OpenCloudOS-Kernel/include/linux/edac.h

784 lines
24 KiB
C
Raw Normal View History

/*
* Generic EDAC defs
*
* Author: Dave Jiang <djiang@mvista.com>
*
* 2006-2008 (c) MontaVista Software, Inc. This file is licensed under
* the terms of the GNU General Public License version 2. This program
* is licensed "as is" without any warranty of any kind, whether express
* or implied.
*
*/
#ifndef _LINUX_EDAC_H_
#define _LINUX_EDAC_H_
#include <linux/atomic.h>
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
#include <linux/device.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/debugfs.h>
struct device;
#define EDAC_OPSTATE_INVAL -1
#define EDAC_OPSTATE_POLL 0
#define EDAC_OPSTATE_NMI 1
#define EDAC_OPSTATE_INT 2
extern int edac_op_state;
extern int edac_err_assert;
extern atomic_t edac_handlers;
extern int edac_handler_set(void);
extern void edac_atomic_assert_error(void);
extern struct bus_type *edac_get_sysfs_subsys(void);
enum {
EDAC_REPORTING_ENABLED,
EDAC_REPORTING_DISABLED,
EDAC_REPORTING_FORCE
};
extern int edac_report_status;
#ifdef CONFIG_EDAC
static inline int get_edac_report_status(void)
{
return edac_report_status;
}
static inline void set_edac_report_status(int new)
{
edac_report_status = new;
}
#else
static inline int get_edac_report_status(void)
{
return EDAC_REPORTING_DISABLED;
}
static inline void set_edac_report_status(int new)
{
}
#endif
static inline void opstate_init(void)
{
switch (edac_op_state) {
case EDAC_OPSTATE_POLL:
case EDAC_OPSTATE_NMI:
break;
default:
edac_op_state = EDAC_OPSTATE_POLL;
}
return;
}
/* Max length of a DIMM label*/
#define EDAC_MC_LABEL_LEN 31
/* Maximum size of the location string */
#define LOCATION_SIZE 256
/* Defines the maximum number of labels that can be reported */
#define EDAC_MAX_LABELS 8
/* String used to join two or more labels */
#define OTHER_LABEL " or "
/**
* enum dev_type - describe the type of memory DRAM chips used at the stick
* @DEV_UNKNOWN: Can't be determined, or MC doesn't support detect it
* @DEV_X1: 1 bit for data
* @DEV_X2: 2 bits for data
* @DEV_X4: 4 bits for data
* @DEV_X8: 8 bits for data
* @DEV_X16: 16 bits for data
* @DEV_X32: 32 bits for data
* @DEV_X64: 64 bits for data
*
* Typical values are x4 and x8.
*/
enum dev_type {
DEV_UNKNOWN = 0,
DEV_X1,
DEV_X2,
DEV_X4,
DEV_X8,
DEV_X16,
DEV_X32, /* Do these parts exist? */
DEV_X64 /* Do these parts exist? */
};
#define DEV_FLAG_UNKNOWN BIT(DEV_UNKNOWN)
#define DEV_FLAG_X1 BIT(DEV_X1)
#define DEV_FLAG_X2 BIT(DEV_X2)
#define DEV_FLAG_X4 BIT(DEV_X4)
#define DEV_FLAG_X8 BIT(DEV_X8)
#define DEV_FLAG_X16 BIT(DEV_X16)
#define DEV_FLAG_X32 BIT(DEV_X32)
#define DEV_FLAG_X64 BIT(DEV_X64)
/**
* enum hw_event_mc_err_type - type of the detected error
*
* @HW_EVENT_ERR_CORRECTED: Corrected Error - Indicates that an ECC
* corrected error was detected
* @HW_EVENT_ERR_UNCORRECTED: Uncorrected Error - Indicates an error that
* can't be corrected by ECC, but it is not
* fatal (maybe it is on an unused memory area,
* or the memory controller could recover from
* it for example, by re-trying the operation).
* @HW_EVENT_ERR_FATAL: Fatal Error - Uncorrected error that could not
* be recovered.
*/
enum hw_event_mc_err_type {
HW_EVENT_ERR_CORRECTED,
HW_EVENT_ERR_UNCORRECTED,
HW_EVENT_ERR_FATAL,
HW_EVENT_ERR_INFO,
};
static inline char *mc_event_error_type(const unsigned int err_type)
{
switch (err_type) {
case HW_EVENT_ERR_CORRECTED:
return "Corrected";
case HW_EVENT_ERR_UNCORRECTED:
return "Uncorrected";
case HW_EVENT_ERR_FATAL:
return "Fatal";
default:
case HW_EVENT_ERR_INFO:
return "Info";
}
}
/**
* enum mem_type - memory types. For a more detailed reference, please see
* http://en.wikipedia.org/wiki/DRAM
*
* @MEM_EMPTY Empty csrow
* @MEM_RESERVED: Reserved csrow type
* @MEM_UNKNOWN: Unknown csrow type
* @MEM_FPM: FPM - Fast Page Mode, used on systems up to 1995.
* @MEM_EDO: EDO - Extended data out, used on systems up to 1998.
* @MEM_BEDO: BEDO - Burst Extended data out, an EDO variant.
* @MEM_SDR: SDR - Single data rate SDRAM
* http://en.wikipedia.org/wiki/Synchronous_dynamic_random-access_memory
* They use 3 pins for chip select: Pins 0 and 2 are
* for rank 0; pins 1 and 3 are for rank 1, if the memory
* is dual-rank.
* @MEM_RDR: Registered SDR SDRAM
* @MEM_DDR: Double data rate SDRAM
* http://en.wikipedia.org/wiki/DDR_SDRAM
* @MEM_RDDR: Registered Double data rate SDRAM
* This is a variant of the DDR memories.
* A registered memory has a buffer inside it, hiding
* part of the memory details to the memory controller.
* @MEM_RMBS: Rambus DRAM, used on a few Pentium III/IV controllers.
* @MEM_DDR2: DDR2 RAM, as described at JEDEC JESD79-2F.
* Those memories are labed as "PC2-" instead of "PC" to
* differenciate from DDR.
* @MEM_FB_DDR2: Fully-Buffered DDR2, as described at JEDEC Std No. 205
* and JESD206.
* Those memories are accessed per DIMM slot, and not by
* a chip select signal.
* @MEM_RDDR2: Registered DDR2 RAM
* This is a variant of the DDR2 memories.
* @MEM_XDR: Rambus XDR
* It is an evolution of the original RAMBUS memories,
* created to compete with DDR2. Weren't used on any
* x86 arch, but cell_edac PPC memory controller uses it.
* @MEM_DDR3: DDR3 RAM
* @MEM_RDDR3: Registered DDR3 RAM
* This is a variant of the DDR3 memories.
* @MEM_LRDDR3 Load-Reduced DDR3 memory.
* @MEM_DDR4: Unbuffered DDR4 RAM
* @MEM_RDDR4: Registered DDR4 RAM
* This is a variant of the DDR4 memories.
