From 6edbfce0d4b4db31b0eed6db06f2fb59991cb929 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 15:25:23 -0200 Subject: edac: edac_core.h: get rid of unused kobj_complete This element of struct edac_pci_ctl_info is never used. So, get rid of it. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_core.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 4861542163d7..58d66da56486 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -380,7 +380,6 @@ struct edac_pci_ctl_info { * device this structure controls */ struct kobject kobj; - struct completion kobj_complete; }; #define to_edac_pci_ctl_work(w) \ -- cgit v1.2.3 From 26bc684400340fda1ba44112aa266cda99ba0196 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 16:15:02 -0200 Subject: edac: edac_core.h: remove prototype for edac_pci_reset_delay_period() This function doesn't exist. So, remove its prototype. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_core.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 58d66da56486..1723f3643e75 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -493,9 +493,6 @@ extern struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, extern void edac_pci_free_ctl_info(struct edac_pci_ctl_info *pci); -extern void edac_pci_reset_delay_period(struct edac_pci_ctl_info *pci, - unsigned long value); - extern int edac_pci_alloc_index(void); extern int edac_pci_add_device(struct edac_pci_ctl_info *pci, int edac_idx); extern struct edac_pci_ctl_info *edac_pci_del_device(struct device *dev); -- cgit v1.2.3 From 60b3efdc9507aba2fa29db8afd4a162259b69fd8 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Oct 2016 10:00:46 -0200 Subject: edac.txt: add a section explaining the dimmX and rankX directories Documentation for those are missing at the EDAC description. I guess we end by moving such descriptions in the past to the ABI document (or only added it there), but it means that the EDAC documentation is incomplete. So, add it there. Signed-off-by: Mauro Carvalho Chehab --- Documentation/edac.txt | 120 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 120 insertions(+) diff --git a/Documentation/edac.txt b/Documentation/edac.txt index f89cfd85ae13..502988524519 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -208,6 +208,126 @@ For a description of the sysfs API, please see: Documentation/ABI/testing/sysfs-devices-edac +``dimmX`` or ``rankX`` directories +---------------------------------- + +The recommended way to use the EDAC subsystem is to look at the information +provided by the ``dimmX`` or ``rankX`` directories [#f5]_. + +A typical EDAC system has the following structure under +``/sys/devices/system/edac/``\ [#f6]_:: + + /sys/devices/system/edac/ + ├── mc + │   ├── mc0 + │   │   ├── ce_count + │   │   ├── ce_noinfo_count + │   │   ├── dimm0 + │   │   │   ├── dimm_dev_type + │   │   │   ├── dimm_edac_mode + │   │   │   ├── dimm_label + │   │   │   ├── dimm_location + │   │   │   ├── dimm_mem_type + │   │   │   ├── size + │   │   │   └── uevent + │   │   ├── max_location + │   │   ├── mc_name + │   │   ├── reset_counters + │   │   ├── seconds_since_reset + │   │   ├── size_mb + │   │   ├── ue_count + │   │   ├── ue_noinfo_count + │   │   └── uevent + │   ├── mc1 + │   │   ├── ce_count + │   │   ├── ce_noinfo_count + │   │   ├── dimm0 + │   │   │   ├── dimm_dev_type + │   │   │   ├── dimm_edac_mode + │   │   │   ├── dimm_label + │   │   │   ├── dimm_location + │   │   │   ├── dimm_mem_type + │   │   │   ├── size + │   │   │   └── uevent + │   │   ├── max_location + │   │   ├── mc_name + │   │   ├── reset_counters + │   │   ├── seconds_since_reset + │   │   ├── size_mb + │   │   ├── ue_count + │   │   ├── ue_noinfo_count + │   │   └── uevent + │   └── uevent + └── uevent + +In the ``dimmX`` directories are EDAC control and attribute files for +this ``X`` memory module: + +- ``size`` - Total memory managed by this csrow attribute file + + This attribute file displays, in count of megabytes, the memory + that this csrow contains. + +- ``dimm_dev_type`` - Device type attribute file + + This attribute file will display what type of DRAM device is + being utilized on this DIMM. + Examples: + + - x1 + - x2 + - x4 + - x8 + +- ``dimm_edac_mode`` - EDAC Mode of operation attribute file + + This attribute file will display what type of Error detection + and correction is being utilized. + +- ``dimm_label`` - memory module label control file + + This control file allows this DIMM to have a label assigned + to it. With this label in the module, when errors occur + the output can provide the DIMM label in the system log. + This becomes vital for panic events to isolate the + cause of the UE event. + + DIMM Labels must be assigned after booting, with information + that correctly identifies the physical slot with its + silk screen label. This information is currently very + motherboard specific and determination of this information + must occur in userland at this time. + +- ``dimm_location`` - location of the memory module + + The location can have up to 3 levels, and describe how the + memory controller identifies the location of a memory module. + Depending on the type of memory and memory controller, it + can be: + + - *csrow* and *channel* - used when the memory controller + doesn't identify a single DIMM - e. g. in ``rankX`` dir; + - *branch*, *channel*, *slot* - typically used on FB-DIMM memory + controllers; + - *channel*, *slot* - used on Nehalem and newer Intel drivers. + +- ``dimm_mem_type`` - Memory Type attribute file + + This attribute file will display what type of memory is currently + on this csrow. Normally, either buffered or unbuffered memory. + Examples: + + - Registered-DDR + - Unbuffered-DDR + +.. [#f5] On some systems, the memory controller doesn't have any logic + to identify the memory module. On such systems, the directory is called ``rankX`` and works on a similar way as the ``csrowX`` directories. + On modern Intel memory controllers, the memory controller identifies the + memory modules directly. On such systems, the directory is called ``dimmX``. + +.. [#f6] There are also some ``power`` directories and ``subsystem`` + symlinks inside the sysfs mapping that are automatically created by + the sysfs subsystem. Currently, they serve no purpose. 'csrowX' directories -------------------- -- cgit v1.2.3 From 2639fe69eaef9b2278a8ac5a91fac389ec2cc942 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 08:14:12 -0200 Subject: edac.txt: convert EDAC documentation to ReST Converts the EDAC driver subsystem documentation to ReST: - Put paragraph titles in lower case; - Add code blocks where needed; - Convert tables to ReST markup; - Mark filesystem and module names as verbatim; - Adjust document to be properly displayed in html. Signed-off-by: Mauro Carvalho Chehab --- Documentation/edac.txt | 551 ++++++++++++++++++++++++++----------------------- 1 file changed, 295 insertions(+), 256 deletions(-) diff --git a/Documentation/edac.txt b/Documentation/edac.txt index 502988524519..316456ba2e0a 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -1,29 +1,34 @@ +.. include:: + +===================================== EDAC - Error Detection And Correction ===================================== -"bluesmoke" was the name for this device driver when it -was "out-of-tree" and maintained at sourceforge.net - -bluesmoke.sourceforge.net. That site is mostly archaic now and can be -used only for historical purposes. +.. note:: -When the subsystem was pushed into 2.6.16 for the first time, it was -renamed to 'EDAC'. + "bluesmoke" was the name for this device driver when it + was "out-of-tree" and maintained at http://bluesmoke.sourceforge.net. + That site is mostly archaic now and can be used only for historical + purposes. -PURPOSE + When the subsystem was pushed into 2.6.16 for the first time, it was + renamed to ``EDAC``. + +Purpose ------- -The 'edac' kernel module's goal is to detect and report hardware errors +The ``edac`` kernel module's goal is to detect and report hardware errors that occur within the computer system running under linux. -MEMORY +Memory ------ Memory Correctable Errors (CE) and Uncorrectable Errors (UE) are the primary errors being harvested. These types of errors are harvested by -the 'edac_mc' device. +the ``edac_mc`` device. Detecting CE events, then harvesting those events and reporting them, -*can* but must not necessarily be a predictor of future UE events. With +**can** but must not necessarily be a predictor of future UE events. With CE events only, the system can and will continue to operate as no data has been damaged yet. @@ -31,10 +36,10 @@ However, preventive maintenance and proactive part replacement of memory DIMMs exhibiting CEs can reduce the likelihood of the dreaded UE events and system panics. -OTHER HARDWARE ELEMENTS +Other hardware elements ----------------------- -A new feature for EDAC, the edac_device class of device, was added in +A new feature for EDAC, the ``edac_device`` class of device, was added in the 2.6.23 version of the kernel. This new device type allows for non-memory type of ECC hardware detectors @@ -48,14 +53,14 @@ reports it, then a edac_device device probably can be constructed to harvest and present that to userspace. -PCI BUS SCANNING +PCI bus scanning ---------------- In addition, PCI devices are scanned for PCI Bus Parity and SERR Errors in order to determine if errors are occurring during data transfers. The presence of PCI Parity errors must be examined with a grain of salt. -There are several add-in adapters that do *not* follow the PCI specification +There are several add-in adapters that do **not** follow the PCI specification with regards to Parity generation and reporting. The specification says the vendor should tie the parity status bits to 0 if they do not intend to generate parity. Some vendors do not do this, and thus the parity bit @@ -63,62 +68,64 @@ can "float" giving false positives. There is a PCI device attribute located in sysfs that is checked by the EDAC PCI scanning code. If that attribute is set, PCI parity/error -scanning is skipped for that device. The attribute is: +scanning is skipped for that device. The attribute is:: broken_parity_status -and is located in /sys/devices/pci/0000:XX:YY.Z directories for +and is located in ``/sys/devices/pci/0000:XX:YY.Z`` directories for PCI devices. -VERSIONING +Versioning ---------- -EDAC is composed of a "core" module (edac_core.ko) and several Memory +EDAC is composed of a "core" module (``edac_core.ko``) and several Memory Controller (MC) driver modules. On a given system, the CORE is loaded and one MC driver will be loaded. Both the CORE and the MC driver (or -edac_device driver) have individual versions that reflect current +``edac_device`` driver) have individual versions that reflect current release level of their respective modules. Thus, to "report" on what version a system is running, one must report both the CORE's and the MC driver's versions. -LOADING +Loading ------- -If 'edac' was statically linked with the kernel then no loading -is necessary. If 'edac' was built as modules then simply modprobe -the 'edac' pieces that you need. You should be able to modprobe +If ``edac`` was statically linked with the kernel then no loading +is necessary. If ``edac`` was built as modules then simply modprobe +the ``edac`` pieces that you need. You should be able to modprobe hardware-specific modules and have the dependencies load the necessary core modules. -Example: +Example:: -$> modprobe amd76x_edac + $ modprobe amd76x_edac -loads both the amd76x_edac.ko memory controller module and the edac_mc.ko -core module. +loads both the ``amd76x_edac.ko`` memory controller module and the +``edac_mc.ko`` core module. -SYSFS INTERFACE +Sysfs interface --------------- -EDAC presents a 'sysfs' interface for control and reporting purposes. It +EDAC presents a ``sysfs`` interface for control and reporting purposes. It lives in the /sys/devices/system/edac directory. Within this directory there currently reside 2 components: + ======= ============================== mc memory controller(s) system pci PCI control and status system + ======= ============================== Memory Controller (mc) Model ---------------------------- -Each 'mc' device controls a set of DIMM memory modules. These modules -are laid out in a Chip-Select Row (csrowX) and Channel table (chX). +Each ``mc`` device controls a set of DIMM memory modules. These modules +are laid out in a Chip-Select Row (``csrowX``) and Channel table (``chX``). There can be multiple csrows and multiple channels. Memory controllers allow for several csrows, with 8 csrows being a @@ -129,28 +136,28 @@ Dual channels allows for 128 bit data transfers to/from the CPU from/to memory. Some newer chipsets allow for more than 2 channels, like Fully Buffered DIMMs (FB-DIMMs). The following example will assume 2 channels: - - Channel 0 Channel 1 - =================================== - csrow0 | DIMM_A0 | DIMM_B0 | - csrow1 | DIMM_A0 | DIMM_B0 | - =================================== - - =================================== - csrow2 | DIMM_A1 | DIMM_B1 | - csrow3 | DIMM_A1 | DIMM_B1 | - =================================== + +--------+-----------+-----------+ + | | Channel 0 | Channel 1 | + +========+===========+===========+ + | csrow0 | DIMM_A0 | DIMM_B0 | + +--------+ | | + | csrow1 | | | + +--------+-----------+-----------+ + | csrow2 | DIMM_A1 | DIMM_B1 | + +--------+ | | + | csrow3 | | | + +--------+-----------+-----------+ In the above example table there are 4 physical slots on the motherboard for memory DIMMs: - DIMM_A0 - DIMM_B0 - DIMM_A1 - DIMM_B1 + - DIMM_A0 + - DIMM_B0 + - DIMM_A1 + - DIMM_B1 Labels for these slots are usually silk-screened on the motherboard. -Slots labeled 'A' are channel 0 in this example. Slots labeled 'B' are +Slots labeled ``A`` are channel 0 in this example. Slots labeled ``B`` are channel 1. Notice that there are two csrows possible on a physical DIMM. These csrows are allocated their csrow assignment based on the slot into which the memory DIMM is placed. Thus, when 1 DIMM is placed in each @@ -166,8 +173,7 @@ csrow3. The representation of the above is reflected in the directory tree in EDAC's sysfs interface. Starting in directory /sys/devices/system/edac/mc each memory controller will be represented -by its own 'mcX' directory, where 'X' is the index of the MC. - +by its own ``mcX`` directory, where ``X`` is the index of the MC:: ..../edac/mc/ | @@ -176,9 +182,8 @@ by its own 'mcX' directory, where 'X' is the index of the MC. |->mc2 .... -Under each 'mcX' directory each 'csrowX' is again represented by a -'csrowX', where 'X' is the csrow index: - +Under each ``mcX`` directory each ``csrowX`` is again represented by a +``csrowX``, where ``X`` is the csrow index:: .../mc/mc0/ | @@ -194,17 +199,18 @@ csrow3 are populated, this indicates a dual ranked set of DIMMs for channels 0 and 1. -Within each of the 'mcX' and 'csrowX' directories are several EDAC +Within each of the ``mcX`` and ``csrowX`` directories are several EDAC control and attribute files. -'mcX' directories ------------------ +``mcX`` directories +------------------- -In 'mcX' directories are EDAC control and attribute files for -this 'X' instance of the memory controllers. +In ``mcX`` directories are EDAC control and attribute files for +this ``X`` instance of the memory controllers. For a description of the sysfs API, please see: + Documentation/ABI/testing/sysfs-devices-edac @@ -329,21 +335,19 @@ this ``X`` memory module: symlinks inside the sysfs mapping that are automatically created by the sysfs subsystem. Currently, they serve no purpose. -'csrowX' directories --------------------- +``csrowX`` directories +---------------------- When CONFIG_EDAC_LEGACY_SYSFS is enabled, sysfs will contain the csrowX directories. As this API doesn't work properly for Rambus, FB-DIMMs and modern Intel Memory Controllers, this is being deprecated in favor of dimmX directories. -In the 'csrowX' directories are EDAC control and attribute files for -this 'X' instance of csrow: +In the ``csrowX`` directories are EDAC control and attribute files for +this ``X`` instance of csrow: -Total Uncorrectable Errors count attribute file: - - 'ue_count' +- ``ue_count`` - Total Uncorrectable Errors count attribute file This attribute file displays the total count of uncorrectable errors that have occurred on this csrow. If panic_on_ue is set @@ -351,9 +355,7 @@ Total Uncorrectable Errors count attribute file: will panic the system. -Total Correctable Errors count attribute file: - - 'ce_count' +- ``ce_count`` - Total Correctable Errors count attribute file This attribute file displays the total count of correctable errors that have occurred on this csrow. This count is very @@ -363,65 +365,54 @@ Total Correctable Errors count attribute file: to the system administrator. -Total memory managed by this csrow attribute file: - - 'size_mb' +- ``size_mb`` - Total memory managed by this csrow attribute file This attribute file displays, in count of megabytes, the memory that this csrow contains. -Memory Type attribute file: - - 'mem_type' +- ``mem_type`` - Memory Type attribute file This attribute file will display what type of memory is currently on this csrow. Normally, either buffered or unbuffered memory. Examples: - Registered-DDR - Unbuffered-DDR + - Registered-DDR + - Unbuffered-DDR -EDAC Mode of operation attribute file: - 'edac_mode' +- ``edac_mode`` - EDAC Mode of operation attribute file This attribute file will display what type of Error detection and correction is being utilized. -Device type attribute file: - - 'dev_type' +- ``dev_type`` - Device type attribute file This attribute file will display what type of DRAM device is being utilized on this DIMM. Examples: - x1 - x2 - x4 - x8 + - x1 + - x2 + - x4 + - x8 -Channel 0 CE Count attribute file: - 'ch0_ce_count' +- ``ch0_ce_count`` - Channel 0 CE Count attribute file This attribute file will display the count of CEs on this DIMM located in channel 0. -Channel 0 UE Count attribute file: - - 'ch0_ue_count' +- ``ch0_ue_count`` - Channel 0 UE Count attribute file This attribute file will display the count of UEs on this DIMM located in channel 0. -Channel 0 DIMM Label control file: +- ``ch0_dimm_label`` - Channel 0 DIMM Label control file - 'ch0_dimm_label' This control file allows this DIMM to have a label assigned to it. With this label in the module, when errors occur @@ -436,25 +427,21 @@ Channel 0 DIMM Label control file: must occur in userland at this time. -Channel 1 CE Count attribute file: +- ``ch1_ce_count`` - Channel 1 CE Count attribute file - 'ch1_ce_count' This attribute file will display the count of CEs on this DIMM located in channel 1. -Channel 1 UE Count attribute file: +- ``ch1_ue_count`` - Channel 1 UE Count attribute file - 'ch1_ue_count' This attribute file will display the count of UEs on this DIMM located in channel 0. -Channel 1 DIMM Label control file: - - 'ch1_dimm_label' +- ``ch1_dimm_label`` - Channel 1 DIMM Label control file This control file allows this DIMM to have a label assigned to it. With this label in the module, when errors occur @@ -469,33 +456,44 @@ Channel 1 DIMM Label control file: must occur in userland at this time. - -SYSTEM LOGGING +System Logging -------------- If logging for UEs and CEs is enabled, then system logs will contain -information indicating that errors have been detected: +information indicating that errors have been detected:: -EDAC MC0: CE page 0x283, offset 0xce0, grain 8, syndrome 0x6ec3, row 0, -channel 1 "DIMM_B1": amd76x_edac - -EDAC MC0: CE page 0x1e5, offset 0xfb0, grain 8, syndrome 0xb741, row 0, -channel 1 "DIMM_B1": amd76x_edac + EDAC MC0: CE page 0x283, offset 0xce0, grain 8, syndrome 0x6ec3, row 0, channel 1 "DIMM_B1": amd76x_edac + EDAC MC0: CE page 0x1e5, offset 0xfb0, grain 8, syndrome 0xb741, row 0, channel 1 "DIMM_B1": amd76x_edac The structure of the message is: - the memory controller (MC0) - Error type (CE) - memory page (0x283) - offset in the page (0xce0) - the byte granularity (grain 8) - or resolution of the error - the error syndrome (0xb741) - memory row (row 0) - memory channel (channel 1) - DIMM label, if set prior (DIMM B1 - and then an optional, driver-specific message that may - have additional information. + + +---------------------------------------+-------------+ + | Content + Example | + +=======================================+=============+ + | The memory controller | MC0 | + +---------------------------------------+-------------+ + | Error type | CE | + +---------------------------------------+-------------+ + | Memory page | 0x283 | + +---------------------------------------+-------------+ + | Offset in the page | 0xce0 | + +---------------------------------------+-------------+ + | The byte granularity | grain 8 | + | or resolution of the error | | + +---------------------------------------+-------------+ + | The error syndrome | 0xb741 | + +---------------------------------------+-------------+ + | Memory row | row 0 + + +---------------------------------------+-------------+ + | Memory channel | channel 1 | + +---------------------------------------+-------------+ + | DIMM label, if set prior | DIMM B1 | + +---------------------------------------+-------------+ + | And then an optional, driver-specific | | + | message that may have additional | | + | information. | | + +---------------------------------------+-------------+ Both UEs and CEs with no info will lack all but memory controller, error type, a notice of "no info" and then an optional, driver-specific error @@ -512,43 +510,38 @@ Type 01 bridges, the secondary status register is also looked at to see if parity occurred on the bus on the other side of the bridge. -SYSFS CONFIGURATION +Sysfs configuration ------------------- -Under /sys/devices/system/edac/pci are control and attribute files as follows: +Under ``/sys/devices/system/edac/pci`` are control and attribute files as +follows: -Enable/Disable PCI Parity checking control file: - - 'check_pci_parity' - +- ``check_pci_parity`` - Enable/Disable PCI Parity checking control file This control file enables or disables the PCI Bus Parity scanning operation. Writing a 1 to this file enables the scanning. Writing a 0 to this file disables the scanning. - Enable: - echo "1" >/sys/devices/system/edac/pci/check_pci_parity + Enable:: + + echo "1" >/sys/devices/system/edac/pci/check_pci_parity - Disable: - echo "0" >/sys/devices/system/edac/pci/check_pci_parity + Disable:: + echo "0" >/sys/devices/system/edac/pci/check_pci_parity -Parity Count: - 'pci_parity_count' +- ``pci_parity_count`` - Parity Count This attribute file will display the number of parity errors that have been detected. - -MODULE PARAMETERS +Module parameters ----------------- -Panic on UE control file: - - 'edac_mc_panic_on_ue' +- ``edac_mc_panic_on_ue`` - Panic on UE control file An uncorrectable error will cause a machine panic. This is usually desirable. It is a bad idea to continue when an uncorrectable error @@ -557,40 +550,49 @@ Panic on UE control file: corruption. If the kernel has MCE configured, then EDAC will never notice the UE. - LOAD TIME: module/kernel parameter: edac_mc_panic_on_ue=[0|1] + LOAD TIME:: + + module/kernel parameter: edac_mc_panic_on_ue=[0|1] + + RUN TIME:: - RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_panic_on_ue + echo "1" > /sys/module/edac_core/parameters/edac_mc_panic_on_ue -Log UE control file: +- ``edac_mc_log_ue`` - Log UE control file - 'edac_mc_log_ue' Generate kernel messages describing uncorrectable errors. These errors are reported through the system message log system. UE statistics will be accumulated even when UE logging is disabled. - LOAD TIME: module/kernel parameter: edac_mc_log_ue=[0|1] + LOAD TIME:: - RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ue + module/kernel parameter: edac_mc_log_ue=[0|1] + RUN TIME:: -Log CE control file: + echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ue + + +- ``edac_mc_log_ce`` - Log CE control file - 'edac_mc_log_ce' Generate kernel messages describing correctable errors. These errors are reported through the system message log system. CE statistics will be accumulated even when CE logging is disabled. - LOAD TIME: module/kernel parameter: edac_mc_log_ce=[0|1] + LOAD TIME:: + + module/kernel parameter: edac_mc_log_ce=[0|1] + + RUN TIME:: - RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ce + echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ce -Polling period control file: +- ``edac_mc_poll_msec`` - Polling period control file - 'edac_mc_poll_msec' The time period, in milliseconds, for polling for error information. Too small a value wastes resources. Too large a value might delay @@ -599,27 +601,33 @@ Polling period control file: default. Systems which require all the bandwidth they can get, may increase this. - LOAD TIME: module/kernel parameter: edac_mc_poll_msec=[0|1] + LOAD TIME:: - RUN TIME: echo "1000" > /sys/module/edac_core/parameters/edac_mc_poll_msec + module/kernel parameter: edac_mc_poll_msec=[0|1] + RUN TIME:: -Panic on PCI PARITY Error: + echo "1000" > /sys/module/edac_core/parameters/edac_mc_poll_msec - 'panic_on_pci_parity' + +- ``panic_on_pci_parity`` - Panic on PCI PARITY Error This control file enables or disables panicking when a parity error has been detected. - module/kernel parameter: edac_panic_on_pci_pe=[0|1] + module/kernel parameter:: + + edac_panic_on_pci_pe=[0|1] + + Enable:: + + echo "1" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe - Enable: - echo "1" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe + Disable:: - Disable: - echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe + echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe @@ -631,28 +639,31 @@ and APIs for the EDAC_DEVICE. User space access to an edac_device is through the sysfs interface. -At the location /sys/devices/system/edac (sysfs) new edac_device devices will -appear. +At the location ``/sys/devices/system/edac`` (sysfs) new edac_device devices +will appear. -There is a three level tree beneath the above 'edac' directory. For example, -the 'test_device_edac' device (found at the bluesmoke.sourceforget.net website) -installs itself as: +There is a three level tree beneath the above ``edac`` directory. For example, +the ``test_device_edac`` device (found at the http://bluesmoke.sourceforget.net +website) installs itself as:: - /sys/devices/systm/edac/test-instance + /sys/devices/system/edac/test-instance -in this directory are various controls, a symlink and one or more 'instance' +in this directory are various controls, a symlink and one or more ``instance`` directories. The standard default controls are: + ============== ======================================================= log_ce boolean to log CE events log_ue boolean to log UE events - panic_on_ue boolean to 'panic' the system if an UE is encountered + panic_on_ue boolean to ``panic`` the system if an UE is encountered (default off, can be set true via startup script) poll_msec time period between POLL cycles for events + ============== ======================================================= The test_device_edac device adds at least one of its own custom control: + ============== ================================================== test_bits which in the current test driver does nothing but show how it is installed. A ported driver can add one or more such controls and/or attributes @@ -660,42 +671,52 @@ The test_device_edac device adds at least one of its own custom control: One out-of-tree driver uses controls here to allow for ERROR INJECTION operations to hardware injection registers + ============== ================================================== The symlink points to the 'struct dev' that is registered for this edac_device. -INSTANCES +Instances --------- -One or more instance directories are present. For the 'test_device_edac' case: +One or more instance directories are present. For the ``test_device_edac`` +case: - test-instance0 + +----------------+ + | test-instance0 | + +----------------+ In this directory there are two default counter attributes, which are totals of counter in deeper subdirectories. + ============== ==================================== ce_count total of CE events of subdirectories ue_count total of UE events of subdirectories + ============== ==================================== -BLOCKS +Blocks ------ -At the lowest directory level is the 'block' directory. There can be 0, 1 -or more blocks specified in each instance. - - test-block0 +At the lowest directory level is the ``block`` directory. There can be 0, 1 +or more blocks specified in each instance: + +-------------+ + | test-block0 | + +-------------+ In this directory the default attributes are: - ce_count which is counter of CE events for this 'block' + ============== ================================================ + ce_count which is counter of CE events for this ``block`` of hardware being monitored - ue_count which is counter of UE events for this 'block' + ue_count which is counter of UE events for this ``block`` of hardware being monitored + ============== ================================================ -The 'test_device_edac' device adds 4 attributes and 1 control: +The ``test_device_edac`` device adds 4 attributes and 1 control: + ================== ==================================================== test-block-bits-0 for every POLL cycle this counter is incremented test-block-bits-1 every 10 cycles, this counter is bumped once, @@ -704,20 +725,23 @@ The 'test_device_edac' device adds 4 attributes and 1 control: and test-block-bits-1 is set to 0 test-block-bits-3 every 1000 cycles, this counter is bumped once, and test-block-bits-2 is set to 0 + ================== ==================================================== + ================== ==================================================== reset-counters writing ANY thing to this control will reset all the above counters. + ================== ==================================================== -Use of the 'test_device_edac' driver should enable any others to create their own +Use of the ``test_device_edac`` driver should enable any others to create their own unique drivers for their hardware systems. -The 'test_device_edac' sample driver is located at the -bluesmoke.sourceforge.net project site for EDAC. +The ``test_device_edac`` sample driver is located at the +http://bluesmoke.sourceforge.net project site for EDAC. -NEHALEM USAGE OF EDAC APIs +Nehalem Usage of EDAC APIs -------------------------- This chapter documents some EXPERIMENTAL mappings for EDAC API to handle @@ -739,7 +763,8 @@ were done at i7core_edac driver. This chapter will cover those differences As EDAC API maps the minimum unity is csrows, the driver sequentially maps channel/dimm into different csrows. - For example, supposing the following layout: + For example, supposing the following layout:: + Ch0 phy rd0, wr0 (0x063f4031): 2 ranks, UDIMMs dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 dimm 1 1024 Mb offset: 4, bank: 8, rank: 1, row: 0x4000, col: 0x400 @@ -747,14 +772,15 @@ were done at i7core_edac driver. This chapter will cover those differences dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 Ch2 phy rd3, wr3 (0x063f4031): 2 ranks, UDIMMs dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 - The driver will map it as: + + The driver will map it as:: + csrow0: channel 0, dimm0 csrow1: channel 0, dimm1 csrow2: channel 1, dimm0 csrow3: channel 2, dimm0 -exports one - DIMM per csrow. + exports one DIMM per csrow. Each QPI is exported as a different memory controller. @@ -762,47 +788,53 @@ exports one functionality via some error injection nodes: For injecting a memory error, there are some sysfs nodes, under - /sys/devices/system/edac/mc/mc?