INTEL_I7_MC_TAD) }, + /* Exists only for RDIMM */ + { PCI_DESCR(3, 2, PCI_DEVICE_ID_INTEL_I7_MC_RAS), .optional = 1 }, + { PCI_DESCR(3, 4, PCI_DEVICE_ID_INTEL_I7_MC_TEST) }, + + /* Channel 0 */ + { PCI_DESCR(4, 0, PCI_DEVICE_ID_INTEL_I7_MC_CH0_CTRL) }, + { PCI_DESCR(4, 1, PCI_DEVICE_ID_INTEL_I7_MC_CH0_ADDR) }, + { PCI_DESCR(4, 2, PCI_DEVICE_ID_INTEL_I7_MC_CH0_RANK) }, + { PCI_DESCR(4, 3, PCI_DEVICE_ID_INTEL_I7_MC_CH0_TC) }, + + /* Channel 1 */ + { PCI_DESCR(5, 0, PCI_DEVICE_ID_INTEL_I7_MC_CH1_CTRL) }, + { PCI_DESCR(5, 1, PCI_DEVICE_ID_INTEL_I7_MC_CH1_ADDR) }, + { PCI_DESCR(5, 2, PCI_DEVICE_ID_INTEL_I7_MC_CH1_RANK) }, + { PCI_DESCR(5, 3, PCI_DEVICE_ID_INTEL_I7_MC_CH1_TC) }, + + /* Channel 2 */ + { PCI_DESCR(6, 0, PCI_DEVICE_ID_INTEL_I7_MC_CH2_CTRL) }, + { PCI_DESCR(6, 1, PCI_DEVICE_ID_INTEL_I7_MC_CH2_ADDR) }, + { PCI_DESCR(6, 2, PCI_DEVICE_ID_INTEL_I7_MC_CH2_RANK) }, + { PCI_DESCR(6, 3, PCI_DEVICE_ID_INTEL_I7_MC_CH2_TC) }, + + /* Generic Non-core registers */ + /* + * This is the PCI device on i7core and on Xeon 35xx (8086:2c41) + * On Xeon 55xx, however, it has a different id (8086:2c40). So, + * the probing code needs to test for the other address in case of + * failure of this one + */ + { PCI_DESCR(0, 0, PCI_DEVICE_ID_INTEL_I7_NONCORE) }, + +}; + +struct pci_id_descr pci_dev_descr_lynnfield[] = { + { PCI_DESCR( 3, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_MCR) }, + { PCI_DESCR( 3, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TAD) }, + { PCI_DESCR( 3, 4, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST) }, + + { PCI_DESCR( 4, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_CTRL) }, + { PCI_DESCR( 4, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_ADDR) }, + { PCI_DESCR( 4, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_RANK) }, + { PCI_DESCR( 4, 3, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_TC) }, + + { PCI_DESCR( 5, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_CTRL) }, + { PCI_DESCR( 5, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_ADDR) }, + { PCI_DESCR( 5, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_RANK) }, + { PCI_DESCR( 5, 3, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_TC) }, + + /* + * This is the PCI device has an alternate address on some + * processors like Core i7 860 + */ + { PCI_DESCR( 0, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE) }, +}; + +struct pci_id_descr pci_dev_descr_i7core_westmere[] = { + /* Memory controller */ + { PCI_DESCR(3, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_MCR_REV2) }, + { PCI_DESCR(3, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TAD_REV2) }, + /* Exists only for RDIMM */ + { PCI_DESCR(3, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_RAS_REV2), .optional = 1 }, + { PCI_DESCR(3, 4, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST_REV2) }, + + /* Channel 0 */ + { PCI_DESCR(4, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_CTRL_REV2) }, + { PCI_DESCR(4, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_ADDR_REV2) }, + { PCI_DESCR(4, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_RANK_REV2) }, + { PCI_DESCR(4, 3, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_TC_REV2) }, + + /* Channel 1 */ + { PCI_DESCR(5, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_CTRL_REV2) }, + { PCI_DESCR(5, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_ADDR_REV2) }, + { PCI_DESCR(5, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_RANK_REV2) }, + { PCI_DESCR(5, 3, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH1_TC_REV2) }, + + /* Channel 2 */ + { PCI_DESCR(6, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH2_CTRL_REV2) }, + { PCI_DESCR(6, 1, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH2_ADDR_REV2) }, + { PCI_DESCR(6, 2, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH2_RANK_REV2) }, + { PCI_DESCR(6, 3, PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH2_TC_REV2) }, + + /* Generic Non-core registers */ + { PCI_DESCR(0, 0, PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_REV2) }, + +}; + +#define PCI_ID_TABLE_ENTRY(A) { A, ARRAY_SIZE(A) } +struct pci_id_table pci_dev_table[] = { + PCI_ID_TABLE_ENTRY(pci_dev_descr_i7core_nehalem), + PCI_ID_TABLE_ENTRY(pci_dev_descr_lynnfield), + PCI_ID_TABLE_ENTRY(pci_dev_descr_i7core_westmere), +}; + +/* + * pci_device_id table for which devices we are looking for + */ +static const struct pci_device_id i7core_pci_tbl[] __devinitdata = { + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_X58_HUB_MGMT)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LYNNFIELD_QPI_LINK0)}, + {0,} /* 0 terminated list. */ +}; + +static struct edac_pci_ctl_info *i7core_pci; + +/**************************************************************************** + Anciliary status routines + ****************************************************************************/ + + /* MC_CONTROL bits */ +#define CH_ACTIVE(pvt, ch) ((pvt)->info.mc_control & (1 << (8 + ch))) +#define ECCx8(pvt) ((pvt)->info.mc_control & (1 << 1)) + + /* MC_STATUS bits */ +#define ECC_ENABLED(pvt) ((pvt)->info.mc_status & (1 << 4)) +#define CH_DISABLED(pvt, ch) ((pvt)->info.mc_status & (1 << ch)) + + /* MC_MAX_DOD read functions */ +static inline int numdimms(u32 dimms) +{ + return (dimms & 0x3) + 1; +} + +static inline int numrank(u32 rank) +{ + static int ranks[4] = { 1, 2, 4, -EINVAL }; + + return ranks[rank & 0x3]; +} + +static inline int numbank(u32 bank) +{ + static int banks[4] = { 4, 8, 16, -EINVAL }; + + return banks[bank & 0x3]; +} + +static inline int numrow(u32 row) +{ + static int rows[8] = { + 1 << 12, 1 << 13, 1 << 14, 1 << 15, + 1 << 16, -EINVAL, -EINVAL, -EINVAL, + }; + + return rows[row & 0x7]; +} + +static inline int numcol(u32 col) +{ + static int cols[8] = { + 1 << 10, 1 << 11, 1 << 12, -EINVAL, + }; + return cols[col & 0x3]; +} + +static struct i7core_dev *get_i7core_dev(u8 socket) +{ + struct i7core_dev *i7core_dev; + + list_for_each_entry(i7core_dev, &i7core_edac_list, list) { + if (i7core_dev->socket == socket) + return i7core_dev; + } + + return NULL; +} + +/**************************************************************************** + Memory check routines + ****************************************************************************/ +static struct pci_dev *get_pdev_slot_func(u8 socket, unsigned slot, + unsigned func) +{ + struct i7core_dev *i7core_dev = get_i7core_dev(socket); + int i; + + if (!i7core_dev) + return NULL; + + for (i = 0; i < i7core_dev->n_devs; i++) { + if (!i7core_dev->pdev[i]) + continue; + + if (PCI_SLOT(i7core_dev->pdev[i]->devfn) == slot && + PCI_FUNC(i7core_dev->pdev[i]->devfn) == func) { + return i7core_dev->pdev[i]; + } + } + + return NULL; +} + +/** + * i7core_get_active_channels() - gets the number of channels and csrows + * @socket: Quick Path Interconnect socket + * @channels: Number of channels that will be returned + * @csrows: Number of csrows found + * + * Since EDAC core needs to know in advance the number of available channels + * and csrows, in order to allocate memory for csrows/channels, it is needed + * to run two similar steps. At the first step, implemented on this function, + * it checks