*/
enum mem_type {
MEM_EMPTY = 0,
MEM_RESERVED,
MEM_UNKNOWN,
MEM_FPM,
MEM_EDO,
MEM_BEDO,
MEM_SDR,
MEM_RDR,
MEM_DDR,
MEM_RDDR,
MEM_RMBS,
MEM_DDR2,
MEM_FB_DDR2,
MEM_RDDR2,
MEM_XDR,
MEM_DDR3,
MEM_RDDR3,
MEM_LRDDR3,
MEM_DDR4,
MEM_RDDR4,
};
#define MEM_FLAG_EMPTY BIT(MEM_EMPTY)
#define MEM_FLAG_RESERVED BIT(MEM_RESERVED)
#define MEM_FLAG_UNKNOWN BIT(MEM_UNKNOWN)
#define MEM_FLAG_FPM BIT(MEM_FPM)
#define MEM_FLAG_EDO BIT(MEM_EDO)
#define MEM_FLAG_BEDO BIT(MEM_BEDO)
#define MEM_FLAG_SDR BIT(MEM_SDR)
#define MEM_FLAG_RDR BIT(MEM_RDR)
#define MEM_FLAG_DDR BIT(MEM_DDR)
#define MEM_FLAG_RDDR BIT(MEM_RDDR)
#define MEM_FLAG_RMBS BIT(MEM_RMBS)
#define MEM_FLAG_DDR2 BIT(MEM_DDR2)
#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2)
#define MEM_FLAG_RDDR2 BIT(MEM_RDDR2)
#define MEM_FLAG_XDR BIT(MEM_XDR)
#define MEM_FLAG_DDR3 BIT(MEM_DDR3)
#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3)
#define MEM_FLAG_DDR4 BIT(MEM_DDR4)
#define MEM_FLAG_RDDR4 BIT(MEM_RDDR4)
/**
* enum edac-type - Error Detection and Correction capabilities and mode
* @EDAC_UNKNOWN: Unknown if ECC is available
* @EDAC_NONE: Doesn't support ECC
* @EDAC_RESERVED: Reserved ECC type
* @EDAC_PARITY: Detects parity errors
* @EDAC_EC: Error Checking - no correction
* @EDAC_SECDED: Single bit error correction, Double detection
* @EDAC_S2ECD2ED: Chipkill x2 devices - do these exist?
* @EDAC_S4ECD4ED: Chipkill x4 devices
* @EDAC_S8ECD8ED: Chipkill x8 devices
* @EDAC_S16ECD16ED: Chipkill x16 devices
*/
enum edac_type {
EDAC_UNKNOWN = 0,
EDAC_NONE,
EDAC_RESERVED,
EDAC_PARITY,
EDAC_EC,
EDAC_SECDED,
EDAC_S2ECD2ED,
EDAC_S4ECD4ED,
EDAC_S8ECD8ED,
EDAC_S16ECD16ED,
};
#define EDAC_FLAG_UNKNOWN BIT(EDAC_UNKNOWN)
#define EDAC_FLAG_NONE BIT(EDAC_NONE)
#define EDAC_FLAG_PARITY BIT(EDAC_PARITY)
#define EDAC_FLAG_EC BIT(EDAC_EC)
#define EDAC_FLAG_SECDED BIT(EDAC_SECDED)
#define EDAC_FLAG_S2ECD2ED BIT(EDAC_S2ECD2ED)
#define EDAC_FLAG_S4ECD4ED BIT(EDAC_S4ECD4ED)
#define EDAC_FLAG_S8ECD8ED BIT(EDAC_S8ECD8ED)
#define EDAC_FLAG_S16ECD16ED BIT(EDAC_S16ECD16ED)
/**
* enum scrub_type - scrubbing capabilities
* @SCRUB_UNKNOWN Unknown if scrubber is available
* @SCRUB_NONE: No scrubber
* @SCRUB_SW_PROG: SW progressive (sequential) scrubbing
* @SCRUB_SW_SRC: Software scrub only errors
* @SCRUB_SW_PROG_SRC: Progressive software scrub from an error
* @SCRUB_SW_TUNABLE: Software scrub frequency is tunable
* @SCRUB_HW_PROG: HW progressive (sequential) scrubbing
* @SCRUB_HW_SRC: Hardware scrub only errors
* @SCRUB_HW_PROG_SRC: Progressive hardware scrub from an error
* SCRUB_HW_TUNABLE: Hardware scrub frequency is tunable
*/
enum scrub_type {
SCRUB_UNKNOWN = 0,
SCRUB_NONE,
SCRUB_SW_PROG,
SCRUB_SW_SRC,
SCRUB_SW_PROG_SRC,
SCRUB_SW_TUNABLE,
SCRUB_HW_PROG,
SCRUB_HW_SRC,
SCRUB_HW_PROG_SRC,
SCRUB_HW_TUNABLE
};
#define SCRUB_FLAG_SW_PROG BIT(SCRUB_SW_PROG)
#define SCRUB_FLAG_SW_SRC BIT(SCRUB_SW_SRC)
#define SCRUB_FLAG_SW_PROG_SRC BIT(SCRUB_SW_PROG_SRC)
#define SCRUB_FLAG_SW_TUN BIT(SCRUB_SW_SCRUB_TUNABLE)
#define SCRUB_FLAG_HW_PROG BIT(SCRUB_HW_PROG)
#define SCRUB_FLAG_HW_SRC BIT(SCRUB_HW_SRC)
#define SCRUB_FLAG_HW_PROG_SRC BIT(SCRUB_HW_PROG_SRC)
#define SCRUB_FLAG_HW_TUN BIT(SCRUB_HW_TUNABLE)
/* FIXME - should have notify capabilities: NMI, LOG, PROC, etc */
/* EDAC internal operation states */
#define OP_ALLOC 0x100
#define OP_RUNNING_POLL 0x201
#define OP_RUNNING_INTERRUPT 0x202
#define OP_RUNNING_POLL_INTR 0x203
#define OP_OFFLINE 0x300
/*
* Concepts used at the EDAC subsystem
*
* There are several things to be aware of that aren't at all obvious:
*
* SOCKETS, SOCKET SETS, BANKS, ROWS, CHIP-SELECT ROWS, CHANNELS, etc..
*
* These are some of the many terms that are thrown about that don't always
* mean what people think they mean (Inconceivable!). In the interest of
* creating a common ground for discussion, terms and their definitions
* will be established.
*
* Memory devices: The individual DRAM chips on a memory stick. These
* devices commonly output 4 and 8 bits each (x4, x8).
* Grouping several of these in parallel provides the
* number of bits that the memory controller expects:
* typically 72 bits, in order to provide 64 bits +
* 8 bits of ECC data.
*
* Memory Stick: A printed circuit board that aggregates multiple
* memory devices in parallel. In general, this is the
* Field Replaceable Unit (FRU) which gets replaced, in
* the case of excessive errors. Most often it is also
* called DIMM (Dual Inline Memory Module).
*
* Memory Socket: A physical connector on the motherboard that accepts
* a single memory stick. Also called as "slot" on several
* datasheets.
*
* Channel: A memory controller channel, responsible to communicate
* with a group of DIMMs. Each channel has its own
* independent control (command) and data bus, and can
* be used independently or grouped with other channels.
*
* Branch: It is typically the highest hierarchy on a
* Fully-Buffered DIMM memory controller.
* Typically, it contains two channels.
* Two channels at the same branch can be used in single
* mode or in lockstep mode.
