Commit 7dfc15c4 authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'edac_updates_for_v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras

Pull EDAC updates from Borislav Petkov:

 - Drop a now obsolete ppc4xx_edac driver

 - Fix conversion to physical memory addresses on Intel's Elkhart Lake
   and Ice Lake hardware when the system address is above the
   (Top-Of-Memory) TOM address

 - Pay attention to the memory hole on Zynq UltraScale+ MPSoC DDR
   controllers when injecting errors for testing purposes

 - Add support for translating normalized error addresses reported by an
   AMD memory controller into system physical addresses using an UEFI
   mechanism called platform runtime mechanism (PRM).

 - The usual cleanups and fixes

* tag 'edac_updates_for_v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
  EDAC: Drop obsolete PPC4xx driver
  EDAC/sb_edac: Fix the compile warning of large frame size
  EDAC/{skx_common,i10nm}: Remove the AMAP register for determing DDR5
  EDAC/{skx_common,skx,i10nm}: Move the common debug code to skx_common
  EDAC/igen6: Fix conversion of system address to physical memory address
  EDAC/synopsys: Fix error injection on Zynq UltraScale+
  RAS/AMD/ATL: Translate normalized to system physical addresses using PRM
  ACPI: PRM: Add PRM handler direct call support
parents 1636f57c 92f8358b
......@@ -214,6 +214,30 @@ static struct prm_handler_info *find_prm_handler(const guid_t *guid)
#define UPDATE_LOCK_ALREADY_HELD 4
#define UPDATE_UNLOCK_WITHOUT_LOCK 5
int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer)
{
struct prm_handler_info *handler = find_prm_handler(&handler_guid);
struct prm_module_info *module = find_prm_module(&handler_guid);
struct prm_context_buffer context;
efi_status_t status;
if (!module || !handler)
return -ENODEV;
memset(&context, 0, sizeof(context));
ACPI_COPY_NAMESEG(context.signature, "PRMC");
context.identifier = handler->guid;
context.static_data_buffer = handler->static_data_buffer_addr;
context.mmio_ranges = module->mmio_info;
status = efi_call_acpi_prm_handler(handler->handler_addr,
(u64)param_buffer,
&context);
return efi_status_to_err(status);
}
EXPORT_SYMBOL_GPL(acpi_call_prm_handler);
/*
* This is the PlatformRtMechanism opregion space handler.
* @function: indicates the read/write. In fact as the PlatformRtMechanism
......
......@@ -311,15 +311,6 @@ config EDAC_CELL
Cell Broadband Engine internal memory controller
on platform without a hypervisor
config EDAC_PPC4XX
tristate "PPC4xx IBM DDR2 Memory Controller"
depends on 4xx
help
This enables support for EDAC on the ECC memory used
with the IBM DDR2 memory controller found in various
PowerPC 4xx embedded processors such as the 405EX[r],
440SP, 440SPe, 460EX, 460GT and 460SX.
config EDAC_AMD8131
tristate "AMD8131 HyperTransport PCI-X Tunnel"
depends on PCI && PPC_MAPLE
......
......@@ -63,7 +63,6 @@ i10nm_edac-y := i10nm_base.o
obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o skx_edac_common.o
obj-$(CONFIG_EDAC_CELL) += cell_edac.o
obj-$(CONFIG_EDAC_PPC4XX) += ppc4xx_edac.o
obj-$(CONFIG_EDAC_AMD8111) += amd8111_edac.o
obj-$(CONFIG_EDAC_AMD8131) += amd8131_edac.o
......
......@@ -47,10 +47,6 @@
readl((m)->mbase + ((m)->hbm_mc ? 0xef8 : \
(res_cfg->type == GNR ? 0xaf8 : 0x20ef8)) + \
(i) * (m)->chan_mmio_sz)
#define I10NM_GET_AMAP(m, i) \
readl((m)->mbase + ((m)->hbm_mc ? 0x814 : \
(res_cfg->type == GNR ? 0xc14 : 0x20814)) + \
(i) * (m)->chan_mmio_sz)
#define I10NM_GET_REG32(m, i, offset) \
readl((m)->mbase + (i) * (m)->chan_mmio_sz + (offset))
#define I10NM_GET_REG64(m, i, offset) \
......@@ -971,7 +967,7 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci,
{
struct skx_pvt *pvt = mci->pvt_info;
struct skx_imc *imc = pvt->imc;
u32 mtr, amap, mcddrtcfg = 0;
u32 mtr, mcddrtcfg = 0;
struct dimm_info *dimm;
int i, j, ndimms;
......@@ -980,7 +976,6 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci,
continue;
ndimms = 0;
amap = I10NM_GET_AMAP(imc, i);
if (res_cfg->type != GNR)
mcddrtcfg = I10NM_GET_MCDDRTCFG(imc, i);
......@@ -992,7 +987,7 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci,
mtr, mcddrtcfg, imc->mc, i, j);
if (IS_DIMM_PRESENT(mtr))
ndimms += skx_get_dimm_info(mtr, 0, amap, dimm,
ndimms += skx_get_dimm_info(mtr, 0, 0, dimm,
imc, i, j, cfg);
else if (IS_NVDIMM_PRESENT(mcddrtcfg, j))
ndimms += skx_get_nvdimm_info(dimm, imc, i, j,
......@@ -1013,54 +1008,6 @@ static struct notifier_block i10nm_mce_dec = {
.priority = MCE_PRIO_EDAC,
};
#ifdef CONFIG_EDAC_DEBUG
/*
* Debug feature.
* Exercise the address decode logic by writing an address to
* /sys/kernel/debug/edac/i10nm_test/addr.
*/
static struct dentry *i10nm_test;
static int debugfs_u64_set(void *data, u64 val)
{
struct mce m;
pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
memset(&m, 0, sizeof(m));
/* ADDRV + MemRd + Unknown channel */
m.status = MCI_STATUS_ADDRV + 0x90;
/* One corrected error */
m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
m.addr = val;
skx_mce_check_error(NULL, 0, &m);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
static void setup_i10nm_debug(void)
{
i10nm_test = edac_debugfs_create_dir("i10nm_test");
if (!i10nm_test)
return;
if (!edac_debugfs_create_file("addr", 0200, i10nm_test,
NULL, &fops_u64_wo)) {
debugfs_remove(i10nm_test);
i10nm_test = NULL;
}
}
static void teardown_i10nm_debug(void)
{
debugfs_remove_recursive(i10nm_test);
}
#else
static inline void setup_i10nm_debug(void) {}
static inline void teardown_i10nm_debug(void) {}
#endif /*CONFIG_EDAC_DEBUG*/
static int __init i10nm_init(void)
{
u8 mc = 0, src_id = 0, node_id = 0;
......@@ -1159,7 +1106,7 @@ static int __init i10nm_init(void)
opstate_init();
mce_register_decode_chain(&i10nm_mce_dec);
setup_i10nm_debug();
skx_setup_debug("i10nm_test");
if (retry_rd_err_log && res_cfg->offsets_scrub && res_cfg->offsets_demand) {
skx_set_decode(i10nm_mc_decode, show_retry_rd_err_log);
......@@ -1187,7 +1134,7 @@ static void __exit i10nm_exit(void)
enable_retry_rd_err_log(false);
}
teardown_i10nm_debug();
skx_teardown_debug();
mce_unregister_decode_chain(&i10nm_mce_dec);
skx_adxl_put();
skx_remove();
......
......@@ -316,7 +316,7 @@ static u64 ehl_err_addr_to_imc_addr(u64 eaddr, int mc)
if (igen6_tom <= _4GB)
return eaddr + igen6_tolud - _4GB;
if (eaddr < _4GB)
if (eaddr >= igen6_tom)
return eaddr + igen6_tolud - igen6_tom;
return eaddr;
......
