iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

misc: smpro-errmon: Add Ampere's SMpro error monitor driver

Browse Source 
Add Ampere's SMpro error monitor driver for monitoring and reporting
RAS-related errors as reported by SMpro co-processor found on Ampere's
Altra processor family.

Signed-off-by: Quan Nguyen <quan@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20221031024442.2490881-3-quan@os.amperecomputing.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Quan Nguyen 2022-10-31 09:44:41 +07:00 committed by Greg Kroah-Hartman
parent c08645ea21
commit 4a4a4e9eba
4 changed files with 806 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

264
Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro Normal file
View File

@ -0,0 +1,264 @@
What: /sys/bus/platform/devices/smpro-errmon.*/error_[core|mem|pcie|other]_[ce|ue]
KernelVersion: 6.1
Contact: Quan Nguyen <quan@os.amperecomputing.com>
Description:
(RO) Contains the 48-byte Ampere (Vendor-Specific) Error Record printed
in hex format according to the table below:
+--------+---------------+-------------+------------------------------------------------------------+
| Offset | Field | Size (byte) | Description |
+--------+---------------+-------------+------------------------------------------------------------+
| 00 | Error Type | 1 | See :ref:`the table below <smpro-error-types>` for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 01 | Subtype | 1 | See :ref:`the table below <smpro-error-types>` for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 02 | Instance | 2 | See :ref:`the table below <smpro-error-types>` for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 04 | Error status | 4 | See ARM RAS specification for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 08 | Error Address | 8 | See ARM RAS specification for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 16 | Error Misc 0 | 8 | See ARM RAS specification for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 24 | Error Misc 1 | 8 | See ARM RAS specification for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 32 | Error Misc 2 | 8 | See ARM RAS specification for details |
+--------+---------------+-------------+------------------------------------------------------------+
| 40 | Error Misc 3 | 8 | See ARM RAS specification for details |
+--------+---------------+-------------+------------------------------------------------------------+
The table below defines the value of error types, their subtype, subcomponent and instance:
.. _smpro-error-types:
+-----------------+------------+----------+----------------+----------------------------------------+
| Error Group | Error Type | Sub type | Sub component | Instance |
+-----------------+------------+----------+----------------+----------------------------------------+
| CPM (core) | 0 | 0 | Snoop-Logic | CPM # |
+-----------------+------------+----------+----------------+----------------------------------------+
| CPM (core) | 0 | 2 | Armv8 Core 1 | CPM # |
+-----------------+------------+----------+----------------+----------------------------------------+
| MCU (mem) | 1 | 1 | ERR1 | MCU # \| SLOT << 11 |
+-----------------+------------+----------+----------------+----------------------------------------+
| MCU (mem) | 1 | 2 | ERR2 | MCU # \| SLOT << 11 |
+-----------------+------------+----------+----------------+----------------------------------------+
| MCU (mem) | 1 | 3 | ERR3 | MCU # |
+-----------------+------------+----------+----------------+----------------------------------------+
| MCU (mem) | 1 | 4 | ERR4 | MCU # |
+-----------------+------------+----------+----------------+----------------------------------------+
| MCU (mem) | 1 | 5 | ERR5 | MCU # |
+-----------------+------------+----------+----------------+----------------------------------------+
| MCU (mem) | 1 | 6 | ERR6 | MCU # |
+-----------------+------------+----------+----------------+----------------------------------------+
| MCU (mem) | 1 | 7 | Link Error | MCU # |
+-----------------+------------+----------+----------------+----------------------------------------+
| Mesh (other) | 2 | 0 | Cross Point | X \| (Y << 5) \| NS <<11 |
+-----------------+------------+----------+----------------+----------------------------------------+
| Mesh (other) | 2 | 1 | Home Node(IO) | X \| (Y << 5) \| NS <<11 |
+-----------------+------------+----------+----------------+----------------------------------------+
| Mesh (other) | 2 | 2 | Home Node(Mem) | X \| (Y << 5) \| NS <<11 \| device<<12 |
+-----------------+------------+----------+----------------+----------------------------------------+
| Mesh (other) | 2 | 4 | CCIX Node | X \| (Y << 5) \| NS <<11 |
+-----------------+------------+----------+----------------+----------------------------------------+