* When lockstep is enabled, the cacheline is doubled,
* but it generally brings some performance penalty.
* Also, it is generally not possible to point to just one
* memory stick when an error occurs, as the error
* correction code is calculated using two DIMMs instead
* of one. Due to that, it is capable of correcting more
* errors than on single mode.
*
* Single-channel: The data accessed by the memory controller is contained
* into one dimm only. E. g. if the data is 64 bits-wide,
* the data flows to the CPU using one 64 bits parallel
* access.
* Typically used with SDR, DDR, DDR2 and DDR3 memories.
* FB-DIMM and RAMBUS use a different concept for channel,
* so this concept doesn't apply there.
*
* Double-channel: The data size accessed by the memory controller is
* interlaced into two dimms, accessed at the same time.
* E. g. if the DIMM is 64 bits-wide (72 bits with ECC),
* the data flows to the CPU using a 128 bits parallel
* access.
*
* Chip-select row: This is the name of the DRAM signal used to select the
* DRAM ranks to be accessed. Common chip-select rows for
* single channel are 64 bits, for dual channel 128 bits.
* It may not be visible by the memory controller, as some
* DIMM types have a memory buffer that can hide direct
* access to it from the Memory Controller.
*
* Single-Ranked stick: A Single-ranked stick has 1 chip-select row of memory.
* Motherboards commonly drive two chip-select pins to
* a memory stick. A single-ranked stick, will occupy
* only one of those rows. The other will be unused.
*
* Double-Ranked stick: A double-ranked stick has two chip-select rows which
* access different sets of memory devices. The two
* rows cannot be accessed concurrently.
*
* Double-sided stick: DEPRECATED TERM, see Double-Ranked stick.
* A double-sided stick has two chip-select rows which
* access different sets of memory devices. The two
* rows cannot be accessed concurrently. "Double-sided"
* is irrespective of the memory devices being mounted
* on both sides of the memory stick.
*
* Socket set: All of the memory sticks that are required for
* a single memory access or all of the memory sticks
* spanned by a chip-select row. A single socket set
* has two chip-select rows and if double-sided sticks
* are used these will occupy those chip-select rows.
*
* Bank: This term is avoided because it is unclear when
* needing to distinguish between chip-select rows and
* socket sets.
*
* Controller pages:
*
* Physical pages:
*
* Virtual pages:
*
*
* STRUCTURE ORGANIZATION AND CHOICES
*
*
*
* PS - I enjoyed writing all that about as much as you enjoyed reading it.
*/
/**
* enum edac_mc_layer - memory controller hierarchy layer
*
* @EDAC_MC_LAYER_BRANCH: memory layer is named "branch"
* @EDAC_MC_LAYER_CHANNEL: memory layer is named "channel"
* @EDAC_MC_LAYER_SLOT: memory layer is named "slot"
* @EDAC_MC_LAYER_CHIP_SELECT: memory layer is named "chip select"
* @EDAC_MC_LAYER_ALL_MEM: memory layout is unknown. All memory is mapped
* as a single memory area. This is used when
* retrieving errors from a firmware driven driver.
*
* This enum is used by the drivers to tell edac_mc_sysfs what name should
* be used when describing a memory stick location.
*/
enum edac_mc_layer_type {
EDAC_MC_LAYER_BRANCH,
EDAC_MC_LAYER_CHANNEL,
EDAC_MC_LAYER_SLOT,
EDAC_MC_LAYER_CHIP_SELECT,
EDAC_MC_LAYER_ALL_MEM,
};
/**
* struct edac_mc_layer - describes the memory controller hierarchy
* @layer: layer type
* @size: number of components per layer. For example,
* if the channel layer has two channels, size = 2
* @is_virt_csrow: This layer is part of the "csrow" when old API
* compatibility mode is enabled. Otherwise, it is
* a channel
*/
struct edac_mc_layer {
enum edac_mc_layer_type type;
unsigned size;
bool is_virt_csrow;
};
/*
* Maximum number of layers used by the memory controller to uniquely
* identify a single memory stick.
* NOTE: Changing this constant requires not only to change the constant
* below, but also to change the existing code at the core, as there are
* some code there that are optimized for 3 layers.
*/
#define EDAC_MAX_LAYERS 3
/**
* EDAC_DIMM_OFF - Macro responsible to get a pointer offset inside a pointer array
* for the element given by [layer0,layer1,layer2] position
*
* @layers: a struct edac_mc_layer array, describing how many elements
* were allocated for each layer
* @n_layers: Number of layers at the @layers array
* @layer0: layer0 position
* @layer1: layer1 position. Unused if n_layers < 2
* @layer2: layer2 position. Unused if n_layers < 3
*
* For 1 layer, this macro returns &var[layer0] - &var
* For 2 layers, this macro is similar to allocate a bi-dimensional array
* and to return "&var[layer0][layer1] - &var"
* For 3 layers, this macro is similar to allocate a tri-dimensional array
* and to return "&var[layer0][layer1][layer2] - &var"
*
* A loop could be used here to make it more generic, but, as we only have
* 3 layers, this is a little faster.
* By design, layers can never be 0 or more than 3. If that ever happens,
* a NULL is returned, causing an OOPS during the memory allocation routine,
* with would point to the developer that he's doing something wrong.
