From 8b6f04ce6b9fb3aa8dd5dcd57d91be5d73e643a0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 17 Apr 2012 08:53:34 -0300 Subject: edac: move documentation ABI to ABI/testing/sysfs-devices-edac The EDAC MC API is currently stored at the wrong place. Move the parts of the EDAC MC ABI that will be kept to ABI/testing/sysfs-devices-edac. The Date: field were added based on git timestamps for the git commit patches that added the functionality at edac.txt. Acked-by: Greg Kroah-Hartman Signed-off-by: Mauro Carvalho Chehab --- Documentation/ABI/testing/sysfs-devices-edac | 76 ++++++++++++++++++ Documentation/edac.txt | 112 ++------------------------- 2 files changed, 84 insertions(+), 104 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-devices-edac (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-devices-edac b/Documentation/ABI/testing/sysfs-devices-edac new file mode 100644 index 000000000000..40db633b00f6 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-edac @@ -0,0 +1,76 @@ +What: /sys/devices/system/edac/mc/mc*/reset_counters +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This write-only control file will zero all the statistical + counters for UE and CE errors on the given memory controller. + Zeroing the counters will also reset the timer indicating how + long since the last counter were reset. This is useful for + computing errors/time. Since the counters are always reset + at driver initialization time, no module/kernel parameter + is available. + +What: /sys/devices/system/edac/mc/mc*/seconds_since_reset +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays how many seconds have elapsed + since the last counter reset. This can be used with the error + counters to measure error rates. + +What: /sys/devices/system/edac/mc/mc*/mc_name +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays the type of memory controller + that is being utilized. + +What: /sys/devices/system/edac/mc/mc*/size_mb +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays, in count of megabytes, of memory + that this memory controller manages. + +What: /sys/devices/system/edac/mc/mc*/ue_count +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays the total count of uncorrectable + errors that have occurred on this memory controller. If + panic_on_ue is set, this counter will not have a chance to + increment, since EDAC will panic the system + +What: /sys/devices/system/edac/mc/mc*/ue_noinfo_count +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays the number of UEs that have + occurred on this memory controller with no information as to + which DIMM slot is having errors. + +What: /sys/devices/system/edac/mc/mc*/ce_count +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays the total count of correctable + errors that have occurred on this memory controller. 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. + +What: /sys/devices/system/edac/mc/mc*/ce_noinfo_count +Date: January 2006 +Contact: linux-edac@vger.kernel.org +Description: This attribute file displays the number of CEs that + have occurred on this memory controller wherewith no + information as to which DIMM slot is having errors. Memory is + handicapped, but operational, yet no information is available + to indicate which slot the failing memory is in. This count + field should be also be monitored for non-zero values. + +What: /sys/devices/system/edac/mc/mc*/sdram_scrub_rate +Date: February 2007 +Contact: linux-edac@vger.kernel.org +Description: Read/Write attribute file that controls memory scrubbing. + The scrubbing rate used by the memory controller is set by + writing a minimum bandwidth in bytes/sec to the attribute file. + The rate will be translated to an internal value that gives at + least the specified rate. + Reading the file will return the actual scrubbing rate employed. + If configuration fails or memory scrubbing is not implemented, + the value of the attribute file will be -1. diff --git a/Documentation/edac.txt b/Documentation/edac.txt index fdcc49fad8e1..c25f086a6960 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -232,116 +232,20 @@ EDAC control and attribute files. In 'mcX' directories are EDAC control and attribute files for -this 'X' instance of the memory controllers: - - -Counter reset control file: - - 'reset_counters' - - This write-only control file will zero all the statistical counters - for UE and CE