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2008 Nuovation System Designs, LLC
* Grant Erickson <gerickson@nuovations.com>
*/
#include <linux/edac.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/of_device.h>
#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <linux/types.h>
#include <asm/dcr.h>
#include "edac_module.h"
#include "ppc4xx_edac.h"
/*
* This file implements a driver for monitoring and handling events
* associated with the IMB DDR2 ECC controller found in the AMCC/IBM
* 405EX[r], 440SP, 440SPe, 460EX, 460GT and 460SX.
*
* As realized in the 405EX[r], this controller features:
*
* - Support for registered- and non-registered DDR1 and DDR2 memory.
* - 32-bit or 16-bit memory interface with optional ECC.
*
* o ECC support includes:
*
* - 4-bit SEC/DED
* - Aligned-nibble error detect
* - Bypass mode
*
* - Two (2) memory banks/ranks.
* - Up to 1 GiB per bank/rank in 32-bit mode and up to 512 MiB per
* bank/rank in 16-bit mode.
*
* As realized in the 440SP and 440SPe, this controller changes/adds:
*
* - 64-bit or 32-bit memory interface with optional ECC.
*
* o ECC support includes:
*
* - 8-bit SEC/DED
* - Aligned-nibble error detect
* - Bypass mode
*
* - Up to 4 GiB per bank/rank in 64-bit mode and up to 2 GiB
* per bank/rank in 32-bit mode.
*
* As realized in the 460EX and 460GT, this controller changes/adds:
*
* - 64-bit or 32-bit memory interface with optional ECC.
*
* o ECC support includes:
*
* - 8-bit SEC/DED
* - Aligned-nibble error detect
* - Bypass mode
*
* - Four (4) memory banks/ranks.
* - Up to 16 GiB per bank/rank in 64-bit mode and up to 8 GiB
* per bank/rank in 32-bit mode.
*
* At present, this driver has ONLY been tested against the controller
* realization in the 405EX[r] on the AMCC Kilauea and Haleakala
* boards (256 MiB w/o ECC memory soldered onto the board) and a
* proprietary board based on those designs (128 MiB ECC memory, also
* soldered onto the board).
*
* Dynamic feature detection and handling needs to be added for the
* other realizations of this controller listed above.
*
* Eventually, this driver will likely be adapted to the above variant
* realizations of this controller as well as broken apart to handle
* the other known ECC-capable controllers prevalent in other 4xx
* processors:
*
* - IBM SDRAM (405GP, 405CR and 405EP) "ibm,sdram-4xx"
* - IBM DDR1 (440GP, 440GX, 440EP and 440GR) "ibm,sdram-4xx-ddr"
* - Denali DDR1/DDR2 (440EPX and 440GRX) "denali,sdram-4xx-ddr2"
*
* For this controller, unfortunately, correctable errors report
* nothing more than the beat/cycle and byte/lane the correction
* occurred on and the check bit group that covered the error.
*
* In contrast, uncorrectable errors also report the failing address,
* the bus master and the transaction direction (i.e. read or write)
*
* Regardless of whether the error is a CE or a UE, we report the
* following pieces of information in the driver-unique message to the
* EDAC subsystem:
*
* - Device tree path
* - Bank(s)
* - Check bit error group
* - Beat(s)/lane(s)
*/
/* Preprocessor Definitions */
#define EDAC_OPSTATE_INT_STR "interrupt"
#define EDAC_OPSTATE_POLL_STR "polled"
#define EDAC_OPSTATE_UNKNOWN_STR "unknown"
#define PPC4XX_EDAC_MODULE_NAME "ppc4xx_edac"
#define PPC4XX_EDAC_MODULE_REVISION "v1.0.0"
#define PPC4XX_EDAC_MESSAGE_SIZE 256
/*
* Kernel logging without an EDAC instance
*/
#define ppc4xx_edac_printk(level, fmt, arg...) \
edac_printk(level, "PPC4xx MC", fmt, ##arg)
/*
* Kernel logging with an EDAC instance
*/
#define ppc4xx_edac_mc_printk(level, mci, fmt, arg...) \
edac_mc_chipset_printk(mci, level, "PPC4xx", fmt, ##arg)
/*
* Macros to convert bank configuration size enumerations into MiB and
* page values.
*/
#define SDRAM_MBCF_SZ_MiB_MIN 4
#define SDRAM_MBCF_SZ_TO_MiB(n) (SDRAM_MBCF_SZ_MiB_MIN \
<< (SDRAM_MBCF_SZ_DECODE(n)))
#define SDRAM_MBCF_SZ_TO_PAGES(n) (SDRAM_MBCF_SZ_MiB_MIN \
<< (20 - PAGE_SHIFT + \
SDRAM_MBCF_SZ_DECODE(n)))
/*
* The ibm,sdram-4xx-ddr2 Device Control Registers (DCRs) are
* indirectly accessed and have a base and length defined by the
* device tree. The base can be anything; however, we expect the
* length to be precisely two registers, the first for the address
* window and the second for the data window.
*/
#define SDRAM_DCR_RESOURCE_LEN 2
#define SDRAM_DCR_ADDR_OFFSET 0
#define SDRAM_DCR_DATA_OFFSET 1
/*
* Device tree interrupt indices
*/
#define INTMAP_ECCDED_INDEX 0 /* Double-bit Error Detect */
#define INTMAP_ECCSEC_INDEX 1 /* Single-bit Error Correct */
/* Type Definitions */
/*
* PPC4xx SDRAM memory controller private instance data
*/
struct ppc4xx_edac_pdata {
dcr_host_t dcr_host; /* Indirect DCR address/data window mapping */
struct {
int sec; /* Single-bit correctable error IRQ assigned */
int ded; /* Double-bit detectable error IRQ assigned */
} irqs;
};
/*
* Various status data gathered and manipulated when checking and
* reporting ECC status.
*/
struct ppc4xx_ecc_status {
u32 ecces;
u32 besr;
u32 bearh;
u32 bearl;
u32 wmirq;
};
/* Global Variables */
/*
* Device tree node type and compatible tuples this driver can match
* on.
*/
static const struct of_device_id ppc4xx_edac_match[] = {
{
.compatible = "ibm,sdram-4xx-ddr2"
},
{ }
};
MODULE_DEVICE_TABLE(of, ppc4xx_edac_match);
/*
* TODO: The row and channel parameters likely need to be dynamically
* set based on the aforementioned variant controller realizations.
*/
static const unsigned ppc4xx_edac_nr_csrows = 2;
static const unsigned ppc4xx_edac_nr_chans = 1;
/*
* Strings associated with PLB master IDs capable of being posted in
* SDRAM_BESR or SDRAM_WMIRQ on uncorrectable ECC errors.
*/
static const char * const ppc4xx_plb_masters[9] = {
[SDRAM_PLB_M0ID_ICU] = "ICU",
[SDRAM_PLB_M0ID_PCIE0] = "PCI-E 0",
[SDRAM_PLB_M0ID_PCIE1] = "PCI-E 1",
[SDRAM_PLB_M0ID_DMA] = "DMA",
[SDRAM_PLB_M0ID_DCU] = "DCU",
[SDRAM_PLB_M0ID_OPB] = "OPB",
[SDRAM_PLB_M0ID_MAL] = "MAL",
[SDRAM_PLB_M0ID_SEC] = "SEC",
[SDRAM_PLB_M0ID_AHB] = "AHB"
};
/**
* mfsdram - read and return controller register data
* @dcr_host: A pointer to the DCR mapping.
* @idcr_n: The indirect DCR register to read.
*
* This routine reads and returns the data associated with the
* controller's specified indirect DCR register.
*
* Returns the read data.
*/
static inline u32
mfsdram(const dcr_host_t *dcr_host, unsigned int idcr_n)
{
return __mfdcri(dcr_host->base + SDRAM_DCR_ADDR_OFFSET,
dcr_host->base + SDRAM_DCR_DATA_OFFSET,
idcr_n);
}
/**
* mtsdram - write controller register data
* @dcr_host: A pointer to the DCR mapping.
* @idcr_n: The indirect DCR register to write.