*/
#define EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2) ({ \
int __i; \
if ((nlayers) == 1) \
__i = layer0; \
else if ((nlayers) == 2) \
__i = (layer1) + ((layers[1]).size * (layer0)); \
else if ((nlayers) == 3) \
__i = (layer2) + ((layers[2]).size * ((layer1) + \
((layers[1]).size * (layer0)))); \
else \
__i = -EINVAL; \
__i; \
})
/**
* EDAC_DIMM_PTR - Macro responsible to get a pointer inside a pointer array
* for the element given by [layer0,layer1,layer2] position
*
* @layers: a struct edac_mc_layer array, describing how many elements
* were allocated for each layer
* @var: name of the var where we want to get the pointer
* (like mci->dimms)
* @n_layers: Number of layers at the @layers array
* @layer0: layer0 position
* @layer1: layer1 position. Unused if n_layers < 2
* @layer2: layer2 position. Unused if n_layers < 3
*
* For 1 layer, this macro returns &var[layer0]
* For 2 layers, this macro is similar to allocate a bi-dimensional array
* and to return "&var[layer0][layer1]"
* For 3 layers, this macro is similar to allocate a tri-dimensional array
* and to return "&var[layer0][layer1][layer2]"
*/
#define EDAC_DIMM_PTR(layers, var, nlayers, layer0, layer1, layer2) ({ \
typeof(*var) __p; \
int ___i = EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2); \
if (___i < 0) \
__p = NULL; \
else \
__p = (var)[___i]; \
__p; \
})
edac: Create a dimm struct and move the labels into it The way a DIMM is currently represented implies that they're linked into a per-csrow struct. However, some drivers don't see csrows, as they're ridden behind some chip like the AMB's on FBDIMM's, for example. This forced drivers to fake^Wvirtualize a csrow struct, and to create a mess under csrow/channel original's concept. Move the DIMM labels into a per-DIMM struct, and add there the real location of the socket, in terms of csrow/channel. Latter patches will modify the location to properly represent the memory architecture. All other drivers will use a per-csrow type of location. Some of those drivers will require a latter conversion, as they also fake the csrows internally. TODO: While this patch doesn't change the existing behavior, on csrows-based memory controllers, a csrow/channel pair points to a memory rank. There's a known bug at the EDAC core that allows having different labels for the same DIMM, if it has more than one rank. A latter patch is need to merge the several ranks for a DIMM into the same dimm_info struct, in order to avoid having different labels for the same DIMM. The edac_mc_alloc() will now contain a per-dimm initialization loop that will be changed by latter patches in order to match other types of memory architectures. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 01:12:32 +08:00
struct dimm_info {
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
struct device dev;
edac: Create a dimm struct and move the labels into it The way a DIMM is currently represented implies that they're linked into a per-csrow struct. However, some drivers don't see csrows, as they're ridden behind some chip like the AMB's on FBDIMM's, for example. This forced drivers to fake^Wvirtualize a csrow struct, and to create a mess under csrow/channel original's concept. Move the DIMM labels into a per-DIMM struct, and add there the real location of the socket, in terms of csrow/channel. Latter patches will modify the location to properly represent the memory architecture. All other drivers will use a per-csrow type of location. Some of those drivers will require a latter conversion, as they also fake the csrows internally. TODO: While this patch doesn't change the existing behavior, on csrows-based memory controllers, a csrow/channel pair points to a memory rank. There's a known bug at the EDAC core that allows having different labels for the same DIMM, if it has more than one rank. A latter patch is need to merge the several ranks for a DIMM into the same dimm_info struct, in order to avoid having different labels for the same DIMM. The edac_mc_alloc() will now contain a per-dimm initialization loop that will be changed by latter patches in order to match other types of memory architectures. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 01:12:32 +08:00
char label[EDAC_MC_LABEL_LEN + 1]; /* DIMM label on motherboard */
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
/* Memory location data */
unsigned location[EDAC_MAX_LAYERS];
struct mem_ctl_info *mci; /* the parent */
edac: move dimm properties to struct dimm_info On systems based on chip select rows, all channels need to use memories with the same properties, otherwise the memories on channels A and B won't be recognized. However, such assumption is not true for all types of memory controllers. Controllers for FB-DIMM's don't have such requirements. Also, modern Intel controllers seem to be capable of handling such differences. So, we need to get rid of storing the DIMM information into a per-csrow data, storing it, instead at the right place. The first step is to move grain, mtype, dtype and edac_mode to the per-dimm struct. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Acked-by: Chris Metcalf <cmetcalf@tilera.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: James Bottomley <James.Bottomley@parallels.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: Mike Williams <mike@mikebwilliams.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 05:38:08 +08:00
u32 grain; /* granularity of reported error in bytes */
enum dev_type dtype; /* memory device type */
enum mem_type mtype; /* memory dimm type */
enum edac_type edac_mode; /* EDAC mode for this dimm */
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
u32 nr_pages; /* number of pages on this dimm */
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
unsigned csrow, cschannel; /* Points to the old API data */
edac: Create a dimm struct and move the labels into it The way a DIMM is currently represented implies that they're linked into a per-csrow struct. However, some drivers don't see csrows, as they're ridden behind some chip like the AMB's on FBDIMM's, for example. This forced drivers to fake^Wvirtualize a csrow struct, and to create a mess under csrow/channel original's concept. Move the DIMM labels into a per-DIMM struct, and add there the real location of the socket, in terms of csrow/channel. Latter patches will modify the location to properly represent the memory architecture. All other drivers will use a per-csrow type of location. Some of those drivers will require a latter conversion, as they also fake the csrows internally. TODO: While this patch doesn't change the existing behavior, on csrows-based memory controllers, a csrow/channel pair points to a memory rank. There's a known bug at the EDAC core that allows having different labels for the same DIMM, if it has more than one rank. A latter patch is need to merge the several ranks for a DIMM into the same dimm_info struct, in order to avoid having different labels for the same DIMM. The edac_mc_alloc() will now contain a per-dimm initialization loop that will be changed by latter patches in order to match other types of memory architectures. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 01:12:32 +08:00
};
edac: rename channel_info to rank_info What it is pointed by a csrow/channel vector is a rank information, and not a channel information. On a traditional architecture, the memory controller directly access the memory ranks, via chip select rows. Different ranks at the same DIMM is selected via different chip select rows. So, typically, one csrow/channel pair means one different DIMM. On FB-DIMMs, there's a microcontroller chip at the DIMM, called Advanced Memory Buffer (AMB) that serves as the interface between the memory controller and the memory chips. The AMB selection is via the DIMM slot, and not via a csrow. It is up to the AMB to talk with the csrows of the DRAM chips. So, the FB-DIMM memory controllers see the DIMM slot, and not the DIMM rank. RAMBUS is similar. Newer memory controllers, like the ones found on Intel Sandy Bridge and Nehalem, even working with normal DDR3 DIMM's, don't use the usual channel A/channel B interleaving schema to provide 128 bits data access. Instead, they have more channels (3 or 4 channels), and they can use several interleaving schemas. Such memory controllers see the DIMMs directly on their registers, instead of the ranks, which is better for the driver, as its main usageis to point to a broken DIMM stick (the Field Repleceable Unit), and not to point to a broken DRAM chip. The drivers that support such such newer memory architecture models currently need to fake information and to abuse on EDAC structures, as the subsystem was conceived with the idea that the csrow would always be visible by the CPU. To make things a little worse, those drivers don't currently fake csrows/channels on a consistent way, as the concepts there don't apply to the memory controllers they're talking with. So, each driver author interpreted the concepts using a different logic. In order to fix it, let's rename the data structure that points into a DIMM rank to "rank_info", in order to be clearer about what's stored there. Latter patches will provide a better way to represent the memory hierarchy for the other types of memory controller. Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-27 21:26:13 +08:00
/**
* struct rank_info - contains the information for one DIMM rank
*
* @chan_idx: channel number where the rank is (typically, 0 or 1)
* @ce_count: number of correctable errors for this rank
* @csrow: A pointer to the chip select row structure (the parent
* structure). The location of the rank is given by
* the (csrow->csrow_idx, chan_idx) vector.
edac: Create a dimm struct and move the labels into it The way a DIMM is currently represented implies that they're linked into a per-csrow struct. However, some drivers don't see csrows, as they're ridden behind some chip like the AMB's on FBDIMM's, for example. This forced drivers to fake^Wvirtualize a csrow struct, and to create a mess under csrow/channel original's concept. Move the DIMM labels into a per-DIMM struct, and add there the real location of the socket, in terms of csrow/channel. Latter patches will modify the location to properly represent the memory architecture. All other drivers will use a per-csrow type of location. Some of those drivers will require a latter conversion, as they also fake the csrows internally. TODO: While this patch doesn't change the existing behavior, on csrows-based memory controllers, a csrow/channel pair points to a memory rank. There's a known bug at the EDAC core that allows having different labels for the same DIMM, if it has more than one rank. A latter patch is need to merge the several ranks for a DIMM into the same dimm_info struct, in order to avoid having different labels for the same DIMM. The edac_mc_alloc() will now contain a per-dimm initialization loop that will be changed by latter patches in order to match other types of memory architectures. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 01:12:32 +08:00
* @dimm: A pointer to the DIMM structure, where the DIMM label
* information is stored.