| 2P Link (other) | 3 | 0 | N/A | Altra 2P Link # |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 0 | ERR0 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 1 | ERR1 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 2 | ERR2 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 3 | ERR3 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 4 | ERR4 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 5 | ERR5 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 6 | ERR6 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 7 | ERR7 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 8 | ERR8 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 9 | ERR9 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 10 | ERR10 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 11 | ERR11 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 12 | ERR12 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| GIC (other) | 5 | 13-21 | ERR13 | RC # + 1 |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TCU | 100 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU0 | 0 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU1 | 1 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU2 | 2 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU3 | 3 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU4 | 4 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU5 | 5 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU6 | 6 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU7 | 7 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU8 | 8 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMMU (other) | 6 | TBU9 | 9 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| PCIe AER (pcie) | 7 | Root | 0 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| PCIe AER (pcie) | 7 | Device | 1 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| PCIe RC (pcie) | 8 | RCA HB | 0 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| PCIe RC (pcie) | 8 | RCB HB | 1 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| PCIe RC (pcie) | 8 | RASDP | 8 | RC # |
+-----------------+------------+----------+----------------+----------------------------------------+
| OCM (other) | 9 | ERR0 | 0 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| OCM (other) | 9 | ERR1 | 1 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| OCM (other) | 9 | ERR2 | 2 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMpro (other) | 10 | ERR0 | 0 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMpro (other) | 10 | ERR1 | 1 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| SMpro (other) | 10 | MPA_ERR | 2 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| PMpro (other) | 11 | ERR0 | 0 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| PMpro (other) | 11 | ERR1 | 1 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
| PMpro (other) | 11 | MPA_ERR | 2 | 0 |
+-----------------+------------+----------+----------------+----------------------------------------+
Example::
# cat error_other_ue
880807001e004010401040101500000001004010401040100c0000000000000000000000000000000000000000000000
The detail of each sysfs entries is as below:
+-------------+---------------------------------------------------------+----------------------------------+
| Error | Sysfs entry | Description (when triggered) |
+-------------+---------------------------------------------------------+----------------------------------+
| Core's CE | /sys/bus/platform/devices/smpro-errmon.*/error_core_ce | Core has CE error |
+-------------+---------------------------------------------------------+----------------------------------+
| Core's UE | /sys/bus/platform/devices/smpro-errmon.*/error_core_ue | Core has UE error |
+-------------+---------------------------------------------------------+----------------------------------+
| Memory's CE | /sys/bus/platform/devices/smpro-errmon.*/error_mem_ce | Memory has CE error |
+-------------+---------------------------------------------------------+----------------------------------+
| Memory's UE | /sys/bus/platform/devices/smpro-errmon.*/error_mem_ue | Memory has UE error |
+-------------+---------------------------------------------------------+----------------------------------+
| PCIe's CE | /sys/bus/platform/devices/smpro-errmon.*/error_pcie_ce | any PCIe controller has CE error |
+-------------+---------------------------------------------------------+----------------------------------+
| PCIe's UE | /sys/bus/platform/devices/smpro-errmon.*/error_pcie_ue | any PCIe controller has UE error |
+-------------+---------------------------------------------------------+----------------------------------+
| Other's CE | /sys/bus/platform/devices/smpro-errmon.*/error_other_ce | any other CE error |
+-------------+---------------------------------------------------------+----------------------------------+
| Other's UE | /sys/bus/platform/devices/smpro-errmon.*/error_other_ue | any other UE error |
+-------------+---------------------------------------------------------+----------------------------------+
UE: Uncorrect-able Error
CE: Correct-able Error
For details, see section `3.3 Ampere (Vendor-Specific) Error Record Formats,
Altra Family RAS Supplement`.