/: + ``/sys/devices/system/edac/mc/mc?/``: - inject_addrmatch/*: + - ``inject_addrmatch/*``: Controls the error injection mask register. It is possible to specify - several characteristics of the address to match an error code: + several characteristics of the address to match an error code:: + dimm = the affected dimm. Numbers are relative to a channel; rank = the memory rank; channel = the channel that will generate an error; bank = the affected bank; page = the page address; column (or col) = the address column. + each of the above values can be set to "any" to match any valid value. At driver init, all values are set to any. For example, to generate an error at rank 1 of dimm 2, for any channel, - any bank, any page, any column: + any bank, any page, any column:: + echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm echo 1 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank - To return to the default behaviour of matching any, you can do: + To return to the default behaviour of matching any, you can do:: + echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank - inject_eccmask: - specifies what bits will have troubles, + - ``inject_eccmask``: + specifies what bits will have troubles, + + - ``inject_section``: + specifies what ECC cache section will get the error:: - inject_section: - specifies what ECC cache section will get the error: 3 for both 2 for the highest 1 for the lowest - inject_type: - specifies the type of error, being a combination of the following bits: + - ``inject_type``: + specifies the type of error, being a combination of the following bits:: + bit 0 - repeat bit 1 - ecc bit 2 - parity - inject_enable starts the error generation when something different - than 0 is written. + - ``inject_enable``: + starts the error generation when something different than 0 is written. All inject vars can be read. root permission is needed for write. @@ -811,21 +843,21 @@ exports one also produce an error. For example, the following code will generate an error for any write access - at socket 0, on any DIMM/address on channel 2: + at socket 0, on any DIMM/address on channel 2:: - echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/channel - echo 2 >/sys/devices/system/edac/mc/mc0/inject_type - echo 64 >/sys/devices/system/edac/mc/mc0/inject_eccmask - echo 3 >/sys/devices/system/edac/mc/mc0/inject_section - echo 1 >/sys/devices/system/edac/mc/mc0/inject_enable - dd if=/dev/mem of=/dev/null seek=16k bs=4k count=1 >& /dev/null + echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/channel + echo 2 >/sys/devices/system/edac/mc/mc0/inject_type + echo 64 >/sys/devices/system/edac/mc/mc0/inject_eccmask + echo 3 >/sys/devices/system/edac/mc/mc0/inject_section + echo 1 >/sys/devices/system/edac/mc/mc0/inject_enable + dd if=/dev/mem of=/dev/null seek=16k bs=4k count=1 >& /dev/null For socket 1, it is needed to replace "mc0" by "mc1" at the above commands. - The generated error message will look like: + The generated error message will look like:: - EDAC MC0: UE row 0, channel-a= 0 channel-b= 0 labels "-": NON_FATAL (addr = 0x0075b980, socket=0, Dimm=0, Channel=2, syndrome=0x00000040, count=1, Err=8c0000400001009f:4000080482 (read error: read ECC error)) + EDAC MC0: UE row 0, channel-a= 0 channel-b= 0 labels "-": NON_FATAL (addr = 0x0075b980, socket=0, Dimm=0, Channel=2, syndrome=0x00000040, count=1, Err=8c0000400001009f:4000080482 (read error: read ECC error)) 3) Nehalem specific Corrected Error memory counters @@ -837,9 +869,9 @@ exports one granularity than the default ones), the driver exposes those registers for UDIMM memories. - They can be read by looking at the contents of all_channel_counts/ + They can be read by looking at the contents of ``all_channel_counts/``:: - $ for i in /sys/devices/system/edac/mc/mc0/all_channel_counts/*; do echo $i; cat $i; done + $ for i in /sys/devices/system/edac/mc/mc0/all_channel_counts/*; do echo $i; cat $i; done /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm0 0 /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm1 @@ -849,17 +881,21 @@ exports one What happens here is that errors on different csrows, but at the same dimm number will increment the same counter. - So, in this memory mapping: + So, in this memory mapping:: + csrow0: channel 0, dimm0 csrow1: channel 0, dimm1 csrow2: channel 1, dimm0 csrow3: channel 2, dimm0 + The hardware will increment udimm0 for an error at the first dimm at either - csrow0, csrow2 or csrow3; + csrow0, csrow2 or csrow3; + The hardware will increment udimm1 for an error at the second dimm at either - csrow0, csrow2 or csrow3; + csrow0, csrow2 or csrow3; + The hardware will increment udimm2 for an error at the third dimm at either - csrow0, csrow2 or csrow3; + csrow0, csrow2 or csrow3; 4) Standard error counters @@ -868,65 +904,68 @@ exports one possible that some errors could be lost. With rdimm's, they display the contents of the registers -AMD64_EDAC REFERENCE DOCUMENTS USED ------------------------------------ -amd64_edac module is based on the following documents +Reference documents used on ``amd64_edac`` +------------------------------------------ + +``amd64_edac`` module is based on the following documents (available from http://support.amd.com/en-us/search/tech-docs): -1. Title: BIOS and Kernel Developer's Guide for AMD Athlon 64 and AMD +1. :Title: BIOS and Kernel Developer's Guide for AMD Athlon 64 and AMD Opteron Processors - AMD publication #: 26094 - Revision: 3.26 - Link: http://support.amd.com/TechDocs/26094.PDF + :AMD publication #: 26094 + :Revision: 3.26 + :Link: http://support.amd.com/TechDocs/26094.PDF -2. Title: BIOS and Kernel Developer's Guide for AMD NPT Family 0Fh +2. :Title: BIOS and Kernel Developer's Guide for AMD NPT Family 0Fh Processors - AMD publication #: 32559 - Revision: 3.00 - Issue Date: May 2006 - Link: http://support.amd.com/TechDocs/32559.pdf + :AMD publication #: 32559 + :Revision: 3.00 + :Issue Date: May 2006 + :Link: http://support.amd.com/TechDocs/32559.pdf -3. Title: BIOS and Kernel Developer's Guide (BKDG) For AMD Family 10h +3. :Title: BIOS and Kernel Developer's Guide (BKDG) For AMD Family 10h Processors - AMD publication #: 31116 - Revision: 3.00 - Issue Date: September 07, 2007 - Link: http://support.amd.com/TechDocs/31116.pdf + :AMD publication #: 31116 + :Revision: 3.00 + :Issue Date: September 07, 2007 + :Link: http://support.amd.com/TechDocs/31116.pdf -4. Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h +4. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h Models 30h-3Fh Processors - AMD publication #: 49125 - Revision: 3.06 - Issue Date: 2/12/2015 (latest release) - Link: http://support.amd.com/TechDocs/49125_15h_Models_30h-3Fh_BKDG.pdf + :AMD publication #: 49125 + :Revision: 3.06 + :Issue Date: 2/12/2015 (latest release) + :Link: http://support.amd.com/TechDocs/49125_15h_Models_30h-3Fh_BKDG.pdf -5. Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h +5. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h Models 60h-6Fh Processors - AMD publication #: 50742 - Revision: 3.01 - Issue Date: 7/23/2015 (latest release) - Link: http://support.amd.com/TechDocs/50742_15h_Models_60h-6Fh_BKDG.pdf + :AMD publication #: 50742 + :Revision: 3.01 + :Issue Date: 7/23/2015 (latest release) + :Link: http://support.amd.com/TechDocs/50742_15h_Models_60h-6Fh_BKDG.pdf -6. Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 16h +6. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 16h Models 00h-0Fh Processors - AMD publication #: 48751 - Revision: 3.03 - Issue Date: 2/23/2015 (latest release) - Link: http://support.amd.com/TechDocs/48751_16h_bkdg.pdf + :AMD publication #: 48751 + :Revision: 3.03 + :Issue Date: 2/23/2015 (latest release) + :Link: http://support.amd.com/TechDocs/48751_16h_bkdg.pdf + +Credits +======= + +* Written by Doug Thompson -CREDITS: -======== + - 7 Dec 2005 + - 17 Jul 2007 Updated -Written by Doug Thompson -7 Dec 2005 -17 Jul 2007 Updated +* |copy| Mauro Carvalho Chehab -(c) Mauro Carvalho Chehab -05 Aug 2009 Nehalem interface + - 05 Aug 2009 Nehalem interface -EDAC authors/maintainers: +* EDAC authors/maintainers: - Doug Thompson, Dave Jiang, Dave Peterson et al, - Mauro Carvalho Chehab - Borislav Petkov - original author: Thayne Harbaugh + - Doug Thompson, Dave Jiang, Dave Peterson et al, + - Mauro Carvalho Chehab + - Borislav Petkov + - original author: Thayne Harbaugh -- cgit v1.2.3 From de8de8533d1bc13dd3eed3452d611d4457c3fead Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 08:19:57 -0200 Subject: edac.txt: remove info that the Nehalem EDAC is experimental This driver has been there for almost 3 years, without any conceptual changes. So, it is not experimental anymore, and won't likely have any changes at the API or on log outputs. Signed-off-by: Mauro Carvalho Chehab --- Documentation/edac.txt | 4 ---- 1 file changed, 4 deletions(-) diff --git a/Documentation/edac.txt b/Documentation/edac.txt index 316456ba2e0a..fba193044af0 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -744,10 +744,6 @@ http://bluesmoke.sourceforge.net project site for EDAC. Nehalem Usage of EDAC APIs -------------------------- -This chapter documents some EXPERIMENTAL mappings for EDAC API to handle -Nehalem EDAC driver. They will likely be changed on future versions -of the driver. - Due to the way Nehalem exports Memory Controller data, some adjustments were done at i7core_edac driver. This chapter will cover those differences -- cgit v1.2.3 From 0041475f6b2d094710e150cf9dff6b6e2fde87e4 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 08:43:58 -0200 Subject: edac.txt: update information about newer Intel CPUs There's a chapter at edac.rst written by the time Nehalem support was added. Such information is used not only by the Nehalem driver (i7core_edac), but by all newer Intel CPU architectures that are supported by i7core_edac, sb_edac and sbx_edac drivers. Update the information to reflect that. Signed-off-by: Mauro Carvalho Chehab --- Documentation/edac.txt | 44 +++++++++++++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 15 deletions(-) diff --git a/Documentation/edac.txt b/Documentation/edac.txt index fba193044af0..0c9161c9ed7a 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -741,13 +741,25 @@ The ``test_device_edac`` sample driver is located at the http://bluesmoke.sourceforge.net project site for EDAC. -Nehalem Usage of EDAC APIs --------------------------- +Usage of EDAC APIs on Nehalem and newer Intel CPUs +-------------------------------------------------- -Due to the way Nehalem exports Memory Controller data, some adjustments -were done at i7core_edac driver. This chapter will cover those differences +On older Intel architectures, the memory controller was part of the North +Bridge chipset. Nehalem, Sandy Bridge, Ivy Bridge, Haswell, Sky Lake and +newer Intel architectures integrated an enhanced version of the memory +controller (MC) inside the CPUs. -1) On Nehalem, there is one Memory Controller per Quick Patch Interconnect +This chapter will cover the differences of the enhanced memory controllers +found on newer Intel CPUs, such as ``i7core_edac``, ``sb_edac`` and +``sbx_edac`` drivers. + +.. note:: + + The Xeon E7 processor families use a separate chip for the memory + controller, called Intel Scalable Memory Buffer. This section doesn't + apply for such families. + +1) There is one Memory Controller per Quick Patch Interconnect (QPI). At the driver, the term "socket" means one QPI. This is associated with a physical CPU socket. @@ -757,7 +769,7 @@ were done at i7core_edac driver. This chapter will cover those differences The minimum known unity is DIMMs. There are no information about csrows. As EDAC API maps the minimum unity is csrows, the driver sequentially - maps channel/dimm into different csrows. + maps channel/DIMM into different csrows. For example, supposing the following layout:: @@ -780,8 +792,8 @@ were done at i7core_edac driver. This chapter will cover those differences Each QPI is exported as a different memory controller. -2) Nehalem MC has the ability to generate errors. The driver implements this - functionality via some error injection nodes: +2) The MC has the ability to inject errors to test drivers. The drivers + implement this functionality via some error injection nodes: For injecting a memory error, there are some sysfs nodes, under ``/sys/devices/system/edac/mc/mc?/``: @@ -855,13 +867,14 @@ were done at i7core_edac driver. This chapter will cover those differences EDAC MC0: UE row 0, channel-a= 0 channel-b= 0 labels "-": NON_FATAL (addr = 0x0075b980, socket=0, Dimm=0, Channel=2, syndrome=0x00000040, count=1, Err=8c0000400001009f:4000080482 (read error: read ECC error)) -3) Nehalem specific Corrected Error memory counters +3) Corrected Error memory register counters - Nehalem have some registers to count memory errors. The driver uses those - registers to report Corrected Errors on devices with Registered Dimms. + Those newer MCs have some registers to count memory errors. The driver + uses those registers to report Corrected Errors on devices with Registered + DIMMs. - However, those counters don't work with Unregistered Dimms. As the chipset - offers some counters that also work with UDIMMS (but with a worse level of + However, those counters don't work with Unregistered DIMM. As the chipset + offers some counters that also work with UDIMMs (but with a worse level of granularity than the default ones), the driver exposes those registers for UDIMM memories. @@ -896,8 +909,8 @@ were done at i7core_edac driver. This chapter will cover those differences 4) Standard error counters The standard error counters are generated when an mcelog error is received - by the driver. Since, with udimm, this is counted by software, it is - possible that some errors could be lost. With rdimm's, they display the + by the driver. Since, with UDIMM, this is counted by software, it is + possible that some errors could be lost. With RDIMM's, they display the contents of the registers Reference documents used on ``amd64_edac`` @@ -958,6 +971,7 @@ Credits * |copy| Mauro Carvalho Chehab - 05 Aug 2009 Nehalem interface + - 26 Oct 2016 Converted to ReST and cleanups at the Nehalem section * EDAC authors/maintainers: -- cgit v1.2.3 From d68aa2562286084131e40b6cf509998979fde3f2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Oct 2016 09:26:36 -0200 Subject: edac.txt: Improve documentation, adding RAS introduction The edac.txt assumes that the reader has already deep knowledge on RAS features. However, this may not be the case. So, add an introduction chapter explaining the main concepts that are used by the EDAC subsystem and by other RAS drivers within the Kernel. Signed-off-by: Mauro Carvalho Chehab --- Documentation/edac.txt | 287 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 248 insertions(+), 39 deletions(-) diff --git a/Documentation/edac.txt b/Documentation/edac.txt index 0c9161c9ed7a..2f8706bae5a4 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -1,18 +1,218 @@ .. include:: -===================================== +============================================ +Reliability, Availability and Serviceability +============================================ + +RAS concepts +************ + +Reliability, Availability and Serviceability (RAS) is a concept used on +servers meant to measure their robusteness. + +Reliability + is the probability that a system will produce correct outputs. + + * Generally measured as Mean Time Between Failures (MTBF) + * Enhanced by features that help to avoid, detect and repair hardware faults + +Availability + is the probability that a system is operational at a given time + + * Generally measured as a percentage of downtime per a period of time + * Often uses mechanisms to detect and correct hardware faults in + runtime; + +Serviceability (or maintainability) + is the simplicity and speed with which a system can be repaired or + maintained + + * Generally measured on Mean Time Between Repair (MTBR) + +Improving RAS +------------- + +In order to reduce systems downtime, a system should be capable of detecting +hardware errors, and, when possible correcting them in runtime. It should +also provide mechanisms to detect hardware degradation, in order to warn +the system administrator to take the action of replacing a component before +it causes data loss or system downtime. + +Among the monitoring measures, the most usual ones include: + +* CPU – detect errors at instruction execution and at L1/L2/L3 caches; +* Memory – add error correction logic (ECC) to detect and correct errors; +* I/O – add CRC checksums for tranfered data; +* Storage – RAID, journal file systems, checksums, + Self-Monitoring, Analysis and Reporting Technology (SMART). + +By monitoring the number of occurrences of error detections, it is possible +to identify if the probability of hardware errors is increasing, and, on such +case, do a preventive maintainance to replace a degrated component while +those errors are correctable. + +Types of errors +--------------- + +Most mechanisms used on modern systems use use technologies like Hamming +Codes that allow error correction when the number of errors on a bit packet +is below a threshold. If the number of errors is above, those mechanisms +can indicate with a high degree of confidence that an error happened, but +they can't correct. + +Also, sometimes an error occur on a component that it is not used. For +example, a part of the memory that it is not currently allocated. + +That defines some categories of errors: + +* **Correctable Error (CE)** - the error detection mechanism detected and + corrected the error. Such errors are usually not fatal, although some + Kernel mechanisms allow the system administrator to consider them as fatal. + +* **Uncorrected Error (UE)** - the amount of errors happened above the error + correction threshold, and the system was unable to auto-correct. + +* **Fatal Error** - when an UE error happens on a critical component of the + system (for example, a piece of the Kernel got corrupted by an UE), the + only reliable way to avoid data corruption is to hang or reboot the machine. + +* **Non-fatal Error** - when an UE error happens on an unused component, + like a CPU in power down state or an unused memory bank, the system may + still run, eventually replacing the affected hardware by a hot spare, + if available. + + Also, when an error happens on an userspace process, it is also possible to + kill such process and let userspace restart it. + +The mechanism for handling non-fatal errors is usually complex and may +require the help of some userspace application, in order to apply the +policy desired by the system administrator. + +Identifying a bad hardware component +------------------------------------ + +Just detecting a hardware flaw is usually not enough, as the system needs +to pinpoint to the minimal replaceable unit (MRU) that should be exchanged +to make the hardware reliable again. + +So, it requires not only error logging facilities, but also mechanisms that +will translate the error message to the silkscreen or component label for +the MRU. + +Typically, it is very complex for memory, as modern CPUs interlace memory +from different memory modules, in order to provide a better performance. The +DMI BIOS usually have a list of memory module labels, with can be obtained +using the ``dmidecode`` tool. For example, on a desktop machine, it shows:: + + Memory Device + Total Width: 64 bits + Data Width: 64 bits + Size: 16384 MB + Form Factor: SODIMM + Set: None + Locator: ChannelA-DIMM0 + Bank Locator: BANK 0 + Type: DDR4 + Type Detail: Synchronous + Speed: 2133 MHz + Rank: 2 + Configured Clock Speed: 2133 MHz + +On the above example, a DDR4 SO-DIMM memory module is located at the +system's memory labeled as "BANK 0", as given by the *bank locator* field. +Please notice that, on such system, the *total width* is equal to the +*data witdh*. It means that such memory module doesn't have error +detection/correction mechanisms. + +Unfortunately, not all systems use the same field to specify the memory +bank. On this example, from an older server, ``dmidecode`` shows:: + + Memory Device + Array Handle: 0x1000 + Error Information Handle: Not Provided + Total Width: 72 bits + Data Width: 64 bits + Size: 8192 MB + Form Factor: DIMM + Set: 1 + Locator: DIMM_A1 + Bank Locator: Not Specified + Type: DDR3 + Type Detail: Synchronous Registered (Buffered) + Speed: 1600 MHz + Rank: 2 + Configured Clock Speed: 1600 MHz + +There, the DDR3 RDIMM memory module is located at the system's memory labeled +as "DIMM_A1", as given by the *locator* field. Please notice that this +memory module has 64 bits of *data witdh* and 72 bits of *total width*. So, +it has 8 extra bits to be used by error detection and correction mechanisms. +Such kind of memory is called Error-correcting code memory (ECC memory). + +To make things even worse, it is not uncommon that systems with different +labels on their system's board to use exactly the same BIOS, meaning that +the labels provided by the BIOS won't match the real ones. + +ECC memory +---------- + +As mentioned on the previous section, ECC memory has extra bits to be +used for error correction. So, on 64 bit systems, a memory module +has 64 bits of *data width*, and 74 bits of *total width*. So, there are +8 bits extra bits to be used for the error detection and correction +mechanisms. Those extra bits are called *syndrome*\ [#f1]_\ [#f2]_. + +So, when the cpu requests the memory controller to write a word with +*data width*, the memory controller calculates the *syndrome* in real time, +using Hamming code, or some other error correction code, like SECDED+, +producing a code with *total width* size. Such code is then written +on the memory modules. + +At read, the *total width* bits code is converted back, using the same +ECC code used on write, producing a word with *data width* and a *syndrome*. +The word with *data width* is sent to the CPU, even when errors happen. + +The memory controller also looks at the *syndrome* in order to check if +there was an error, and if the ECC code was able to fix such error. +If the error was corrected, a Corrected Error (CE) happened. If not, an +Uncorrected Error (UE) happened. + +The information about the CE/UE errors is stored on some special registers +at the memory controller and can be accessed by reading such registers, +either by BIOS, by some special CPUs or by Linux EDAC driver. On x86 64 +bit CPUs, such errors can also be retrieved via the Machine Check +Architecture (MCA)\ [#f3]_. + +.. [#f1] Please notice that several memory controllers allow operation on a + mode called "Lock-Step", where it groups two memory modules together, + doing 128-bit reads/writes. That gives 16 bits for error correction, with + significatively improves the error correction mechanism, at the expense + that, when an error happens, there's no way to know what memory module is + to blame. So, it has to blame both memory modules. + +.. [#f2] Some memory controllers also allow using memory in mirror mode. + On such mode, the same data is written to two memory modules. At read, + the system checks both memory modules, in order to check if both provide + identical data. On such configuration, when an error happens, there's no + way to know what memory module is to blame. So, it has to blame both + memory modules (or 4 memory modules, if the system is also on Lock-step + mode). + +.. [#f3] For more details about the Machine Check Architecture (MCA), + please read Documentation/x86/x86_64/machinecheck at the Kernel tree. + EDAC - Error Detection And Correction -===================================== +************************************* .. note:: - "bluesmoke" was the name for this device driver when it + "bluesmoke" was the name for this device driver subsystem when it was "out-of-tree" and maintained at http://bluesmoke.sourceforge.net. That site is mostly archaic now and can be used only for historical purposes. - When the subsystem was pushed into 2.6.16 for the first time, it was - renamed to ``EDAC``. + When the subsystem was pushed upstream for the first time, on + Kernel 2.6.16, for the first time, it was renamed to ``EDAC``. Purpose ------- @@ -33,7 +233,7 @@ CE events only, the system can and will continue to operate as no data has been damaged yet. However, preventive maintenance and proactive part replacement of memory -DIMMs exhibiting CEs can reduce the likelihood of the dreaded UE events +modules exhibiting CEs can reduce the likelihood of the dreaded UE events and system panics. Other hardware elements @@ -124,37 +324,47 @@ Within this directory there currently reside 2 components: Memory Controller (mc) Model ---------------------------- -Each ``mc`` device controls a set of DIMM memory modules. These modules +Each ``mc`` device controls a set of memory modules [#f4]_. These modules are laid out in a Chip-Select Row (``csrowX``) and Channel table (``chX``). There can be multiple csrows and multiple channels. +.. [#f4] Nowadays, the term DIMM (Dual In-line Memory Module) is widely + used to refer to a memory module, although there are other memory + packaging alternatives, like SO-DIMM, SIMM, etc. Along this document, + and inside the EDAC system, the term "dimm" is used for all memory + modules, even when they use a different kind of packaging. + Memory controllers allow for several csrows, with 8 csrows being a typical value. Yet, the actual number of csrows depends on the layout of -a given motherboard, memory controller and DIMM characteristics. - -Dual channels allows for 128 bit data transfers to/from the CPU from/to -memory. Some newer chipsets allow for more than 2 channels, like Fully -Buffered DIMMs (FB-DIMMs). The following example will assume 2 channels: - - +--------+-----------+-----------+ - | | Channel 0 | Channel 1 | - +========+===========+===========+ - | csrow0 | DIMM_A0 | DIMM_B0 | - +--------+ | | - | csrow1 | | | - +--------+-----------+-----------+ - | csrow2 | DIMM_A1 | DIMM_B1 | - +--------+ | | - | csrow3 | | | - +--------+-----------+-----------+ - -In the above example table there are 4 physical slots on the motherboard +a given motherboard, memory controller and memory module characteristics. + +Dual channels allow for dual data length (e. g. 128 bits, on 64 bit systems) +data transfers to/from the CPU from/to memory. Some newer chipsets allow +for more than 2 channels, like Fully Buffered DIMMs (FB-DIMMs) memory +controllers. The following example will assume 2 channels: + + +------------+-----------------------+ + | Chip | Channels | + | Select +-----------+-----------+ + | rows | ``ch0`` | ``ch1`` | + +============+===========+===========+ + | ``csrow0`` | DIMM_A0 | DIMM_B0 | + +------------+ | | + | ``csrow1`` | | | + +------------+-----------+-----------+ + | ``csrow2`` | DIMM_A1 | DIMM_B1 | + +------------+ | | + | ``csrow3`` | | | + +------------+-----------+-----------+ + +In the above example, there are 4 physical slots on the motherboard for memory DIMMs: - - DIMM_A0 - - DIMM_B0 - - DIMM_A1 - - DIMM_B1 + +---------+---------+ + | DIMM_A0 | DIMM_B0 | + +---------+---------+ + | DIMM_A1 | DIMM_B1 | + +---------+---------+ Labels for these slots are usually silk-screened on the motherboard. Slots labeled ``A`` are channel 0 in this example. Slots labeled ``B`` are @@ -165,15 +375,16 @@ Channel, the csrows cross both DIMMs. Memory DIMMs come single or dual "ranked". A rank is a populated csrow. Thus, 2 single ranked DIMMs, placed in slots DIMM_A0 and DIMM_B0 above -will have 1 csrow, csrow0. csrow1 will be empty. On the other hand, -when 2 dual ranked DIMMs are similarly placed, then both csrow0 and -csrow1 will be populated. The pattern repeats itself for csrow2 and +will have just one csrow (csrow0). csrow1 will be empty. On the other +hand, when 2 dual ranked DIMMs are similarly placed, then both csrow0 +and csrow1 will be populated. The pattern repeats itself for csrow2 and csrow3. The representation of the above is reflected in the directory tree in EDAC's sysfs interface. Starting in directory -/sys/devices/system/edac/mc each memory controller will be represented -by its own ``mcX`` directory, where ``X`` is the index of the MC:: +``/sys/devices/system/edac/mc``, each memory controller will be +represented by its own ``mcX`` directory, where ``X`` is the +index of the MC:: ..../edac/mc/ | @@ -198,11 +409,9 @@ order to have dual-channel mode be operational. Since both csrow2 and csrow3 are populated, this indicates a dual ranked set of DIMMs for channels 0 and 1. - Within each of the ``mcX`` and ``csrowX`` directories are several EDAC control and attribute files. - ``mcX`` directories ------------------- @@ -338,10 +547,10 @@ this ``X`` memory module: ``csrowX`` directories ---------------------- -When CONFIG_EDAC_LEGACY_SYSFS is enabled, sysfs will contain the csrowX +When CONFIG_EDAC_LEGACY_SYSFS is enabled, sysfs will contain the ``csrowX`` directories. As this API doesn't work properly for Rambus, FB-DIMMs and modern Intel Memory Controllers, this is being deprecated in favor of -dimmX directories. +``dimmX`` directories. In the ``csrowX`` directories are EDAC control and attribute files for this ``X`` instance of csrow: -- cgit v1.2.3 From b06ee0d49311666c5e06311e0f18a0161ec18df5 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 16:24:41 -0200 Subject: docs-rst: admin-guide: add documentation for EDAC EDAC is part of the Kernel's RAS facilities, with is useful for system admins to detect errors. So, add it to the admin's guide. Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/index.rst | 1 + Documentation/admin-guide/ras.rst | 1190 +++++++++++++++++++++++++++++++++++ Documentation/edac.txt | 1190 ----------------------------------- 3 files changed, 1191 insertions(+), 1190 deletions(-) create mode 100644 Documentation/admin-guide/ras.rst delete mode 100644 Documentation/edac.txt diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index 2681cbd24cdd..8ddae4e4299a 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -59,6 +59,7 @@ configure specific aspects of kernel behavior to your liking. binfmt-misc mono java + ras .. only:: subproject and html diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/ras.rst new file mode 100644 index 000000000000..2f8706bae5a4 --- /dev/null +++ b/Documentation/admin-guide/ras.rst @@ -0,0 +1,1190 @@ +.. include:: + +============================================ +Reliability, Availability and Serviceability +============================================ + +RAS concepts +************ + +Reliability, Availability and Serviceability (RAS) is a concept used on +servers meant to measure their robusteness. + +Reliability + is the probability that a system will produce correct outputs. + + * Generally measured as Mean Time Between Failures (MTBF) + * Enhanced by features that help to avoid, detect and repair hardware faults + +Availability + is the probability that a system is operational at a given time + + * Generally measured as a percentage of downtime per a period of time + * Often uses mechanisms to detect and correct hardware faults in + runtime; + +Serviceability (or maintainability) + is the simplicity and speed with which a system can be repaired or + maintained + + * Generally measured on Mean Time Between Repair (MTBR) + +Improving RAS +------------- + +In order to reduce systems downtime, a system should be capable of detecting +hardware errors, and, when possible correcting them in runtime. It should +also provide mechanisms to detect hardware degradation, in order to warn +the system administrator to take the action of replacing a component before +it causes data loss or system downtime. + +Among the monitoring measures, the most usual ones include: + +* CPU – detect errors at instruction execution and at L1/L2/L3 caches; +* Memory – add error correction logic (ECC) to detect and correct errors; +* I/O – add CRC checksums for tranfered data; +* Storage – RAID, journal file systems, checksums, + Self-Monitoring, Analysis and Reporting Technology (SMART). + +By monitoring the number of occurrences of error detections, it is possible +to identify if the probability of hardware errors is increasing, and, on such +case, do a preventive maintainance to replace a degrated component while +those errors are correctable. + +Types of errors +--------------- + +Most mechanisms used on modern systems use use technologies like Hamming +Codes that allow error correction when the number of errors on a bit packet +is below a threshold. If the number of errors is above, those mechanisms +can indicate with a high degree of confidence that an error happened, but +they can't correct. + +Also, sometimes an error occur on a component that it is not used. For +example, a part of the memory that it is not currently allocated. + +That defines some categories of errors: + +* **Correctable Error (CE)** - the error detection mechanism detected and + corrected the error. Such errors are usually not fatal, although some + Kernel mechanisms allow the system administrator to consider them as fatal. + +* **Uncorrected Error (UE)** - the amount of errors happened above the error + correction threshold, and the system was unable to auto-correct. + +* **Fatal Error** - when an UE error happens on a critical component of the + system (for example, a piece of the Kernel got corrupted by an UE), the + only reliable way to avoid data corruption is to hang or reboot the machine. + +* **Non-fatal Error** - when an UE error happens on an unused component, + like a CPU in power down state or an unused memory bank, the system may + still run, eventually replacing the affected hardware by a hot spare, + if available. + + Also, when an error happens on an userspace process, it is also possible to + kill such process and let userspace restart it. + +The mechanism for handling non-fatal errors is usually complex and may +require the help of some userspace application, in order to apply the +policy desired by the system administrator. + +Identifying a bad hardware component +------------------------------------ + +Just detecting a hardware flaw is usually not enough, as the system needs +to pinpoint to the minimal replaceable unit (MRU) that should be exchanged +to make the hardware reliable again. + +So, it requires not only error logging facilities, but also mechanisms that +will translate the error message to the silkscreen or component label for +the MRU. + +Typically, it is very complex for memory, as modern CPUs interlace memory +from different memory modules, in order to provide a better performance. The +DMI BIOS usually have a list of memory module labels, with can be obtained +using the ``dmidecode`` tool. For example, on a desktop machine, it shows:: + + Memory Device + Total Width: 64 bits + Data Width: 64 bits + Size: 16384 MB + Form Factor: SODIMM + Set: None + Locator: ChannelA-DIMM0 + Bank Locator: BANK 0 + Type: DDR4 + Type Detail: Synchronous + Speed: 2133 MHz + Rank: 2 + Configured Clock Speed: 2133 MHz + +On the above example, a DDR4 SO-DIMM memory module is located at the +system's memory labeled as "BANK 0", as given by the *bank locator* field. +Please notice that, on such system, the *total width* is equal to the +*data witdh*. It means that such memory module doesn't have error +detection/correction mechanisms. + +Unfortunately, not all systems use the same field to specify the memory +bank. On this example, from an older server, ``dmidecode`` shows:: + + Memory Device + Array Handle: 0x1000 + Error Information Handle: Not Provided + Total Width: 72 bits + Data Width: 64 bits + Size: 8192 MB + Form Factor: DIMM + Set: 1 + Locator: DIMM_A1 + Bank Locator: Not Specified + Type: DDR3 + Type Detail: Synchronous Registered (Buffered) + Speed: 1600 MHz + Rank: 2 + Configured Clock Speed: 1600 MHz + +There, the DDR3 RDIMM memory module is located at the system's memory labeled +as "DIMM_A1", as given by the *locator* field. Please notice that this +memory module has 64 bits of *data witdh* and 72 bits of *total width*. So, +it has 8 extra bits to be used by error detection and correction mechanisms. +Such kind of memory is called Error-correcting code memory (ECC memory). + +To make things even worse, it is not uncommon that systems with different +labels on their system's board to use exactly the same BIOS, meaning that +the labels provided by the BIOS won't match the real ones. + +ECC memory +---------- + +As mentioned on the previous section, ECC memory has extra bits to be +used for error correction. So, on 64 bit systems, a memory module +has 64 bits of *data width*, and 74 bits of *total width*. So, there are +8 bits extra bits to be used for the error detection and correction +mechanisms. Those extra bits are called *syndrome*\ [#f1]_\ [#f2]_. + +So, when the cpu requests the memory controller to write a word with +*data width*, the memory controller calculates the *syndrome* in real time, +using Hamming code, or some other error correction code, like SECDED+, +producing a code with *total width* size. Such code is then written +on the memory modules. + +At read, the *total width* bits code is converted back, using the same +ECC code used on write, producing a word with *data width* and a *syndrome*. +The word with *data width* is sent to the CPU, even when errors happen. + +The memory controller also looks at the *syndrome* in order to check if +there was an error, and if the ECC code was able to fix such error. +If the error was corrected, a Corrected Error (CE) happened. If not, an +Uncorrected Error (UE) happened. + +The information about the CE/UE errors is stored on some special registers +at the memory controller and can be accessed by reading such registers, +either by BIOS, by some special CPUs or by Linux EDAC driver. On x86 64 +bit CPUs, such errors can also be retrieved via the Machine Check +Architecture (MCA)\ [#f3]_. + +.. [#f1] Please notice that several memory controllers allow operation on a + mode called "Lock-Step", where it groups two memory modules together, + doing 128-bit reads/writes. That gives 16 bits for error correction, with + significatively improves the error correction mechanism, at the expense + that, when an error happens, there's no way to know what memory module is + to blame. So, it has to blame both memory modules. + +.. [#f2] Some memory controllers also allow using memory in mirror mode. + On such mode, the same data is written to two memory modules. At read, + the system checks both memory modules, in order to check if both provide + identical data. On such configuration, when an error happens, there's no + way to know what memory module is to blame. So, it has to blame both + memory modules (or 4 memory modules, if the system is also on Lock-step + mode). + +.. [#f3] For more details about the Machine Check Architecture (MCA), + please read Documentation/x86/x86_64/machinecheck at the Kernel tree. + +EDAC - Error Detection And Correction +************************************* + +.. note:: + + "bluesmoke" was the name for this device driver subsystem when it + was "out-of-tree" and maintained at http://bluesmoke.sourceforge.net. + That site is mostly archaic now and can be used only for historical + purposes. + + When the subsystem was pushed upstream for the first time, on + Kernel 2.6.16, for the first time, it was renamed to ``EDAC``. + +Purpose +------- + +The ``edac`` kernel module's goal is to detect and report hardware errors +that occur within the computer system running under linux. + +Memory +------ + +Memory Correctable Errors (CE) and Uncorrectable Errors (UE) are the +primary errors being harvested. These types of errors are harvested by +the ``edac_mc`` device. + +Detecting CE events, then harvesting those events and reporting them, +**can** but must not necessarily be a predictor of future UE events. With +CE events only, the system can and will continue to operate as no data +has been damaged yet. + +However, preventive maintenance and proactive part replacement of memory +modules exhibiting CEs can reduce the likelihood of the dreaded UE events +and system panics. + +Other hardware elements +----------------------- + +A new feature for EDAC, the ``edac_device`` class of device, was added in +the 2.6.23 version of the kernel. + +This new device type allows for non-memory type of ECC hardware detectors +to have their states harvested and presented to userspace via the sysfs +interface. + +Some architectures have ECC detectors for L1, L2 and L3 caches, +along with DMA engines, fabric switches, main data path switches, +interconnections, and various other hardware data paths. If the hardware +reports it, then a edac_device device probably can be constructed to +harvest and present that to userspace. + + +PCI bus scanning +---------------- + +In addition, PCI devices are scanned for PCI Bus Parity and SERR Errors +in order to determine if errors are occurring during data transfers. + +The presence of PCI Parity errors must be examined with a grain of salt. +There are several add-in adapters that do **not** follow the PCI specification +with regards to Parity generation and reporting. The specification says +the vendor should tie the parity status bits to 0 if they do not intend +to generate parity. Some vendors do not do this, and thus the parity bit +can "float" giving false positives. + +There is a PCI device attribute located in sysfs that is checked by +the EDAC PCI scanning code. If that attribute is set, PCI parity/error +scanning is skipped for that device. The attribute is:: + + broken_parity_status + +and is located in ``/sys/devices/pci/0000:XX:YY.Z`` directories for +PCI devices. + + +Versioning +---------- + +EDAC is composed of a "core" module (``edac_core.ko``) and several Memory +Controller (MC) driver modules. On a given system, the CORE is loaded +and one MC driver will be loaded. Both the CORE and the MC driver (or +``edac_device`` driver) have individual versions that reflect current +release level of their respective modules. + +Thus, to "report" on what version a system is running, one must report +both the CORE's and the MC driver's versions. + + +Loading +------- + +If ``edac`` was statically linked with the kernel then no loading +is necessary. If ``edac`` was built as modules then simply modprobe +the ``edac`` pieces that you need. You should be able to modprobe +hardware-specific modules and have the dependencies load the necessary +core modules. + +Example:: + + $ modprobe amd76x_edac + +loads both the ``amd76x_edac.ko`` memory controller module and the +``edac_mc.ko`` core module. + + +Sysfs interface +--------------- + +EDAC presents a ``sysfs`` interface for control and reporting purposes. It +lives in the /sys/devices/system/edac directory. + +Within this directory there currently reside 2 components: + + ======= ============================== + mc memory controller(s) system + pci PCI control and status system + ======= ============================== + + + +Memory Controller (mc) Model +---------------------------- + +Each ``mc`` device controls a set of memory modules [#f4]_. These modules +are laid out in a Chip-Select Row (``csrowX``) and Channel table (``chX``). +There can be multiple csrows and multiple channels. + +.. [#f4] Nowadays, the term DIMM (Dual In-line Memory Module) is widely + used to refer to a memory module, although there are other memory + packaging alternatives, like SO-DIMM, SIMM, etc. Along this document, + and inside the EDAC system, the term "dimm" is used for all memory + modules, even when they use a different kind of packaging. + +Memory controllers allow for several csrows, with 8 csrows being a +typical value. Yet, the actual number of csrows depends on the layout of +a given motherboard, memory controller and memory module characteristics. + +Dual channels allow for dual data length (e. g. 128 bits, on 64 bit systems) +data transfers to/from the CPU from/to memory. Some newer chipsets allow +for more than 2 channels, like Fully Buffered DIMMs (FB-DIMMs) memory +controllers. The following example will assume 2 channels: + + +------------+-----------------------+ + | Chip | Channels | + | Select +-----------+-----------+ + | rows | ``ch0`` | ``ch1`` | + +============+===========+===========+ + | ``csrow0`` | DIMM_A0 | DIMM_B0 | + +------------+ | | + | ``csrow1`` | | | + +------------+-----------+-----------+ + | ``csrow2`` | DIMM_A1 | DIMM_B1 | + +------------+ | | + | ``csrow3`` | | | + +------------+-----------+-----------+ + +In the above example, there are 4 physical slots on the motherboard +for memory DIMMs: + + +---------+---------+ + | DIMM_A0 | DIMM_B0 | + +---------+---------+ + | DIMM_A1 | DIMM_B1 | + +---------+---------+ + +Labels for these slots are usually silk-screened on the motherboard. +Slots labeled ``A`` are channel 0 in this example. Slots labeled ``B`` are +channel 1. Notice that there are two csrows possible on a physical DIMM. +These csrows are allocated their csrow assignment based on the slot into +which the memory DIMM is placed. Thus, when 1 DIMM is placed in each +Channel, the csrows cross both DIMMs. + +Memory DIMMs come single or dual "ranked". A rank is a populated csrow. +Thus, 2 single ranked DIMMs, placed in slots DIMM_A0 and DIMM_B0 above +will have just one csrow (csrow0). csrow1 will be empty. On the other +hand, when 2 dual ranked DIMMs are similarly placed, then both csrow0 +and csrow1 will be populated. The pattern repeats itself for csrow2 and +csrow3. + +The representation of the above is reflected in the directory +tree in EDAC's sysfs interface. Starting in directory +``/sys/devices/system/edac/mc``, each memory controller will be +represented by its own ``mcX`` directory, where ``X`` is the +index of the MC:: + + ..../edac/mc/ + | + |->mc0 + |->mc1 + |->mc2 + .... + +Under each ``mcX`` directory each ``csrowX`` is again represented by a +``csrowX``, where ``X`` is the csrow index:: + + .../mc/mc0/ + | + |->csrow0 + |->csrow2 + |->csrow3 + .... + +Notice that there is no csrow1, which indicates that csrow0 is composed +of a single ranked DIMMs. This should also apply in both Channels, in +order to have dual-channel mode be operational. Since both csrow2 and +csrow3 are populated, this indicates a dual ranked set of DIMMs for +channels 0 and 1. + +Within each of the ``mcX`` and ``csrowX`` directories are several EDAC +control and attribute files. + +``mcX`` directories +------------------- + +In ``mcX`` directories are EDAC control and attribute files for +this ``X`` instance of the memory controllers. + +For a description of the sysfs API, please see: + + Documentation/ABI/testing/sysfs-devices-edac + + +``dimmX`` or ``rankX`` directories +---------------------------------- + +The recommended way to use the EDAC subsystem is to look at the information +provided by the ``dimmX`` or ``rankX`` directories [#f5]_. + +A typical EDAC system has the following structure under +``/sys/devices/system/edac/``\ [#f6]_:: + + /sys/devices/system/edac/ + ├── mc + │   ├── mc0 + │   │   ├── ce_count + │   │   ├── ce_noinfo_count + │   │   ├── dimm0 + │   │   │   ├── dimm_dev_type + │   │   │   ├── dimm_edac_mode + │   │   │   ├── dimm_label + │   │   │   ├── dimm_location + │   │   │   ├── dimm_mem_type + │   │   │   ├── size + │   │   │   └── uevent + │   │   ├── max_location + │   │   ├── mc_name + │   │   ├── reset_counters + │   │   ├── seconds_since_reset + │   │   ├── size_mb + │   │   ├── ue_count + │   │   ├── ue_noinfo_count + │   │   └── uevent + │   ├── mc1 + │   │   ├── ce_count + │   │   ├── ce_noinfo_count + │   │   ├── dimm0 + │   │   │   ├── dimm_dev_type + │   │   │   ├── dimm_edac_mode + │   │   │   ├── dimm_label + │   │   │   ├── dimm_location + │   │   │   ├── dimm_mem_type + │   │   │   ├── size + │   │   │   └── uevent + │   │   ├── max_location + │   │   ├── mc_name + │   │   ├── reset_counters + │   │   ├── seconds_since_reset + │   │   ├── size_mb + │   │   ├── ue_count + │   │   ├── ue_noinfo_count + │   │   └── uevent + │   └── uevent + └── uevent + +In the ``dimmX`` directories are EDAC control and attribute files for +this ``X`` memory module: + +- ``size`` - Total memory managed by this csrow attribute file + + This attribute file displays, in count of megabytes, the memory + that this csrow contains. + +- ``dimm_dev_type`` - Device type attribute file + + This attribute file will display what type of DRAM device is + being utilized on this DIMM. + Examples: + + - x1 + - x2 + - x4 + - x8 + +- ``dimm_edac_mode`` - EDAC Mode of operation attribute file + + This attribute file will display what type of Error detection + and correction is being utilized. + +- ``dimm_label`` - memory module label control file + + This control file allows this DIMM to have a label assigned + to it. With this label in the module, when errors occur + the output can provide the DIMM label in the system log. + This becomes vital for panic events to isolate the + cause of the UE event. + + DIMM Labels must be assigned after booting, with information + that correctly identifies the physical slot with its + silk screen label. This information is currently very + motherboard specific and determination of this information + must occur in userland at this time. + +- ``dimm_location`` - location of the memory module + + The location can have up to 3 levels, and describe how the + memory controller identifies the location of a memory module. + Depending on the type of memory and memory controller, it + can be: + + - *csrow* and *channel* - used when the memory controller + doesn't identify a single DIMM - e. g. in ``rankX`` dir; + - *branch*, *channel*, *slot* - typically used on FB-DIMM memory + controllers; + - *channel*, *slot* - used on Nehalem and newer Intel drivers. + +- ``dimm_mem_type`` - Memory Type attribute file + + This attribute file will display what type of memory is currently + on this csrow. Normally, either buffered or unbuffered memory. + Examples: + + - Registered-DDR + - Unbuffered-DDR + +.. [#f5] On some systems, the memory controller doesn't have any logic + to identify the memory module. On such systems, the directory is called ``rankX`` and works on a similar way as the ``csrowX`` directories. + On modern Intel memory controllers, the memory controller identifies the + memory modules directly. On such systems, the directory is called ``dimmX``. + +.. [#f6] There are also some ``power`` directories and ``subsystem`` + symlinks inside the sysfs mapping that are automatically created by + the sysfs subsystem. Currently, they serve no purpose. + +``csrowX`` directories +---------------------- + +When CONFIG_EDAC_LEGACY_SYSFS is enabled, sysfs will contain the ``csrowX`` +directories. As this API doesn't work properly for Rambus, FB-DIMMs and +modern Intel Memory Controllers, this is being deprecated in favor of +``dimmX`` directories. + +In the ``csrowX`` directories are EDAC control and attribute files for +this ``X`` instance of csrow: + + +- ``ue_count`` - Total Uncorrectable Errors count attribute file + + This attribute file displays the total count of uncorrectable + errors that have occurred on this csrow. If panic_on_ue is set + this counter will not have a chance to increment, since EDAC + will panic the system. + + +- ``ce_count`` - Total Correctable Errors count attribute file + + This attribute file displays the total count of correctable + errors that have occurred on this csrow. This count is very + important to examine. CEs provide early indications that a + DIMM is beginning to fail. This count field should be + monitored for non-zero values and report such information + to the system administrator. + + +- ``size_mb`` - Total memory managed by this csrow attribute file + + This attribute file displays, in count of megabytes, the memory + that this csrow contains. + + +- ``mem_type`` - Memory Type attribute file + + This attribute file will display what type of memory is currently + on this csrow. Normally, either buffered or unbuffered memory. + Examples: + + - Registered-DDR + - Unbuffered-DDR + + +- ``edac_mode`` - EDAC Mode of operation attribute file + + This attribute file will display what type of Error detection + and correction is being utilized. + + +- ``dev_type`` - Device type attribute file + + This attribute file will display what type of DRAM device is + being utilized on this DIMM. + Examples: + + - x1 + - x2 + - x4 + - x8 + + +- ``ch0_ce_count`` - Channel 0 CE Count attribute file + + This attribute file will display the count of CEs on this + DIMM located in channel 0. + + +- ``ch0_ue_count`` - Channel 0 UE Count attribute file + + This attribute file will display the count of UEs on this + DIMM located in channel 0. + + +- ``ch0_dimm_label`` - Channel 0 DIMM Label control file + + + This control file allows this DIMM to have a label assigned + to it. With this label in the module, when errors occur + the output can provide the DIMM label in the system log. + This becomes vital for panic events to isolate the + cause of the UE event. + + DIMM Labels must be assigned after booting, with information + that correctly identifies the physical slot with its + silk screen label. This information is currently very + motherboard specific and determination of this information + must occur in userland at this time. + + +- ``ch1_ce_count`` - Channel 1 CE Count attribute file + + + This attribute file will display the count of CEs on this + DIMM located in channel 1. + + +- ``ch1_ue_count`` - Channel 1 UE Count attribute file + + + This attribute file will display the count of UEs on this + DIMM located in channel 0. + + +- ``ch1_dimm_label`` - Channel 1 DIMM Label control file + + This control file allows this DIMM to have a label assigned + to it. With this label in the module, when errors occur + the output can provide the DIMM label in the system log. + This becomes vital for panic events to isolate the + cause of the UE event. + + DIMM Labels must be assigned after booting, with information + that correctly identifies the physical slot with its + silk screen label. This information is currently very + motherboard specific and determination of this information + must occur in userland at this time. + + +System Logging +-------------- + +If logging for UEs and CEs is enabled, then system logs will contain +information indicating that errors have been detected:: + + EDAC MC0: CE page 0x283, offset 0xce0, grain 8, syndrome 0x6ec3, row 0, channel 1 "DIMM_B1": amd76x_edac + EDAC MC0: CE page 0x1e5, offset 0xfb0, grain 8, syndrome 0xb741, row 0, channel 1 "DIMM_B1": amd76x_edac + + +The structure of the message is: + + +---------------------------------------+-------------+ + | Content + Example | + +=======================================+=============+ + | The memory controller | MC0 | + +---------------------------------------+-------------+ + | Error type | CE | + +---------------------------------------+-------------+ + | Memory page | 0x283 | + +---------------------------------------+-------------+ + | Offset in the page | 0xce0 | + +---------------------------------------+-------------+ + | The byte granularity | grain 8 | + | or resolution of the error | | + +---------------------------------------+-------------+ + | The error syndrome | 0xb741 | + +---------------------------------------+-------------+ + | Memory row | row 0 + + +---------------------------------------+-------------+ + | Memory channel | channel 1 | + +---------------------------------------+-------------+ + | DIMM label, if set prior | DIMM B1 | + +---------------------------------------+-------------+ + | And then an optional, driver-specific | | + | message that may have additional | | + | information. | | + +---------------------------------------+-------------+ + +Both UEs and CEs with no info will lack all but memory controller, error +type, a notice of "no info" and then an optional, driver-specific error +message. + + +PCI Bus Parity Detection +------------------------ + +On Header Type 00 devices, the primary status is looked at for any +parity error regardless of whether parity is enabled on the device or +not. (The spec indicates parity is generated in some cases). On Header +Type 01 bridges, the secondary status register is also looked at to see +if parity occurred on the bus on the other side of the bridge. + + +Sysfs configuration +------------------- + +Under ``/sys/devices/system/edac/pci`` are control and attribute files as +follows: + + +- ``check_pci_parity`` - Enable/Disable PCI Parity checking control file + + This control file enables or disables the PCI Bus Parity scanning + operation. Writing a 1 to this file enables the scanning. Writing + a 0 to this file disables the scanning. + + Enable:: + + echo "1" >/sys/devices/system/edac/pci/check_pci_parity + + Disable:: + + echo "0" >/sys/devices/system/edac/pci/check_pci_parity + + +- ``pci_parity_count`` - Parity Count + + This attribute file will display the number of parity errors that + have been detected. + + +Module parameters +----------------- + +- ``edac_mc_panic_on_ue`` - Panic on UE control file + + An uncorrectable error will cause a machine panic. This is usually + desirable. It is a bad idea to continue when an uncorrectable error + occurs - it is indeterminate what was uncorrected and the operating + system context might be so mangled that continuing will lead to further + corruption. If the kernel has MCE configured, then EDAC will never + notice the UE. + + LOAD TIME:: + + module/kernel parameter: edac_mc_panic_on_ue=[0|1] + + RUN TIME:: + + echo "1" > /sys/module/edac_core/parameters/edac_mc_panic_on_ue + + +- ``edac_mc_log_ue`` - Log UE control file + + + Generate kernel messages describing uncorrectable errors. These errors + are reported through the system message log system. UE statistics + will be accumulated even when UE logging is disabled. + + LOAD TIME:: + + module/kernel parameter: edac_mc_log_ue=[0|1] + + RUN TIME:: + + echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ue + + +- ``edac_mc_log_ce`` - Log CE control file + + + Generate kernel messages describing correctable errors. These + errors are reported through the system message log system. + CE statistics will be accumulated even when CE logging is disabled. + + LOAD TIME:: + + module/kernel parameter: edac_mc_log_ce=[0|1] + + RUN TIME:: + + echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ce + + +- ``edac_mc_poll_msec`` - Polling period control file + + + The time period, in milliseconds, for polling for error information. + Too small a value wastes resources. Too large a value might delay + necessary handling of errors and might loose valuable information for + locating the error. 