*
* FIXME: Currently, the EDAC core model will assume one DIMM per rank.
* This is a bad assumption, but it makes this patch easier. Later
* patches in this series will fix this issue.
edac: rename channel_info to rank_info What it is pointed by a csrow/channel vector is a rank information, and not a channel information. On a traditional architecture, the memory controller directly access the memory ranks, via chip select rows. Different ranks at the same DIMM is selected via different chip select rows. So, typically, one csrow/channel pair means one different DIMM. On FB-DIMMs, there's a microcontroller chip at the DIMM, called Advanced Memory Buffer (AMB) that serves as the interface between the memory controller and the memory chips. The AMB selection is via the DIMM slot, and not via a csrow. It is up to the AMB to talk with the csrows of the DRAM chips. So, the FB-DIMM memory controllers see the DIMM slot, and not the DIMM rank. RAMBUS is similar. Newer memory controllers, like the ones found on Intel Sandy Bridge and Nehalem, even working with normal DDR3 DIMM's, don't use the usual channel A/channel B interleaving schema to provide 128 bits data access. Instead, they have more channels (3 or 4 channels), and they can use several interleaving schemas. Such memory controllers see the DIMMs directly on their registers, instead of the ranks, which is better for the driver, as its main usageis to point to a broken DIMM stick (the Field Repleceable Unit), and not to point to a broken DRAM chip. The drivers that support such such newer memory architecture models currently need to fake information and to abuse on EDAC structures, as the subsystem was conceived with the idea that the csrow would always be visible by the CPU. To make things a little worse, those drivers don't currently fake csrows/channels on a consistent way, as the concepts there don't apply to the memory controllers they're talking with. So, each driver author interpreted the concepts using a different logic. In order to fix it, let's rename the data structure that points into a DIMM rank to "rank_info", in order to be clearer about what's stored there. Latter patches will provide a better way to represent the memory hierarchy for the other types of memory controller. Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-27 21:26:13 +08:00
*/
struct rank_info {
int chan_idx;
edac: Create a dimm struct and move the labels into it The way a DIMM is currently represented implies that they're linked into a per-csrow struct. However, some drivers don't see csrows, as they're ridden behind some chip like the AMB's on FBDIMM's, for example. This forced drivers to fake^Wvirtualize a csrow struct, and to create a mess under csrow/channel original's concept. Move the DIMM labels into a per-DIMM struct, and add there the real location of the socket, in terms of csrow/channel. Latter patches will modify the location to properly represent the memory architecture. All other drivers will use a per-csrow type of location. Some of those drivers will require a latter conversion, as they also fake the csrows internally. TODO: While this patch doesn't change the existing behavior, on csrows-based memory controllers, a csrow/channel pair points to a memory rank. There's a known bug at the EDAC core that allows having different labels for the same DIMM, if it has more than one rank. A latter patch is need to merge the several ranks for a DIMM into the same dimm_info struct, in order to avoid having different labels for the same DIMM. The edac_mc_alloc() will now contain a per-dimm initialization loop that will be changed by latter patches in order to match other types of memory architectures. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 01:12:32 +08:00
struct csrow_info *csrow;
struct dimm_info *dimm;
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
u32 ce_count; /* Correctable Errors for this csrow */
};
struct csrow_info {
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
struct device dev;
/* Used only by edac_mc_find_csrow_by_page() */
edac: move dimm properties to struct dimm_info On systems based on chip select rows, all channels need to use memories with the same properties, otherwise the memories on channels A and B won't be recognized. However, such assumption is not true for all types of memory controllers. Controllers for FB-DIMM's don't have such requirements. Also, modern Intel controllers seem to be capable of handling such differences. So, we need to get rid of storing the DIMM information into a per-csrow data, storing it, instead at the right place. The first step is to move grain, mtype, dtype and edac_mode to the per-dimm struct. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Acked-by: Chris Metcalf <cmetcalf@tilera.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: James Bottomley <James.Bottomley@parallels.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: Mike Williams <mike@mikebwilliams.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 05:38:08 +08:00
unsigned long first_page; /* first page number in csrow */
unsigned long last_page; /* last page number in csrow */
unsigned long page_mask; /* used for interleaving -
* 0UL for non intlv */
edac: move dimm properties to struct dimm_info On systems based on chip select rows, all channels need to use memories with the same properties, otherwise the memories on channels A and B won't be recognized. However, such assumption is not true for all types of memory controllers. Controllers for FB-DIMM's don't have such requirements. Also, modern Intel controllers seem to be capable of handling such differences. So, we need to get rid of storing the DIMM information into a per-csrow data, storing it, instead at the right place. The first step is to move grain, mtype, dtype and edac_mode to the per-dimm struct. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Acked-by: Chris Metcalf <cmetcalf@tilera.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: James Bottomley <James.Bottomley@parallels.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: Mike Williams <mike@mikebwilliams.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 05:38:08 +08:00
int csrow_idx; /* the chip-select row */
u32 ue_count; /* Uncorrectable Errors for this csrow */
u32 ce_count; /* Correctable Errors for this csrow */
edac: move dimm properties to struct dimm_info On systems based on chip select rows, all channels need to use memories with the same properties, otherwise the memories on channels A and B won't be recognized. However, such assumption is not true for all types of memory controllers. Controllers for FB-DIMM's don't have such requirements. Also, modern Intel controllers seem to be capable of handling such differences. So, we need to get rid of storing the DIMM information into a per-csrow data, storing it, instead at the right place. The first step is to move grain, mtype, dtype and edac_mode to the per-dimm struct. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Acked-by: Chris Metcalf <cmetcalf@tilera.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: James Bottomley <James.Bottomley@parallels.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: Mike Williams <mike@mikebwilliams.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 05:38:08 +08:00
struct mem_ctl_info *mci; /* the parent */
/* channel information for this csrow */
u32 nr_channels;
struct rank_info **channels;
};