What: /sys/bus/platform/devices/smpro-errmon.*/overflow_[core|mem|pcie|other]_[ce|ue]
KernelVersion: 6.1
Contact: Quan Nguyen <quan@os.amperecomputing.com>
Description:
(RO) Return the overflow status of each type HW error reported:
- 0 : No overflow
- 1 : There is an overflow and the oldest HW errors are dropped
The detail of each sysfs entries is as below:
+-------------+-----------------------------------------------------------+---------------------------------------+
| Overflow | Sysfs entry | Description |
+-------------+-----------------------------------------------------------+---------------------------------------+
| Core's CE | /sys/bus/platform/devices/smpro-errmon.*/overflow_core_ce | Core CE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
| Core's UE | /sys/bus/platform/devices/smpro-errmon.*/overflow_core_ue | Core UE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
| Memory's CE | /sys/bus/platform/devices/smpro-errmon.*/overflow_mem_ce | Memory CE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
| Memory's UE | /sys/bus/platform/devices/smpro-errmon.*/overflow_mem_ue | Memory UE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
| PCIe's CE | /sys/bus/platform/devices/smpro-errmon.*/overflow_pcie_ce | any PCIe controller CE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
| PCIe's UE | /sys/bus/platform/devices/smpro-errmon.*/overflow_pcie_ue | any PCIe controller UE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
| Other's CE | /sys/bus/platform/devices/smpro-errmon.*/overflow_other_ce| any other CE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
| Other's UE | /sys/bus/platform/devices/smpro-errmon.*/overflow_other_ue| other UE error overflow |
+-------------+-----------------------------------------------------------+---------------------------------------+
where:
- UE: Uncorrect-able Error
- CE: Correct-able Error
What: /sys/bus/platform/devices/smpro-errmon.*/[error|warn]_[smpro|pmpro]
KernelVersion: 6.1
Contact: Quan Nguyen <quan@os.amperecomputing.com>
Description:
(RO) Contains the internal firmware error/warning printed as hex format.
The detail of each sysfs entries is as below:
+---------------+------------------------------------------------------+--------------------------+
| Error | Sysfs entry | Description |
+---------------+------------------------------------------------------+--------------------------+
| SMpro error | /sys/bus/platform/devices/smpro-errmon.*/error_smpro | system has SMpro error |
+---------------+------------------------------------------------------+--------------------------+
| SMpro warning | /sys/bus/platform/devices/smpro-errmon.*/warn_smpro | system has SMpro warning |
+---------------+------------------------------------------------------+--------------------------+
| PMpro error | /sys/bus/platform/devices/smpro-errmon.*/error_pmpro | system has PMpro error |
+---------------+------------------------------------------------------+--------------------------+
| PMpro warning | /sys/bus/platform/devices/smpro-errmon.*/warn_pmpro | system has PMpro warning |
+---------------+------------------------------------------------------+--------------------------+
For details, see section `5.10 RAS Internal Error Register Definitions,
Altra Family Soc BMC Interface Specification`.
What: /sys/bus/platform/devices/smpro-errmon.*/event_[vrd_warn_fault|vrd_hot|dimm_hot]
KernelVersion: 6.1
Contact: Quan Nguyen <quan@os.amperecomputing.com>
Description:
(RO) Contains the detail information in case of VRD/DIMM warning/hot events
in hex format as below::
AAAA
where:
- ``AAAA``: The event detail information data
The detail of each sysfs entries is as below:
+---------------+---------------------------------------------------------------+---------------------+
| Event | Sysfs entry | Description |
+---------------+---------------------------------------------------------------+---------------------+
| VRD HOT | /sys/bus/platform/devices/smpro-errmon.*/event_vrd_hot | VRD Hot |
+---------------+---------------------------------------------------------------+---------------------+
| VR Warn/Fault | /sys/bus/platform/devices/smpro-errmon.*/event_vrd_warn_fault | VR Warning or Fault |
+---------------+---------------------------------------------------------------+---------------------+
| DIMM HOT | /sys/bus/platform/devices/smpro-errmon.*/event_dimm_hot | DIMM Hot |
+---------------+---------------------------------------------------------------+---------------------+
For more details, see section `5.7 GPI Status Registers,
Altra Family Soc BMC Interface Specification`.