* @value: The data to write.
*
* This routine writes the provided data to the controller's specified
* indirect DCR register.
*/
static inline void
mtsdram(const dcr_host_t *dcr_host, unsigned int idcr_n, u32 value)
{
return __mtdcri(dcr_host->base + SDRAM_DCR_ADDR_OFFSET,
dcr_host->base + SDRAM_DCR_DATA_OFFSET,
idcr_n,
value);
}
/**
* ppc4xx_edac_check_bank_error - check a bank for an ECC bank error
* @status: A pointer to the ECC status structure to check for an
* ECC bank error.
* @bank: The bank to check for an ECC error.
*
* This routine determines whether the specified bank has an ECC
* error.
*
* Returns true if the specified bank has an ECC error; otherwise,
* false.
*/
static bool
ppc4xx_edac_check_bank_error(const struct ppc4xx_ecc_status *status,
unsigned int bank)
{
switch (bank) {
case 0:
return status->ecces & SDRAM_ECCES_BK0ER;
case 1:
return status->ecces & SDRAM_ECCES_BK1ER;
default:
return false;
}
}
/**
* ppc4xx_edac_generate_bank_message - generate interpretted bank status message
* @mci: A pointer to the EDAC memory controller instance associated
* with the bank message being generated.
* @status: A pointer to the ECC status structure to generate the
* message from.
* @buffer: A pointer to the buffer in which to generate the
* message.
* @size: The size, in bytes, of space available in buffer.
*
* This routine generates to the provided buffer the portion of the
* driver-unique report message associated with the ECCESS[BKNER]
* field of the specified ECC status.
*
* Returns the number of characters generated on success; otherwise, <
* 0 on error.
*/
static int
ppc4xx_edac_generate_bank_message(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status,
char *buffer,
size_t size)
{
int n, total = 0;
unsigned int row, rows;
n = snprintf(buffer, size, "%s: Banks: ", mci->dev_name);
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
for (rows = 0, row = 0; row < mci->nr_csrows; row++) {
if (ppc4xx_edac_check_bank_error(status, row)) {
n = snprintf(buffer, size, "%s%u",
(rows++ ? ", " : ""), row);
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
}
}
n = snprintf(buffer, size, "%s; ", rows ? "" : "None");
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
fail:
return total;
}
/**
* ppc4xx_edac_generate_checkbit_message - generate interpretted checkbit message
* @mci: A pointer to the EDAC memory controller instance associated
* with the checkbit message being generated.
* @status: A pointer to the ECC status structure to generate the
* message from.
* @buffer: A pointer to the buffer in which to generate the
* message.
* @size: The size, in bytes, of space available in buffer.
*
* This routine generates to the provided buffer the portion of the
* driver-unique report message associated with the ECCESS[CKBER]
* field of the specified ECC status.
*
* Returns the number of characters generated on success; otherwise, <
* 0 on error.
*/
static int
ppc4xx_edac_generate_checkbit_message(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status,
char *buffer,
size_t size)
{
const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
const char *ckber = NULL;
switch (status->ecces & SDRAM_ECCES_CKBER_MASK) {
case SDRAM_ECCES_CKBER_NONE:
ckber = "None";
break;
case SDRAM_ECCES_CKBER_32_ECC_0_3:
ckber = "ECC0:3";
break;
case SDRAM_ECCES_CKBER_32_ECC_4_8:
switch (mfsdram(&pdata->dcr_host, SDRAM_MCOPT1) &
SDRAM_MCOPT1_WDTH_MASK) {
case SDRAM_MCOPT1_WDTH_16:
ckber = "ECC0:3";
break;
case SDRAM_MCOPT1_WDTH_32:
ckber = "ECC4:8";
break;
default:
ckber = "Unknown";
break;
}
break;
case SDRAM_ECCES_CKBER_32_ECC_0_8:
ckber = "ECC0:8";
break;
default:
ckber = "Unknown";
break;
}
return snprintf(buffer, size, "Checkbit Error: %s", ckber);
}
/**
* ppc4xx_edac_generate_lane_message - generate interpretted byte lane message
* @mci: A pointer to the EDAC memory controller instance associated
* with the byte lane message being generated.
* @status: A pointer to the ECC status structure to generate the
* message from.
* @buffer: A pointer to the buffer in which to generate the
* message.
* @size: The size, in bytes, of space available in buffer.
*
* This routine generates to the provided buffer the portion of the
* driver-unique report message associated with the ECCESS[BNCE]
* field of the specified ECC status.
*
* Returns the number of characters generated on success; otherwise, <
* 0 on error.
*/
static int
ppc4xx_edac_generate_lane_message(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status,
char *buffer,
size_t size)
{
int n, total = 0;
unsigned int lane, lanes;
const unsigned int first_lane = 0;
const unsigned int lane_count = 16;
n = snprintf(buffer, size, "; Byte Lane Errors: ");
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
for (lanes = 0, lane = first_lane; lane < lane_count; lane++) {
if ((status->ecces & SDRAM_ECCES_BNCE_ENCODE(lane)) != 0) {
n = snprintf(buffer, size,
"%s%u",
(lanes++ ? ", " : ""), lane);
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
}
}
n = snprintf(buffer, size, "%s; ", lanes ? "" : "None");
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
fail:
return total;
}
/**
* ppc4xx_edac_generate_ecc_message - generate interpretted ECC status message
* @mci: A pointer to the EDAC memory controller instance associated
* with the ECCES message being generated.
* @status: A pointer to the ECC status structure to generate the
* message from.
* @buffer: A pointer to the buffer in which to generate the
* message.
* @size: The size, in bytes, of space available in buffer.
*
* This routine generates to the provided buffer the portion of the
* driver-unique report message associated with the ECCESS register of
* the specified ECC status.
*
* Returns the number of characters generated on success; otherwise, <
* 0 on error.
*/
static int
ppc4xx_edac_generate_ecc_message(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status,
char *buffer,
size_t size)
{
int n, total = 0;
n = ppc4xx_edac_generate_bank_message(mci, status, buffer, size);
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
n = ppc4xx_edac_generate_checkbit_message(mci, status, buffer, size);
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
n = ppc4xx_edac_generate_lane_message(mci, status, buffer, size);
if (n < 0 || n >= size)
goto fail;
buffer += n;
size -= n;
total += n;
fail:
return total;
}
/**
* ppc4xx_edac_generate_plb_message - generate interpretted PLB status message
* @mci: A pointer to the EDAC memory controller instance associated
* with the PLB message being generated.
* @status: A pointer to the ECC status structure to generate the
* message from.
* @buffer: A pointer to the buffer in which to generate the
* message.
* @size: The size, in bytes, of space available in buffer.
*
* This routine generates to the provided buffer the portion of the
* driver-unique report message associated with the PLB-related BESR
* and/or WMIRQ registers of the specified ECC status.
*
* Returns the number of characters generated on success; otherwise, <
* 0 on error.
*/
static int
ppc4xx_edac_generate_plb_message(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status,
char *buffer,
size_t size)
{
unsigned int master;
bool read;
if ((status->besr & SDRAM_BESR_MASK) == 0)
return 0;
if ((status->besr & SDRAM_BESR_M0ET_MASK) == SDRAM_BESR_M0ET_NONE)
return 0;
read = ((status->besr & SDRAM_BESR_M0RW_MASK) == SDRAM_BESR_M0RW_READ);
master = SDRAM_BESR_M0ID_DECODE(status->besr);
return snprintf(buffer, size,
"%s error w/ PLB master %u \"%s\"; ",
(read ? "Read" : "Write"),
master,
(((master >= SDRAM_PLB_M0ID_FIRST) &&
(master <= SDRAM_PLB_M0ID_LAST)) ?
ppc4xx_plb_masters[master] : "UNKNOWN"));
}
/**
* ppc4xx_edac_generate_message - generate interpretted status message
* @mci: A pointer to the EDAC memory controller instance associated
* with the driver-unique message being generated.