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
/*
* struct errcount_attribute - used to store the several error counts
*/
struct errcount_attribute_data {
int n_layers;
int pos[EDAC_MAX_LAYERS];
int layer0, layer1, layer2;
};
/**
* edac_raw_error_desc - Raw error report structure
* @grain: minimum granularity for an error report, in bytes
* @error_count: number of errors of the same type
* @top_layer: top layer of the error (layer[0])
* @mid_layer: middle layer of the error (layer[1])
* @low_layer: low layer of the error (layer[2])
* @page_frame_number: page where the error happened
* @offset_in_page: page offset
* @syndrome: syndrome of the error (or 0 if unknown or if
* the syndrome is not applicable)
* @msg: error message
* @location: location of the error
* @label: label of the affected DIMM(s)
* @other_detail: other driver-specific detail about the error
* @enable_per_layer_report: if false, the error affects all layers
* (typically, a memory controller error)
*/
struct edac_raw_error_desc {
/*
* NOTE: everything before grain won't be cleaned by
* edac_raw_error_desc_clean()
*/
char location[LOCATION_SIZE];
char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * EDAC_MAX_LABELS];
long grain;
/* the vars below and grain will be cleaned on every new error report */
u16 error_count;
int top_layer;
int mid_layer;
int low_layer;
unsigned long page_frame_number;
unsigned long offset_in_page;
unsigned long syndrome;
const char *msg;
const char *other_detail;
bool enable_per_layer_report;
};
/* MEMORY controller information structure
*/
struct mem_ctl_info {
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
struct device dev;
EDAC: Fix lockdep splat Fix the following: BUG: key ffff88043bdd0330 not in .data! ------------[ cut here ]------------ WARNING: at kernel/lockdep.c:2987 lockdep_init_map+0x565/0x5a0() DEBUG_LOCKS_WARN_ON(1) Modules linked in: glue_helper sb_edac(+) edac_core snd acpi_cpufreq lrw gf128mul ablk_helper iTCO_wdt evdev i2c_i801 dcdbas button cryptd pcspkr iTCO_vendor_support usb_common lpc_ich mfd_core soundcore mperf processor microcode CPU: 2 PID: 599 Comm: modprobe Not tainted 3.10.0 #1 Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013 0000000000000009 ffff880439a1d920 ffffffff8160a9a9 ffff880439a1d958 ffffffff8103d9e0 ffff88043af4a510 ffffffff81a16e11 0000000000000000 ffff88043bdd0330 0000000000000000 ffff880439a1d9b8 ffffffff8103dacc Call Trace: dump_stack warn_slowpath_common warn_slowpath_fmt lockdep_init_map ? trace_hardirqs_on_caller ? trace_hardirqs_on debug_mutex_init __mutex_init bus_register edac_create_sysfs_mci_device edac_mc_add_mc sbridge_probe pci_device_probe driver_probe_device __driver_attach ? driver_probe_device bus_for_each_dev driver_attach bus_add_driver driver_register __pci_register_driver ? 0xffffffffa0010fff sbridge_init ? 0xffffffffa0010fff do_one_initcall load_module ? unset_module_init_ro_nx SyS_init_module tracesys ---[ end trace d24a70b0d3ddf733 ]--- EDAC MC0: Giving out device to 'sbridge_edac.c' 'Sandy Bridge Socket#0': DEV 0000:3f:0e.0 EDAC sbridge: Driver loaded. What happens is that bus_register needs a statically allocated lock_key because the last is handed in to lockdep. However, struct mem_ctl_info embeds struct bus_type (the whole struct, not a pointer to it) and the whole thing gets dynamically allocated. Fix this by using a statically allocated struct bus_type for the MC bus. Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: stable@kernel.org # v3.10 Signed-off-by: Tony Luck <tony.luck@intel.com>
2013-07-19 18:28:25 +08:00
struct bus_type *bus;
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
struct list_head link; /* for global list of mem_ctl_info structs */
struct module *owner; /* Module owner of this control struct */
unsigned long mtype_cap; /* memory types supported by mc */
unsigned long edac_ctl_cap; /* Mem controller EDAC capabilities */
unsigned long edac_cap; /* configuration capabilities - this is
* closely related to edac_ctl_cap. The
* difference is that the controller may be
* capable of s4ecd4ed which would be listed
* in edac_ctl_cap, but if channels aren't
* capable of s4ecd4ed then the edac_cap would
* not have that capability.
*/
unsigned long scrub_cap; /* chipset scrub capabilities */
enum scrub_type scrub_mode; /* current scrub mode */
/* Translates sdram memory scrub rate given in bytes/sec to the
internal representation and configures whatever else needs
to be configured.
*/
int (*set_sdram_scrub_rate) (struct mem_ctl_info * mci, u32 bw);
/* Get the current sdram memory scrub rate from the internal
representation and converts it to the closest matching
bandwidth in bytes/sec.
*/
int (*get_sdram_scrub_rate) (struct mem_ctl_info * mci);
/* pointer to edac checking routine */
void (*edac_check) (struct mem_ctl_info * mci);
/*
* Remaps memory pages: controller pages to physical pages.
* For most MC's, this will be NULL.
*/
/* FIXME - why not send the phys page to begin with? */
unsigned long (*ctl_page_to_phys) (struct mem_ctl_info * mci,
unsigned long page);
int mc_idx;
struct csrow_info **csrows;
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
unsigned nr_csrows, num_cschannel;
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
/*
* Memory Controller hierarchy
*
* There are basically two types of memory controller: the ones that
* sees memory sticks ("dimms"), and the ones that sees memory ranks.
* All old memory controllers enumerate memories per rank, but most
* of the recent drivers enumerate memories per DIMM, instead.
* When the memory controller is per rank, csbased is true.
edac: rewrite the sysfs code to use struct device The EDAC subsystem uses the old struct sysdev approach, creating all nodes using the raw sysfs API. This is bad, as the API is deprecated. As we'll be changing the EDAC API, let's first port the existing code to struct device. There's one drawback on this patch: driver-specific sysfs nodes, used by mpc85xx_edac, amd64_edac and i7core_edac won't be created anymore. While it would be possible to also port the device-specific code, that would mix kobj with struct device, with is not recommended. Also, it is easier and nicer to move the code to the drivers, instead, as the core can get rid of some complex logic that just emulates what the device_add() and device_create_file() already does. The next patches will convert the driver-specific code to use the device-specific calls. Then, the remaining bits of the old sysfs API will be removed. NOTE: a per-MC bus is required, otherwise devices with more than one memory controller will hit a bug like the one below: [ 819.094946] EDAC DEBUG: find_mci_by_dev: find_mci_by_dev() [ 819.094948] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device() idx=1 [ 819.094952] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device(): creating device mc1 [ 819.094967] EDAC DEBUG: edac_create_sysfs_mci_device: edac_create_sysfs_mci_device creating dimm0, located at channel 0 slot 0 [ 819.094984] ------------[ cut here ]------------ [ 819.100142] WARNING: at fs/sysfs/dir.c:481 sysfs_add_one+0xc1/0xf0() [ 819.107282] Hardware name: S2600CP [ 819.111078] sysfs: cannot create duplicate filename '/bus/edac/devices/dimm0' [ 819.119062] Modules linked in: sb_edac(+) edac_core ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc sunrpc binfmt_misc dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan tun kvm microcode pcspkr iTCO_wdt iTCO_vendor_support igb