12
drivers/misc/Kconfig
View File

@ -176,6 +176,18 @@ config SGI_XP
this feature will allow for direct communication between SSIs
based on a network adapter and DMA messaging.
config SMPRO_ERRMON
tristate "Ampere Computing SMPro error monitor driver"
depends on MFD_SMPRO || COMPILE_TEST
help
Say Y here to get support for the SMpro error monitor function
provided by Ampere Computing's Altra and Altra Max SoCs. Upon
loading, the driver creates sysfs files which can be use to gather
multiple HW error data reported via read and write system calls.
To compile this driver as a module, say M here. The driver will be
called smpro-errmon.
config CS5535_MFGPT
tristate "CS5535/CS5536 Geode Multi-Function General Purpose Timer (MFGPT) support"
depends on MFD_CS5535

1
drivers/misc/Makefile
View File

@ -23,6 +23,7 @@ obj-$(CONFIG_ENCLOSURE_SERVICES) += enclosure.o
obj-$(CONFIG_KGDB_TESTS) += kgdbts.o
obj-$(CONFIG_SGI_XP) += sgi-xp/
obj-$(CONFIG_SGI_GRU) += sgi-gru/
obj-$(CONFIG_SMPRO_ERRMON) += smpro-errmon.o
obj-$(CONFIG_CS5535_MFGPT) += cs5535-mfgpt.o
obj-$(CONFIG_GEHC_ACHC) += gehc-achc.o
obj-$(CONFIG_HP_ILO) += hpilo.o

529
drivers/misc/smpro-errmon.c Normal file
View File

@ -0,0 +1,529 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* Ampere Computing SoC's SMpro Error Monitoring Driver
*
* Copyright (c) 2022, Ampere Computing LLC
*
*/
#include <linux/i2c.h>
#include <linux/mod_devicetable.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/regmap.h>
/* GPI RAS Error Registers */
#define GPI_RAS_ERR 0x7E
/* Core and L2C Error Registers */
#define CORE_CE_ERR_CNT 0x80
#define CORE_CE_ERR_LEN 0x81
#define CORE_CE_ERR_DATA 0x82
#define CORE_UE_ERR_CNT 0x83
#define CORE_UE_ERR_LEN 0x84
#define CORE_UE_ERR_DATA 0x85
/* Memory Error Registers */
#define MEM_CE_ERR_CNT 0x90
#define MEM_CE_ERR_LEN 0x91
#define MEM_CE_ERR_DATA 0x92
#define MEM_UE_ERR_CNT 0x93
#define MEM_UE_ERR_LEN 0x94
#define MEM_UE_ERR_DATA 0x95
/* RAS Error/Warning Registers */
#define ERR_SMPRO_TYPE 0xA0
#define ERR_PMPRO_TYPE 0xA1
#define ERR_SMPRO_INFO_LO 0xA2
#define ERR_SMPRO_INFO_HI 0xA3
#define ERR_SMPRO_DATA_LO 0xA4
#define ERR_SMPRO_DATA_HI 0xA5
#define WARN_SMPRO_INFO_LO 0xAA
#define WARN_SMPRO_INFO_HI 0xAB
#define ERR_PMPRO_INFO_LO 0xA6