* @status: A pointer to the ECC status structure to generate the
* message from.
* @buffer: A pointer to the buffer in which to generate the
* message.
* @size: The size, in bytes, of space available in buffer.
*
* This routine generates to the provided buffer the driver-unique
* EDAC report message from the specified ECC status.
*/
static void
ppc4xx_edac_generate_message(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status,
char *buffer,
size_t size)
{
int n;
if (buffer == NULL || size == 0)
return;
n = ppc4xx_edac_generate_ecc_message(mci, status, buffer, size);
if (n < 0 || n >= size)
return;
buffer += n;
size -= n;
ppc4xx_edac_generate_plb_message(mci, status, buffer, size);
}
#ifdef DEBUG
/**
* ppc4xx_ecc_dump_status - dump controller ECC status registers
* @mci: A pointer to the EDAC memory controller instance
* associated with the status being dumped.
* @status: A pointer to the ECC status structure to generate the
* dump from.
*
* This routine dumps to the kernel log buffer the raw and
* interpretted specified ECC status.
*/
static void
ppc4xx_ecc_dump_status(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status)
{
char message[PPC4XX_EDAC_MESSAGE_SIZE];
ppc4xx_edac_generate_message(mci, status, message, sizeof(message));
ppc4xx_edac_mc_printk(KERN_INFO, mci,
"\n"
"\tECCES: 0x%08x\n"
"\tWMIRQ: 0x%08x\n"
"\tBESR: 0x%08x\n"
"\tBEAR: 0x%08x%08x\n"
"\t%s\n",
status->ecces,
status->wmirq,
status->besr,
status->bearh,
status->bearl,
message);
}
#endif /* DEBUG */
/**
* ppc4xx_ecc_get_status - get controller ECC status
* @mci: A pointer to the EDAC memory controller instance
* associated with the status being retrieved.
* @status: A pointer to the ECC status structure to populate the
* ECC status with.
*
* This routine reads and masks, as appropriate, all the relevant
* status registers that deal with ibm,sdram-4xx-ddr2 ECC errors.
* While we read all of them, for correctable errors, we only expect
* to deal with ECCES. For uncorrectable errors, we expect to deal
* with all of them.
*/
static void
ppc4xx_ecc_get_status(const struct mem_ctl_info *mci,
struct ppc4xx_ecc_status *status)
{
const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
const dcr_host_t *dcr_host = &pdata->dcr_host;
status->ecces = mfsdram(dcr_host, SDRAM_ECCES) & SDRAM_ECCES_MASK;
status->wmirq = mfsdram(dcr_host, SDRAM_WMIRQ) & SDRAM_WMIRQ_MASK;
status->besr = mfsdram(dcr_host, SDRAM_BESR) & SDRAM_BESR_MASK;
status->bearl = mfsdram(dcr_host, SDRAM_BEARL);
status->bearh = mfsdram(dcr_host, SDRAM_BEARH);
}
/**
* ppc4xx_ecc_clear_status - clear controller ECC status
* @mci: A pointer to the EDAC memory controller instance
* associated with the status being cleared.
* @status: A pointer to the ECC status structure containing the
* values to write to clear the ECC status.
*
* This routine clears--by writing the masked (as appropriate) status
* values back to--the status registers that deal with
* ibm,sdram-4xx-ddr2 ECC errors.
*/
static void
ppc4xx_ecc_clear_status(const struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status)
{
const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
const dcr_host_t *dcr_host = &pdata->dcr_host;
mtsdram(dcr_host, SDRAM_ECCES, status->ecces & SDRAM_ECCES_MASK);
mtsdram(dcr_host, SDRAM_WMIRQ, status->wmirq & SDRAM_WMIRQ_MASK);
mtsdram(dcr_host, SDRAM_BESR, status->besr & SDRAM_BESR_MASK);
mtsdram(dcr_host, SDRAM_BEARL, 0);
mtsdram(dcr_host, SDRAM_BEARH, 0);
}
/**
* ppc4xx_edac_handle_ce - handle controller correctable ECC error (CE)
* @mci: A pointer to the EDAC memory controller instance
* associated with the correctable error being handled and reported.
* @status: A pointer to the ECC status structure associated with
* the correctable error being handled and reported.
*
* This routine handles an ibm,sdram-4xx-ddr2 controller ECC
* correctable error. Per the aforementioned discussion, there's not
* enough status available to use the full EDAC correctable error
* interface, so we just pass driver-unique message to the "no info"
* interface.
*/
static void
ppc4xx_edac_handle_ce(struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status)
{
int row;
char message[PPC4XX_EDAC_MESSAGE_SIZE];
ppc4xx_edac_generate_message(mci, status, message, sizeof(message));
for (row = 0; row < mci->nr_csrows; row++)
if (ppc4xx_edac_check_bank_error(status, row))
edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
0, 0, 0,
row, 0, -1,
message, "");
}
/**
* ppc4xx_edac_handle_ue - handle controller uncorrectable ECC error (UE)
* @mci: A pointer to the EDAC memory controller instance
* associated with the uncorrectable error being handled and
* reported.
* @status: A pointer to the ECC status structure associated with
* the uncorrectable error being handled and reported.
*
* This routine handles an ibm,sdram-4xx-ddr2 controller ECC
* uncorrectable error.
*/
static void
ppc4xx_edac_handle_ue(struct mem_ctl_info *mci,
const struct ppc4xx_ecc_status *status)
{
const u64 bear = ((u64)status->bearh << 32 | status->bearl);
const unsigned long page = bear >> PAGE_SHIFT;
const unsigned long offset = bear & ~PAGE_MASK;
int row;
char message[PPC4XX_EDAC_MESSAGE_SIZE];
ppc4xx_edac_generate_message(mci, status, message, sizeof(message));
for (row = 0; row < mci->nr_csrows; row++)
if (ppc4xx_edac_check_bank_error(status, row))
edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
page, offset, 0,
row, 0, -1,
message, "");
}
/**
* ppc4xx_edac_check - check controller for ECC errors
* @mci: A pointer to the EDAC memory controller instance
* associated with the ibm,sdram-4xx-ddr2 controller being
* checked.
*
* This routine is used to check and post ECC errors and is called by
* both the EDAC polling thread and this driver's CE and UE interrupt
* handler.
*/
static void
ppc4xx_edac_check(struct mem_ctl_info *mci)
{
#ifdef DEBUG
static unsigned int count;
#endif
struct ppc4xx_ecc_status status;
ppc4xx_ecc_get_status(mci, &status);
#ifdef DEBUG
if (count++ % 30 == 0)
ppc4xx_ecc_dump_status(mci, &status);
#endif
if (status.ecces & SDRAM_ECCES_UE)
ppc4xx_edac_handle_ue(mci, &status);
if (status.ecces & SDRAM_ECCES_CE)
ppc4xx_edac_handle_ce(mci, &status);
ppc4xx_ecc_clear_status(mci, &status);
}
/**
* ppc4xx_edac_isr - SEC (CE) and DED (UE) interrupt service routine
* @irq: The virtual interrupt number being serviced.
* @dev_id: A pointer to the EDAC memory controller instance
* associated with the interrupt being handled.
*
* This routine implements the interrupt handler for both correctable
* (CE) and uncorrectable (UE) ECC errors for the ibm,sdram-4xx-ddr2
* controller. It simply calls through to the same routine used during
* polling to check, report and clear the ECC status.
*
* Unconditionally returns IRQ_HANDLED.
*/
static irqreturn_t
ppc4xx_edac_isr(int irq, void *dev_id)
{
struct mem_ctl_info *mci = dev_id;
ppc4xx_edac_check(mci);
return IRQ_HANDLED;
}
/**
* ppc4xx_edac_get_dtype - return the controller memory width
* @mcopt1: The 32-bit Memory Controller Option 1 register value
* currently set for the controller, from which the width
* is derived.
*
* This routine returns the EDAC device type width appropriate for the
* current controller configuration.