i2c_i801 i2c_core sg ioatdma dca sr_mod cdrom sd_mod crc_t10dif ahci libahci isci libsas libata scsi_transport_sas scsi_mod wmi dm_mod [last unloaded: scsi_wait_scan] [ 819.175748] Pid: 10902, comm: modprobe Not tainted 3.3.0-0.11.el7.v12.2.x86_64 #1 [ 819.184113] Call Trace: [ 819.186868] [<ffffffff8105adaf>] warn_slowpath_common+0x7f/0xc0 [ 819.193573] [<ffffffff8105aea6>] warn_slowpath_fmt+0x46/0x50 [ 819.200000] [<ffffffff811f53d1>] sysfs_add_one+0xc1/0xf0 [ 819.206025] [<ffffffff811f5cf5>] sysfs_do_create_link+0x135/0x220 [ 819.212944] [<ffffffff811f7023>] ? sysfs_create_group+0x13/0x20 [ 819.219656] [<ffffffff811f5df3>] sysfs_create_link+0x13/0x20 [ 819.226109] [<ffffffff813b04f6>] bus_add_device+0xe6/0x1b0 [ 819.232350] [<ffffffff813ae7cb>] device_add+0x2db/0x460 [ 819.238300] [<ffffffffa0325634>] edac_create_dimm_object+0x84/0xf0 [edac_core] [ 819.246460] [<ffffffffa0325e18>] edac_create_sysfs_mci_device+0xe8/0x290 [edac_core] [ 819.255215] [<ffffffffa0322e2a>] edac_mc_add_mc+0x5a/0x2c0 [edac_core] [ 819.262611] [<ffffffffa03412df>] sbridge_register_mci+0x1bc/0x279 [sb_edac] [ 819.270493] [<ffffffffa03417a3>] sbridge_probe+0xef/0x175 [sb_edac] [ 819.277630] [<ffffffff813ba4e8>] ? pm_runtime_enable+0x58/0x90 [ 819.284268] [<ffffffff812f430c>] local_pci_probe+0x5c/0xd0 [ 819.290508] [<ffffffff812f5ba1>] __pci_device_probe+0xf1/0x100 [ 819.297117] [<ffffffff812f5bea>] pci_device_probe+0x3a/0x60 [ 819.303457] [<ffffffff813b1003>] really_probe+0x73/0x270 [ 819.309496] [<ffffffff813b138e>] driver_probe_device+0x4e/0xb0 [ 819.316104] [<ffffffff813b149b>] __driver_attach+0xab/0xb0 [ 819.322337] [<ffffffff813b13f0>] ? driver_probe_device+0xb0/0xb0 [ 819.329151] [<ffffffff813af5d6>] bus_for_each_dev+0x56/0x90 [ 819.335489] [<ffffffff813b0d7e>] driver_attach+0x1e/0x20 [ 819.341534] [<ffffffff813b0980>] bus_add_driver+0x1b0/0x2a0 [ 819.347884] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.353641] [<ffffffff813b19f6>] driver_register+0x76/0x140 [ 819.359980] [<ffffffff8159f18b>] ? printk+0x51/0x53 [ 819.365524] [<ffffffffa0347000>] ? 0xffffffffa0346fff [ 819.371291] [<ffffffff812f5896>] __pci_register_driver+0x56/0xd0 [ 819.378096] [<ffffffffa0347054>] sbridge_init+0x54/0x1000 [sb_edac] [ 819.385231] [<ffffffff8100203f>] do_one_initcall+0x3f/0x170 [ 819.391577] [<ffffffff810bcd2e>] sys_init_module+0xbe/0x230 [ 819.397926] [<ffffffff815bb529>] system_call_fastpath+0x16/0x1b [ 819.404633] ---[ end trace 1654fdd39556689f ]--- This happens because the bus is not being properly initialized. Instead of putting the memory sub-devices inside the memory controller, it is putting everything under the same directory: $ tree /sys/bus/edac/ /sys/bus/edac/ ├── devices │ ├── all_channel_counts -> ../../../devices/system/edac/mc/mc0/all_channel_counts │ ├── csrow0 -> ../../../devices/system/edac/mc/mc0/csrow0 │ ├── csrow1 -> ../../../devices/system/edac/mc/mc0/csrow1 │ ├── csrow2 -> ../../../devices/system/edac/mc/mc0/csrow2 │ ├── dimm0 -> ../../../devices/system/edac/mc/mc0/dimm0 │ ├── dimm1 -> ../../../devices/system/edac/mc/mc0/dimm1 │ ├── dimm3 -> ../../../devices/system/edac/mc/mc0/dimm3 │ ├── dimm6 -> ../../../devices/system/edac/mc/mc0/dimm6 │ ├── inject_addrmatch -> ../../../devices/system/edac/mc/mc0/inject_addrmatch │ ├── mc -> ../../../devices/system/edac/mc │ └── mc0 -> ../../../devices/system/edac/mc/mc0 ├── drivers ├── drivers_autoprobe ├── drivers_probe └── uevent On a multi-memory controller system, the names "csrow%d" and "dimm%d" should be under "mc%d", and not at the main hierarchy level. So, we need to create a per-MC bus, in order to have its own namespace. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Greg K H <gregkh@linuxfoundation.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-17 03:41:11 +08:00
*/
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
unsigned n_layers;
struct edac_mc_layer *layers;
bool csbased;
edac: Create a dimm struct and move the labels into it The way a DIMM is currently represented implies that they're linked into a per-csrow struct. However, some drivers don't see csrows, as they're ridden behind some chip like the AMB's on FBDIMM's, for example. This forced drivers to fake^Wvirtualize a csrow struct, and to create a mess under csrow/channel original's concept. Move the DIMM labels into a per-DIMM struct, and add there the real location of the socket, in terms of csrow/channel. Latter patches will modify the location to properly represent the memory architecture. All other drivers will use a per-csrow type of location. Some of those drivers will require a latter conversion, as they also fake the csrows internally. TODO: While this patch doesn't change the existing behavior, on csrows-based memory controllers, a csrow/channel pair points to a memory rank. There's a known bug at the EDAC core that allows having different labels for the same DIMM, if it has more than one rank. A latter patch is need to merge the several ranks for a DIMM into the same dimm_info struct, in order to avoid having different labels for the same DIMM. The edac_mc_alloc() will now contain a per-dimm initialization loop that will be changed by latter patches in order to match other types of memory architectures. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 01:12:32 +08:00
/*
* DIMM info. Will eventually remove the entire csrows_info some day
*/
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
unsigned tot_dimms;
struct dimm_info **dimms;
edac: Create a dimm struct and move the labels into it The way a DIMM is currently represented implies that they're linked into a per-csrow struct. However, some drivers don't see csrows, as they're ridden behind some chip like the AMB's on FBDIMM's, for example. This forced drivers to fake^Wvirtualize a csrow struct, and to create a mess under csrow/channel original's concept. Move the DIMM labels into a per-DIMM struct, and add there the real location of the socket, in terms of csrow/channel. Latter patches will modify the location to properly represent the memory architecture. All other drivers will use a per-csrow type of location. Some of those drivers will require a latter conversion, as they also fake the csrows internally. TODO: While this patch doesn't change the existing behavior, on csrows-based memory controllers, a csrow/channel pair points to a memory rank. There's a known bug at the EDAC core that allows having different labels for the same DIMM, if it has more than one rank. A latter patch is need to merge the several ranks for a DIMM into the same dimm_info struct, in order to avoid having different labels for the same DIMM. The edac_mc_alloc() will now contain a per-dimm initialization loop that will be changed by latter patches in order to match other types of memory architectures. Reviewed-by: Aristeu Rozanski <arozansk@redhat.com> Reviewed-by: Borislav Petkov <borislav.petkov@amd.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-01-28 01:12:32 +08:00
/*
* FIXME - what about controllers on other busses? - IDs must be
* unique. dev pointer should be sufficiently unique, but
* BUS:SLOT.FUNC numbers may not be unique.
*/
struct device *pdev;
const char *mod_name;
const char *mod_ver;
const char *ctl_name;
const char *dev_name;
void *pvt_info;
unsigned long start_time; /* mci load start time (in jiffies) */
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
/*
* drivers shouldn't access those fields directly, as the core
* already handles that.