#define ERR_PMPRO_INFO_HI 0xA7
#define ERR_PMPRO_DATA_LO 0xA8
#define ERR_PMPRO_DATA_HI 0xA9
#define WARN_PMPRO_INFO_LO 0xAC
#define WARN_PMPRO_INFO_HI 0xAD
/* PCIE Error Registers */
#define PCIE_CE_ERR_CNT 0xC0
#define PCIE_CE_ERR_LEN 0xC1
#define PCIE_CE_ERR_DATA 0xC2
#define PCIE_UE_ERR_CNT 0xC3
#define PCIE_UE_ERR_LEN 0xC4
#define PCIE_UE_ERR_DATA 0xC5
/* Other Error Registers */
#define OTHER_CE_ERR_CNT 0xD0
#define OTHER_CE_ERR_LEN 0xD1
#define OTHER_CE_ERR_DATA 0xD2
#define OTHER_UE_ERR_CNT 0xD8
#define OTHER_UE_ERR_LEN 0xD9
#define OTHER_UE_ERR_DATA 0xDA
/* Event Data Registers */
#define VRD_WARN_FAULT_EVENT_DATA 0x78
#define VRD_HOT_EVENT_DATA 0x79
#define DIMM_HOT_EVENT_DATA 0x7A
#define MAX_READ_BLOCK_LENGTH 48
#define RAS_SMPRO_ERR 0
#define RAS_PMPRO_ERR 1
enum RAS_48BYTES_ERR_TYPES {
CORE_CE_ERR,
CORE_UE_ERR,
MEM_CE_ERR,
MEM_UE_ERR,
PCIE_CE_ERR,
PCIE_UE_ERR,
OTHER_CE_ERR,
OTHER_UE_ERR,
NUM_48BYTES_ERR_TYPE,
};
struct smpro_error_hdr {
u8 count; /* Number of the RAS errors */
u8 len; /* Number of data bytes */
u8 data; /* Start of 48-byte data */
u8 max_cnt; /* Max num of errors */
};
/*
* Included Address of registers to get Count, Length of data and Data
* of the 48 bytes error data
*/
static struct smpro_error_hdr smpro_error_table[] = {
[CORE_CE_ERR] = {
.count = CORE_CE_ERR_CNT,
.len = CORE_CE_ERR_LEN,
.data = CORE_CE_ERR_DATA,
.max_cnt = 32
},
[CORE_UE_ERR] = {
.count = CORE_UE_ERR_CNT,
.len = CORE_UE_ERR_LEN,
.data = CORE_UE_ERR_DATA,
.max_cnt = 32
},
[MEM_CE_ERR] = {
.count = MEM_CE_ERR_CNT,
.len = MEM_CE_ERR_LEN,
.data = MEM_CE_ERR_DATA,
.max_cnt = 16
},
[MEM_UE_ERR] = {
.count = MEM_UE_ERR_CNT,
.len = MEM_UE_ERR_LEN,
.data = MEM_UE_ERR_DATA,
.max_cnt = 16
},
[PCIE_CE_ERR] = {
.count = PCIE_CE_ERR_CNT,
.len = PCIE_CE_ERR_LEN,
.data = PCIE_CE_ERR_DATA,
.max_cnt = 96
},
[PCIE_UE_ERR] = {
.count = PCIE_UE_ERR_CNT,
.len = PCIE_UE_ERR_LEN,
.data = PCIE_UE_ERR_DATA,
.max_cnt = 96
},
[OTHER_CE_ERR] = {
.count = OTHER_CE_ERR_CNT,
.len = OTHER_CE_ERR_LEN,
.data = OTHER_CE_ERR_DATA,
.max_cnt = 8
},
[OTHER_UE_ERR] = {
.count = OTHER_UE_ERR_CNT,
.len = OTHER_UE_ERR_LEN,
.data = OTHER_UE_ERR_DATA,
.max_cnt = 8
},
};
/*
* List of SCP registers which are used to get
* one type of RAS Internal errors.