1000 milliseconds (once each second) is the current + default. Systems which require all the bandwidth they can get, may + increase this. + + LOAD TIME:: + + module/kernel parameter: edac_mc_poll_msec=[0|1] + + RUN TIME:: + + echo "1000" > /sys/module/edac_core/parameters/edac_mc_poll_msec + + +- ``panic_on_pci_parity`` - Panic on PCI PARITY Error + + + This control file enables or disables panicking when a parity + error has been detected. + + + module/kernel parameter:: + + edac_panic_on_pci_pe=[0|1] + + Enable:: + + echo "1" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe + + Disable:: + + echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe + + + +EDAC device type +---------------- + +In the header file, edac_core.h, there is a series of edac_device structures +and APIs for the EDAC_DEVICE. + +User space access to an edac_device is through the sysfs interface. + +At the location ``/sys/devices/system/edac`` (sysfs) new edac_device devices +will appear. + +There is a three level tree beneath the above ``edac`` directory. For example, +the ``test_device_edac`` device (found at the http://bluesmoke.sourceforget.net +website) installs itself as:: + + /sys/devices/system/edac/test-instance + +in this directory are various controls, a symlink and one or more ``instance`` +directories. + +The standard default controls are: + + ============== ======================================================= + log_ce boolean to log CE events + log_ue boolean to log UE events + panic_on_ue boolean to ``panic`` the system if an UE is encountered + (default off, can be set true via startup script) + poll_msec time period between POLL cycles for events + ============== ======================================================= + +The test_device_edac device adds at least one of its own custom control: + + ============== ================================================== + test_bits which in the current test driver does nothing but + show how it is installed. A ported driver can + add one or more such controls and/or attributes + for specific uses. + One out-of-tree driver uses controls here to allow + for ERROR INJECTION operations to hardware + injection registers + ============== ================================================== + +The symlink points to the 'struct dev' that is registered for this edac_device. + +Instances +--------- + +One or more instance directories are present. For the ``test_device_edac`` +case: + + +----------------+ + | test-instance0 | + +----------------+ + + +In this directory there are two default counter attributes, which are totals of +counter in deeper subdirectories. + + ============== ==================================== + ce_count total of CE events of subdirectories + ue_count total of UE events of subdirectories + ============== ==================================== + +Blocks +------ + +At the lowest directory level is the ``block`` directory. There can be 0, 1 +or more blocks specified in each instance: + + +-------------+ + | test-block0 | + +-------------+ + +In this directory the default attributes are: + + ============== ================================================ + ce_count which is counter of CE events for this ``block`` + of hardware being monitored + ue_count which is counter of UE events for this ``block`` + of hardware being monitored + ============== ================================================ + + +The ``test_device_edac`` device adds 4 attributes and 1 control: + + ================== ==================================================== + test-block-bits-0 for every POLL cycle this counter + is incremented + test-block-bits-1 every 10 cycles, this counter is bumped once, + and test-block-bits-0 is set to 0 + test-block-bits-2 every 100 cycles, this counter is bumped once, + and test-block-bits-1 is set to 0 + test-block-bits-3 every 1000 cycles, this counter is bumped once, + and test-block-bits-2 is set to 0 + ================== ==================================================== + + + ================== ==================================================== + reset-counters writing ANY thing to this control will + reset all the above counters. + ================== ==================================================== + + +Use of the ``test_device_edac`` driver should enable any others to create their own +unique drivers for their hardware systems. + +The ``test_device_edac`` sample driver is located at the +http://bluesmoke.sourceforge.net project site for EDAC. + + +Usage of EDAC APIs on Nehalem and newer Intel CPUs +-------------------------------------------------- + +On older Intel architectures, the memory controller was part of the North +Bridge chipset. Nehalem, Sandy Bridge, Ivy Bridge, Haswell, Sky Lake and +newer Intel architectures integrated an enhanced version of the memory +controller (MC) inside the CPUs. + +This chapter will cover the differences of the enhanced memory controllers +found on newer Intel CPUs, such as ``i7core_edac``, ``sb_edac`` and +``sbx_edac`` drivers. + +.. note:: + + The Xeon E7 processor families use a separate chip for the memory + controller, called Intel Scalable Memory Buffer. This section doesn't + apply for such families. + +1) There is one Memory Controller per Quick Patch Interconnect + (QPI). At the driver, the term "socket" means one QPI. This is + associated with a physical CPU socket. + + Each MC have 3 physical read channels, 3 physical write channels and + 3 logic channels. The driver currently sees it as just 3 channels. + Each channel can have up to 3 DIMMs. + + The minimum known unity is DIMMs. There are no information about csrows. + As EDAC API maps the minimum unity is csrows, the driver sequentially + maps channel/DIMM into different csrows. + + For example, supposing the following layout:: + + Ch0 phy rd0, wr0 (0x063f4031): 2 ranks, UDIMMs + dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 + dimm 1 1024 Mb offset: 4, bank: 8, rank: 1, row: 0x4000, col: 0x400 + Ch1 phy rd1, wr1 (0x063f4031): 2 ranks, UDIMMs + dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 + Ch2 phy rd3, wr3 (0x063f4031): 2 ranks, UDIMMs + dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 + + The driver will map it as:: + + csrow0: channel 0, dimm0 + csrow1: channel 0, dimm1 + csrow2: channel 1, dimm0 + csrow3: channel 2, dimm0 + + exports one DIMM per csrow. + + Each QPI is exported as a different memory controller. + +2) The MC has the ability to inject errors to test drivers. The drivers + implement this functionality via some error injection nodes: + + For injecting a memory error, there are some sysfs nodes, under + ``/sys/devices/system/edac/mc/mc?/``: + + - ``inject_addrmatch/*``: + Controls the error injection mask register. It is possible to specify + several characteristics of the address to match an error code:: + + dimm = the affected dimm. Numbers are relative to a channel; + rank = the memory rank; + channel = the channel that will generate an error; + bank = the affected bank; + page = the page address; + column (or col) = the address column. + + each of the above values can be set to "any" to match any valid value. + + At driver init, all values are set to any. + + For example, to generate an error at rank 1 of dimm 2, for any channel, + any bank, any page, any column:: + + echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm + echo 1 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank + + To return to the default behaviour of matching any, you can do:: + + echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm + echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank + + - ``inject_eccmask``: + specifies what bits will have troubles, + + - ``inject_section``: + specifies what ECC cache section will get the error:: + + 3 for both + 2 for the highest + 1 for the lowest + + - ``inject_type``: + specifies the type of error, being a combination of the following bits:: + + bit 0 - repeat + bit 1 - ecc + bit 2 - parity + + - ``inject_enable``: + starts the error generation when something different than 0 is written. + + All inject vars can be read. root permission is needed for write. + + Datasheet states that the error will only be generated after a write on an + address that matches inject_addrmatch. It seems, however, that reading will + also produce an error. + + For example, the following code will generate an error for any write access + at socket 0, on any DIMM/address on channel 2:: + + echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/channel + echo 2 >/sys/devices/system/edac/mc/mc0/inject_type + echo 64 >/sys/devices/system/edac/mc/mc0/inject_eccmask + echo 3 >/sys/devices/system/edac/mc/mc0/inject_section + echo 1 >/sys/devices/system/edac/mc/mc0/inject_enable + dd if=/dev/mem of=/dev/null seek=16k bs=4k count=1 >& /dev/null + + For socket 1, it is needed to replace "mc0" by "mc1" at the above + commands. + + The generated error message will look like:: + + EDAC MC0: UE row 0, channel-a= 0 channel-b= 0 labels "-": NON_FATAL (addr = 0x0075b980, socket=0, Dimm=0, Channel=2, syndrome=0x00000040, count=1, Err=8c0000400001009f:4000080482 (read error: read ECC error)) + +3) Corrected Error memory register counters + + Those newer MCs have some registers to count memory errors. The driver + uses those registers to report Corrected Errors on devices with Registered + DIMMs. + + However, those counters don't work with Unregistered DIMM. As the chipset + offers some counters that also work with UDIMMs (but with a worse level of + granularity than the default ones), the driver exposes those registers for + UDIMM memories. + + They can be read by looking at the contents of ``all_channel_counts/``:: + + $ for i in /sys/devices/system/edac/mc/mc0/all_channel_counts/*; do echo $i; cat $i; done + /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm0 + 0 + /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm1 + 0 + /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm2 + 0 + + What happens here is that errors on different csrows, but at the same + dimm number will increment the same counter. + So, in this memory mapping:: + + csrow0: channel 0, dimm0 + csrow1: channel 0, dimm1 + csrow2: channel 1, dimm0 + csrow3: channel 2, dimm0 + + The hardware will increment udimm0 for an error at the first dimm at either + csrow0, csrow2 or csrow3; + + The hardware will increment udimm1 for an error at the second dimm at either + csrow0, csrow2 or csrow3; + + The hardware will increment udimm2 for an error at the third dimm at either + csrow0, csrow2 or csrow3; + +4) Standard error counters + + The standard error counters are generated when an mcelog error is received + by the driver. Since, with UDIMM, this is counted by software, it is + possible that some errors could be lost. With RDIMM's, they display the + contents of the registers + +Reference documents used on ``amd64_edac`` +------------------------------------------ + +``amd64_edac`` module is based on the following documents +(available from http://support.amd.com/en-us/search/tech-docs): + +1. :Title: BIOS and Kernel Developer's Guide for AMD Athlon 64 and AMD + Opteron Processors + :AMD publication #: 26094 + :Revision: 3.26 + :Link: http://support.amd.com/TechDocs/26094.PDF + +2. :Title: BIOS and Kernel Developer's Guide for AMD NPT Family 0Fh + Processors + :AMD publication #: 32559 + :Revision: 3.00 + :Issue Date: May 2006 + :Link: http://support.amd.com/TechDocs/32559.pdf + +3. :Title: BIOS and Kernel Developer's Guide (BKDG) For AMD Family 10h + Processors + :AMD publication #: 31116 + :Revision: 3.00 + :Issue Date: September 07, 2007 + :Link: http://support.amd.com/TechDocs/31116.pdf + +4. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h + Models 30h-3Fh Processors + :AMD publication #: 49125 + :Revision: 3.06 + :Issue Date: 2/12/2015 (latest release) + :Link: http://support.amd.com/TechDocs/49125_15h_Models_30h-3Fh_BKDG.pdf + +5. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h + Models 60h-6Fh Processors + :AMD publication #: 50742 + :Revision: 3.01 + :Issue Date: 7/23/2015 (latest release) + :Link: http://support.amd.com/TechDocs/50742_15h_Models_60h-6Fh_BKDG.pdf + +6. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 16h + Models 00h-0Fh Processors + :AMD publication #: 48751 + :Revision: 3.03 + :Issue Date: 2/23/2015 (latest release) + :Link: http://support.amd.com/TechDocs/48751_16h_bkdg.pdf + +Credits +======= + +* Written by Doug Thompson + + - 7 Dec 2005 + - 17 Jul 2007 Updated + +* |copy| Mauro Carvalho Chehab + + - 05 Aug 2009 Nehalem interface + - 26 Oct 2016 Converted to ReST and cleanups at the Nehalem section + +* EDAC authors/maintainers: + + - Doug Thompson, Dave Jiang, Dave Peterson et al, + - Mauro Carvalho Chehab + - Borislav Petkov + - original author: Thayne Harbaugh diff --git a/Documentation/edac.txt b/Documentation/edac.txt deleted file mode 100644 index 2f8706bae5a4..000000000000 --- a/Documentation/edac.txt +++ /dev/null @@ -1,1190 +0,0 @@ -.. include:: - -============================================ -Reliability, Availability and Serviceability -============================================ - -RAS concepts -************ - -Reliability, Availability and Serviceability (RAS) is a concept used on -servers meant to measure their robusteness. - -Reliability - is the probability that a system will produce correct outputs. - - * Generally measured as Mean Time Between Failures (MTBF) - * Enhanced by features that help to avoid, detect and repair hardware faults - -Availability - is the probability that a system is operational at a given time - - * Generally measured as a percentage of downtime per a period of time - * Often uses mechanisms to detect and correct hardware faults in - runtime; - -Serviceability (or maintainability) - is the simplicity and speed with which a system can be repaired or - maintained - - * Generally measured on Mean Time Between Repair (MTBR) - -Improving RAS -------------- - -In order to reduce systems downtime, a system should be capable of detecting -hardware errors, and, when possible correcting them in runtime. It should -also provide mechanisms to detect hardware degradation, in order to warn -the system administrator to take the action of replacing a component before -it causes data loss or system downtime. - -Among the monitoring measures, the most usual ones include: - -* CPU – detect errors at instruction execution and at L1/L2/L3 caches; -* Memory – add error correction logic (ECC) to detect and correct errors; -* I/O – add CRC checksums for tranfered data; -* Storage – RAID, journal file systems, checksums, - Self-Monitoring, Analysis and Reporting Technology (SMART). - -By monitoring the number of occurrences of error detections, it is possible -to identify if the probability of hardware errors is increasing, and, on such -case, do a preventive maintainance to replace a degrated component while -those errors are correctable. - -Types of errors ---------------- - -Most mechanisms used on modern systems use use technologies like Hamming -Codes that allow error correction when the number of errors on a bit packet -is below a threshold. If the number of errors is above, those mechanisms -can indicate with a high degree of confidence that an error happened, but -they can't correct. - -Also, sometimes an error occur on a component that it is not used. For -example, a part of the memory that it is not currently allocated. - -That defines some categories of errors: - -* **Correctable Error (CE)** - the error detection mechanism detected and - corrected the error. Such errors are usually not fatal, although some - Kernel mechanisms allow the system administrator to consider them as fatal. - -* **Uncorrected Error (UE)** - the amount of errors happened above the error - correction threshold, and the system was unable to auto-correct. - -* **Fatal Error** - when an UE error happens on a critical component of the - system (for example, a piece of the Kernel got corrupted by an UE), the - only reliable way to avoid data corruption is to hang or reboot the machine. - -* **Non-fatal Error** - when an UE error happens on an unused component, - like a CPU in power down state or an unused memory bank, the system may - still run, eventually replacing the affected hardware by a hot spare, - if available. - - Also, when an error happens on an userspace process, it is also possible to - kill such process and let userspace restart it. - -The mechanism for handling non-fatal errors is usually complex and may -require the help of some userspace application, in order to apply the -policy desired by the system administrator. - -Identifying a bad hardware component ------------------------------------- - -Just detecting a hardware flaw is usually not enough, as the system needs -to pinpoint to the minimal replaceable unit (MRU) that should be exchanged -to make the hardware reliable again. - -So, it requires not only error logging facilities, but also mechanisms that -will translate the error message to the silkscreen or component label for -the MRU. - -Typically, it is very complex for memory, as modern CPUs interlace memory -from different memory modules, in order to provide a better performance. The -DMI BIOS usually have a list of memory module labels, with can be obtained -using the ``dmidecode`` tool. For example, on a desktop machine, it shows:: - - Memory Device - Total Width: 64 bits - Data Width: 64 bits - Size: 16384 MB - Form Factor: SODIMM - Set: None - Locator: ChannelA-DIMM0 - Bank Locator: BANK 0 - Type: DDR4 - Type Detail: Synchronous - Speed: 2133 MHz - Rank: 2 - Configured Clock Speed: 2133 MHz - -On the above example, a DDR4 SO-DIMM memory module is located at the -system's memory labeled as "BANK 0", as given by the *bank locator* field. -Please notice that, on such system, the *total width* is equal to the -*data witdh*. It means that such memory module doesn't have error -detection/correction mechanisms. - -Unfortunately, not all systems use the same field to specify the memory -bank. On this example, from an older server, ``dmidecode`` shows:: - - Memory Device - Array Handle: 0x1000 - Error Information Handle: Not Provided - Total Width: 72 bits - Data Width: 64 bits - Size: 8192 MB - Form Factor: DIMM - Set: 1 - Locator: DIMM_A1 - Bank Locator: Not Specified - Type: DDR3 - Type Detail: Synchronous Registered (Buffered) - Speed: 1600 MHz - Rank: 2 - Configured Clock Speed: 1600 MHz - -There, the DDR3 RDIMM memory module is located at the system's memory labeled -as "DIMM_A1", as given by the *locator* field. Please notice that this -memory module has 64 bits of *data witdh* and 72 bits of *total width*. So, -it has 8 extra bits to be used by error detection and correction mechanisms. -Such kind of memory is called Error-correcting code memory (ECC memory). - -To make things even worse, it is not uncommon that systems with different -labels on their system's board to use exactly the same BIOS, meaning that -the labels provided by the BIOS won't match the real ones. - -ECC memory ----------- - -As mentioned on the previous section, ECC memory has extra bits to be -used for error correction. So, on 64 bit systems, a memory module -has 64 bits of *data width*, and 74 bits of *total width*. So, there are -8 bits extra bits to be used for the error detection and correction -mechanisms. Those extra bits are called *syndrome*\ [#f1]_\ [#f2]_. - -So, when the cpu requests the memory controller to write a word with -*data width*, the memory controller calculates the *syndrome* in real time, -using Hamming code, or some other error correction code, like SECDED+, -producing a code with *total width* size. Such code is then written -on the memory modules. - -At read, the *total width* bits code is converted back, using the same -ECC code used on write, producing a word with *data width* and a *syndrome*. -The word with *data width* is sent to the CPU, even when errors happen. - -The memory controller also looks at the *syndrome* in order to check if -there was an error, and if the ECC code was able to fix such error. -If the error was corrected, a Corrected Error (CE) happened. If not, an -Uncorrected Error (UE) happened. - -The information about the CE/UE errors is stored on some special registers -at the memory controller and can be accessed by reading such registers, -either by BIOS, by some special CPUs or by Linux EDAC driver. On x86 64 -bit CPUs, such errors can also be retrieved via the Machine Check -Architecture (MCA)\ [#f3]_. - -.. [#f1] Please notice that several memory controllers allow operation on a - mode called "Lock-Step", where it groups two memory modules together, - doing 128-bit reads/writes. That gives 16 bits for error correction, with - significatively improves the error correction mechanism, at the expense - that, when an error happens, there's no way to know what memory module is - to blame. So, it has to blame both memory modules. - -.. [#f2] Some memory controllers also allow using memory in mirror mode. - On such mode, the same data is written to two memory modules. At read, - the system checks both memory modules, in order to check if both provide - identical data. On such configuration, when an error happens, there's no - way to know what memory module is to blame. So, it has to blame both - memory modules (or 4 memory modules, if the system is also on Lock-step - mode). - -.. [#f3] For more details about the Machine Check Architecture (MCA), - please read Documentation/x86/x86_64/machinecheck at the Kernel tree. - -EDAC - Error Detection And Correction -************************************* - -.. note:: - - "bluesmoke" was the name for this device driver subsystem when it - was "out-of-tree" and maintained at http://bluesmoke.sourceforge.net. - That site is mostly archaic now and can be used only for historical - purposes. - - When the subsystem was pushed upstream for the first time, on - Kernel 2.6.16, for the first time, it was renamed to ``EDAC``. - -Purpose -------- - -The ``edac`` kernel module's goal is to detect and report hardware errors -that occur within the computer system running under linux. - -Memory ------- - -Memory Correctable Errors (CE) and Uncorrectable Errors (UE) are the -primary errors being harvested. These types of errors are harvested by -the ``edac_mc`` device. - -Detecting CE events, then harvesting those events and reporting them, -**can** but must not necessarily be a predictor of future UE events. With -CE events only, the system can and will continue to operate as no data -has been damaged yet. - -However, preventive maintenance and proactive part replacement of memory -modules exhibiting CEs can reduce the likelihood of the dreaded UE events -and system panics. - -Other hardware elements ------------------------ - -A new feature for EDAC, the ``edac_device`` class of device, was added in -the 2.6.23 version of the kernel. - -This new device type allows for non-memory type of ECC hardware detectors -to have their states harvested and presented to userspace via the sysfs -interface. - -Some architectures have ECC detectors for L1, L2 and L3 caches, -along with DMA engines, fabric switches, main data path switches, -interconnections, and various other hardware data paths. If the hardware -reports it, then a edac_device device probably can be constructed to -harvest and present that to userspace. - - -PCI bus scanning ----------------- - -In addition, PCI devices are scanned for PCI Bus Parity and SERR Errors -in order to determine if errors are occurring during data transfers. - -The presence of PCI Parity errors must be examined with a grain of salt. -There are several add-in adapters that do **not** follow the PCI specification -with regards to Parity generation and reporting. The specification says -the vendor should tie the parity status bits to 0 if they do not intend -to generate parity. Some vendors do not do this, and thus the parity bit -can "float" giving false positives. - -There is a PCI device attribute located in sysfs that is checked by -the EDAC PCI scanning code. If that attribute is set, PCI parity/error -scanning is skipped for that device. The attribute is:: - - broken_parity_status - -and is located in ``/sys/devices/pci/0000:XX:YY.Z`` directories for -PCI devices. - - -Versioning ----------- - -EDAC is composed of a "core" module (``edac_core.ko``) and several Memory -Controller (MC) driver modules. On a given system, the CORE is loaded -and one MC driver will be loaded. Both the CORE and the MC driver (or -``edac_device`` driver) have individual versions that reflect current -release level of their respective modules. - -Thus, to "report" on what version a system is running, one must report -both the CORE's and the MC driver's versions. - - -Loading -------- - -If ``edac`` was statically linked with the kernel then no loading -is necessary. If ``edac`` was built as modules then simply modprobe -the ``edac`` pieces that you need. You should be able to modprobe -hardware-specific modules and have the dependencies load the necessary -core modules. - -Example:: - - $ modprobe amd76x_edac - -loads both the ``amd76x_edac.ko`` memory controller module and the -``edac_mc.ko`` core module. - - -Sysfs interface ---------------- - -EDAC presents a ``sysfs`` interface for control and reporting purposes. It -lives in the /sys/devices/system/edac directory. - -Within this directory there currently reside 2 components: - - ======= ============================== - mc memory controller(s) system - pci PCI control and status system - ======= ============================== - - - -Memory Controller (mc) Model ----------------------------- - -Each ``mc`` device controls a set of memory modules [#f4]_. These modules -are laid out in a Chip-Select Row (``csrowX``) and Channel table (``chX``). -There can be multiple csrows and multiple channels. - -.. [#f4] Nowadays, the term DIMM (Dual In-line Memory Module) is widely - used to refer to a memory module, although there are other memory - packaging alternatives, like SO-DIMM, SIMM, etc. Along this document, - and inside the EDAC system, the term "dimm" is used for all memory - modules, even when they use a different kind of packaging. - -Memory controllers allow for several csrows, with 8 csrows being a -typical value. Yet, the actual number of csrows depends on the layout of -a given motherboard, memory controller and memory module characteristics. - -Dual channels allow for dual data length (e. g. 128 bits, on 64 bit systems) -data transfers to/from the CPU from/to memory. Some newer chipsets allow -for more than 2 channels, like Fully Buffered DIMMs (FB-DIMMs) memory -controllers. The following example will assume 2 channels: - - +------------+-----------------------+ - | Chip | Channels | - | Select +-----------+-----------+ - | rows | ``ch0`` | ``ch1`` | - +============+===========+===========+ - | ``csrow0`` | DIMM_A0 | DIMM_B0 | - +------------+ | | - | ``csrow1`` | | | - +------------+-----------+-----------+ - | ``csrow2`` | DIMM_A1 | DIMM_B1 | - +------------+ | | - | ``csrow3`` | | | - +------------+-----------+-----------+ - -In the above example, there are 4 physical slots on the motherboard -for memory DIMMs: - - +---------+---------+ - | DIMM_A0 | DIMM_B0 | - +---------+---------+ - | DIMM_A1 | DIMM_B1 | - +---------+---------+ - -Labels for these slots are usually silk-screened on the motherboard. -Slots labeled ``A`` are channel 0 in this example. Slots labeled ``B`` are -channel 1. Notice that there are two csrows possible on a physical DIMM. -These csrows are allocated their csrow assignment based on the slot into -which the memory DIMM is placed. Thus, when 1 DIMM is placed in each -Channel, the csrows cross both DIMMs. - -Memory DIMMs come single or dual "ranked". A rank is a populated csrow. -Thus, 2 single ranked DIMMs, placed in slots DIMM_A0 and DIMM_B0 above -will have just one csrow (csrow0). csrow1 will be empty. On the other -hand, when 2 dual ranked DIMMs are similarly placed, then both csrow0 -and csrow1 will be populated. The pattern repeats itself for csrow2 and -csrow3. - -The representation of the above is reflected in the directory -tree in EDAC's sysfs interface. Starting in directory -``/sys/devices/system/edac/mc``, each memory controller will be -represented by its own ``mcX`` directory, where ``X`` is the -index of the MC:: - - ..../edac/mc/ - | - |->mc0 - |->mc1 - |->mc2 - .... - -Under each ``mcX`` directory each ``csrowX`` is again represented by a -``csrowX``, where ``X`` is the csrow index:: - - .../mc/mc0/ - | - |->csrow0 - |->csrow2 - |->csrow3 - .... - -Notice that there is no csrow1, which indicates that csrow0 is composed -of a single ranked DIMMs. This should also apply in both Channels, in -order to have dual-channel mode be operational. Since both csrow2 and -csrow3 are populated, this indicates a dual ranked set of DIMMs for -channels 0 and 1. - -Within each of the ``mcX`` and ``csrowX`` directories are several EDAC -control and attribute files. - -``mcX`` directories -------------------- - -In ``mcX`` directories are EDAC control and attribute files for -this ``X`` instance of the memory controllers. - -For a description of the sysfs API, please see: - - Documentation/ABI/testing/sysfs-devices-edac - - -``dimmX`` or ``rankX`` directories ----------------------------------- - -The recommended way to use the EDAC subsystem is to look at the information -provided by the ``dimmX`` or ``rankX`` directories [#f5]_. - -A typical EDAC system has the following structure under -``/sys/devices/system/edac/``\ [#f6]_:: - - /sys/devices/system/edac/ - ├── mc - │   ├── mc0 - │   │   ├── ce_count - │   │   ├── ce_noinfo_count - │   │   ├── dimm0 - │   │   │   ├── dimm_dev_type - │   │   │   ├── dimm_edac_mode - │   │   │   ├── dimm_label - │   │   │   ├── dimm_location - │   │   │   ├── dimm_mem_type - │   │   │   ├── size - │   │   │   └── uevent - │   │   ├── max_location - │   │   ├── mc_name - │   │   ├── reset_counters - │   │   ├── seconds_since_reset - │   │   ├── size_mb - │   │   ├── ue_count - │   │   ├── ue_noinfo_count - │   │   └── uevent - │   ├── mc1 - │   │   ├── ce_count - │   │   ├── ce_noinfo_count - │   │   ├── dimm0 - │   │   │   ├── dimm_dev_type - │   │   │   ├── dimm_edac_mode - │   │   │   ├── dimm_label - │   │   │   ├── dimm_location - │   │   │   ├── dimm_mem_type - │   │   │   ├── size - │   │   │   └── uevent - │   │   ├── max_location - │   │   ├── mc_name - │   │   ├── reset_counters - │   │   ├── seconds_since_reset - │   │   ├── size_mb - │   │   ├── ue_count - │   │   ├── ue_noinfo_count - │   │   └── uevent - │   └── uevent - └── uevent - -In the ``dimmX`` directories are EDAC control and attribute files for -this ``X`` memory module: - -- ``size`` - Total memory managed by this csrow attribute file - - This attribute file displays, in count of megabytes, the memory - that this csrow contains. - -- ``dimm_dev_type`` - Device type attribute file - - This attribute file will display what type of DRAM device is - being utilized on this DIMM. - Examples: - - - x1 - - x2 - - x4 - - x8 - -- ``dimm_edac_mode`` - EDAC Mode of operation attribute file - - This attribute file will display what type of Error detection - and correction is being utilized. - -- ``dimm_label`` - memory module label control file - - This control file allows this DIMM to have a label assigned - to it. With this label in the module, when errors occur - the output can provide the DIMM label in the system log. - This becomes vital for panic events to isolate the - cause of the UE event. - - DIMM Labels must be assigned after booting, with information - that correctly identifies the physical slot with its - silk screen label. This information is currently very - motherboard specific and determination of this information - must occur in userland at this time. - -- ``dimm_location`` - location of the memory module - - The location can have up to 3 levels, and describe how the - memory controller identifies the location of a memory module. - Depending on the type of memory and memory controller, it - can be: - - - *csrow* and *channel* - used when the memory controller - doesn't identify a single DIMM - e. g. in ``rankX`` dir; - - *branch*, *channel*, *slot* - typically used on FB-DIMM memory - controllers; - - *channel*, *slot* - used on Nehalem and newer Intel drivers. - -- ``dimm_mem_type`` - Memory Type attribute file - - This attribute file will display what type of memory is currently - on this csrow. Normally, either buffered or unbuffered memory. - Examples: - - - Registered-DDR - - Unbuffered-DDR - -.. [#f5] On some systems, the memory controller doesn't have any logic - to identify the memory module. On such systems, the directory is called ``rankX`` and works on a similar way as the ``csrowX`` directories. - On modern Intel memory controllers, the memory controller identifies the - memory modules directly. On such systems, the directory is called ``dimmX``. - -.. [#f6] There are also some ``power`` directories and ``subsystem`` - symlinks inside the sysfs mapping that are automatically created by - the sysfs subsystem. Currently, they serve no purpose. - -``csrowX`` directories ----------------------- - -When CONFIG_EDAC_LEGACY_SYSFS is enabled, sysfs will contain the ``csrowX`` -directories. As this API doesn't work properly for Rambus, FB-DIMMs and -modern Intel Memory Controllers, this is being deprecated in favor of -``dimmX`` directories. - -In the ``csrowX`` directories are EDAC control and attribute files for -this ``X`` instance of csrow: - - -- ``ue_count`` - Total Uncorrectable Errors count attribute file - - This attribute file displays the total count of uncorrectable - errors that have occurred on this csrow. If panic_on_ue is set - this counter will not have a chance to increment, since EDAC - will panic the system. - - -- ``ce_count`` - Total Correctable Errors count attribute file - - This attribute file displays the total count of correctable - errors that have occurred on this csrow. This count is very - important to examine. CEs provide early indications that a - DIMM is beginning to fail. This count field should be - monitored for non-zero values and report such information - to the system administrator. - - -- ``size_mb`` - Total memory managed by this csrow attribute file - - This attribute file displays, in count of megabytes, the memory - that this csrow contains. - - -- ``mem_type`` - Memory Type attribute file - - This attribute file will display what type of memory is currently - on this csrow. Normally, either buffered or unbuffered memory. - Examples: - - - Registered-DDR - - Unbuffered-DDR - - -- ``edac_mode`` - EDAC Mode of operation attribute file - - This attribute file will display what type of Error detection - and correction is being utilized. - - -- ``dev_type`` - Device type attribute file - - This attribute file will display what type of DRAM device is - being utilized on this DIMM. - Examples: - - - x1 - - x2 - - x4 - - x8 - - -- ``ch0_ce_count`` - Channel 0 CE Count attribute file - - This attribute file will display the count of CEs on this - DIMM located in channel 0. - - -- ``ch0_ue_count`` - Channel 0 UE Count attribute file - - This attribute file will display the count of UEs on this - DIMM located in channel 0. - - -- ``ch0_dimm_label`` - Channel 0 DIMM Label control file - - - This control file allows this DIMM to have a label assigned - to it. With this label in the module, when errors occur - the output can provide the DIMM label in the system log. - This becomes vital for panic events to isolate the - cause of the UE event. - - DIMM Labels must be assigned after booting, with information - that correctly identifies the physical slot with its - silk screen label. This information is currently very - motherboard specific and determination of this information - must occur in userland at this time. - - -- ``ch1_ce_count`` - Channel 1 CE Count attribute file - - - This attribute file will display the count of CEs on this - DIMM located in channel 1. - - -- ``ch1_ue_count`` - Channel 1 UE Count attribute file - - - This attribute file will display the count of UEs on this - DIMM located in channel 0. - - -- ``ch1_dimm_label`` - Channel 1 DIMM Label control file - - This control file allows this DIMM to have a label assigned - to it. With this label in the module, when errors occur - the output can provide the DIMM label in the system log. - This becomes vital for panic events to isolate the - cause of the UE event. - - DIMM Labels must be assigned after booting, with information - that correctly identifies the physical slot with its - silk screen label. This information is currently very - motherboard specific and determination of this information - must occur in userland at this time. - - -System Logging --------------- - -If logging for UEs and CEs is enabled, then system logs will contain -information indicating that errors have been detected:: - - EDAC MC0: CE page 0x283, offset 0xce0, grain 8, syndrome 0x6ec3, row 0, channel 1 "DIMM_B1": amd76x_edac - EDAC MC0: CE page 0x1e5, offset 0xfb0, grain 8, syndrome 0xb741, row 0, channel 1 "DIMM_B1": amd76x_edac - - -The structure of the message is: - - +---------------------------------------+-------------+ - | Content + Example | - +=======================================+=============+ - | The memory controller | MC0 | - +---------------------------------------+-------------+ - | Error type | CE | - +---------------------------------------+-------------+ - | Memory page | 0x283 | - +---------------------------------------+-------------+ - | Offset in the page | 0xce0 | - +---------------------------------------+-------------+ - | The byte granularity | grain 8 | - | or resolution of the error | | - +---------------------------------------+-------------+ - | The error syndrome | 0xb741 | - +---------------------------------------+-------------+ - | Memory row | row 0 + - +---------------------------------------+-------------+ - | Memory channel | channel 1 | - +---------------------------------------+-------------+ - | DIMM label, if set prior | DIMM B1 | - +---------------------------------------+-------------+ - | And then an optional, driver-specific | | - | message that may have additional | | - | information. | | - +---------------------------------------+-------------+ - -Both UEs and CEs with no info will lack all but memory controller, error -type, a notice of "no info" and then an optional, driver-specific error -message. - - -PCI Bus Parity Detection ------------------------- - -On Header Type 00 devices, the primary status is looked at for any -parity error regardless of whether parity is enabled on the device or -not. (The spec indicates parity is generated in some cases). On Header -Type 01 bridges, the secondary status register is also looked at to see -if parity occurred on the bus on the other side of the bridge. - - -Sysfs configuration -------------------- - -Under ``/sys/devices/system/edac/pci`` are control and attribute files as -follows: - - -- ``check_pci_parity`` - Enable/Disable PCI Parity checking control file - - This control file enables or disables the PCI Bus Parity scanning - operation. Writing a 1 to this file enables the scanning. Writing - a 0 to this file disables the scanning. - - Enable:: - - echo "1" >/sys/devices/system/edac/pci/check_pci_parity - - Disable:: - - echo "0" >/sys/devices/system/edac/pci/check_pci_parity - - -- ``pci_parity_count`` - Parity Count - - This attribute file will display the number of parity errors that - have been detected. - - -Module parameters ------------------ - -- ``edac_mc_panic_on_ue`` - Panic on UE control file - - An uncorrectable error will cause a machine panic. This is usually - desirable. It is a bad idea to continue when an uncorrectable error - occurs - it is indeterminate what was uncorrected and the operating - system context might be so mangled that continuing will lead to further - corruption. If the kernel has MCE configured, then EDAC will never - notice the UE. - - LOAD TIME:: - - module/kernel parameter: edac_mc_panic_on_ue=[0|1] - - RUN TIME:: - - echo "1" > /sys/module/edac_core/parameters/edac_mc_panic_on_ue - - -- ``edac_mc_log_ue`` - Log UE control file - - - Generate kernel messages describing uncorrectable errors. These errors - are reported through the system message log system. UE statistics - will be accumulated even when UE logging is disabled. - - LOAD TIME:: - - module/kernel parameter: edac_mc_log_ue=[0|1] - - RUN TIME:: - - echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ue - - -- ``edac_mc_log_ce`` - Log CE control file - - - Generate kernel messages describing correctable errors. These - errors are reported through the system message log system. - CE statistics will be accumulated even when CE logging is disabled. - - LOAD TIME:: - - module/kernel parameter: edac_mc_log_ce=[0|1] - - RUN TIME:: - - echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ce - - -- ``edac_mc_poll_msec`` - Polling period control file - - - The time period, in milliseconds, for polling for error information. - Too small a value wastes resources. Too large a value might delay - necessary handling of errors and might loose valuable information for - locating the error. 1000 milliseconds (once each second) is the current - default. Systems which require all the bandwidth they can get, may - increase this. - - LOAD TIME:: - - module/kernel parameter: edac_mc_poll_msec=[0|1] - - RUN TIME:: - - echo "1000" > /sys/module/edac_core/parameters/edac_mc_poll_msec - - -- ``panic_on_pci_parity`` - Panic on PCI PARITY Error - - - This control file enables or disables panicking when a parity - error has been detected. - - - module/kernel parameter:: - - edac_panic_on_pci_pe=[0|1] - - Enable:: - - echo "1" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe - - Disable:: - - echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe - - - -EDAC device type ----------------- - -In the header file, edac_core.h, there is a series of edac_device structures -and APIs for the EDAC_DEVICE. - -User space access to an edac_device is through the sysfs interface. - -At the location ``/sys/devices/system/edac`` (sysfs) new edac_device devices -will appear. - -There is a three level tree beneath the above ``edac`` directory. For example, -the ``test_device_edac`` device (found at the http://bluesmoke.sourceforget.net -website) installs itself as:: - - /sys/devices/system/edac/test-instance - -in this directory are various controls, a symlink and one or more ``instance`` -directories. - -The standard default controls are: - - ============== ======================================================= - log_ce boolean to log CE events - log_ue boolean to log UE events - panic_on_ue boolean to ``panic`` the system if an UE is encountered - (default off, can be set true via startup script) - poll_msec time period between POLL cycles for events - ============== ======================================================= - -The test_device_edac device adds at least one of its own custom control: - - ============== ================================================== - test_bits which in the current test driver does nothing but - show how it is installed. A ported driver can - add one or more such controls and/or attributes - for specific uses. - One out-of-tree driver uses controls here to allow - for ERROR INJECTION operations to hardware - injection registers - ============== ================================================== - -The symlink points to the 'struct dev' that is registered for this edac_device. - -Instances ---------- - -One or more instance directories are present. For the ``test_device_edac`` -case: - - +----------------+ - | test-instance0 | - +----------------+ - - -In this directory there are two default counter attributes, which are totals of -counter in deeper subdirectories. - - ============== ==================================== - ce_count total of CE events of subdirectories - ue_count total of UE events of subdirectories - ============== ==================================== - -Blocks ------- - -At the lowest directory level is the ``block`` directory. There can be 0, 1 -or more blocks specified in each instance: - - +-------------+ - | test-block0 | - +-------------+ - -In this directory the default attributes are: - - ============== ================================================ - ce_count which is counter of CE events for this ``block`` - of hardware being monitored - ue_count which is counter of UE events for this ``block`` - of hardware being monitored - ============== ================================================ - - -The ``test_device_edac`` device adds 4 attributes and 1 control: - - ================== ==================================================== - test-block-bits-0 for every POLL cycle this counter - is incremented - test-block-bits-1 every 10 cycles, this counter is bumped once, - and test-block-bits-0 is set to 0 - test-block-bits-2 every 100 cycles, this counter is bumped once, - and test-block-bits-1 is set to 0 - test-block-bits-3 every 1000 cycles, this counter is bumped once, - and test-block-bits-2 is set to 0 - ================== ==================================================== - - - ================== ==================================================== - reset-counters writing ANY thing to this control will - reset all the above counters. - ================== ==================================================== - - -Use of the ``test_device_edac`` driver should enable any others to create their own -unique drivers for their hardware systems. - -The ``test_device_edac`` sample driver is located at the -http://bluesmoke.sourceforge.net project site for EDAC. - - -Usage of EDAC APIs on Nehalem and newer Intel CPUs --------------------------------------------------- - -On older Intel architectures, the memory controller was part of the North -Bridge chipset. Nehalem, Sandy Bridge, Ivy Bridge, Haswell, Sky Lake and -newer Intel architectures integrated an enhanced version of the memory -controller (MC) inside the CPUs. - -This chapter will cover the differences of the enhanced memory controllers -found on newer Intel CPUs, such as ``i7core_edac``, ``sb_edac`` and -``sbx_edac`` drivers. - -.. note:: - - The Xeon E7 processor families use a separate chip for the memory - controller, called Intel Scalable Memory Buffer. This section doesn't - apply for such families. - -1) There is one Memory Controller per Quick Patch Interconnect - (QPI). At the driver, the term "socket" means one QPI. This is - associated with a physical CPU socket. - - Each MC have 3 physical read channels, 3 physical write channels and - 3 logic channels. The driver currently sees it as just 3 channels. - Each channel can have up to 3 DIMMs. - - The minimum known unity is DIMMs. There are no information about csrows. - As EDAC API maps the minimum unity is csrows, the driver sequentially - maps channel/DIMM into different csrows. - - For example, supposing the following layout:: - - Ch0 phy rd0, wr0 (0x063f4031): 2 ranks, UDIMMs - dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 - dimm 1 1024 Mb offset: 4, bank: 8, rank: 1, row: 0x4000, col: 0x400 - Ch1 phy rd1, wr1 (0x063f4031): 2 ranks, UDIMMs - dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 - Ch2 phy rd3, wr3 (0x063f4031): 2 ranks, UDIMMs - dimm 0 1024 Mb offset: 0, bank: 8, rank: 1, row: 0x4000, col: 0x400 - - The driver will map it as:: - - csrow0: channel 0, dimm0 - csrow1: channel 0, dimm1 - csrow2: channel 1, dimm0 - csrow3: channel 2, dimm0 - - exports one DIMM per csrow. - - Each QPI is exported as a different memory controller. - -2) The MC has the ability to inject errors to test drivers. The drivers - implement this functionality via some error injection nodes: - - For injecting a memory error, there are some sysfs nodes, under - ``/sys/devices/system/edac/mc/mc?/``: - - - ``inject_addrmatch/*``: - Controls the error injection mask register. It is possible to specify - several characteristics of the address to match an error code:: - - dimm = the affected dimm. Numbers are relative to a channel; - rank = the memory rank; - channel = the channel that will generate an error; - bank = the affected bank; - page = the page address; - column (or col) = the address column. - - each of the above values can be set to "any" to match any valid value. - - At driver init, all values are set to any. - - For example, to generate an error at rank 1 of dimm 2, for any channel, - any bank, any page, any column:: - - echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm - echo 1 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank - - To return to the default behaviour of matching any, you can do:: - - echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/dimm - echo any >/sys/devices/system/edac/mc/mc0/inject_addrmatch/rank - - - ``inject_eccmask``: - specifies what bits will have troubles, - - - ``inject_section``: - specifies what ECC cache section will get the error:: - - 3 for both - 2 for the highest - 1 for the lowest - - - ``inject_type``: - specifies the type of error, being a combination of the following bits:: - - bit 0 - repeat - bit 1 - ecc - bit 2 - parity - - - ``inject_enable``: - starts the error generation when something different than 0 is written. - - All inject vars can be read. root permission is needed for write. - - Datasheet states that the error will only be generated after a write on an - address that matches inject_addrmatch. It seems, however, that reading will - also produce an error. - - For example, the following code will generate an error for any write access - at socket 0, on any DIMM/address on channel 2:: - - echo 2 >/sys/devices/system/edac/mc/mc0/inject_addrmatch/channel - echo 2 >/sys/devices/system/edac/mc/mc0/inject_type - echo 64 >/sys/devices/system/edac/mc/mc0/inject_eccmask - echo 3 >/sys/devices/system/edac/mc/mc0/inject_section - echo 1 >/sys/devices/system/edac/mc/mc0/inject_enable - dd if=/dev/mem of=/dev/null seek=16k bs=4k count=1 >& /dev/null - - For socket 1, it is needed to replace "mc0" by "mc1" at the above - commands. - - The generated error message will look like:: - - EDAC MC0: UE row 0, channel-a= 0 channel-b= 0 labels "-": NON_FATAL (addr = 0x0075b980, socket=0, Dimm=0, Channel=2, syndrome=0x00000040, count=1, Err=8c0000400001009f:4000080482 (read error: read ECC error)) - -3) Corrected Error memory register counters - - Those newer MCs have some registers to count memory errors. The driver - uses those registers to report Corrected Errors on devices with Registered - DIMMs. - - However, those counters don't work with Unregistered DIMM. As the chipset - offers some counters that also work with UDIMMs (but with a worse level of - granularity than the default ones), the driver exposes those registers for - UDIMM memories. - - They can be read by looking at the contents of ``all_channel_counts/``:: - - $ for i in /sys/devices/system/edac/mc/mc0/all_channel_counts/*; do echo $i; cat $i; done - /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm0 - 0 - /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm1 - 0 - /sys/devices/system/edac/mc/mc0/all_channel_counts/udimm2 - 0 - - What happens here is that errors on different csrows, but at the same - dimm number will increment the same counter. - So, in this memory mapping:: - - csrow0: channel 0, dimm0 - csrow1: channel 0, dimm1 - csrow2: channel 1, dimm0 - csrow3: channel 2, dimm0 - - The hardware will increment udimm0 for an error at the first dimm at either - csrow0, csrow2 or csrow3; - - The hardware will increment udimm1 for an error at the second dimm at either - csrow0, csrow2 or csrow3; - - The hardware will increment udimm2 for an error at the third dimm at either - csrow0, csrow2 or csrow3; - -4) Standard error counters - - The standard error counters are generated when an mcelog error is received - by the driver. Since, with UDIMM, this is counted by software, it is - possible that some errors could be lost. With RDIMM's, they display the - contents of the registers - -Reference documents used on ``amd64_edac`` ------------------------------------------- - -``amd64_edac`` module is based on the following documents -(available from http://support.amd.com/en-us/search/tech-docs): - -1. :Title: BIOS and Kernel Developer's Guide for AMD Athlon 64 and AMD - Opteron Processors - :AMD publication #: 26094 - :Revision: 3.26 - :Link: http://support.amd.com/TechDocs/26094.PDF - -2. :Title: BIOS and Kernel Developer's Guide for AMD NPT Family 0Fh - Processors - :AMD publication #: 32559 - :Revision: 3.00 - :Issue Date: May 2006 - :Link: http://support.amd.com/TechDocs/32559.pdf - -3. :Title: BIOS and Kernel Developer's Guide (BKDG) For AMD Family 10h - Processors - :AMD publication #: 31116 - :Revision: 3.00 - :Issue Date: September 07, 2007 - :Link: http://support.amd.com/TechDocs/31116.pdf - -4. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h - Models 30h-3Fh Processors - :AMD publication #: 49125 - :Revision: 3.06 - :Issue Date: 2/12/2015 (latest release) - :Link: http://support.amd.com/TechDocs/49125_15h_Models_30h-3Fh_BKDG.pdf - -5. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h - Models 60h-6Fh Processors - :AMD publication #: 50742 - :Revision: 3.01 - :Issue Date: 7/23/2015 (latest release) - :Link: http://support.amd.com/TechDocs/50742_15h_Models_60h-6Fh_BKDG.pdf - -6. :Title: BIOS and Kernel Developer's Guide (BKDG) for AMD Family 16h - Models 00h-0Fh Processors - :AMD publication #: 48751 - :Revision: 3.03 - :Issue Date: 2/23/2015 (latest release) - :Link: http://support.amd.com/TechDocs/48751_16h_bkdg.pdf - -Credits -======= - -* Written by Doug Thompson - - - 7 Dec 2005 - - 17 Jul 2007 Updated - -* |copy| Mauro Carvalho Chehab - - - 05 Aug 2009 Nehalem interface - - 26 Oct 2016 Converted to ReST and cleanups at the Nehalem section - -* EDAC authors/maintainers: - - - Doug Thompson, Dave Jiang, Dave Peterson et al, - - Mauro Carvalho Chehab - - Borislav Petkov - - original author: Thayne Harbaugh -- cgit v1.2.3 From 02a1904cfa6014e77e6c32a60ab5f61dc6bf336c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 29 Oct 2016 09:56:00 -0200 Subject: edac: move EDAC PCI definitions to drivers/edac/edac_pci.h The edac_core.h header contain data structures and function definitions for the 3 parts of EDAC: MC, PCI and device. Let's move the PCI ones to a separate header file, as part of a header reorganization. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_core.h | 145 +---------------------------------- drivers/edac/edac_pci.c | 19 ++--- drivers/edac/edac_pci.h | 173 ++++++++++++++++++++++++++++++++++++++++++ drivers/edac/edac_pci_sysfs.c | 2 +- include/linux/edac.h | 2 + 5 files changed, 185 insertions(+), 156 deletions(-) create mode 100644 drivers/edac/edac_pci.h diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 1723f3643e75..8c7cca2d6e40 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -35,8 +35,7 @@ #include #include -#define EDAC_DEVICE_NAME_LEN 31 -#define EDAC_ATTRIB_VALUE_LEN 15 +#include "edac_pci.h" #if PAGE_SHIFT < 20 #define PAGES_TO_MiB(pages) ((pages) >> (20 - PAGE_SHIFT)) @@ -321,128 +320,6 @@ extern struct edac_device_ctl_info *edac_device_alloc_ctl_info( extern void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info); -#ifdef CONFIG_PCI - -struct edac_pci_counter { - atomic_t pe_count; - atomic_t npe_count; -}; - -/* - * Abstract edac_pci control info structure - * - */ -struct edac_pci_ctl_info { - /* for global list of edac_pci_ctl_info structs */ - struct list_head link; - - int pci_idx; - - struct bus_type *edac_subsys; /* pointer to subsystem */ - - /* the internal state of this controller instance */ - int op_state; - /* work struct for this instance */ - struct delayed_work work; - - /* pointer to edac polling checking routine: - * If NOT NULL: points to polling check routine - * If NULL: Then assumes INTERRUPT operation, where - * MC driver will receive events - */ - void (*edac_check) (struct edac_pci_ctl_info * edac_dev); - - struct device *dev; /* pointer to device structure */ - - const char *mod_name; /* module name */ - const char *ctl_name; /* edac controller name */ - const char *dev_name; /* pci/platform/etc... name */ - - void *pvt_info; /* pointer to 'private driver' info */ - - unsigned long start_time; /* edac_pci load start time (jiffies) */ - - struct completion complete; - - /* sysfs top name under 'edac' directory - * and instance name: - * cpu/cpu0/... - * cpu/cpu1/... - * cpu/cpu2/... - * ... - */ - char name[EDAC_DEVICE_NAME_LEN + 1]; - - /* Event counters for the this whole EDAC Device */ - struct edac_pci_counter counters; - - /* edac sysfs device control for the 'name' - * device this structure controls - */ - struct kobject kobj; -}; - -#define to_edac_pci_ctl_work(w) \ - container_of(w, struct edac_pci_ctl_info,work) - -/* write all or some bits in a byte-register*/ -static inline void pci_write_bits8(struct pci_dev *pdev, int offset, u8 value, - u8 mask) -{ - if (mask != 0xff) { - u8 buf; - - pci_read_config_byte(pdev, offset, &buf); - value &= mask; - buf &= ~mask; - value |= buf; - } - - pci_write_config_byte(pdev, offset, value); -} - -/* write all or some bits in a word-register*/ -static inline void pci_write_bits16(struct pci_dev *pdev, int offset, - u16 value, u16 mask) -{ - if (mask != 0xffff) { - u16 buf; - - pci_read_config_word(pdev, offset, &buf); - value &= mask; - buf &= ~mask; - value |= buf; - } - - pci_write_config_word(pdev, offset, value); -} - -/* - * pci_write_bits32 - * - * edac local routine to do pci_write_config_dword, but adds - * a mask parameter. If mask is all ones, ignore the mask. - * Otherwise utilize the mask to isolate specified bits - * - * write all or some bits in a dword-register - */ -static inline void pci_write_bits32(struct pci_dev *pdev, int offset, - u32 value, u32 mask) -{ - if (mask != 0xffffffff) { - u32 buf; - - pci_read_config_dword(pdev, offset, &buf); - value &= mask; - buf &= ~mask; - value |= buf; - } - - pci_write_config_dword(pdev, offset, value); -} - -#endif /* CONFIG_PCI */ - struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, unsigned n_layers, struct edac_mc_layer *layers, @@ -485,26 +362,6 @@ extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, extern int edac_device_alloc_index(void); extern const char *edac_layer_name[]; -/* - * edac_pci APIs - */ -extern struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, - const char *edac_pci_name); - -extern void edac_pci_free_ctl_info(struct edac_pci_ctl_info *pci); - -extern int edac_pci_alloc_index(void); -extern int edac_pci_add_device(struct edac_pci_ctl_info *pci, int edac_idx); -extern struct edac_pci_ctl_info *edac_pci_del_device(struct device *dev); - -extern struct edac_pci_ctl_info *edac_pci_create_generic_ctl( - struct device *dev, - const char *mod_name); - -extern void edac_pci_release_generic_ctl(struct edac_pci_ctl_info *pci); -extern int edac_pci_create_sysfs(struct edac_pci_ctl_info *pci); -extern void edac_pci_remove_sysfs(struct edac_pci_ctl_info *pci); - /* * edac misc APIs */ diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c index 8f2f2899a7a2..02a0af4f53b3 100644 --- a/drivers/edac/edac_pci.c +++ b/drivers/edac/edac_pci.c @@ -9,22 +9,19 @@ * or implied. * */ +#include +#include +#include +#include +#include #include -#include +#include #include -#include +#include #include -#include #include -#include -#include -#include -#include -#include -#include -#include -#include "edac_core.h" +#include "edac_pci.h" #include "edac_module.h" static DEFINE_MUTEX(edac_pci_ctls_mutex); diff --git a/drivers/edac/edac_pci.h b/drivers/edac/edac_pci.h new file mode 100644 index 000000000000..9da0c6fb0634 --- /dev/null +++ b/drivers/edac/edac_pci.h @@ -0,0 +1,173 @@ +/* + * Defines, structures, APIs for edac_pci and edac_pci_sysfs + * + * (C) 2007 Linux Networx (http://lnxi.com) + * This file may be distributed under the terms of the + * GNU General Public License. + * + * Written by Thayne Harbaugh + * Based on work by Dan Hollis and others. + * http://www.anime.net/~goemon/linux-ecc/ + * + * NMI handling support added by + * Dave Peterson + * + * Refactored for multi-source files: + * Doug Thompson + * + * Please look at Documentation/driver-api/edac.rst for more info about + * EDAC core structs and functions. + */ + +#ifndef _EDAC_PCI_H_ +#define _EDAC_PCI_H_ + +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_PCI + +struct edac_pci_counter { + atomic_t pe_count; + atomic_t npe_count; +}; + +/* + * Abstract edac_pci control info structure + * + */ +struct edac_pci_ctl_info { + /* for global list of edac_pci_ctl_info structs */ + struct list_head link; + + int pci_idx; + + struct bus_type *edac_subsys; /* pointer to subsystem */ + + /* the internal state of this controller instance */ + int op_state; + /* work struct for this instance */ + struct delayed_work work; + + /* pointer to edac polling checking routine: + * If NOT NULL: points to polling check routine + * If NULL: Then assumes INTERRUPT operation, where + * MC driver will receive events + */ + void (*edac_check) (struct edac_pci_ctl_info * edac_dev); + + struct device *dev; /* pointer to device structure */ + + const char *mod_name; /* module name */ + const char *ctl_name; /* edac controller name */ + const char *dev_name; /* pci/platform/etc... name */ + + void *pvt_info; /* pointer to 'private driver' info */ + + unsigned long start_time; /* edac_pci load start time (jiffies) */ + + struct completion complete; + + /* sysfs top name under 'edac' directory + * and instance name: + * cpu/cpu0/... + * cpu/cpu1/... + * cpu/cpu2/... + * ... + */ + char name[EDAC_DEVICE_NAME_LEN + 1]; + + /* Event counters for the this whole EDAC Device */ + struct edac_pci_counter counters; + + /* edac sysfs device control for the 'name' + * device this structure controls + */ + struct kobject kobj; +}; + +#define to_edac_pci_ctl_work(w) \ + container_of(w, struct edac_pci_ctl_info,work) + +/* write all or some bits in a byte-register*/ +static inline void pci_write_bits8(struct pci_dev *pdev, int offset, u8 value, + u8 mask) +{ + if (mask != 0xff) { + u8 buf; + + pci_read_config_byte(pdev, offset, &buf); + value &= mask; + buf &= ~mask; + value |= buf; + } + + pci_write_config_byte(pdev, offset, value); +} + +/* write all or some bits in a word-register*/ +static inline void pci_write_bits16(struct pci_dev *pdev, int offset, + u16 value, u16 mask) +{ + if (mask != 0xffff) { + u16 buf; + + pci_read_config_word(pdev, offset, &buf); + value &= mask; + buf &= ~mask; + value |= buf; + } + + pci_write_config_word(pdev, offset, value); +} + +/* + * pci_write_bits32 + * + * edac local routine to do pci_write_config_dword, but adds + * a mask parameter. If mask is all ones, ignore the mask. + * Otherwise utilize the mask to isolate specified bits + * + * write all or some bits in a dword-register + */ +static inline void pci_write_bits32(struct pci_dev *pdev, int offset, + u32 value, u32 mask) +{ + if (mask != 0xffffffff) { + u32 buf; + + pci_read_config_dword(pdev, offset, &buf); + value &= mask; + buf &= ~mask; + value |= buf; + } + + pci_write_config_dword(pdev, offset, value); +} + +#endif /* CONFIG_PCI */ + +extern struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, + const char *edac_pci_name); + +extern void edac_pci_free_ctl_info(struct edac_pci_ctl_info *pci); + +extern int edac_pci_alloc_index(void); +extern int edac_pci_add_device(struct edac_pci_ctl_info *pci, int edac_idx); +extern struct edac_pci_ctl_info *edac_pci_del_device(struct device *dev); + +extern struct edac_pci_ctl_info *edac_pci_create_generic_ctl( + struct device *dev, + const char *mod_name); + +extern void edac_pci_release_generic_ctl(struct edac_pci_ctl_info *pci); +extern int edac_pci_create_sysfs(struct edac_pci_ctl_info *pci); +extern void edac_pci_remove_sysfs(struct edac_pci_ctl_info *pci); + +#endif diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index 6e3428ba400f..dbeb048d8efb 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -11,7 +11,7 @@ #include #include -#include "edac_core.h" +#include "edac_pci.h" #include "edac_module.h" #define EDAC_PCI_SYMLINK "device" diff --git a/include/linux/edac.h b/include/linux/edac.h index cb56dcba68c6..0fec0f26469b 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -18,6 +18,8 @@ #include #include +#define EDAC_DEVICE_NAME_LEN 31 + struct device; #define EDAC_OPSTATE_INVAL -1 -- cgit v1.2.3 From 2362ed2f6b2b35357beddaba98298078f48b41bd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 29 Oct 2016 10:01:41 -0200 Subject: edac: move EDAC device definitions to drivers/edac/edac_device.h The edac_core.h header contain data structures and function definitions for both EDAC MC and EDAC device. Let's move the devices ones to a separate header file, as part of a header reorganization. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_core.h | 238 +--------------------------------- drivers/edac/edac_device.c | 21 ++- drivers/edac/edac_device.h | 269 +++++++++++++++++++++++++++++++++++++++ drivers/edac/edac_device_sysfs.c | 4 +- 4 files changed, 281 insertions(+), 251 deletions(-) create mode 100644 drivers/edac/edac_device.h diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h index 8c7cca2d6e40..3e11d9d85462 100644 --- a/drivers/edac/edac_core.h +++ b/drivers/edac/edac_core.h @@ -36,6 +36,7 @@ #include #include "edac_pci.h" +#include "edac_device.h" #if PAGE_SHIFT < 20 #define PAGES_TO_MiB(pages) ((pages) >> (20 - PAGE_SHIFT)) @@ -95,231 +96,6 @@ do { \ #define to_mci(k) container_of(k, struct mem_ctl_info, dev) -/* - * The following are the structures to provide for a generic - * or abstract 'edac_device'. This set of structures and the - * code that implements the APIs for the same, provide for - * registering EDAC type devices which are NOT standard memory. - * - * CPU caches (L1 and L2) - * DMA engines - * Core CPU switches - * Fabric switch units - * PCIe interface controllers - * other EDAC/ECC type devices that can be monitored for - * errors, etc. - * - * It allows for a 2 level set of hierarchy. For example: - * - * cache could be composed of L1, L2 and L3 levels of cache. - * Each CPU core would have its own L1 cache, while sharing - * L2 and maybe L3 caches. - * - * View them arranged, via the sysfs presentation: - * /sys/devices/system/edac/.. - * - * mc/ - * cpu/cpu0/.. - * /L1-cache/ce_count - * /ue_count - * /L2-cache/ce_count - * /ue_count - * cpu/cpu1/.. - * /L1-cache/ce_count - * /ue_count - * /L2-cache/ce_count - * /ue_count - * ... - * - * the L1 and L2 directories would be "edac_device_block's" - */ - -struct edac_device_counter { - u32 ue_count; - u32 ce_count; -}; - -/* forward reference */ -struct edac_device_ctl_info; -struct edac_device_block; - -/* edac_dev_sysfs_attribute structure - * used for driver sysfs attributes in mem_ctl_info - * for extra controls and attributes: - * like high level error Injection controls - */ -struct edac_dev_sysfs_attribute { - struct attribute attr; - ssize_t (*show)(struct edac_device_ctl_info *, char *); - ssize_t (*store)(struct edac_device_ctl_info *, const char *, size_t); -}; - -/* edac_dev_sysfs_block_attribute structure - * - * used in leaf 'block' nodes for adding controls/attributes - * - * each block in each instance of the containing control structure - * can have an array of the following. The show and store functions - * will be filled in with the show/store function in the - * low level driver. - * - * The 'value' field will be the actual value field used for - * counting - */ -struct edac_dev_sysfs_block_attribute { - struct attribute attr; - ssize_t (*show)(struct kobject *, struct attribute *, char *); - ssize_t (*store)(struct kobject *, struct attribute *, - const char *, size_t); - struct edac_device_block *block; - - unsigned int value; -}; - -/* device block control structure */ -struct edac_device_block { - struct edac_device_instance *instance; /* Up Pointer */ - char name[EDAC_DEVICE_NAME_LEN + 1]; - - struct edac_device_counter counters; /* basic UE and CE counters */ - - int nr_attribs; /* how many attributes */ - - /* this block's attributes, could be NULL */ - struct edac_dev_sysfs_block_attribute *block_attributes; - - /* edac sysfs device control */ - struct kobject kobj; -}; - -/* device instance control structure */ -struct edac_device_instance { - struct edac_device_ctl_info *ctl; /* Up pointer */ - char name[EDAC_DEVICE_NAME_LEN + 4]; - - struct edac_device_counter counters; /* instance counters */ - - u32 nr_blocks; /* how many blocks */ - struct edac_device_block *blocks; /* block array */ - - /* edac sysfs device control */ - struct kobject kobj; -}; - - -/* - * Abstract edac_device control info structure - * - */ -struct edac_device_ctl_info { - /* for global list of edac_device_ctl_info structs */ - struct list_head link; - - struct module *owner; /* Module owner of this control struct */ - - int dev_idx; - - /* Per instance controls for this edac_device */ - int log_ue; /* boolean for logging UEs */ - int log_ce; /* boolean for logging CEs */ - int panic_on_ue; /* boolean for panic'ing on an UE */ - unsigned poll_msec; /* number of milliseconds to poll interval */ - unsigned long delay; /* number of jiffies for poll_msec */ - - /* Additional top controller level attributes, but specified - * by the low level driver. - * - * Set by the low level driver to provide attributes at the - * controller level, same level as 'ue_count' and 'ce_count' above. - * An array of structures, NULL terminated - * - * If attributes are desired, then set to array of attributes - * If no attributes are desired, leave NULL - */ - struct edac_dev_sysfs_attribute *sysfs_attributes; - - /* pointer to main 'edac' subsys in sysfs */ - struct bus_type *edac_subsys; - - /* the internal state of this controller instance */ - int op_state; - /* work struct for this instance */ - struct delayed_work work; - - /* pointer to edac polling checking routine: - * If NOT NULL: points to polling check routine - * If NULL: Then assumes INTERRUPT operation, where - * MC driver will receive events - */ - void (*edac_check) (struct edac_device_ctl_info * edac_dev); - - struct device *dev; /* pointer to device structure */ - - const char *mod_name; /* module name */ - const char *ctl_name; /* edac controller name */ - const char *dev_name; /* pci/platform/etc... name */ - - void *pvt_info; /* pointer to 'private driver' info */ - - unsigned long start_time; /* edac_device load start time (jiffies) */ - - struct completion removal_complete; - - /* sysfs top name under 'edac' directory - * and instance name: - * cpu/cpu0/... - * cpu/cpu1/... - * cpu/cpu2/... - * ... - */ - char name[EDAC_DEVICE_NAME_LEN + 1]; - - /* Number of instances supported on this control structure - * and the array of those instances - */ - u32 nr_instances; - struct edac_device_instance *instances; - - /* Event counters for the this whole EDAC Device */ - struct edac_device_counter counters; - - /* edac sysfs device control for the 'name' - * device this structure controls - */ - struct kobject kobj; -}; - -/* To get from the instance's wq to the beginning of the ctl structure */ -#define to_edac_mem_ctl_work(w) \ - container_of(w, struct mem_ctl_info, work) - -#define to_edac_device_ctl_work(w) \ - container_of(w,struct edac_device_ctl_info,work) - -/* - * The alloc() and free() functions for the 'edac_device' control info - * structure. A MC driver will allocate one of these for each edac_device - * it is going to control/register with the EDAC CORE. - */ -extern struct edac_device_ctl_info *edac_device_alloc_ctl_info( - unsigned sizeof_private, - char *edac_device_name, unsigned nr_instances, - char *edac_block_name, unsigned nr_blocks, - unsigned offset_value, - struct edac_dev_sysfs_block_attribute *block_attributes, - unsigned nr_attribs, - int device_index); - -/* The offset value can be: - * -1 indicating no offset value - * 0 for zero-based block numbers - * 1 for 1-based block number - * other for other-based block number - */ -#define BLOCK_OFFSET_VALUE_OFF ((unsigned) -1) - -extern void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info); - struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, unsigned n_layers, struct edac_mc_layer *layers, @@ -350,18 +126,6 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, const char *msg, const char *other_detail); -/* - * edac_device APIs - */ -extern int edac_device_add_device(struct edac_device_ctl_info *edac_dev); -extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); -extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, - int inst_nr, int block_nr, const char *msg); -extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, - int inst_nr, int block_nr, const char *msg); -extern int edac_device_alloc_index(void); -extern const char *edac_layer_name[]; - /* * edac misc APIs */ diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index a97900333e2d..046ab7794fc2 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -12,23 +12,20 @@ * 19 Jan 2007 */ +#include +#include +#include +#include +#include +#include #include -#include +#include #include -#include +#include #include -#include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include "edac_core.h" +#include "edac_device.h" #include "edac_module.h" /* lock for the list: 'edac_device_list', manipulation of this list diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h new file mode 100644 index 000000000000..eb1204408529 --- /dev/null +++ b/drivers/edac/edac_device.h @@ -0,0 +1,269 @@ +/* + * Defines, structures, APIs for edac_device + * + * (C) 2007 Linux Networx (http://lnxi.com) + * This file may be distributed under the terms of the + * GNU General Public License. + * + * Written by Thayne Harbaugh + * Based on work by Dan Hollis and others. + * http://www.anime.net/~goemon/linux-ecc/ + * + * NMI handling support added by + * Dave Peterson + * + * Refactored for multi-source files: + * Doug Thompson + * + * Please look at Documentation/driver-api/edac.rst for more info about + * EDAC core structs and functions. + */ + +#ifndef _EDAC_DEVICE_H_ +#define _EDAC_DEVICE_H_ + +#include +#include +#include +#include +#include +#include +#include +#include + + +/* + * The following are the structures to provide for a generic + * or abstract 'edac_device'. This set of structures and the + * code that implements the APIs for the same, provide for + * registering EDAC type devices which are NOT standard memory. + * + * CPU caches (L1 and L2) + * DMA engines + * Core CPU switches + * Fabric switch units + * PCIe interface controllers + * other EDAC/ECC type devices that can be monitored for + * errors, etc. + * + * It allows for a 2 level set of hierarchy. For example: + * + * cache could be composed of L1, L2 and L3 levels of cache. + * Each CPU core would have its own L1 cache, while sharing + * L2 and maybe L3 caches. + * + * View them arranged, via the sysfs presentation: + * /sys/devices/system/edac/.. + * + * mc/ + * cpu/cpu0/.. + * /L1-cache/ce_count + * /ue_count + * /L2-cache/ce_count + * /ue_count + * cpu/cpu1/.. + * /L1-cache/ce_count + * /ue_count + * /L2-cache/ce_count + * /ue_count + * ... + * + * the L1 and L2 directories would be "edac_device_block's" + */ + +struct edac_device_counter { + u32 ue_count; + u32 ce_count; +}; + +/* forward reference */ +struct edac_device_ctl_info; +struct edac_device_block; + +/* edac_dev_sysfs_attribute structure + * used for driver sysfs attributes in mem_ctl_info + * for extra controls and attributes: + * like high level error Injection controls + */ +struct edac_dev_sysfs_attribute { + struct attribute attr; + ssize_t (*show)(struct edac_device_ctl_info *, char *); + ssize_t (*store)(struct edac_device_ctl_info *, const char *, size_t); +}; + +/* edac_dev_sysfs_block_attribute structure + * + * used in leaf 'block' nodes for adding controls/attributes + * + * each block in each instance of the containing control structure + * can have an array of the following. The show and store functions + * will be filled in with the show/store function in the + * low level driver. + * + * The 'value' field will be the actual value field used for + * counting + */ +struct edac_dev_sysfs_block_attribute { + struct attribute attr; + ssize_t (*show)(struct kobject *, struct attribute *, char *); + ssize_t (*store)(struct kobject *, struct attribute *, + const char *, size_t); + struct edac_device_block *block; + + unsigned int value; +}; + +/* device block control structure */ +struct edac_device_block { + struct edac_device_instance *instance; /* Up Pointer */ + char name[EDAC_DEVICE_NAME_LEN + 1]; + + struct edac_device_counter counters; /* basic UE and CE counters */ + + int nr_attribs; /* how many attributes */ + + /* this block's attributes, could be NULL */ + struct edac_dev_sysfs_block_attribute *block_attributes; + + /* edac sysfs device control */ + struct kobject kobj; +}; + +/* device instance control structure */ +struct edac_device_instance { + struct edac_device_ctl_info *ctl; /* Up pointer */ + char name[EDAC_DEVICE_NAME_LEN + 4]; + + struct edac_device_counter counters; /* instance counters */ + + u32 nr_blocks; /* how many blocks */ + struct edac_device_block *blocks; /* block array */ + + /* edac sysfs device control */ + struct kobject kobj; +}; + + +/* + * Abstract edac_device control info structure + * + */ +struct edac_device_ctl_info { + /* for global list of edac_device_ctl_info structs */ + struct list_head link; + + struct module *owner; /* Module owner of this control struct */ + + int dev_idx; + + /* Per instance controls for this edac_device */ + int log_ue; /* boolean for logging UEs */ + int log_ce; /* boolean for logging CEs */ + int panic_on_ue; /* boolean for panic'ing on an UE */ + unsigned poll_msec; /* number of milliseconds to poll interval */ + unsigned long delay; /* number of jiffies for poll_msec */ + + /* Additional top controller level attributes, but specified + * by the low level driver. + * + * Set by the low level driver to provide attributes at the + * controller level, same level as 'ue_count' and 'ce_count' above. + * An array of structures, NULL terminated + * + * If attributes are desired, then set to array of attributes + * If no attributes are desired, leave NULL + */ + struct edac_dev_sysfs_attribute *sysfs_attributes; + + /* pointer to main 'edac' subsys in sysfs */ + struct bus_type *edac_subsys; + + /* the internal state of this controller instance */ + int op_state; + /* work struct for this instance */ + struct delayed_work work; + + /* pointer to edac polling checking routine: + * If NOT NULL: points to polling check routine + * If NULL: Then assumes INTERRUPT operation, where + * MC driver will receive events + */ + void (*edac_check) (struct edac_device_ctl_info * edac_dev); + + struct device *dev; /* pointer to device structure */ + + const char *mod_name; /* module name */ + const char *ctl_name; /* edac controller name */ + const char *dev_name; /* pci/platform/etc... name */ + + void *pvt_info; /* pointer to 'private driver' info */ + + unsigned long start_time; /* edac_device load start time (jiffies) */ + + struct completion removal_complete; + + /* sysfs top name under 'edac' directory + * and instance name: + * cpu/cpu0/... + * cpu/cpu1/... + * cpu/cpu2/... + * ... + */ + char name[EDAC_DEVICE_NAME_LEN + 1]; + + /* Number of instances supported on this control structure + * and the array of those instances + */ + u32 nr_instances; + struct edac_device_instance *instances; + + /* Event counters for the this whole EDAC Device */ + struct edac_device_counter counters; + + /* edac sysfs device control for the 'name' + * device this structure controls + */ + struct kobject kobj; +}; + +/* To get from the instance's wq to the beginning of the ctl structure */ +#define to_edac_mem_ctl_work(w) \ + container_of(w, struct mem_ctl_info, work) + +#define to_edac_device_ctl_work(w) \ + container_of(w,struct edac_device_ctl_info,work) + +/* + * The alloc() and free() functions for the 'edac_device' control info + * structure. A MC driver will allocate one of these for each edac_device + * it is going to control/register with the EDAC CORE. + */ +extern struct edac_device_ctl_info *edac_device_alloc_ctl_info( + unsigned sizeof_private, + char *edac_device_name, unsigned nr_instances, + char *edac_block_name, unsigned nr_blocks, + unsigned offset_value, + struct edac_dev_sysfs_block_attribute *block_attributes, + unsigned nr_attribs, + int device_index); + +/* The offset value can be: + * -1 indicating no offset value + * 0 for zero-based block numbers + * 1 for 1-based block number + * other for other-based block number + */ +#define BLOCK_OFFSET_VALUE_OFF ((unsigned) -1) + +extern void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info); + +extern int edac_device_add_device(struct edac_device_ctl_info *edac_dev); +extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); +extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, + int inst_nr, int block_nr, const char *msg); +extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, + int inst_nr, int block_nr, const char *msg); +extern int edac_device_alloc_index(void); +extern const char *edac_layer_name[]; + +#endif diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index 93da1a45c716..0e7ea3591b78 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -1,7 +1,7 @@ /* * file for managing the edac_device subsystem of devices for EDAC * - * (C) 2007 SoftwareBitMaker + * (C) 2007 SoftwareBitMaker * * This file may be distributed under the terms of the * GNU General Public License. @@ -15,7 +15,7 @@ #include #include -#include "edac_core.h" +#include "edac_device.h" #include "edac_module.h" #define EDAC_DEVICE_SYMLINK "device" -- cgit v1.2.3 From a16c11b18164d213144e92dcd692accf8bff9344 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 29 Oct 2016 15:16:34 -0200 Subject: edac: rename edac_core.h to edac_mc.h Now, all left at edac_core.h are at drivers/edac/edac_mc.c, so rename it to edac_mc.h. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/altera_edac.c | 1 - drivers/edac/amd64_edac.h | 2 +- drivers/edac/amd76x_edac.c | 2 +- drivers/edac/amd8111_edac.c | 1 - drivers/edac/amd8131_edac.c | 1 - drivers/edac/cell_edac.c | 2 +- drivers/edac/cpc925_edac.c | 1 - drivers/edac/e752x_edac.c | 2 +- drivers/edac/e7xxx_edac.c | 2 +- drivers/edac/edac_core.h | 134 ---------------------------------------- drivers/edac/edac_mc.c | 2 +- drivers/edac/edac_mc.h | 131 +++++++++++++++++++++++++++++++++++++++ drivers/edac/edac_mc_sysfs.c | 2 +- drivers/edac/edac_module.c | 2 +- drivers/edac/edac_module.h | 4 +- drivers/edac/fsl_ddr_edac.c | 1 - drivers/edac/ghes_edac.c | 2 +- drivers/edac/highbank_l2_edac.c | 1 - drivers/edac/highbank_mc_edac.c | 1 - drivers/edac/i3000_edac.c | 2 +- drivers/edac/i3200_edac.c | 2 +- drivers/edac/i5000_edac.c | 2 +- drivers/edac/i5100_edac.c | 1 - drivers/edac/i5400_edac.c | 2 +- drivers/edac/i7300_edac.c | 2 +- drivers/edac/i7core_edac.c | 2 +- drivers/edac/i82443bxgx_edac.c | 2 +- drivers/edac/i82860_edac.c | 2 +- drivers/edac/i82875p_edac.c | 2 +- drivers/edac/i82975x_edac.c | 2 +- drivers/edac/ie31200_edac.c | 2 +- drivers/edac/layerscape_edac.c | 2 +- drivers/edac/mpc85xx_edac.c | 1 - drivers/edac/mv64x60_edac.c | 1 - drivers/edac/octeon_edac-l2c.c | 1 - drivers/edac/octeon_edac-lmc.c | 1 - drivers/edac/octeon_edac-pc.c | 1 - drivers/edac/octeon_edac-pci.c | 1 - drivers/edac/pasemi_edac.c | 2 +- drivers/edac/ppc4xx_edac.c | 2 +- drivers/edac/r82600_edac.c | 2 +- drivers/edac/sb_edac.c | 2 +- drivers/edac/skx_edac.c | 2 +- drivers/edac/synopsys_edac.c | 2 +- drivers/edac/tile_edac.c | 2 +- drivers/edac/x38_edac.c | 2 +- drivers/edac/xgene_edac.c | 1 - 47 files changed, 163 insertions(+), 179 deletions(-) delete mode 100644 drivers/edac/edac_core.h create mode 100644 drivers/edac/edac_mc.h diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 6421cc3c7dc1..c5a5b91f37f0 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -35,7 +35,6 @@ #include #include "altera_edac.h" -#include "edac_core.h" #include "edac_module.h" #define EDAC_MOD_STR "altera_edac" diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index f14c24d5b140..496603d8f3d2 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -17,7 +17,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #include "mce_amd.h" #define amd64_debug(fmt, arg...) \ diff --git a/drivers/edac/amd76x_edac.c b/drivers/edac/amd76x_edac.c index 3a501b530e11..a7450275ad28 100644 --- a/drivers/edac/amd76x_edac.c +++ b/drivers/edac/amd76x_edac.c @@ -17,7 +17,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define AMD76X_REVISION " Ver: 2.0.2" #define EDAC_MOD_STR "amd76x_edac" diff --git a/drivers/edac/amd8111_edac.c b/drivers/edac/amd8111_edac.c index 2b63f7c2d6d2..b5786cfded3a 100644 --- a/drivers/edac/amd8111_edac.c +++ b/drivers/edac/amd8111_edac.c @@ -29,7 +29,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #include "amd8111_edac.h" diff --git a/drivers/edac/amd8131_edac.c b/drivers/edac/amd8131_edac.c index a5c680561c73..8851c33d7d24 100644 --- a/drivers/edac/amd8131_edac.c +++ b/drivers/edac/amd8131_edac.c @@ -29,7 +29,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #include "amd8131_edac.h" diff --git a/drivers/edac/cell_edac.c b/drivers/edac/cell_edac.c index a9259b069dcd..bc1f3416400e 100644 --- a/drivers/edac/cell_edac.c +++ b/drivers/edac/cell_edac.c @@ -19,7 +19,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" struct cell_edac_priv { diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c index 682288ced4ac..837b62c4993d 100644 --- a/drivers/edac/cpc925_edac.c +++ b/drivers/edac/cpc925_edac.c @@ -27,7 +27,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #define CPC925_EDAC_REVISION " Ver: 1.0.0" diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c index b2d71388172b..1a352cae1f52 100644 --- a/drivers/edac/e752x_edac.c +++ b/drivers/edac/e752x_edac.c @@ -24,7 +24,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define E752X_REVISION " Ver: 2.0.2" #define EDAC_MOD_STR "e752x_edac" diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c index ece3aef16bb1..67ef07aed923 100644 --- a/drivers/edac/e7xxx_edac.c +++ b/drivers/edac/e7xxx_edac.c @@ -30,7 +30,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define E7XXX_REVISION " Ver: 2.0.2" #define EDAC_MOD_STR "e7xxx_edac" diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h deleted file mode 100644 index 3e11d9d85462..000000000000 --- a/drivers/edac/edac_core.h +++ /dev/null @@ -1,134 +0,0 @@ -/* - * Defines, structures, APIs for edac_core module - * - * (C) 2007 Linux Networx (http://lnxi.com) - * This file may be distributed under the terms of the - * GNU General Public License. - * - * Written by Thayne Harbaugh - * Based on work by Dan Hollis and others. - * http://www.anime.net/~goemon/linux-ecc/ - * - * NMI handling support added by - * Dave Peterson - * - * Refactored for multi-source files: - * Doug Thompson - * - */ - -#ifndef _EDAC_CORE_H_ -#define _EDAC_CORE_H_ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "edac_pci.h" -#include "edac_device.h" - -#if PAGE_SHIFT < 20 -#define PAGES_TO_MiB(pages) ((pages) >> (20 - PAGE_SHIFT)) -#define MiB_TO_PAGES(mb) ((mb) << (20 - PAGE_SHIFT)) -#else /* PAGE_SHIFT > 20 */ -#define PAGES_TO_MiB(pages) ((pages) << (PAGE_SHIFT - 20)) -#define MiB_TO_PAGES(mb) ((mb) >> (PAGE_SHIFT - 20)) -#endif - -#define edac_printk(level, prefix, fmt, arg...) \ - printk(level "EDAC " prefix ": " fmt, ##arg) - -#define edac_mc_printk(mci, level, fmt, arg...) \ - printk(level "EDAC MC%d: " fmt, mci->mc_idx, ##arg) - -#define edac_mc_chipset_printk(mci, level, prefix, fmt, arg...) \ - printk(level "EDAC " prefix " MC%d: " fmt, mci->mc_idx, ##arg) - -#define edac_device_printk(ctl, level, fmt, arg...) \ - printk(level "EDAC DEVICE%d: " fmt, ctl->dev_idx, ##arg) - -#define edac_pci_printk(ctl, level, fmt, arg...) \ - printk(level "EDAC PCI%d: " fmt, ctl->pci_idx, ##arg) - -/* prefixes for edac_printk() and edac_mc_printk() */ -#define EDAC_MC "MC" -#define EDAC_PCI "PCI" -#define EDAC_DEBUG "DEBUG" - -extern const char * const edac_mem_types[]; - -#ifdef CONFIG_EDAC_DEBUG -extern int edac_debug_level; - -#define edac_dbg(level, fmt, ...) \ -do { \ - if (level <= edac_debug_level) \ - edac_printk(KERN_DEBUG, EDAC_DEBUG, \ - "%s: " fmt, __func__, ##__VA_ARGS__); \ -} while (0) - -#else /* !CONFIG_EDAC_DEBUG */ - -#define edac_dbg(level, fmt, ...) \ -do { \ - if (0) \ - edac_printk(KERN_DEBUG, EDAC_DEBUG, \ - "%s: " fmt, __func__, ##__VA_ARGS__); \ -} while (0) - -#endif /* !CONFIG_EDAC_DEBUG */ - -#define PCI_VEND_DEV(vend, dev) PCI_VENDOR_ID_ ## vend, \ - PCI_DEVICE_ID_ ## vend ## _ ## dev - -#define edac_dev_name(dev) (dev)->dev_name - -#define to_mci(k) container_of(k, struct mem_ctl_info, dev) - -struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, - unsigned n_layers, - struct edac_mc_layer *layers, - unsigned sz_pvt); -extern int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, - const struct attribute_group **groups); -#define edac_mc_add_mc(mci) edac_mc_add_mc_with_groups(mci, NULL) -extern void edac_mc_free(struct mem_ctl_info *mci); -extern struct mem_ctl_info *edac_mc_find(int idx); -extern struct mem_ctl_info *find_mci_by_dev(struct device *dev); -extern struct mem_ctl_info *edac_mc_del_mc(struct device *dev); -extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, - unsigned long page); - -void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, - struct mem_ctl_info *mci, - struct edac_raw_error_desc *e); - -void edac_mc_handle_error(const enum hw_event_mc_err_type type, - struct mem_ctl_info *mci, - const u16 error_count, - const unsigned long page_frame_number, - const unsigned long offset_in_page, - const unsigned long syndrome, - const int top_layer, - const int mid_layer, - const int low_layer, - const char *msg, - const char *other_detail); - -/* - * edac misc APIs - */ -extern char *edac_op_state_to_string(int op_state); - -#endif /* _EDAC_CORE_H_ */ diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index d2ea9c4f1824..4ff5116a90a5 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -30,7 +30,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_mc.h" #include "edac_module.h" #include diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h new file mode 100644 index 000000000000..b62d9bad9859 --- /dev/null +++ b/drivers/edac/edac_mc.h @@ -0,0 +1,131 @@ +/* + * Defines, structures, APIs for edac_mc module + * + * (C) 2007 Linux Networx (http://lnxi.com) + * This file may be distributed under the terms of the + * GNU General Public License. + * + * Written by Thayne Harbaugh + * Based on work by Dan Hollis and others. + * http://www.anime.net/~goemon/linux-ecc/ + * + * NMI handling support added by + * Dave Peterson + * + * Refactored for multi-source files: + * Doug Thompson + * + */ + +#ifndef _EDAC_MC_H_ +#define _EDAC_MC_H_ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if PAGE_SHIFT < 20 +#define PAGES_TO_MiB(pages) ((pages) >> (20 - PAGE_SHIFT)) +#define MiB_TO_PAGES(mb) ((mb) << (20 - PAGE_SHIFT)) +#else /* PAGE_SHIFT > 20 */ +#define PAGES_TO_MiB(pages) ((pages) << (PAGE_SHIFT - 20)) +#define MiB_TO_PAGES(mb) ((mb) >> (PAGE_SHIFT - 20)) +#endif + +#define edac_printk(level, prefix, fmt, arg...) \ + printk(level "EDAC " prefix ": " fmt, ##arg) + +#define edac_mc_printk(mci, level, fmt, arg...) \ + printk(level "EDAC MC%d: " fmt, mci->mc_idx, ##arg) + +#define edac_mc_chipset_printk(mci, level, prefix, fmt, arg...) \ + printk(level "EDAC " prefix " MC%d: " fmt, mci->mc_idx, ##arg) + +#define edac_device_printk(ctl, level, fmt, arg...) \ + printk(level "EDAC DEVICE%d: " fmt, ctl->dev_idx, ##arg) + +#define edac_pci_printk(ctl, level, fmt, arg...) \ + printk(level "EDAC PCI%d: " fmt, ctl->pci_idx, ##arg) + +/* prefixes for edac_printk() and edac_mc_printk() */ +#define EDAC_MC "MC" +#define EDAC_PCI "PCI" +#define EDAC_DEBUG "DEBUG" + +extern const char * const edac_mem_types[]; + +#ifdef CONFIG_EDAC_DEBUG +extern int edac_debug_level; + +#define edac_dbg(level, fmt, ...) \ +do { \ + if (level <= edac_debug_level) \ + edac_printk(KERN_DEBUG, EDAC_DEBUG, \ + "%s: " fmt, __func__, ##__VA_ARGS__); \ +} while (0) + +#else /* !CONFIG_EDAC_DEBUG */ + +#define edac_dbg(level, fmt, ...) \ +do { \ + if (0) \ + edac_printk(KERN_DEBUG, EDAC_DEBUG, \ + "%s: " fmt, __func__, ##__VA_ARGS__); \ +} while (0) + +#endif /* !CONFIG_EDAC_DEBUG */ + +#define PCI_VEND_DEV(vend, dev) PCI_VENDOR_ID_ ## vend, \ + PCI_DEVICE_ID_ ## vend ## _ ## dev + +#define edac_dev_name(dev) (dev)->dev_name + +#define to_mci(k) container_of(k, struct mem_ctl_info, dev) + +struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, + unsigned n_layers, + struct edac_mc_layer *layers, + unsigned sz_pvt); +extern int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, + const struct attribute_group **groups); +#define edac_mc_add_mc(mci) edac_mc_add_mc_with_groups(mci, NULL) +extern void edac_mc_free(struct mem_ctl_info *mci); +extern struct mem_ctl_info *edac_mc_find(int idx); +extern struct mem_ctl_info *find_mci_by_dev(struct device *dev); +extern struct mem_ctl_info *edac_mc_del_mc(struct device *dev); +extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, + unsigned long page); + +void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, + struct mem_ctl_info *mci, + struct edac_raw_error_desc *e); + +void edac_mc_handle_error(const enum hw_event_mc_err_type type, + struct mem_ctl_info *mci, + const u16 error_count, + const unsigned long page_frame_number, + const unsigned long offset_in_page, + const unsigned long syndrome, + const int top_layer, + const int mid_layer, + const int low_layer, + const char *msg, + const char *other_detail); + +/* + * edac misc APIs + */ +extern char *edac_op_state_to_string(int op_state); + +#endif /* _EDAC_MC_H_ */ diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 4e0f8e720ad9..39dbab7d62f1 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -19,7 +19,7 @@ #include #include -#include "edac_core.h" +#include "edac_mc.h" #include "edac_module.h" /* MC EDAC Controls, setable by module parameter, and sysfs */ diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c index 5f8543be995a..172598a27d7d 100644 --- a/drivers/edac/edac_module.c +++ b/drivers/edac/edac_module.c @@ -12,7 +12,7 @@ */ #include -#include "edac_core.h" +#include "edac_mc.h" #include "edac_module.h" #define EDAC_VERSION "Ver: 3.0.0" diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index cfaacb99c973..014871e169cc 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -10,7 +10,9 @@ #ifndef __EDAC_MODULE_H__ #define __EDAC_MODULE_H__ -#include "edac_core.h" +#include "edac_mc.h" +#include "edac_pci.h" +#include "edac_device.h" /* * INTERNAL EDAC MODULE: diff --git a/drivers/edac/fsl_ddr_edac.c b/drivers/edac/fsl_ddr_edac.c index 9774f52f0c3e..4e9608a958e7 100644 --- a/drivers/edac/fsl_ddr_edac.c +++ b/drivers/edac/fsl_ddr_edac.c @@ -28,7 +28,6 @@ #include #include #include "edac_module.h" -#include "edac_core.h" #include "fsl_ddr_edac.h" #define EDAC_MOD_STR "fsl_ddr_edac" diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index e3fa4390f846..4e61a6229dd2 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -14,7 +14,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #include #define GHES_EDAC_REVISION " Ver: 1.0.0" diff --git a/drivers/edac/highbank_l2_edac.c b/drivers/edac/highbank_l2_edac.c index 2f193668ebc7..cd9a2bb7c548 100644 --- a/drivers/edac/highbank_l2_edac.c +++ b/drivers/edac/highbank_l2_edac.c @@ -21,7 +21,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #define SR_CLR_SB_ECC_INTR 0x0 diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index 11260cc3360e..0e7e0a404d89 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -22,7 +22,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" /* DDR Ctrlr Error Registers */ diff --git a/drivers/edac/i3000_edac.c b/drivers/edac/i3000_edac.c index 5cb36a6022cc..5306240570d7 100644 --- a/drivers/edac/i3000_edac.c +++ b/drivers/edac/i3000_edac.c @@ -14,7 +14,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define I3000_REVISION "1.1" diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index 1f453382258a..77c58d201a30 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -13,7 +13,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #include diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c index 72e07e3cf718..1670d27bcac8 100644 --- a/drivers/edac/i5000_edac.c +++ b/drivers/edac/i5000_edac.c @@ -22,7 +22,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" /* * Alter this version for the I5000 module when modifications are made diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index c655162caf08..a8334c4acea7 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -29,7 +29,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" /* register addresses */ diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c index 6ef6ad1ba16e..abf6ef22e220 100644 --- a/drivers/edac/i5400_edac.c +++ b/drivers/edac/i5400_edac.c @@ -32,7 +32,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" /* * Alter this version for the I5400 module when modifications are made diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index dcac982fdc7a..0a912bf6de00 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -26,7 +26,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" /* * Alter this version for the I7300 module when modifications are made diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 8a68a5e943ea..69b5adead0ad 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -39,7 +39,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" /* Static vars */ static LIST_HEAD(i7core_edac_list); diff --git a/drivers/edac/i82443bxgx_edac.c b/drivers/edac/i82443bxgx_edac.c index 4d4110364f02..cb61a5b7d080 100644 --- a/drivers/edac/i82443bxgx_edac.c +++ b/drivers/edac/i82443bxgx_edac.c @@ -29,7 +29,7 @@ #include -#include "edac_core.h" +#include "edac_module.h" #define I82443_REVISION "0.1" diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c index ee1078cd3b96..236c813227fc 100644 --- a/drivers/edac/i82860_edac.c +++ b/drivers/edac/i82860_edac.c @@ -14,7 +14,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define I82860_REVISION " Ver: 2.0.2" #define EDAC_MOD_STR "i82860_edac" diff --git a/drivers/edac/i82875p_edac.c b/drivers/edac/i82875p_edac.c index c26a513f8869..e286b7e74c7a 100644 --- a/drivers/edac/i82875p_edac.c +++ b/drivers/edac/i82875p_edac.c @@ -18,7 +18,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define I82875P_REVISION " Ver: 2.0.2" #define EDAC_MOD_STR "i82875p_edac" diff --git a/drivers/edac/i82975x_edac.c b/drivers/edac/i82975x_edac.c index 35ab66c623a3..7baa8ace267b 100644 --- a/drivers/edac/i82975x_edac.c +++ b/drivers/edac/i82975x_edac.c @@ -14,7 +14,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define I82975X_REVISION " Ver: 1.0.0" #define EDAC_MOD_STR "i82975x_edac" diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 1c88d9707495..2733fb5938a4 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -41,7 +41,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" #define IE31200_REVISION "1.0" #define EDAC_MOD_STR "ie31200_edac" diff --git a/drivers/edac/layerscape_edac.c b/drivers/edac/layerscape_edac.c index 6c59d897ad12..94cac7686a56 100644 --- a/drivers/edac/layerscape_edac.c +++ b/drivers/edac/layerscape_edac.c @@ -16,7 +16,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include "edac_core.h" +#include "edac_module.h" #include "fsl_ddr_edac.h" static const struct of_device_id fsl_ddr_mc_err_of_match[] = { diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index c62602141f95..8f66cbed70b7 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -25,7 +25,6 @@ #include #include #include "edac_module.h" -#include "edac_core.h" #include "mpc85xx_edac.h" #include "fsl_ddr_edac.h" diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c index cb9b8577acbc..14b7e7b71eaa 100644 --- a/drivers/edac/mv64x60_edac.c +++ b/drivers/edac/mv64x60_edac.c @@ -17,7 +17,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #include "mv64x60_edac.h" diff --git a/drivers/edac/octeon_edac-l2c.c b/drivers/edac/octeon_edac-l2c.c index afea7fc625cc..c33059e9b0be 100644 --- a/drivers/edac/octeon_edac-l2c.c +++ b/drivers/edac/octeon_edac-l2c.c @@ -16,7 +16,6 @@ #include -#include "edac_core.h" #include "edac_module.h" #define EDAC_MOD_STR "octeon-l2c" diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c index cda6dab5067a..9c1ffe3e912b 100644 --- a/drivers/edac/octeon_edac-lmc.c +++ b/drivers/edac/octeon_edac-lmc.c @@ -19,7 +19,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #define OCTEON_MAX_MC 4 diff --git a/drivers/edac/octeon_edac-pc.c b/drivers/edac/octeon_edac-pc.c index 2ab6cf24c959..754eced59c32 100644 --- a/drivers/edac/octeon_edac-pc.c +++ b/drivers/edac/octeon_edac-pc.c @@ -15,7 +15,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #include diff --git a/drivers/edac/octeon_edac-pci.c b/drivers/edac/octeon_edac-pci.c index 9ca73cec74e7..28b238eecefc 100644 --- a/drivers/edac/octeon_edac-pci.c +++ b/drivers/edac/octeon_edac-pci.c @@ -18,7 +18,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" static void octeon_pci_poll(struct edac_pci_ctl_info *pci) diff --git a/drivers/edac/pasemi_edac.c b/drivers/edac/pasemi_edac.c index 9c971b575530..199f2c80480d 100644 --- a/drivers/edac/pasemi_edac.c +++ b/drivers/edac/pasemi_edac.c @@ -26,7 +26,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define MODULE_NAME "pasemi_edac" diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c index 691ce25e9010..e55e92590106 100644 --- a/drivers/edac/ppc4xx_edac.c +++ b/drivers/edac/ppc4xx_edac.c @@ -21,7 +21,7 @@ #include -#include "edac_core.h" +#include "edac_module.h" #include "ppc4xx_edac.h" /* diff --git a/drivers/edac/r82600_edac.c b/drivers/edac/r82600_edac.c index 8f936bc7a010..978916625ced 100644 --- a/drivers/edac/r82600_edac.c +++ b/drivers/edac/r82600_edac.c @@ -20,7 +20,7 @@ #include #include #include -#include "edac_core.h" +#include "edac_module.h" #define R82600_REVISION " Ver: 2.0.2" #define EDAC_MOD_STR "r82600_edac" diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index c1ad0eb7d5dd..54ae6dc45ab2 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -27,7 +27,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" /* Static vars */ static LIST_HEAD(sbridge_edac_list); diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index 9edcb29b3001..79ef675e4d6f 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -29,7 +29,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" #define SKX_REVISION " Ver: 1.0 " diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index fc153aea2f6c..1c01dec78ec3 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -23,7 +23,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" /* Number of cs_rows needed per memory controller */ #define SYNPS_EDAC_NR_CSROWS 1 diff --git a/drivers/edac/tile_edac.c b/drivers/edac/tile_edac.c index 71381642ce2a..8a33a87e67f1 100644 --- a/drivers/edac/tile_edac.c +++ b/drivers/edac/tile_edac.c @@ -30,7 +30,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" #define DRV_NAME "tile-edac" diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c index 314cf5cf268c..03c97a4bf590 100644 --- a/drivers/edac/x38_edac.c +++ b/drivers/edac/x38_edac.c @@ -16,7 +16,7 @@ #include #include -#include "edac_core.h" +#include "edac_module.h" #define X38_REVISION "1.1" diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index 5569391ea800..6c270d9d304a 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -28,7 +28,6 @@ #include #include -#include "edac_core.h" #include "edac_module.h" #define EDAC_MOD_STR "xgene_edac" -- cgit v1.2.3 From 3002934eb3bc0ca843536c7b501d792bcca6b7a5 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 16:01:47 -0200 Subject: edac: move documentation from edac_device to edac_core.h Several functions are documented at edac_device.c. As we'll be including edac_core.h at drivers-api book, move those, in order for the kernel-doc markups be part of the API documentation book. As several of those kernel-doc macros are not in the right format, fix them. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_device.c | 58 ---------------------------------------------- drivers/edac/edac_device.h | 51 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+), 58 deletions(-) diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 046ab7794fc2..de4d5d08af9e 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -47,21 +47,6 @@ static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev) } #endif /* CONFIG_EDAC_DEBUG */ - -/* - * edac_device_alloc_ctl_info() - * Allocate a new edac device control info structure - * - * The control structure is allocated in complete chunk - * from the OS. It is in turn sub allocated to the - * various objects that compose the structure - * - * The structure has a 'nr_instance' array within itself. - * Each instance represents a major component - * Example: L1 cache and L2 cache are 2 instance components - * - * Within each instance is an array of 'nr_blocks' blockoffsets - */ struct edac_device_ctl_info *edac_device_alloc_ctl_info( unsigned sz_private, char *edac_device_name, unsigned nr_instances, @@ -241,11 +226,6 @@ struct edac_device_ctl_info *edac_device_alloc_ctl_info( } EXPORT_SYMBOL_GPL(edac_device_alloc_ctl_info); -/* - * edac_device_free_ctl_info() - * frees the memory allocated by the edac_device_alloc_ctl_info() - * function - */ void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info) { edac_device_unregister_sysfs_main_kobj(ctl_info); @@ -457,12 +437,6 @@ void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, edac_mod_work(&edac_dev->work, jiffs); } -/* - * edac_device_alloc_index: Allocate a unique device index number - * - * Return: - * allocated index number - */ int edac_device_alloc_index(void) { static atomic_t device_indexes = ATOMIC_INIT(0); @@ -471,17 +445,6 @@ int edac_device_alloc_index(void) } EXPORT_SYMBOL_GPL(edac_device_alloc_index); -/** - * edac_device_add_device: Insert the 'edac_dev' structure into the - * edac_device global list and create sysfs entries associated with - * edac_device structure. - * @edac_device: pointer to the edac_device structure to be added to the list - * 'edac_device' structure. - * - * Return: - * 0 Success - * !0 Failure - */ int edac_device_add_device(struct edac_device_ctl_info *edac_dev) { edac_dbg(0, "\n"); @@ -538,19 +501,6 @@ fail0: } EXPORT_SYMBOL_GPL(edac_device_add_device); -/** - * edac_device_del_device: - * Remove sysfs entries for specified edac_device structure and - * then remove edac_device structure from global list - * - * @dev: - * Pointer to 'struct device' representing edac_device - * structure to remove. - * - * Return: - * Pointer to removed edac_device structure, - * OR NULL if device not found. - */ struct edac_device_ctl_info *edac_device_del_device(struct device *dev) { struct edac_device_ctl_info *edac_dev; @@ -605,10 +555,6 @@ static inline int edac_device_get_panic_on_ue(struct edac_device_ctl_info return edac_dev->panic_on_ue; } -/* - * edac_device_handle_ce - * perform a common output and handling of an 'edac_dev' CE event - */ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, int inst_nr, int block_nr, const char *msg) { @@ -651,10 +597,6 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, } EXPORT_SYMBOL_GPL(edac_device_handle_ce); -/* - * edac_device_handle_ue - * perform a common output and handling of an 'edac_dev' UE event - */ void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, int inst_nr, int block_nr, const char *msg) { diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h index eb1204408529..1aaba74ae411 100644 --- a/drivers/edac/edac_device.h +++ b/drivers/edac/edac_device.h @@ -257,12 +257,63 @@ extern struct edac_device_ctl_info *edac_device_alloc_ctl_info( extern void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info); +/** + * edac_device_add_device: Insert the 'edac_dev' structure into the + * edac_device global list and create sysfs entries associated with + * edac_device structure. + * + * @edac_dev: pointer to edac_device structure to be added to the list + * 'edac_device' structure. + * + * Returns: + * 0 on Success, or an error code on failure + */ extern int edac_device_add_device(struct edac_device_ctl_info *edac_dev); + +/** + * edac_device_del_device: + * Remove sysfs entries for specified edac_device structure and + * then remove edac_device structure from global list + * + * @dev: + * Pointer to struct &device representing the edac device + * structure to remove. + * + * Returns: + * Pointer to removed edac_device structure, + * or %NULL if device not found. + */ extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); + +/** + * edac_device_handle_ue(): + * perform a common output and handling of an 'edac_dev' UE event + * + * @edac_dev: pointer to struct &edac_device_ctl_info + * @inst_nr: number of the instance where the UE error happened + * @block_nr: number of the block where the UE error happened + * @msg: message to be printed + */ extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, int inst_nr, int block_nr, const char *msg); +/** + * edac_device_handle_ce(): + * perform a common output and handling of an 'edac_dev' CE event + * + * @edac_dev: pointer to struct &edac_device_ctl_info + * @inst_nr: number of the instance where the CE error happened + * @block_nr: number of the block where the CE error happened + * @msg: message to be printed + */ extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, int inst_nr, int block_nr, const char *msg); + +/** + * edac_device_alloc_index: Allocate a unique device index number + * + * Returns: + * allocated index number + */ extern int edac_device_alloc_index(void); extern const char *edac_layer_name[]; -- cgit v1.2.3 From e756a4068620402a5dd507f0b10a6148fe20250a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 16:13:43 -0200 Subject: edac: move documentation from edac_pci*.c to edac_pci.h Several functions are documented at edac_pci.c and edac_pci_sysfs.c. As we'll be including edac_pci.h at drivers-api book, move those, in order for the kernel-doc markups be part of the API documentation book. As several of those kernel-doc macros are not in the right format, fix them. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_pci.c | 65 ---------------------------- drivers/edac/edac_pci.h | 98 +++++++++++++++++++++++++++++++++++++++++++ drivers/edac/edac_pci_sysfs.c | 11 ----- 3 files changed, 98 insertions(+), 76 deletions(-) diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c index 02a0af4f53b3..4e9d5632041a 100644 --- a/drivers/edac/edac_pci.c +++ b/drivers/edac/edac_pci.c @@ -28,13 +28,6 @@ static DEFINE_MUTEX(edac_pci_ctls_mutex); static LIST_HEAD(edac_pci_list); static atomic_t pci_indexes = ATOMIC_INIT(0); -/* - * edac_pci_alloc_ctl_info - * - * The alloc() function for the 'edac_pci' control info - * structure. The chip driver will allocate one of these for each - * edac_pci it is going to control/register with the EDAC CORE. - */ struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, const char *edac_pci_name) { @@ -65,16 +58,6 @@ struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, } EXPORT_SYMBOL_GPL(edac_pci_alloc_ctl_info); -/* - * edac_pci_free_ctl_info() - * - * Last action on the pci control structure. - * - * call the remove sysfs information, which will unregister - * this control struct's kobj. When that kobj's ref count - * goes to zero, its release function will be call and then - * kfree() the memory. - */ void edac_pci_free_ctl_info(struct edac_pci_ctl_info *pci) { edac_dbg(1, "\n"); @@ -212,31 +195,12 @@ static void edac_pci_workq_function(struct work_struct *work_req) mutex_unlock(&edac_pci_ctls_mutex); } -/* - * edac_pci_alloc_index: Allocate a unique PCI index number - * - * Return: - * allocated index number - * - */ int edac_pci_alloc_index(void) { return atomic_inc_return(&pci_indexes) - 1; } EXPORT_SYMBOL_GPL(edac_pci_alloc_index); -/* - * edac_pci_add_device: Insert the 'edac_dev' structure into the - * edac_pci global list and create sysfs entries associated with - * edac_pci structure. - * @pci: pointer to the edac_device structure to be added to the list - * @edac_idx: A unique numeric identifier to be assigned to the - * 'edac_pci' structure. - * - * Return: - * 0 Success - * !0 Failure - */ int edac_pci_add_device(struct edac_pci_ctl_info *pci, int edac_idx) { edac_dbg(0, "\n"); @@ -282,19 +246,6 @@ fail0: } EXPORT_SYMBOL_GPL(edac_pci_add_device); -/* - * edac_pci_del_device() - * Remove sysfs entries for specified edac_pci structure and - * then remove edac_pci structure from global list - * - * @dev: - * Pointer to 'struct device' representing edac_pci structure - * to remove - * - * Return: - * Pointer to removed edac_pci structure, - * or NULL if device not found - */ struct edac_pci_ctl_info *edac_pci_del_device(struct device *dev) { struct edac_pci_ctl_info *pci; @@ -348,17 +299,6 @@ struct edac_pci_gen_data { int edac_idx; }; -/* - * edac_pci_create_generic_ctl - * - * A generic constructor for a PCI parity polling device - * Some systems have more than one domain of PCI busses. - * For systems with one domain, then this API will - * provide for a generic poller. - * - * This routine calls the edac_pci_alloc_ctl_info() for - * the generic device, with default values - */ struct edac_pci_ctl_info *edac_pci_create_generic_ctl(struct device *dev, const char *mod_name) { @@ -391,11 +331,6 @@ struct edac_pci_ctl_info *edac_pci_create_generic_ctl(struct device *dev, } EXPORT_SYMBOL_GPL(edac_pci_create_generic_ctl); -/* - * edac_pci_release_generic_ctl - * - * The release function of a generic EDAC PCI polling device - */ void edac_pci_release_generic_ctl(struct edac_pci_ctl_info *pci) { edac_dbg(0, "pci mod=%s\n", pci->mod_name); diff --git a/drivers/edac/edac_pci.h b/drivers/edac/edac_pci.h index 9da0c6fb0634..5175f5724cfa 100644 --- a/drivers/edac/edac_pci.h +++ b/drivers/edac/edac_pci.h @@ -153,21 +153,119 @@ static inline void pci_write_bits32(struct pci_dev *pdev, int offset, #endif /* CONFIG_PCI */ +/* + * edac_pci APIs + */ + +/** + * edac_pci_alloc_ctl_info: + * The alloc() function for the 'edac_pci' control info + * structure. + * + * @sz_pvt: size of the private info at struct &edac_pci_ctl_info + * @edac_pci_name: name of the PCI device + * + * The chip driver will allocate one of these for each + * edac_pci it is going to control/register with the EDAC CORE. + * + * Returns: a pointer to struct &edac_pci_ctl_info on success; %NULL otherwise. + */ extern struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, const char *edac_pci_name); +/** + * edac_pci_free_ctl_info(): + * Last action on the pci control structure. + * + * @pci: pointer to struct &edac_pci_ctl_info + * + * Calls the remove sysfs information, which will unregister + * this control struct's kobj. When that kobj's ref count + * goes to zero, its release function will be call and then + * kfree() the memory. + */ extern void edac_pci_free_ctl_info(struct edac_pci_ctl_info *pci); +/** + * edac_pci_alloc_index: Allocate a unique PCI index number + * + * Returns: + * allocated index number + * + */ extern int edac_pci_alloc_index(void); + +/** + * edac_pci_add_device(): Insert the 'edac_dev' structure into the + * edac_pci global list and create sysfs entries associated with + * edac_pci structure. + * + * @pci: pointer to the edac_device structure to be added to the list + * @edac_idx: A unique numeric identifier to be assigned to the + * 'edac_pci' structure. + * + * Returns: + * 0 on Success, or an error code on failure + */ extern int edac_pci_add_device(struct edac_pci_ctl_info *pci, int edac_idx); + +/** + * edac_pci_del_device() + * Remove sysfs entries for specified edac_pci structure and + * then remove edac_pci structure from global list + * + * @dev: + * Pointer to 'struct device' representing edac_pci structure + * to remove + * + * Returns: + * Pointer to removed edac_pci structure, + * or %NULL if device not found + */ extern struct edac_pci_ctl_info *edac_pci_del_device(struct device *dev); +/** + * edac_pci_create_generic_ctl() + * A generic constructor for a PCI parity polling device + * Some systems have more than one domain of PCI busses. + * For systems with one domain, then this API will + * provide for a generic poller. + * + * @dev: pointer to struct &device; + * @mod_name: name of the PCI device + * + * This routine calls the edac_pci_alloc_ctl_info() for + * the generic device, with default values + * + * Returns: Pointer to struct &edac_pci_ctl_info on success, %NULL on + * failure. + */ extern struct edac_pci_ctl_info *edac_pci_create_generic_ctl( struct device *dev, const char *mod_name); +/** + * edac_pci_release_generic_ctl + * The release function of a generic EDAC PCI polling device + * + * @pci: pointer to struct &edac_pci_ctl_info + */ extern void edac_pci_release_generic_ctl(struct edac_pci_ctl_info *pci); + +/** + * edac_pci_create_sysfs + * Create the controls/attributes for the specified EDAC PCI device + * + * @pci: pointer to struct &edac_pci_ctl_info + */ extern int edac_pci_create_sysfs(struct edac_pci_ctl_info *pci); + +/** + * edac_pci_remove_sysfs() + * remove the controls and attributes for this EDAC PCI device + * + * @pci: pointer to struct &edac_pci_ctl_info + */ extern void edac_pci_remove_sysfs(struct edac_pci_ctl_info *pci); #endif diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index dbeb048d8efb..72c9eb9fdffb 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -418,12 +418,6 @@ static void edac_pci_main_kobj_teardown(void) } } -/* - * - * edac_pci_create_sysfs - * - * Create the controls/attributes for the specified EDAC PCI device - */ int edac_pci_create_sysfs(struct edac_pci_ctl_info *pci) { int err; @@ -459,11 +453,6 @@ unregister_cleanup: return err; } -/* - * edac_pci_remove_sysfs - * - * remove the controls and attributes for this EDAC PCI device - */ void edac_pci_remove_sysfs(struct edac_pci_ctl_info *pci) { edac_dbg(0, "index=%d\n", pci->pci_idx); -- cgit v1.2.3 From 1c5991a9d14235a8a54636ac331e237c96f61d58 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 15:47:55 -0200 Subject: edac: move documentation from edac_mc.c to edac_core.h Several functions are documented at edac_mc.c. As we'll be including edac_core.h at drivers-api book, move those, in order for the kernel-doc markups be part of the API documentation book. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_mc.c | 82 --------------------------------------- drivers/edac/edac_mc.h | 101 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 101 insertions(+), 82 deletions(-) diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 4ff5116a90a5..5f2c717f8053 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -239,30 +239,6 @@ static void _edac_mc_free(struct mem_ctl_info *mci) kfree(mci); } -/** - * edac_mc_alloc: Allocate and partially fill a struct mem_ctl_info structure - * @mc_num: Memory controller number - * @n_layers: Number of MC hierarchy layers - * layers: Describes each layer as seen by the Memory Controller - * @size_pvt: size of private storage needed - * - * - * Everything is kmalloc'ed as one big chunk - more efficient. - * Only can be used if all structures have the same lifetime - otherwise - * you have to allocate and initialize your own structures. - * - * Use edac_mc_free() to free mc structures allocated by this function. - * - * NOTE: drivers handle multi-rank memories in different ways: in some - * drivers, one multi-rank memory stick is mapped as one entry, while, in - * others, a single multi-rank memory stick would be mapped into several - * entries. Currently, this function will allocate multiple struct dimm_info - * on such scenarios, as grouping the multiple ranks require drivers change. - * - * Returns: - * On failure: NULL - * On success: struct mem_ctl_info pointer - */ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, unsigned n_layers, struct edac_mc_layer *layers, @@ -460,11 +436,6 @@ error: } EXPORT_SYMBOL_GPL(edac_mc_alloc); -/** - * edac_mc_free - * 'Free' a previously allocated 'mci' structure - * @mci: pointer to a struct mem_ctl_info structure - */ void edac_mc_free(struct mem_ctl_info *mci) { edac_dbg(1, "\n"); @@ -646,12 +617,6 @@ static int del_mc_from_global_list(struct mem_ctl_info *mci) return handlers; } -/** - * edac_mc_find: Search for a mem_ctl_info structure whose index is 'idx'. - * - * If found, return a pointer to the structure. - * Else return NULL. - */ struct mem_ctl_info *edac_mc_find(int idx) { struct mem_ctl_info *mci = NULL; @@ -676,16 +641,6 @@ unlock: } EXPORT_SYMBOL(edac_mc_find); -/** - * edac_mc_add_mc_with_groups: Insert the 'mci' structure into the mci - * global list and create sysfs entries associated with mci structure - * @mci: pointer to the mci structure to be added to the list - * @groups: optional attribute groups for the driver-specific sysfs entries - * - * Return: - * 0 Success - * !0 Failure - */ /* FIXME - should a warning be printed if no error detection? correction? */ int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, @@ -776,13 +731,6 @@ fail0: } EXPORT_SYMBOL_GPL(edac_mc_add_mc_with_groups); -/** - * edac_mc_del_mc: Remove sysfs entries for specified mci structure and - * remove mci structure from global list - * @pdev: Pointer to 'struct device' representing mci structure to remove. - * - * Return pointer to removed mci structure, or NULL if device not found. - */ struct mem_ctl_info *edac_mc_del_mc(struct device *dev) { struct mem_ctl_info *mci; @@ -1046,18 +994,6 @@ static void edac_ue_error(struct mem_ctl_info *mci, edac_inc_ue_error(mci, enable_per_layer_report, pos, error_count); } -/** - * edac_raw_mc_handle_error - reports a memory event to userspace without doing - * anything to discover the error location - * - * @type: severity of the error (CE/UE/Fatal) - * @mci: a struct mem_ctl_info pointer - * @e: error description - * - * This raw function is used internally by edac_mc_handle_error(). It should - * only be called directly when the hardware error come directly from BIOS, - * like in the case of APEI GHES driver. - */ void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, struct mem_ctl_info *mci, struct edac_raw_error_desc *e) @@ -1087,24 +1023,6 @@ void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, } EXPORT_SYMBOL_GPL(edac_raw_mc_handle_error); -/** - * edac_mc_handle_error - reports a memory event to userspace - * - * @type: severity of the error (CE/UE/Fatal) - * @mci: a struct mem_ctl_info pointer - * @error_count: Number of errors of the same type - * @page_frame_number: mem page where the error occurred - * @offset_in_page: offset of the error inside the page - * @syndrome: ECC syndrome - * @top_layer: Memory layer[0] position - * @mid_layer: Memory layer[1] position - * @low_layer: Memory layer[2] position - * @msg: Message meaningful to the end users that - * explains the event - * @other_detail: Technical details about the event that - * may help hardware manufacturers and - * EDAC developers to analyse the event - */ void edac_mc_handle_error(const enum hw_event_mc_err_type type, struct mem_ctl_info *mci, const u16 error_count, diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h index b62d9bad9859..97ee6a91f633 100644 --- a/drivers/edac/edac_mc.h +++ b/drivers/edac/edac_mc.h @@ -93,24 +93,125 @@ do { \ #define to_mci(k) container_of(k, struct mem_ctl_info, dev) +/** + * edac_mc_alloc: Allocate and partially fill a struct mem_ctl_info structure + * @mc_num: Memory controller number + * @n_layers: Number of MC hierarchy layers + * @layers: Describes each layer as seen by the Memory Controller + * @sz_pvt: size of private storage needed + * + * + * Everything is kmalloc'ed as one big chunk - more efficient. + * Only can be used if all structures have the same lifetime - otherwise + * you have to allocate and initialize your own structures. + * + * Use edac_mc_free() to free mc structures allocated by this function. + * + * .. note:: + * + * drivers handle multi-rank memories in different ways: in some + * drivers, one multi-rank memory stick is mapped as one entry, while, in + * others, a single multi-rank memory stick would be mapped into several + * entries. Currently, this function will allocate multiple struct dimm_info + * on such scenarios, as grouping the multiple ranks require drivers change. + * + * Returns: + * On failure: NULL + * On success: struct mem_ctl_info pointer + */ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, unsigned n_layers, struct edac_mc_layer *layers, unsigned sz_pvt); + +/** + * edac_mc_add_mc_with_groups: Insert the 'mci' structure into the mci + * global list and create sysfs entries associated with mci structure + * @mci: pointer to the mci structure to be added to the list + * @groups: optional attribute groups for the driver-specific sysfs entries + * + * Return: + * 0 Success + * !0 Failure + */ extern int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, const struct attribute_group **groups); #define edac_mc_add_mc(mci) edac_mc_add_mc_with_groups(mci, NULL) + +/** + * edac_mc_free + * 'Free' a previously allocated 'mci' structure + * @mci: pointer to a struct mem_ctl_info structure + */ extern void edac_mc_free(struct mem_ctl_info *mci); + +/** + * edac_mc_find: Search for a mem_ctl_info structure whose index is @idx. + * + * @idx: index to be seek + * + * If found, return a pointer to the structure. + * Else return NULL. + * + * Caller must hold mem_ctls_mutex. + */ extern struct mem_ctl_info *edac_mc_find(int idx); + +/** + * find_mci_by_dev + * + * scan list of controllers looking for the one that manages + * the 'dev' device + * @dev: pointer to a struct device related with the MCI + */ extern struct mem_ctl_info *find_mci_by_dev(struct device *dev); + +/** + * edac_mc_del_mc: Remove sysfs entries for specified mci structure and + * remove mci structure from global list + * + * @dev: Pointer to struct &device representing mci structure to remove. + * + * Returns: pointer to removed mci structure, or NULL if device not found. + */ extern struct mem_ctl_info *edac_mc_del_mc(struct device *dev); extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, unsigned long page); +/** + * edac_raw_mc_handle_error - reports a memory event to userspace without doing + * anything to discover the error location + * + * @type: severity of the error (CE/UE/Fatal) + * @mci: a struct mem_ctl_info pointer + * @e: error description + * + * This raw function is used internally by edac_mc_handle_error(). It should + * only be called directly when the hardware error come directly from BIOS, + * like in the case of APEI GHES driver. + */ void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, struct mem_ctl_info *mci, struct edac_raw_error_desc *e); +/** + * edac_mc_handle_error - reports a memory event to userspace + * + * @type: severity of the error (CE/UE/Fatal) + * @mci: a struct mem_ctl_info pointer + * @error_count: Number of errors of the same type + * @page_frame_number: mem page where the error occurred + * @offset_in_page: offset of the error inside the page + * @syndrome: ECC syndrome + * @top_layer: Memory layer[0] position + * @mid_layer: Memory layer[1] position + * @low_layer: Memory layer[2] position + * @msg: Message meaningful to the end users that + * explains the event + * @other_detail: Technical details about the event that + * may help hardware manufacturers and + * EDAC developers to analyse the event + */ void edac_mc_handle_error(const enum hw_event_mc_err_type type, struct mem_ctl_info *mci, const u16 error_count, -- cgit v1.2.3 From 2a3cf0ab634c8a30b2c91cd728ada5b9879cac53 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 26 Oct 2016 14:14:45 -0200 Subject: driver-api: create an edac.rst file with EDAC documentation Currently, there's no device driver documentation for the EDAC subsystem at the driver-api book. Fill in the blanks for the structures and functions that misses documentation, uniform the word on the existing ones, and add a new edac.rst file at driver-api, in order to document the EDAC subsystem. Signed-off-by: Mauro Carvalho Chehab --- Documentation/driver-api/edac.rst | 72 ++++++++++++++++++++++++++++++++++++++ Documentation/driver-api/index.rst | 1 + drivers/edac/edac_mc.h | 2 -- 3 files changed, 73 insertions(+), 2 deletions(-) create mode 100644 Documentation/driver-api/edac.rst diff --git a/Documentation/driver-api/edac.rst b/Documentation/driver-api/edac.rst new file mode 100644 index 000000000000..3771e768fda1 --- /dev/null +++ b/Documentation/driver-api/edac.rst @@ -0,0 +1,72 @@ +Error Detection And Correction (EDAC) Devices +============================================= + +Memory Controllers +------------------ + +Most of the EDAC core is focused on doing Memory Controller error detection. +The :c:func:`edac_mc_alloc`. It uses internally the struct ``mem_ctl_info`` +to describe the memory controllers, with is an opaque struct for the EDAC +drivers. Only the EDAC core is allowed to touch it. + +.. kernel-doc:: include/linux/edac.h + +.. kernel-doc:: drivers/edac/edac_mc.h + +PCI Controllers +--------------- + +The EDAC subsystem provides a mechanism to handle PCI controllers by calling +the :c:func:`edac_pci_alloc_ctl_info`. It will use the struct +:c:type:`edac_pci_ctl_info` to describe the PCI controllers. + +.. kernel-doc:: drivers/edac/edac_pci.h + +EDAC Blocks +----------- + +The EDAC subsystem also provides a generic mechanism to report errors on +other parts of the hardware via :c:func:`edac_device_alloc_ctl_info` function. + +The structures :c:type:`edac_dev_sysfs_block_attribute`, +:c:type:`edac_device_block`, :c:type:`edac_device_instance` and +:c:type:`edac_device_ctl_info` provide a generic or abstract 'edac_device' +representation at sysfs. + +This set of structures and the code that implements the APIs for the same, provide for registering EDAC type devices which are NOT standard memory or +PCI, like: + +- CPU caches (L1 and L2) +- DMA engines +- Core CPU switches +- Fabric switch units +- PCIe interface controllers +- other EDAC/ECC type devices that can be monitored for + errors, etc. + +It allows for a 2 level set of hierarchy. + +For example, a cache could be composed of L1, L2 and L3 levels of cache. +Each CPU core would have its own L1 cache, while sharing L2 and maybe L3 +caches. On such case, those can be represented via the following sysfs +nodes:: + + /sys/devices/system/edac/.. + + pci/ + mc/ + cpu/cpu0/.. + /L1-cache/ce_count + /ue_count + /L2-cache/ce_count + /ue_count + cpu/cpu1/.. + /L1-cache/ce_count + /ue_count + /L2-cache/ce_count + /ue_count + ... + + the L1 and L2 directories would be "edac_device_block's" + +.. kernel-doc:: drivers/edac/edac_device.h diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 0dec394b9038..dac2bbcd5442 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -24,6 +24,7 @@ available subsections can be seen below. spi i2c hsi + edac miscellaneous vme 80211/index diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h index 97ee6a91f633..dcc2c7e3b8bc 100644 --- a/drivers/edac/edac_mc.h +++ b/drivers/edac/edac_mc.h @@ -152,8 +152,6 @@ extern void edac_mc_free(struct mem_ctl_info *mci); * * If found, return a pointer to the structure. * Else return NULL. - * - * Caller must hold mem_ctls_mutex. */ extern struct mem_ctl_info *edac_mc_find(int idx); -- cgit v1.2.3 From 2c22eefe07d084a0f63db3d893c2051bdbd57bd5 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Oct 2016 06:35:16 -0200 Subject: edac: adjust docs location at MAINTAINERS and 00-INDEX Update MAINTAINERS and 00-INDEX to reflect the location of edac.rst and ras.rst. Signed-off-by: Mauro Carvalho Chehab --- Documentation/00-INDEX | 4 ++-- MAINTAINERS | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index c08de5574d48..526f48cfabff 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -172,8 +172,8 @@ dynamic-debug-howto.txt - how to use the dynamic debug (dyndbg) feature. early-userspace/ - info about initramfs, klibc, and userspace early during boot. -edac.txt - - information on EDAC - Error Detection And Correction +admin-guide/ras.rst + - information on Reliability, Availability and Serviceability efi-stub.txt - How to use the EFI boot stub to bypass GRUB or elilo on EFI systems. eisa.txt diff --git a/MAINTAINERS b/MAINTAINERS index e13497c79fe4..4b795cc010c8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4481,7 +4481,8 @@ L: linux-edac@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac.git linux_next S: Supported -F: Documentation/edac.txt +F: Documentation/admin-guide/ras.rst +F: Documentation/driver-api/edac.rst F: drivers/edac/ F: include/linux/edac.h -- cgit v1.2.3 From d9809cc4450ebf362ba647cff7e21acc98c29726 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 29 Oct 2016 10:35:23 -0200 Subject: edac: fix kernel-doc tags at the drivers/edac_*.h Some kernel-doc tags don't provide good descriptions or use a different style. Adjust them. Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/ras.rst | 2 +- drivers/edac/edac_mc.h | 55 +++++++++++++++++++++++++-------------- 2 files changed, 36 insertions(+), 21 deletions(-) diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/ras.rst index 2f8706bae5a4..d71340e86c27 100644 --- a/Documentation/admin-guide/ras.rst +++ b/Documentation/admin-guide/ras.rst @@ -843,7 +843,7 @@ Module parameters EDAC device type ---------------- -In the header file, edac_core.h, there is a series of edac_device structures +In the header file, edac_pci.h, there is a series of edac_device structures and APIs for the EDAC_DEVICE. User space access to an edac_device is through the sysfs interface. diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h index dcc2c7e3b8bc..50fc1dc9c0d8 100644 --- a/drivers/edac/edac_mc.h +++ b/drivers/edac/edac_mc.h @@ -15,6 +15,8 @@ * Refactored for multi-source files: * Doug Thompson * + * Please look at Documentation/driver-api/edac.rst for more info about + * EDAC core structs and functions. */ #ifndef _EDAC_MC_H_ @@ -94,7 +96,8 @@ do { \ #define to_mci(k) container_of(k, struct mem_ctl_info, dev) /** - * edac_mc_alloc: Allocate and partially fill a struct mem_ctl_info structure + * edac_mc_alloc() - Allocate and partially fill a struct &mem_ctl_info. + * * @mc_num: Memory controller number * @n_layers: Number of MC hierarchy layers * @layers: Describes each layer as seen by the Memory Controller @@ -116,8 +119,8 @@ do { \ * on such scenarios, as grouping the multiple ranks require drivers change. * * Returns: - * On failure: NULL - * On success: struct mem_ctl_info pointer + * On success, return a pointer to struct mem_ctl_info pointer; + * %NULL otherwise */ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, unsigned n_layers, @@ -125,28 +128,28 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, unsigned sz_pvt); /** - * edac_mc_add_mc_with_groups: Insert the 'mci' structure into the mci - * global list and create sysfs entries associated with mci structure + * edac_mc_add_mc_with_groups() - Insert the @mci structure into the mci + * global list and create sysfs entries associated with @mci structure. + * * @mci: pointer to the mci structure to be added to the list * @groups: optional attribute groups for the driver-specific sysfs entries * - * Return: - * 0 Success - * !0 Failure + * Returns: + * 0 on Success, or an error code on failure */ extern int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, const struct attribute_group **groups); #define edac_mc_add_mc(mci) edac_mc_add_mc_with_groups(mci, NULL) /** - * edac_mc_free - * 'Free' a previously allocated 'mci' structure + * edac_mc_free() - Frees a previously allocated @mci structure + * * @mci: pointer to a struct mem_ctl_info structure */ extern void edac_mc_free(struct mem_ctl_info *mci); /** - * edac_mc_find: Search for a mem_ctl_info structure whose index is @idx. + * edac_mc_find() - Search for a mem_ctl_info structure whose index is @idx. * * @idx: index to be seek * @@ -156,29 +159,41 @@ extern void edac_mc_free(struct mem_ctl_info *mci); extern struct mem_ctl_info *edac_mc_find(int idx); /** - * find_mci_by_dev + * find_mci_by_dev() - Scan list of controllers looking for the one that + * manages the @dev device. * - * scan list of controllers looking for the one that manages - * the 'dev' device * @dev: pointer to a struct device related with the MCI + * + * Returns: on success, returns a pointer to struct &mem_ctl_info; + * %NULL otherwise. */ extern struct mem_ctl_info *find_mci_by_dev(struct device *dev); /** - * edac_mc_del_mc: Remove sysfs entries for specified mci structure and - * remove mci structure from global list + * edac_mc_del_mc() - Remove sysfs entries for mci structure associated with + * @dev and remove mci structure from global list. * * @dev: Pointer to struct &device representing mci structure to remove. * - * Returns: pointer to removed mci structure, or NULL if device not found. + * Returns: pointer to removed mci structure, or %NULL if device not found. */ extern struct mem_ctl_info *edac_mc_del_mc(struct device *dev); + +/** + * edac_mc_find_csrow_by_page() - Ancillary routine to identify what csrow + * contains a memory page. + * + * @mci: pointer to a struct mem_ctl_info structure + * @page: memory page to find + * + * Returns: on success, returns the csrow. -1 if not found. + */ extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci, unsigned long page); /** - * edac_raw_mc_handle_error - reports a memory event to userspace without doing - * anything to discover the error location + * edac_raw_mc_handle_error() - Reports a memory event to userspace without + * doing anything to discover the error location. * * @type: severity of the error (CE/UE/Fatal) * @mci: a struct mem_ctl_info pointer @@ -193,7 +208,7 @@ void edac_raw_mc_handle_error(const enum hw_event_mc_err_type type, struct edac_raw_error_desc *e); /** - * edac_mc_handle_error - reports a memory event to userspace + * edac_mc_handle_error() - Reports a memory event to userspace. * * @type: severity of the error (CE/UE/Fatal) * @mci: a struct mem_ctl_info pointer -- cgit v1.2.3 From ef5367bf6d8218195f83a23e069eaa9c155915a7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 28 Oct 2016 15:04:52 -0200 Subject: edac: fix kenel-doc markups at edac.h As this file was never added to the driver-api, the kernel-doc markups there were never tested. Some of them have issues. Fix them. Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 38 +++++++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 15 deletions(-) diff --git a/include/linux/edac.h b/include/linux/edac.h index 0fec0f26469b..3c20d2d2686a 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -132,6 +132,8 @@ enum dev_type { * it for example, by re-trying the operation). * @HW_EVENT_ERR_FATAL: Fatal Error - Uncorrected error that could not * be recovered. + * @HW_EVENT_ERR_INFO: Informational - The CPER spec defines a forth + * type of error: informational logs. */ enum hw_event_mc_err_type { HW_EVENT_ERR_CORRECTED, @@ -162,7 +164,7 @@ static inline char *mc_event_error_type(const unsigned int err_type) * enum mem_type - memory types. For a more detailed reference, please see * http://en.wikipedia.org/wiki/DRAM * - * @MEM_EMPTY Empty csrow + * @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. @@ -286,7 +288,7 @@ enum edac_type { /** * enum scrub_type - scrubbing capabilities - * @SCRUB_UNKNOWN Unknown if scrubber is available + * @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 @@ -295,7 +297,7 @@ enum edac_type { * @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 + * @SCRUB_HW_TUNABLE: Hardware scrub frequency is tunable */ enum scrub_type { SCRUB_UNKNOWN = 0, @@ -460,7 +462,7 @@ enum edac_mc_layer_type { /** * struct edac_mc_layer - describes the memory controller hierarchy - * @layer: layer type + * @type: 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 @@ -483,24 +485,28 @@ struct edac_mc_layer { #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 + * 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 + * @nlayers: 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 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" + * 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" + * 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. @@ -527,16 +533,18 @@ struct edac_mc_layer { * 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 + * @nlayers: 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 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]" + * 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]" + * and to return "var[layer0][layer1][layer2]"; */ #define EDAC_DIMM_PTR(layers, var, nlayers, layer0, layer1, layer2) ({ \ typeof(*var) __p; \ @@ -622,7 +630,7 @@ struct errcount_attribute_data { }; /** - * edac_raw_error_desc - Raw error report structure + * struct 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]) -- cgit v1.2.3 From 5f21dbd4823fa0e74d7251ea5b04d66307f49af1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 29 Oct 2016 16:13:23 -0200 Subject: edac.rst: move concepts dictionary from edac.h Instead of storing the concepts dictionary inside header file, move it to the subsystem documentation. Signed-off-by: Mauro Carvalho Chehab --- Documentation/driver-api/edac.rst | 106 +++++++++++++++++++++++++++++++++++++ include/linux/edac.h | 108 -------------------------------------- 2 files changed, 106 insertions(+), 108 deletions(-) diff --git a/Documentation/driver-api/edac.rst b/Documentation/driver-api/edac.rst index 3771e768fda1..b8c742aa0a71 100644 --- a/Documentation/driver-api/edac.rst +++ b/Documentation/driver-api/edac.rst @@ -1,6 +1,112 @@ Error Detection And Correction (EDAC) Devices ============================================= +Main Concepts used at the EDAC subsystem +---------------------------------------- + +There are several things to be aware of that aren't at all obvious, like +*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. + +.. _doubleranked: + +* 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 :ref:`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. + + Memory Controllers ------------------ diff --git a/include/linux/edac.h b/include/linux/edac.h index 3c20d2d2686a..c4433fd6c859 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -330,114 +330,6 @@ enum scrub_type { #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 * -- cgit v1.2.3 From a2e4c787f75b4558ed900f51c025aada15cc827c Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Thu, 1 Dec 2016 14:24:53 -0600 Subject: EDAC: Document HW_EVENT_ERR_DEFERRED type Add a description of the HW_EVENT_ERR_DEFERRED type that wasn't included with commit d12a969ebbfc ("EDAC, amd64: Add Deferred Error type"). Signed-off-by: Yazen Ghannam Acked-by: Borislav Petkov Signed-off-by: Mauro Carvalho Chehab --- include/linux/edac.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/linux/edac.h b/include/linux/edac.h index c4433fd6c859..07c52c0af62d 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -130,6 +130,12 @@ enum dev_type { * 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_DEFERRED: Deferred Error - Indicates an uncorrectable + * error whose handling is not urgent. This could + * be due to hardware data poisoning where the + * system can continue operation until the poisoned + * data is consumed. Preemptive measures may also + * be taken, e.g. offlining pages, etc. * @HW_EVENT_ERR_FATAL: Fatal Error - Uncorrected error that could not * be recovered. * @HW_EVENT_ERR_INFO: Informational - The CPER spec defines a forth -- cgit v1.2.3