*/
u32 ce_noinfo_count, ue_noinfo_count;
edac: Initialize the dimm label with the known information While userspace doesn't fill the dimm labels, add there the dimm location, as described by the used memory model. This could eventually match what is described at the dmidecode, making easier for people to identify the memory. For example, on an Intel motherboard where the DMI table is reliable, the first memory stick is described as: Memory Device Array Handle: 0x0029 Error Information Handle: Not Provided Total Width: 64 bits Data Width: 64 bits Size: 2048 MB Form Factor: DIMM Set: 1 Locator: A1_DIMM0 Bank Locator: A1_Node0_Channel0_Dimm0 Type: <OUT OF SPEC> Type Detail: Synchronous Speed: 800 MHz Manufacturer: A1_Manufacturer0 Serial Number: A1_SerNum0 Asset Tag: A1_AssetTagNum0 Part Number: A1_PartNum0 The memory named as "A1_DIMM0" is physically located at the first memory controller (node 0), at channel 0, dimm slot 0. After this patch, the memory label will be filled with: /sys/devices/system/edac/mc/csrow0/ch0_dimm_label:mc#0channel#0slot#0 And (after the new EDAC API patches) as: /sys/devices/system/edac/mc/mc0/dimm0/dimm_label:mc#0channel#0slot#0 So, even if the memory label is not initialized on userspace, an useful information with the error location is filled there, expecially since several systems/motherboards are provided with enough info to map from channel/slot (or branch/channel/slot) into the DIMM label. So, letting the EDAC core fill it by default is a good thing. It should noticed that, as the label filling happens at the edac_mc_alloc(), drivers can override it to better describe the memories (and some actually do it). Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-02-09 22:05:20 +08:00
u32 ue_mc, ce_mc;
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
u32 *ce_per_layer[EDAC_MAX_LAYERS], *ue_per_layer[EDAC_MAX_LAYERS];
struct completion complete;
/* Additional top controller level attributes, but specified
* by the low level driver.
*
* Set by the low level driver to provide attributes at the
edac: Change internal representation to work with layers Change the EDAC internal representation to work with non-csrow based memory controllers. There are lots of those memory controllers nowadays, and more are coming. So, the EDAC internal representation needs to be changed, in order to work with those memory controllers, while preserving backward compatibility with the old ones. The edac core was written with the idea that memory controllers are able to directly access csrows. This is not true for FB-DIMM and RAMBUS memory controllers. Also, some recent advanced memory controllers don't present a per-csrows view. Instead, they view memories as DIMMs, instead of ranks. So, change the allocation and error report routines to allow them to work with all types of architectures. This will allow the removal of several hacks with FB-DIMM and RAMBUS memory controllers. Also, several tests were done on different platforms using different x86 drivers. TODO: a multi-rank DIMMs are currently represented by multiple DIMM entries in struct dimm_info. That means that changing a label for one rank won't change the same label for the other ranks at the same DIMM. This bug is present since the beginning of the EDAC, so it is not a big deal. However, on several drivers, it is possible to fix this issue, but it should be a per-driver fix, as the csrow => DIMM arrangement may not be equal for all. So, don't try to fix it here yet. I tried to make this patch as short as possible, preceding it with several other patches that simplified the logic here. Yet, as the internal API changes, all drivers need changes. The changes are generally bigger in the drivers for FB-DIMMs. Cc: Aristeu Rozanski <arozansk@redhat.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Borislav Petkov <borislav.petkov@amd.com> Cc: Mark Gross <mark.gross@intel.com> Cc: Jason Uhlenkott <juhlenko@akamai.com> Cc: Tim Small <tim@buttersideup.com> Cc: Ranganathan Desikan <ravi@jetztechnologies.com> Cc: "Arvind R." <arvino55@gmail.com> Cc: Olof Johansson <olof@lixom.net> Cc: Egor Martovetsky <egor@pasemi.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Michal Marek <mmarek@suse.cz> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Hitoshi Mitake <h.mitake@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "Niklas Söderlund" <niklas.soderlund@ericsson.com> Cc: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Josh Boyer <jwboyer@gmail.com> Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2012-04-19 02:20:50 +08:00
* controller level.
* An array of structures, NULL terminated
*
* If attributes are desired, then set to array of attributes
* If no attributes are desired, leave NULL
*/
const struct mcidev_sysfs_attribute *mc_driver_sysfs_attributes;
/* work struct for this MC */
struct delayed_work work;
/*
* Used to report an error - by being at the global struct
* makes the memory allocated by the EDAC core
*/
struct edac_raw_error_desc error_desc;
/* the internal state of this controller instance */
int op_state;
struct dentry *debugfs;
u8 fake_inject_layer[EDAC_MAX_LAYERS];
bool fake_inject_ue;
u16 fake_inject_count;
};
EDAC: Fix lockdep splat Fix the following: BUG: key ffff88043bdd0330 not in .data! ------------[ cut here ]------------ WARNING: at kernel/lockdep.c:2987 lockdep_init_map+0x565/0x5a0() DEBUG_LOCKS_WARN_ON(1) Modules linked in: glue_helper sb_edac(+) edac_core snd acpi_cpufreq lrw gf128mul ablk_helper iTCO_wdt evdev i2c_i801 dcdbas button cryptd pcspkr iTCO_vendor_support usb_common lpc_ich mfd_core soundcore mperf processor microcode CPU: 2 PID: 599 Comm: modprobe Not tainted 3.10.0 #1 Hardware name: Dell Inc. Precision T3600/0PTTT9, BIOS A08 01/24/2013 0000000000000009 ffff880439a1d920 ffffffff8160a9a9 ffff880439a1d958 ffffffff8103d9e0 ffff88043af4a510 ffffffff81a16e11 0000000000000000 ffff88043bdd0330 0000000000000000 ffff880439a1d9b8 ffffffff8103dacc Call Trace: dump_stack warn_slowpath_common warn_slowpath_fmt lockdep_init_map ? trace_hardirqs_on_caller ? trace_hardirqs_on debug_mutex_init __mutex_init bus_register edac_create_sysfs_mci_device edac_mc_add_mc sbridge_probe pci_device_probe driver_probe_device __driver_attach ? driver_probe_device bus_for_each_dev driver_attach bus_add_driver driver_register __pci_register_driver ? 0xffffffffa0010fff sbridge_init ? 0xffffffffa0010fff do_one_initcall load_module ? unset_module_init_ro_nx SyS_init_module tracesys ---[ end trace d24a70b0d3ddf733 ]--- EDAC MC0: Giving out device to 'sbridge_edac.c' 'Sandy Bridge Socket#0': DEV 0000:3f:0e.0 EDAC sbridge: Driver loaded. What happens is that bus_register needs a statically allocated lock_key because the last is handed in to lockdep. However, struct mem_ctl_info embeds struct bus_type (the whole struct, not a pointer to it) and the whole thing gets dynamically allocated. Fix this by using a statically allocated struct bus_type for the MC bus. Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: stable@kernel.org # v3.10 Signed-off-by: Tony Luck <tony.luck@intel.com>
2013-07-19 18:28:25 +08:00
/*
* Maximum number of memory controllers in the coherent fabric.
*/
#define EDAC_MAX_MCS 16
#endif