*/
struct smpro_int_error_hdr {
u8 type;
u8 info_l;
u8 info_h;
u8 data_l;
u8 data_h;
u8 warn_l;
u8 warn_h;
};
static struct smpro_int_error_hdr list_smpro_int_error_hdr[] = {
[RAS_SMPRO_ERR] = {
.type = ERR_SMPRO_TYPE,
.info_l = ERR_SMPRO_INFO_LO,
.info_h = ERR_SMPRO_INFO_HI,
.data_l = ERR_SMPRO_DATA_LO,
.data_h = ERR_SMPRO_DATA_HI,
.warn_l = WARN_SMPRO_INFO_LO,
.warn_h = WARN_SMPRO_INFO_HI,
},
[RAS_PMPRO_ERR] = {
.type = ERR_PMPRO_TYPE,
.info_l = ERR_PMPRO_INFO_LO,
.info_h = ERR_PMPRO_INFO_HI,
.data_l = ERR_PMPRO_DATA_LO,
.data_h = ERR_PMPRO_DATA_HI,
.warn_l = WARN_PMPRO_INFO_LO,
.warn_h = WARN_PMPRO_INFO_HI,
},
};
struct smpro_errmon {
struct regmap *regmap;
};
enum EVENT_TYPES {
VRD_WARN_FAULT_EVENT,
VRD_HOT_EVENT,
DIMM_HOT_EVENT,
NUM_EVENTS_TYPE,
};
/* Included Address of event source and data registers */
static u8 smpro_event_table[NUM_EVENTS_TYPE] = {
VRD_WARN_FAULT_EVENT_DATA,
VRD_HOT_EVENT_DATA,
DIMM_HOT_EVENT_DATA,
};
static ssize_t smpro_event_data_read(struct device *dev,
struct device_attribute *da, char *buf,
int channel)
{
struct smpro_errmon *errmon = dev_get_drvdata(dev);
s32 event_data;
int ret;
ret = regmap_read(errmon->regmap, smpro_event_table[channel], &event_data);
if (ret)
return ret;
/* Clear event after read */
if (event_data != 0)
regmap_write(errmon->regmap, smpro_event_table[channel], event_data);
return sysfs_emit(buf, "%04x\n", event_data);
}
static ssize_t smpro_overflow_data_read(struct device *dev, struct device_attribute *da,
char *buf, int channel)
{
struct smpro_errmon *errmon = dev_get_drvdata(dev);
struct smpro_error_hdr *err_info;
s32 err_count;
int ret;
err_info = &smpro_error_table[channel];
ret = regmap_read(errmon->regmap, err_info->count, &err_count);
if (ret)
return ret;
/* Bit 8 indicates the overflow status */
return sysfs_emit(buf, "%d\n", (err_count & BIT(8)) ? 1 : 0);
}
static ssize_t smpro_error_data_read(struct device *dev, struct device_attribute *da,
char *buf, int channel)
{
struct smpro_errmon *errmon = dev_get_drvdata(dev);
unsigned char err_data[MAX_READ_BLOCK_LENGTH];
struct smpro_error_hdr *err_info;
s32 err_count, err_length;
int ret;
err_info = &smpro_error_table[channel];
ret = regmap_read(errmon->regmap, err_info->count, &err_count);
/* Error count is the low byte */
err_count &= 0xff;
if (ret || !err_count || err_count > err_info->max_cnt)
return ret;
ret = regmap_read(errmon->regmap, err_info->len, &err_length);
if (ret || err_length <= 0)
return ret;
if (err_length > MAX_READ_BLOCK_LENGTH)
err_length = MAX_READ_BLOCK_LENGTH;
memset(err_data, 0x00, MAX_READ_BLOCK_LENGTH);
ret = regmap_noinc_read(errmon->regmap, err_info->data, err_data, err_length);
if (ret < 0)
return ret;
/* clear the error */
ret = regmap_write(errmon->regmap, err_info->count, 0x100);
if (ret)
return ret;
/*
* The output of Core/Memory/PCIe/Others UE/CE errors follows the format
* specified in section 5.8.1 CE/UE Error Data record in
* Altra SOC BMC Interface specification.