errors. Zeroing the counters will also reset the timer - indicating how long since the last counter zero. This is useful - for computing errors/time. Since the counters are always reset at - driver initialization time, no module/kernel parameter is available. - - RUN TIME: echo "anything" >/sys/devices/system/edac/mc/mc0/counter_reset - - This resets the counters on memory controller 0 - - -Seconds since last counter reset control file: - - 'seconds_since_reset' - - This attribute file displays how many seconds have elapsed since the - last counter reset. This can be used with the error counters to - measure error rates. - - - -Memory Controller name attribute file: - - 'mc_name' - - This attribute file displays the type of memory controller - that is being utilized. - - -Total memory managed by this memory controller attribute file: - - 'size_mb' - - This attribute file displays, in count of megabytes, of memory - that this instance of memory controller manages. - - -Total Uncorrectable Errors count attribute file: - - 'ue_count' - - This attribute file displays the total count of uncorrectable - errors that have occurred on this memory controller. If panic_on_ue - is set this counter will not have a chance to increment, - since EDAC will panic the system. - - -Total UE count that had no information attribute fileY: - - 'ue_noinfo_count' - - This attribute file displays the number of UEs that have occurred - with no information as to which DIMM slot is having errors. - - -Total Correctable Errors count attribute file: - - 'ce_count' - - This attribute file displays the total count of correctable - errors that have occurred on this memory controller. 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. - - -Total Correctable Errors count attribute file: - - 'ce_noinfo_count' - - This attribute file displays the number of CEs that - have occurred wherewith no information as to which DIMM slot - is having errors. Memory is handicapped, but operational, - yet no information is available to indicate which slot - the failing memory is in. This count field should be also - be monitored for non-zero values. - -Device Symlink: - - 'device' - - Symlink to the memory controller device. - -Sdram memory scrubbing rate: - - 'sdram_scrub_rate' - - Read/Write attribute file that controls memory scrubbing. The scrubbing - rate is set by writing a minimum bandwidth in bytes/sec to the attribute - file. The rate will be translated to an internal value that gives at - least the specified rate. - - Reading the file will return the actual scrubbing rate employed. - - If configuration fails or memory scrubbing is not implemented, accessing - that attribute will fail. +this 'X' instance of the memory controllers. +For a description of the sysfs API, please see: + Documentation/ABI/testing/sysfs/devices-edac ============================================================================ 'csrowX' DIRECTORIES +When CONFIG_EDAC_LEGACY_SYSFS is enabled, the 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: -- cgit v1.2.3 From 2639c3ee298401881cc560c5e3987f8b222b9f7c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 17 Apr 2012 11:13:10 -0300 Subject: Edac: Add ABI Documentation for the new device nodes The EDAC ABI were extended to add support for per-DIMM or per-rank information and silkscreen labels. Properly document them. Most of the comments there came from edac.txt descriptions of the fields that are part of the legacy csrowX ABI (e. g. /sys/devices/system/edac/mc/mc*/csrow*/*). Acked-by: Greg Kroah-Hartman Signed-off-by: Mauro Carvalho Chehab --- Documentation/ABI/testing/sysfs-devices-edac | 64 ++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-devices-edac b/Documentation/ABI/testing/sysfs-devices-edac index 40db633b00f6..30ee78aaed75 100644 --- a/Documentation/ABI/testing/sysfs-devices-edac +++ b/Documentation/ABI/testing/sysfs-devices-edac @@ -74,3 +74,67 @@ Description: Read/Write attribute file that controls memory scrubbing. Reading the file will return the actual scrubbing rate employed. If configuration fails or memory scrubbing is not implemented, the value of the attribute file will be -1. + +What: /sys/devices/system/edac/mc/mc*/max_location +Date: April 2012 +Contact: Mauro Carvalho Chehab + linux-edac@vger.kernel.org +Description: This attribute file displays the information about the last + available memory slot in this