*
* TODO: This needs to be conditioned dynamically through feature
* flags or some such when other controller variants are supported as
* the 405EX[r] is 16-/32-bit and the others are 32-/64-bit with the
* 16- and 64-bit field definition/value/enumeration (b1) overloaded
* among them.
*
* Returns a device type width enumeration.
*/
static enum dev_type ppc4xx_edac_get_dtype(u32 mcopt1)
{
switch (mcopt1 & SDRAM_MCOPT1_WDTH_MASK) {
case SDRAM_MCOPT1_WDTH_16:
return DEV_X2;
case SDRAM_MCOPT1_WDTH_32:
return DEV_X4;
default:
return DEV_UNKNOWN;
}
}
/**
* ppc4xx_edac_get_mtype - return controller memory type
* @mcopt1: The 32-bit Memory Controller Option 1 register value
* currently set for the controller, from which the memory type
* is derived.
*
* This routine returns the EDAC memory type appropriate for the
* current controller configuration.
*
* Returns a memory type enumeration.
*/
static enum mem_type ppc4xx_edac_get_mtype(u32 mcopt1)
{
bool rden = ((mcopt1 & SDRAM_MCOPT1_RDEN_MASK) == SDRAM_MCOPT1_RDEN);
switch (mcopt1 & SDRAM_MCOPT1_DDR_TYPE_MASK) {
case SDRAM_MCOPT1_DDR2_TYPE:
return rden ? MEM_RDDR2 : MEM_DDR2;
case SDRAM_MCOPT1_DDR1_TYPE:
return rden ? MEM_RDDR : MEM_DDR;
default:
return MEM_UNKNOWN;
}
}
/**
* ppc4xx_edac_init_csrows - initialize driver instance rows
* @mci: A pointer to the EDAC memory controller instance
* associated with the ibm,sdram-4xx-ddr2 controller for which
* the csrows (i.e. banks/ranks) are being initialized.
* @mcopt1: The 32-bit Memory Controller Option 1 register value
* currently set for the controller, from which bank width
* and memory typ information is derived.
*
* This routine initializes the virtual "chip select rows" associated
* with the EDAC memory controller instance. An ibm,sdram-4xx-ddr2
* controller bank/rank is mapped to a row.
*
* Returns 0 if OK; otherwise, -EINVAL if the memory bank size
* configuration cannot be determined.
*/
static int ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1)
{
const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
int status = 0;
enum mem_type mtype;
enum dev_type dtype;
enum edac_type edac_mode;
int row, j;
u32 mbxcf, size, nr_pages;
/* Establish the memory type and width */
mtype = ppc4xx_edac_get_mtype(mcopt1);
dtype = ppc4xx_edac_get_dtype(mcopt1);
/* Establish EDAC mode */
if (mci->edac_cap & EDAC_FLAG_SECDED)
edac_mode = EDAC_SECDED;
else if (mci->edac_cap & EDAC_FLAG_EC)
edac_mode = EDAC_EC;
else
edac_mode = EDAC_NONE;
/*
* Initialize each chip select row structure which correspond
* 1:1 with a controller bank/rank.
*/
for (row = 0; row < mci->nr_csrows; row++) {
struct csrow_info *csi = mci->csrows[row];
/*
* Get the configuration settings for this
* row/bank/rank and skip disabled banks.
*/
mbxcf = mfsdram(&pdata->dcr_host, SDRAM_MBXCF(row));
if ((mbxcf & SDRAM_MBCF_BE_MASK) != SDRAM_MBCF_BE_ENABLE)
continue;
/* Map the bank configuration size setting to pages. */
size = mbxcf & SDRAM_MBCF_SZ_MASK;
switch (size) {
case SDRAM_MBCF_SZ_4MB:
case SDRAM_MBCF_SZ_8MB:
case SDRAM_MBCF_SZ_16MB:
case SDRAM_MBCF_SZ_32MB:
case SDRAM_MBCF_SZ_64MB:
case SDRAM_MBCF_SZ_128MB:
case SDRAM_MBCF_SZ_256MB:
case SDRAM_MBCF_SZ_512MB:
case SDRAM_MBCF_SZ_1GB:
case SDRAM_MBCF_SZ_2GB:
case SDRAM_MBCF_SZ_4GB:
case SDRAM_MBCF_SZ_8GB:
nr_pages = SDRAM_MBCF_SZ_TO_PAGES(size);
break;
default:
ppc4xx_edac_mc_printk(KERN_ERR, mci,
"Unrecognized memory bank %d "
"size 0x%08x\n",
row, SDRAM_MBCF_SZ_DECODE(size));
status = -EINVAL;
goto done;
}
/*
* It's unclear exactly what grain should be set to
* here. The SDRAM_ECCES register allows resolution of
* an error down to a nibble which would potentially
* argue for a grain of '1' byte, even though we only
* know the associated address for uncorrectable
* errors. This value is not used at present for
* anything other than error reporting so getting it
* wrong should be of little consequence. Other
* possible values would be the PLB width (16), the
* page size (PAGE_SIZE) or the memory width (2 or 4).
*/
for (j = 0; j < csi->nr_channels; j++) {
struct dimm_info *dimm = csi->channels[j]->dimm;
dimm->nr_pages = nr_pages / csi->nr_channels;
dimm->grain = 1;
dimm->mtype = mtype;
dimm->dtype = dtype;
dimm->edac_mode = edac_mode;
}
}
done:
return status;
}
/**
* ppc4xx_edac_mc_init - initialize driver instance
* @mci: A pointer to the EDAC memory controller instance being
* initialized.
* @op: A pointer to the OpenFirmware device tree node associated
* with the controller this EDAC instance is bound to.
* @dcr_host: A pointer to the DCR data containing the DCR mapping
* for this controller instance.
* @mcopt1: The 32-bit Memory Controller Option 1 register value
* currently set for the controller, from which ECC capabilities
* and scrub mode are derived.
*
* This routine performs initialization of the EDAC memory controller
* instance and related driver-private data associated with the
* ibm,sdram-4xx-ddr2 memory controller the instance is bound to.
*
* Returns 0 if OK; otherwise, < 0 on error.
*/
static int ppc4xx_edac_mc_init(struct mem_ctl_info *mci,
struct platform_device *op,
const dcr_host_t *dcr_host, u32 mcopt1)
{
int status = 0;
const u32 memcheck = (mcopt1 & SDRAM_MCOPT1_MCHK_MASK);
struct ppc4xx_edac_pdata *pdata = NULL;
const struct device_node *np = op->dev.of_node;
if (of_match_device(ppc4xx_edac_match, &op->dev) == NULL)
return -EINVAL;
/* Initial driver pointers and private data */
mci->pdev = &op->dev;
dev_set_drvdata(mci->pdev, mci);
pdata = mci->pvt_info;
pdata->dcr_host = *dcr_host;
/* Initialize controller capabilities and configuration */
mci->mtype_cap = (MEM_FLAG_DDR | MEM_FLAG_RDDR |
MEM_FLAG_DDR2 | MEM_FLAG_RDDR2);
mci->edac_ctl_cap = (EDAC_FLAG_NONE |
EDAC_FLAG_EC |
EDAC_FLAG_SECDED);
mci->scrub_cap = SCRUB_NONE;
mci->scrub_mode = SCRUB_NONE;
/*
* Update the actual capabilites based on the MCOPT1[MCHK]
* settings. Scrubbing is only useful if reporting is enabled.