*/
return sysfs_emit(buf, "%*phN\n", MAX_READ_BLOCK_LENGTH, err_data);
}
/*
* Output format:
* <4-byte hex value of error info><4-byte hex value of error extensive data>
* Where:
* + error info : The error information
* + error data : Extensive data (32 bits)
* Reference to section 5.10 RAS Internal Error Register Definition in
* Altra SOC BMC Interface specification
*/
static ssize_t smpro_internal_err_read(struct device *dev, struct device_attribute *da,
char *buf, int channel)
{
struct smpro_errmon *errmon = dev_get_drvdata(dev);
struct smpro_int_error_hdr *err_info;
unsigned int err[4] = { 0 };
unsigned int err_type;
unsigned int val;
int ret;
/* read error status */
ret = regmap_read(errmon->regmap, GPI_RAS_ERR, &val);
if (ret)
return ret;
if ((channel == RAS_SMPRO_ERR && !(val & BIT(0))) ||
(channel == RAS_PMPRO_ERR && !(val & BIT(1))))
return 0;
err_info = &list_smpro_int_error_hdr[channel];
ret = regmap_read(errmon->regmap, err_info->type, &val);
if (ret)
return ret;
err_type = (val & BIT(1)) ? BIT(1) :
(val & BIT(2)) ? BIT(2) : 0;
if (!err_type)
return 0;
ret = regmap_read(errmon->regmap, err_info->info_l, err + 1);
if (ret)
return ret;
ret = regmap_read(errmon->regmap, err_info->info_h, err);
if (ret)
return ret;
if (err_type & BIT(2)) {
/* Error with data type */
ret = regmap_read(errmon->regmap, err_info->data_l, err + 3);
if (ret)
return ret;
ret = regmap_read(errmon->regmap, err_info->data_h, err + 2);
if (ret)
return ret;
}
/* clear the read errors */
ret = regmap_write(errmon->regmap, err_info->type, err_type);
if (ret)
return ret;
return sysfs_emit(buf, "%*phN\n", (int)sizeof(err), err);
}
/*
* Output format:
* <4-byte hex value of warining info>
* Reference to section 5.10 RAS Internal Error Register Definition in
* Altra SOC BMC Interface specification
*/
static ssize_t smpro_internal_warn_read(struct device *dev, struct device_attribute *da,
char *buf, int channel)
{
struct smpro_errmon *errmon = dev_get_drvdata(dev);
struct smpro_int_error_hdr *err_info;
unsigned int warn[2] = { 0 };
unsigned int val;
int ret;
/* read error status */
ret = regmap_read(errmon->regmap, GPI_RAS_ERR, &val);
if (ret)
return ret;
if ((channel == RAS_SMPRO_ERR && !(val & BIT(0))) ||
(channel == RAS_PMPRO_ERR && !(val & BIT(1))))
return 0;
err_info = &list_smpro_int_error_hdr[channel];
ret = regmap_read(errmon->regmap, err_info->type, &val);
if (ret)
return ret;
if (!(val & BIT(0)))
return 0;
ret = regmap_read(errmon->regmap, err_info->warn_l, warn + 1);
if (ret)
return ret;
ret = regmap_read(errmon->regmap, err_info->warn_h, warn);
if (ret)
return ret;
/* clear the warning */
ret = regmap_write(errmon->regmap, err_info->type, BIT(0));
if (ret)
return ret;
return sysfs_emit(buf, "%*phN\n", (int)sizeof(warn), warn);
}
#define ERROR_OVERFLOW_RO(_error, _index) \
static ssize_t overflow_##_error##_show(struct device *dev, \
struct device_attribute *da, \
char *buf) \
{ \
return smpro_overflow_data_read(dev, da, buf, _index); \
} \
static DEVICE_ATTR_RO(overflow_##_error)
ERROR_OVERFLOW_RO(core_ce, CORE_CE_ERR);
ERROR_OVERFLOW_RO(core_ue, CORE_UE_ERR);
ERROR_OVERFLOW_RO(mem_ce, MEM_CE_ERR);
ERROR_OVERFLOW_RO(mem_ue, MEM_UE_ERR);
ERROR_OVERFLOW_RO(pcie_ce, PCIE_CE_ERR);
ERROR_OVERFLOW_RO(pcie_ue, PCIE_UE_ERR);
ERROR_OVERFLOW_RO(other_ce, OTHER_CE_ERR);
ERROR_OVERFLOW_RO(other_ue, OTHER_UE_ERR);