the number of csrows/channels present at one socket. + * this is used in order to properly allocate the size of mci components. + * + * It should be noticed that none of the current available datasheets explain + * or even mention how csrows are seen by the memory controller. So, we need + * to add a fake description for csrows. + * So, this driver is attributing one DIMM memory for one csrow. + */ +static int i7core_get_active_channels(u8 socket, unsigned *channels, + unsigned *csrows) +{ + struct pci_dev *pdev = NULL; + int i, j; + u32 status, control; + + *channels = 0; + *csrows = 0; + + pdev = get_pdev_slot_func(socket, 3, 0); + if (!pdev) { + i7core_printk(KERN_ERR, "Couldn't find socket %d fn 3.0!!!\n", + socket); + return -ENODEV; + } + + /* Device 3 function 0 reads */ + pci_read_config_dword(pdev, MC_STATUS, &status); + pci_read_config_dword(pdev, MC_CONTROL, &control); + + for (i = 0; i < NUM_CHANS; i++) { + u32 dimm_dod[3]; + /* Check if the channel is active */ + if (!(control & (1 << (8 + i)))) + continue; + + /* Check if the channel is disabled */ + if (status & (1 << i)) + continue; + + pdev = get_pdev_slot_func(socket, i + 4, 1); + if (!pdev) { + i7core_printk(KERN_ERR, "Couldn't find socket %d " + "fn %d.%d!!!\n", + socket, i + 4, 1); + return -ENODEV; + } + /* Devices 4-6 function 1 */ + pci_read_config_dword(pdev, + MC_DOD_CH_DIMM0, &dimm_dod[0]); + pci_read_config_dword(pdev, + MC_DOD_CH_DIMM1, &dimm_dod[1]); + pci_read_config_dword(pdev, + MC_DOD_CH_DIMM2, &dimm_dod[2]); + + (*channels)++; + + for (j = 0; j < 3; j++) { + if (!DIMM_PRESENT(dimm_dod[j])) + continue; + (*csrows)++; + } + } + + debugf0("Number of active channels on socket %d: %d\n", + socket, *channels); + + return 0; +} + +static int get_dimm_config(struct mem_ctl_info *mci, int *csrow) +{ + struct i7core_pvt *pvt = mci->pvt_info; + struct csrow_info *csr; + struct pci_dev *pdev; + int i, j; + unsigned long last_page = 0; + enum edac_type mode; + enum mem_type mtype; + + /* Get data from the MC register, function 0 */ + pdev = pvt->pci_mcr[0]; + if (!pdev) + return -ENODEV; + + /* Device 3 function 0 reads */ + pci_read_config_dword(pdev, MC_CONTROL, &pvt->info.mc_control); + pci_read_config_dword(pdev, MC_STATUS, &pvt->info.mc_status); + pci_read_config_dword(pdev, MC_MAX_DOD, &pvt->info.max_dod); + pci_read_config_dword(pdev, MC_CHANNEL_MAPPER, &pvt->info.ch_map); + + debugf0("QPI %d control=0x%08x status=0x%08x dod=0x%08x map=0x%08x\n", + pvt->i7core_dev->socket, pvt->info.mc_control, pvt->info.mc_status, + pvt->info.max_dod, pvt->info.ch_map); + + if (ECC_ENABLED(pvt)) { + debugf0("ECC enabled with x%d SDCC\n", ECCx8(pvt) ? 8 : 4); + if (ECCx8(pvt)) + mode = EDAC_S8ECD8ED; + else + mode = EDAC_S4ECD4ED; + } else { + debugf0("ECC disabled\n"); + mode = EDAC_NONE; + } + + /* FIXME: need to handle the error codes */ + debugf0("DOD Max limits: DIMMS: %d, %d-ranked, %d-banked " + "x%x x 0x%x\n", + numdimms(pvt->info.max_dod), + numrank(pvt->info.max_dod >> 2), + numbank(pvt->info.max_dod >> 4), + numrow(pvt->info.max_dod >> 6), + numcol(pvt->info.max_dod >> 9)); + + for (i = 0; i < NUM_CHANS; i++) { + u32 data, dimm_dod[3], value[8]; + + if (!pvt->pci_ch[i][0]) + continue; + + if (!CH_ACTIVE(pvt, i)) { + debugf0("Channel %i is not active\n", i); + continue; + } + if (CH_DISABLED(pvt, i)) { + debugf0("Channel %i is disabled\n", i); + continue; + } + + /* Devices 4-6 function 0 */ + pci_read_config_dword(pvt->pci_ch[i][0], + MC_CHANNEL_DIMM_INIT_PARAMS, &data); + + pvt->channel[i].ranks = (data & QUAD_RANK_PRESENT) ? + 4 : 2; + + if (d |