*/
switch (memcheck) {
case SDRAM_MCOPT1_MCHK_CHK:
mci->edac_cap = EDAC_FLAG_EC;
break;
case SDRAM_MCOPT1_MCHK_CHK_REP:
mci->edac_cap = (EDAC_FLAG_EC | EDAC_FLAG_SECDED);
mci->scrub_mode = SCRUB_SW_SRC;
break;
default:
mci->edac_cap = EDAC_FLAG_NONE;
break;
}
/* Initialize strings */
mci->mod_name = PPC4XX_EDAC_MODULE_NAME;
mci->ctl_name = ppc4xx_edac_match->compatible;
mci->dev_name = np->full_name;
/* Initialize callbacks */
mci->edac_check = ppc4xx_edac_check;
mci->ctl_page_to_phys = NULL;
/* Initialize chip select rows */
status = ppc4xx_edac_init_csrows(mci, mcopt1);
if (status)
ppc4xx_edac_mc_printk(KERN_ERR, mci,
"Failed to initialize rows!\n");
return status;
}
/**
* ppc4xx_edac_register_irq - setup and register controller interrupts
* @op: A pointer to the OpenFirmware device tree node associated
* with the controller this EDAC instance is bound to.
* @mci: A pointer to the EDAC memory controller instance
* associated with the ibm,sdram-4xx-ddr2 controller for which
* interrupts are being registered.
*
* This routine parses the correctable (CE) and uncorrectable error (UE)
* interrupts from the device tree node and maps and assigns them to
* the associated EDAC memory controller instance.
*
* Returns 0 if OK; otherwise, -ENODEV if the interrupts could not be
* mapped and assigned.
*/
static int ppc4xx_edac_register_irq(struct platform_device *op,
struct mem_ctl_info *mci)
{
int status = 0;
int ded_irq, sec_irq;
struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
struct device_node *np = op->dev.of_node;
ded_irq = irq_of_parse_and_map(np, INTMAP_ECCDED_INDEX);
sec_irq = irq_of_parse_and_map(np, INTMAP_ECCSEC_INDEX);
if (!ded_irq || !sec_irq) {
ppc4xx_edac_mc_printk(KERN_ERR, mci,
"Unable to map interrupts.\n");
status = -ENODEV;
goto fail;
}
status = request_irq(ded_irq,
ppc4xx_edac_isr,
0,
"[EDAC] MC ECCDED",
mci);
if (status < 0) {
ppc4xx_edac_mc_printk(KERN_ERR, mci,
"Unable to request irq %d for ECC DED",
ded_irq);
status = -ENODEV;
goto fail1;
}
status = request_irq(sec_irq,
ppc4xx_edac_isr,
0,
"[EDAC] MC ECCSEC",
mci);
if (status < 0) {
ppc4xx_edac_mc_printk(KERN_ERR, mci,
"Unable to request irq %d for ECC SEC",
sec_irq);
status = -ENODEV;
goto fail2;
}
ppc4xx_edac_mc_printk(KERN_INFO, mci, "ECCDED irq is %d\n", ded_irq);
ppc4xx_edac_mc_printk(KERN_INFO, mci, "ECCSEC irq is %d\n", sec_irq);
pdata->irqs.ded = ded_irq;
pdata->irqs.sec = sec_irq;
return 0;
fail2:
free_irq(sec_irq, mci);
fail1:
free_irq(ded_irq, mci);
fail:
return status;
}
/**
* ppc4xx_edac_map_dcrs - locate and map controller registers
* @np: A pointer to the device tree node containing the DCR
* resources to map.
* @dcr_host: A pointer to the DCR data to populate with the
* DCR mapping.
*
* This routine attempts to locate in the device tree and map the DCR
* register resources associated with the controller's indirect DCR
* address and data windows.
*
* Returns 0 if the DCRs were successfully mapped; otherwise, < 0 on
* error.
*/
static int ppc4xx_edac_map_dcrs(const struct device_node *np,
dcr_host_t *dcr_host)
{
unsigned int dcr_base, dcr_len;
if (np == NULL || dcr_host == NULL)
return -EINVAL;
/* Get the DCR resource extent and sanity check the values. */
dcr_base = dcr_resource_start(np, 0);
dcr_len = dcr_resource_len(np, 0);
if (dcr_base == 0 || dcr_len == 0) {
ppc4xx_edac_printk(KERN_ERR,
"Failed to obtain DCR property.\n");
return -ENODEV;
}
if (dcr_len != SDRAM_DCR_RESOURCE_LEN) {
ppc4xx_edac_printk(KERN_ERR,
"Unexpected DCR length %d, expected %d.\n",
dcr_len, SDRAM_DCR_RESOURCE_LEN);
return -ENODEV;
}
/* Attempt to map the DCR extent. */
*dcr_host = dcr_map(np, dcr_base, dcr_len);
if (!DCR_MAP_OK(*dcr_host)) {
ppc4xx_edac_printk(KERN_INFO, "Failed to map DCRs.\n");
return -ENODEV;
}
return 0;
}
/**
* ppc4xx_edac_probe - check controller and bind driver
* @op: A pointer to the OpenFirmware device tree node associated
* with the controller being probed for driver binding.
*
* This routine probes a specific ibm,sdram-4xx-ddr2 controller
* instance for binding with the driver.
*
* Returns 0 if the controller instance was successfully bound to the
* driver; otherwise, < 0 on error.
*/
static int ppc4xx_edac_probe(struct platform_device *op)
{
int status = 0;
u32 mcopt1, memcheck;
dcr_host_t dcr_host;
const struct device_node *np = op->dev.of_node;
struct mem_ctl_info *mci = NULL;
struct edac_mc_layer layers[2];
static int ppc4xx_edac_instance;
/*
* At this point, we only support the controller realized on
* the AMCC PPC 405EX[r]. Reject anything else.
*/
if (!of_device_is_compatible(np, "ibm,sdram-405ex") &&
!of_device_is_compatible(np, "ibm,sdram-405exr")) {
ppc4xx_edac_printk(KERN_NOTICE,
"Only the PPC405EX[r] is supported.\n");
return -ENODEV;
}
/*
* Next, get the DCR property and attempt to map it so that we
* can probe the controller.
*/
status = ppc4xx_edac_map_dcrs(np, &dcr_host);
if (status)
return status;
/*
* First determine whether ECC is enabled at all. If not,
* there is no useful checking or monitoring that can be done
* for this controller.
*/
mcopt1 = mfsdram(&dcr_host, SDRAM_MCOPT1);
memcheck = (mcopt1 & SDRAM_MCOPT1_MCHK_MASK);
if (memcheck == SDRAM_MCOPT1_MCHK_NON) {
ppc4xx_edac_printk(KERN_INFO, "%pOF: No ECC memory detected or "
"ECC is disabled.\n", np);
status = -ENODEV;
goto done;
}
/*
* At this point, we know ECC is enabled, allocate an EDAC
* controller instance and perform the appropriate
* initialization.
*/
layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
layers[0].size = ppc4xx_edac_nr_csrows;
layers[0].is_virt_csrow = true;
layers[1].type = EDAC_MC_LAYER_CHANNEL;
layers[1].size = ppc4xx_edac_nr_chans;
layers[1].is_virt_csrow = false;
mci = edac_mc_alloc(ppc4xx_edac_instance, ARRAY_SIZE(layers), layers,
sizeof(struct ppc4xx_edac_pdata));
if (mci == NULL) {
ppc4xx_edac_printk(KERN_ERR, "%pOF: "
"Failed to allocate EDAC MC instance!\n",
np);
status = -ENOMEM;
goto done;
}
status = ppc4xx_edac_mc_init(mci, op, &dcr_host, mcopt1);
if (status) {
ppc4xx_edac_mc_printk(KERN_ERR, mci,
"Failed to initialize instance!\n");
goto fail;
}
/*
* We have a valid, initialized EDAC instance bound to the
* controller. Attempt to register it with the EDAC subsystem
* and, if necessary, register interrupts.
*/
if (edac_mc_add_mc(mci)) {
ppc4xx_edac_mc_printk(KERN_ERR, mci,
"Failed to add instance!\n");
status = -ENODEV;
goto fail;
}
if (edac_op_state == EDAC_OPSTATE_INT) {
status = ppc4xx_edac_register_irq(op, mci);
if (status)
goto fail1;
}
ppc4xx_edac_instance++;
return 0;
fail1:
edac_mc_del_mc(mci->pdev);
fail:
edac_mc_free(mci);
done:
return status;
}
/**
* ppc4xx_edac_remove - unbind driver from controller
* @op: A pointer to the OpenFirmware device tree node associated
* with the controller this EDAC instance is to be unbound/removed
* from.