memory controller. It is used by + userspace tools in order to display the memory filling layout. + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/size +Date: April 2012 +Contact: Mauro Carvalho Chehab + linux-edac@vger.kernel.org +Description: This attribute file will display the size of dimm or rank. + For dimm*/size, this is the size, in MB of the DIMM memory + stick. For rank*/size, this is the size, in MB for one rank + of the DIMM memory stick. On single rank memories (1R), this + is also the total size of the dimm. On dual rank (2R) memories, + this is half the size of the total DIMM memories. + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_dev_type +Date: April 2012 +Contact: Mauro Carvalho Chehab + linux-edac@vger.kernel.org +Description: This attribute file will display what type of DRAM device is + being utilized on this DIMM (x1, x2, x4, x8, ...). + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_edac_mode +Date: April 2012 +Contact: Mauro Carvalho Chehab + linux-edac@vger.kernel.org +Description: This attribute file will display what type of Error detection + and correction is being utilized. For example: S4ECD4ED would + mean a Chipkill with x4 DRAM. + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_label +Date: April 2012 +Contact: Mauro Carvalho Chehab + linux-edac@vger.kernel.org +Description: 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. + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_location +Date: April 2012 +Contact: Mauro Carvalho Chehab + linux-edac@vger.kernel.org +Description: This attribute file will display the location (csrow/channel, + branch/channel/slot or channel/slot) of the dimm or rank. + +What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_mem_type +Date: April 2012 +Contact: Mauro Carvalho Chehab + linux-edac@vger.kernel.org +Description: This attribute file will display what type of memory is + currently on this csrow. Normally, either buffered or + unbuffered memory (for example, Unbuffered-DDR3). -- cgit v1.2.3 From a1b01edb274518c7da6d69b84e7558c092282aad Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 13 Jun 2012 12:01:55 -0500 Subject: edac: add support for Calxeda highbank memory controller Add support for memory controller on Calxeda Highbank platforms. Highbank platforms support a single 4GB mini-DIMM with 1-bit correction and 2-bit detection. Signed-off-by: Rob Herring Signed-off-by: Mauro Carvalho Chehab --- .../devicetree/bindings/arm/calxeda/mem-ctrlr.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 Documentation/devicetree/bindings/arm/calxeda/mem-ctrlr.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/arm/calxeda/mem-ctrlr.txt b/Documentation/devicetree/bindings/arm/calxeda/mem-ctrlr.txt new file mode 100644 index 000000000000..f770ac0893d4 --- /dev/null +++ b/Documentation/devicetree/bindings/arm/calxeda/mem-ctrlr.txt @@ -0,0 +1,14 @@ +Calxeda DDR memory controller + +Properties: +- compatible : Should be "calxeda,hb-ddr-ctrl" +- reg : Address and size for DDR controller registers. +- interrupts : Interrupt for DDR controller. + +Example: + + memory-controller@fff00000 { + compatible = "calxeda,hb-ddr-ctrl"; + reg = <0xfff00000 0x1000>; + interrupts = <0 91 4>; + }; -- cgit v1.2.3 From 69154d069869b612383cef9d594f39b34ffba6dd Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 11 Jun 2012 21:32:14 -0500 Subject: edac: add support for Calxeda highbank L2 cache ecc Add support for L2 ECC on Calxeda highbank platform. Signed-off-by: Rob Herring Signed-off-by: Mauro Carvalho Chehab --- Documentation/devicetree/bindings/arm/calxeda/l2ecc.txt | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 Documentation/devicetree/bindings/arm/calxeda/l2ecc.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/arm/calxeda/l2ecc.txt b/Documentation/devicetree/bindings/arm/calxeda/l2ecc.txt new file mode 100644 index 000000000000..94e642a33db0 --- /dev/null +++ b/Documentation/devicetree/bindings/arm/calxeda/l2ecc.txt @@ -0,0 +1,15 @@ +Calxeda Highbank L2 cache ECC + +Properties: +- compatible : Should be "calxeda,hb-sregs-l2-ecc" +- reg : Address and size for ECC error interrupt clear registers. +- interrupts : Should be single bit error interrupt, then double bit error + interrupt. + +Example: + + sregs@fff3c200 { + compatible = "calxeda,hb-sregs-l2-ecc"; + reg = <0xfff3c200 0x100>; + interrupts = <0 71 4 0 72 4>; + }; -- cgit v1.2.3