#define ERROR_RO(_error, _index) \
static ssize_t error_##_error##_show(struct device *dev, \
struct device_attribute *da, \
char *buf) \
{ \
return smpro_error_data_read(dev, da, buf, _index); \
} \
static DEVICE_ATTR_RO(error_##_error)
ERROR_RO(core_ce, CORE_CE_ERR);
ERROR_RO(core_ue, CORE_UE_ERR);
ERROR_RO(mem_ce, MEM_CE_ERR);
ERROR_RO(mem_ue, MEM_UE_ERR);
ERROR_RO(pcie_ce, PCIE_CE_ERR);
ERROR_RO(pcie_ue, PCIE_UE_ERR);
ERROR_RO(other_ce, OTHER_CE_ERR);
ERROR_RO(other_ue, OTHER_UE_ERR);
static ssize_t error_smpro_show(struct device *dev, struct device_attribute *da, char *buf)
{
return smpro_internal_err_read(dev, da, buf, RAS_SMPRO_ERR);
}
static DEVICE_ATTR_RO(error_smpro);
static ssize_t error_pmpro_show(struct device *dev, struct device_attribute *da, char *buf)
{
return smpro_internal_err_read(dev, da, buf, RAS_PMPRO_ERR);
}
static DEVICE_ATTR_RO(error_pmpro);
static ssize_t warn_smpro_show(struct device *dev, struct device_attribute *da, char *buf)
{
return smpro_internal_warn_read(dev, da, buf, RAS_SMPRO_ERR);
}
static DEVICE_ATTR_RO(warn_smpro);
static ssize_t warn_pmpro_show(struct device *dev, struct device_attribute *da, char *buf)
{
return smpro_internal_warn_read(dev, da, buf, RAS_PMPRO_ERR);
}
static DEVICE_ATTR_RO(warn_pmpro);
#define EVENT_RO(_event, _index) \
static ssize_t event_##_event##_show(struct device *dev, \
struct device_attribute *da, \
char *buf) \
{ \
return smpro_event_data_read(dev, da, buf, _index); \
} \
static DEVICE_ATTR_RO(event_##_event)
EVENT_RO(vrd_warn_fault, VRD_WARN_FAULT_EVENT);
EVENT_RO(vrd_hot, VRD_HOT_EVENT);
EVENT_RO(dimm_hot, DIMM_HOT_EVENT);
static struct attribute *smpro_errmon_attrs[] = {
&dev_attr_overflow_core_ce.attr,
&dev_attr_overflow_core_ue.attr,
&dev_attr_overflow_mem_ce.attr,
&dev_attr_overflow_mem_ue.attr,
&dev_attr_overflow_pcie_ce.attr,
&dev_attr_overflow_pcie_ue.attr,
&dev_attr_overflow_other_ce.attr,
&dev_attr_overflow_other_ue.attr,
&dev_attr_error_core_ce.attr,
&dev_attr_error_core_ue.attr,
&dev_attr_error_mem_ce.attr,
&dev_attr_error_mem_ue.attr,
&dev_attr_error_pcie_ce.attr,
&dev_attr_error_pcie_ue.attr,
&dev_attr_error_other_ce.attr,
&dev_attr_error_other_ue.attr,
&dev_attr_error_smpro.attr,
&dev_attr_error_pmpro.attr,
&dev_attr_warn_smpro.attr,
&dev_attr_warn_pmpro.attr,
&dev_attr_event_vrd_warn_fault.attr,
&dev_attr_event_vrd_hot.attr,
&dev_attr_event_dimm_hot.attr,
NULL
};
ATTRIBUTE_GROUPS(smpro_errmon);
static int smpro_errmon_probe(struct platform_device *pdev)
{
struct smpro_errmon *errmon;
errmon = devm_kzalloc(&pdev->dev, sizeof(struct smpro_errmon), GFP_KERNEL);
if (!errmon)
return -ENOMEM;
platform_set_drvdata(pdev, errmon);
errmon->regmap = dev_get_regmap(pdev->dev.parent, NULL);
if (!errmon->regmap)
return -ENODEV;
return 0;
}
static struct platform_driver smpro_errmon_driver = {
.probe = smpro_errmon_probe,
.driver = {
.name = "smpro-errmon",
.dev_groups = smpro_errmon_groups,
},
};
module_platform_driver(smpro_errmon_driver);
MODULE_AUTHOR("Tung Nguyen <tung.nguyen@amperecomputing.com>");
MODULE_AUTHOR("Thinh Pham <thinh.pham@amperecomputing.com>");
MODULE_AUTHOR("Hoang Nguyen <hnguyen@amperecomputing.com>");
MODULE_AUTHOR("Thu Nguyen <thu@os.amperecomputing.com>");
MODULE_AUTHOR("Quan Nguyen <quan@os.amperecomputing.com>");
MODULE_DESCRIPTION("Ampere Altra SMpro driver");
MODULE_LICENSE("GPL");