*
* This routine unbinds the EDAC memory controller instance associated
* with the specified ibm,sdram-4xx-ddr2 controller described by the
* OpenFirmware device tree node passed as a parameter.
*
* Unconditionally returns 0.
*/
static void ppc4xx_edac_remove(struct platform_device *op)
{
struct mem_ctl_info *mci = dev_get_drvdata(&op->dev);
struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
if (edac_op_state == EDAC_OPSTATE_INT) {
free_irq(pdata->irqs.sec, mci);
free_irq(pdata->irqs.ded, mci);
}
dcr_unmap(pdata->dcr_host, SDRAM_DCR_RESOURCE_LEN);
edac_mc_del_mc(mci->pdev);
edac_mc_free(mci);
}
/**
* ppc4xx_edac_opstate_init - initialize EDAC reporting method
*
* This routine ensures that the EDAC memory controller reporting
* method is mapped to a sane value as the EDAC core defines the value
* to EDAC_OPSTATE_INVAL by default. We don't call the global
* opstate_init as that defaults to polling and we want interrupt as
* the default.
*/
static inline void __init
ppc4xx_edac_opstate_init(void)
{
switch (edac_op_state) {
case EDAC_OPSTATE_POLL:
case EDAC_OPSTATE_INT:
break;
default:
edac_op_state = EDAC_OPSTATE_INT;
break;
}
ppc4xx_edac_printk(KERN_INFO, "Reporting type: %s\n",
((edac_op_state == EDAC_OPSTATE_POLL) ?
EDAC_OPSTATE_POLL_STR :
((edac_op_state == EDAC_OPSTATE_INT) ?
EDAC_OPSTATE_INT_STR :
EDAC_OPSTATE_UNKNOWN_STR)));
}
static struct platform_driver ppc4xx_edac_driver = {
.probe = ppc4xx_edac_probe,
.remove_new = ppc4xx_edac_remove,
.driver = {
.name = PPC4XX_EDAC_MODULE_NAME,
.of_match_table = ppc4xx_edac_match,
},
};
/**
* ppc4xx_edac_init - driver/module insertion entry point
*
* This routine is the driver/module insertion entry point. It
* initializes the EDAC memory controller reporting state and
* registers the driver as an OpenFirmware device tree platform
* driver.
*/
static int __init
ppc4xx_edac_init(void)
{
ppc4xx_edac_printk(KERN_INFO, PPC4XX_EDAC_MODULE_REVISION "\n");
ppc4xx_edac_opstate_init();
return platform_driver_register(&ppc4xx_edac_driver);
}
/**
* ppc4xx_edac_exit - driver/module removal entry point
*
* This routine is the driver/module removal entry point. It
* unregisters the driver as an OpenFirmware device tree platform
* driver.
*/
static void __exit
ppc4xx_edac_exit(void)
{
platform_driver_unregister(&ppc4xx_edac_driver);
}
module_init(ppc4xx_edac_init);
module_exit(ppc4xx_edac_exit);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Grant Erickson <gerickson@nuovations.com>");
MODULE_DESCRIPTION("EDAC MC Driver for the PPC4xx IBM DDR2 Memory Controller");
module_param(edac_op_state, int, 0444);
MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting State: "
"0=" EDAC_OPSTATE_POLL_STR ", 2=" EDAC_OPSTATE_INT_STR);
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (c) 2008 Nuovation System Designs, LLC
* Grant Erickson <gerickson@nuovations.com>
*
* This file defines processor mnemonics for accessing and managing
* the IBM DDR1/DDR2 ECC controller found in the 405EX[r], 440SP,
* 440SPe, 460EX, 460GT and 460SX.
*/
#ifndef __PPC4XX_EDAC_H
#define __PPC4XX_EDAC_H
#include <linux/types.h>
/*
* Macro for generating register field mnemonics
*/
#define PPC_REG_BITS 32
#define PPC_REG_VAL(bit, val) ((val) << ((PPC_REG_BITS - 1) - (bit)))
#define PPC_REG_DECODE(bit, val) ((val) >> ((PPC_REG_BITS - 1) - (bit)))
/*
* IBM 4xx DDR1/DDR2 SDRAM memory controller registers (at least those
* relevant to ECC)
*/
#define SDRAM_BESR 0x00 /* Error status (read/clear) */
#define SDRAM_BESRT 0x01 /* Error statuss (test/set) */
#define SDRAM_BEARL 0x02 /* Error address low */
#define SDRAM_BEARH 0x03 /* Error address high */
#define SDRAM_WMIRQ 0x06 /* Write master (read/clear) */
#define SDRAM_WMIRQT 0x07 /* Write master (test/set) */
#define SDRAM_MCOPT1 0x20 /* Controller options 1 */
#define SDRAM_MBXCF_BASE 0x40 /* Bank n configuration base */
#define SDRAM_MBXCF(n) (SDRAM_MBXCF_BASE + (4 * (n)))
#define SDRAM_MB0CF SDRAM_MBXCF(0)
#define SDRAM_MB1CF SDRAM_MBXCF(1)
#define SDRAM_MB2CF SDRAM_MBXCF(2)
#define SDRAM_MB3CF SDRAM_MBXCF(3)
#define SDRAM_ECCCR 0x98 /* ECC error status */
#define SDRAM_ECCES SDRAM_ECCCR
/*
* PLB Master IDs
*/
#define SDRAM_PLB_M0ID_FIRST 0
#define SDRAM_PLB_M0ID_ICU SDRAM_PLB_M0ID_FIRST
#define SDRAM_PLB_M0ID_PCIE0 1
#define SDRAM_PLB_M0ID_PCIE1 2
#define SDRAM_PLB_M0ID_DMA 3
#define SDRAM_PLB_M0ID_DCU 4
#define SDRAM_PLB_M0ID_OPB 5
#define SDRAM_PLB_M0ID_MAL 6
#define SDRAM_PLB_M0ID_SEC 7
#define SDRAM_PLB_M0ID_AHB 8
#define SDRAM_PLB_M0ID_LAST SDRAM_PLB_M0ID_AHB
#define SDRAM_PLB_M0ID_COUNT (SDRAM_PLB_M0ID_LAST - \
SDRAM_PLB_M0ID_FIRST + 1)
/*
* Memory Controller Bus Error Status Register
*/
#define SDRAM_BESR_MASK PPC_REG_VAL(7, 0xFF)
#define SDRAM_BESR_M0ID_MASK PPC_REG_VAL(3, 0xF)
#define SDRAM_BESR_M0ID_DECODE(n) PPC_REG_DECODE(3, n)
#define SDRAM_BESR_M0ID_ICU PPC_REG_VAL(3, SDRAM_PLB_M0ID_ICU)
#define SDRAM_BESR_M0ID_PCIE0 PPC_REG_VAL(3, SDRAM_PLB_M0ID_PCIE0)
#define SDRAM_BESR_M0ID_PCIE1 PPC_REG_VAL(3, SDRAM_PLB_M0ID_PCIE1)
#define SDRAM_BESR_M0ID_DMA PPC_REG_VAL(3, SDRAM_PLB_M0ID_DMA)
#define SDRAM_BESR_M0ID_DCU PPC_REG_VAL(3, SDRAM_PLB_M0ID_DCU)
#define SDRAM_BESR_M0ID_OPB PPC_REG_VAL(3, SDRAM_PLB_M0ID_OPB)
#define SDRAM_BESR_M0ID_MAL PPC_REG_VAL(3, SDRAM_PLB_M0ID_MAL)
#define SDRAM_BESR_M0ID_SEC PPC_REG_VAL(3, SDRAM_PLB_M0ID_SEC)
#define SDRAM_BESR_M0ID_AHB PPC_REG_VAL(3, SDRAM_PLB_M0ID_AHB)
#define SDRAM_BESR_M0ET_MASK PPC_REG_VAL(6, 0x7)
#define SDRAM_BESR_M0ET_NONE PPC_REG_VAL(6, 0)
#define SDRAM_BESR_M0ET_ECC PPC_REG_VAL(6, 1)
#define SDRAM_BESR_M0RW_MASK PPC_REG_VAL(7, 1)
#define SDRAM_BESR_M0RW_WRITE PPC_REG_VAL(7, 0)
#define SDRAM_BESR_M0RW_READ PPC_REG_VAL(7, 1)
/*
* Memory Controller PLB Write Master Interrupt Register
*/
#define SDRAM_WMIRQ_MASK PPC_REG_VAL(8, 0x1FF)
#define SDRAM_WMIRQ_ENCODE(id) PPC_REG_VAL((id % \
SDRAM_PLB_M0ID_COUNT), 1)
#define SDRAM_WMIRQ_ICU PPC_REG_VAL(SDRAM_PLB_M0ID_ICU, 1)
#define SDRAM_WMIRQ_PCIE0 PPC_REG_VAL(SDRAM_PLB_M0ID_PCIE0, 1)
#define SDRAM_WMIRQ_PCIE1 PPC_REG_VAL(SDRAM_PLB_M0ID_PCIE1, 1)
#define SDRAM_WMIRQ_DMA PPC_REG_VAL(SDRAM_PLB_M0ID_DMA, 1)
#define SDRAM_WMIRQ_DCU PPC_REG_VAL(SDRAM_PLB_M0ID_DCU, 1)
#define SDRAM_WMIRQ_OPB PPC_REG_VAL(SDRAM_PLB_M0ID_OPB, 1)
#define SDRAM_WMIRQ_MAL PPC_REG_VAL(SDRAM_PLB_M0ID_MAL, 1)
#define SDRAM_WMIRQ_SEC PPC_REG_VAL(SDRAM_PLB_M0ID_SEC, 1)
#define SDRAM_WMIRQ_AHB PPC_REG_VAL(SDRAM_PLB_M0ID_AHB, 1)
/*
* Memory Controller Options 1 Register
*/
#define SDRAM_MCOPT1_MCHK_MASK PPC_REG_VAL(3, 0x3) /* ECC mask */
#define SDRAM_MCOPT1_MCHK_NON PPC_REG_VAL(3, 0x0) /* No ECC gen */
#define SDRAM_MCOPT1_MCHK_GEN PPC_REG_VAL(3, 0x2) /* ECC gen */
#define SDRAM_MCOPT1_MCHK_CHK PPC_REG_VAL(3, 0x1) /* ECC gen and chk */
#define SDRAM_MCOPT1_MCHK_CHK_REP PPC_REG_VAL(3, 0x3) /* ECC gen/chk/rpt */
#define SDRAM_MCOPT1_MCHK_DECODE(n) ((((u32)(n)) >> 28) & 0x3)
#define SDRAM_MCOPT1_RDEN_MASK PPC_REG_VAL(4, 0x1) /* Rgstrd DIMM mask */
#define SDRAM_MCOPT1_RDEN PPC_REG_VAL(4, 0x1) /* Rgstrd DIMM enbl */
#define SDRAM_MCOPT1_WDTH_MASK PPC_REG_VAL(7, 0x1) /* Width mask */
#define SDRAM_MCOPT1_WDTH_32 PPC_REG_VAL(7, 0x0) /* 32 bits */
#define SDRAM_MCOPT1_WDTH_16 PPC_REG_VAL(7, 0x1) /* 16 bits */
#define SDRAM_MCOPT1_DDR_TYPE_MASK PPC_REG_VAL(11, 0x1) /* DDR type mask */
#define SDRAM_MCOPT1_DDR1_TYPE PPC_REG_VAL(11, 0x0) /* DDR1 type */
#define SDRAM_MCOPT1_DDR2_TYPE PPC_REG_VAL(11, 0x1) /* DDR2 type */
/*
* Memory Bank 0 - n Configuration Register
*/
#define SDRAM_MBCF_BA_MASK PPC_REG_VAL(12, 0x1FFF)
#define SDRAM_MBCF_SZ_MASK PPC_REG_VAL(19, 0xF)
#define SDRAM_MBCF_SZ_DECODE(mbxcf) PPC_REG_DECODE(19, mbxcf)
#define SDRAM_MBCF_SZ_4MB PPC_REG_VAL(19, 0x0)
#define SDRAM_MBCF_SZ_8MB PPC_REG_VAL(19, 0x1)
#define SDRAM_MBCF_SZ_16MB PPC_REG_VAL(19, 0x2)
#define SDRAM_MBCF_SZ_32MB PPC_REG_VAL(19, 0x3)
#define SDRAM_MBCF_SZ_64MB PPC_REG_VAL(19, 0x4)
#define SDRAM_MBCF_SZ_128MB PPC_REG_VAL(19, 0x5)
#define SDRAM_MBCF_SZ_256MB PPC_REG_VAL(19, 0x6)
#define SDRAM_MBCF_SZ_512MB PPC_REG_VAL(19, 0x7)
#define SDRAM_MBCF_SZ_1GB PPC_REG_VAL(19, 0x8)
#define SDRAM_MBCF_SZ_2GB PPC_REG_VAL(19, 0x9)
#define SDRAM_MBCF_SZ_4GB PPC_REG_VAL(19, 0xA)
#define SDRAM_MBCF_SZ_8GB PPC_REG_VAL(19, 0xB)
#define SDRAM_MBCF_AM_MASK PPC_REG_VAL(23, 0xF)
#define SDRAM_MBCF_AM_MODE0 PPC_REG_VAL(23, 0x0)
#define SDRAM_MBCF_AM_MODE1 PPC_REG_VAL(23, 0x1)
#define SDRAM_MBCF_AM_MODE2 PPC_REG_VAL(23, 0x2)
#define SDRAM_MBCF_AM_MODE3 PPC_REG_VAL(23, 0x3)
#define SDRAM_MBCF_AM_MODE4 PPC_REG_VAL(23, 0x4)
#define SDRAM_MBCF_AM_MODE5 PPC_REG_VAL(23, 0x5)
#define SDRAM_MBCF_AM_MODE6 PPC_REG_VAL(23, 0x6)
#define SDRAM_MBCF_AM_MODE7 PPC_REG_VAL(23, 0x7)
#define SDRAM_MBCF_AM_MODE8 PPC_REG_VAL(23, 0x8)
#define SDRAM_MBCF_AM_MODE9 PPC_REG_VAL(23, 0x9)
#define SDRAM_MBCF_BE_MASK PPC_REG_VAL(31, 0x1)
#define SDRAM_MBCF_BE_DISABLE PPC_REG_VAL(31, 0x0)
#define SDRAM_MBCF_BE_ENABLE PPC_REG_VAL(31, 0x1)
/*
* ECC Error Status
*/
#define SDRAM_ECCES_MASK PPC_REG_VAL(21, 0x3FFFFF)
#define SDRAM_ECCES_BNCE_MASK PPC_REG_VAL(15, 0xFFFF)
#define SDRAM_ECCES_BNCE_ENCODE(lane) PPC_REG_VAL(((lane) & 0xF), 1)
#define SDRAM_ECCES_CKBER_MASK PPC_REG_VAL(17, 0x3)
#define SDRAM_ECCES_CKBER_NONE PPC_REG_VAL(17, 0)
#define SDRAM_ECCES_CKBER_16_ECC_0_3 PPC_REG_VAL(17, 2)
#define SDRAM_ECCES_CKBER_32_ECC_0_3 PPC_REG_VAL(17, 1)
#define SDRAM_ECCES_CKBER_32_ECC_4_8 PPC_REG_VAL(17, 2)
#define SDRAM_ECCES_CKBER_32_ECC_0_8 PPC_REG_VAL(17, 3)
#define SDRAM_ECCES_CE PPC_REG_VAL(18, 1)
#define SDRAM_ECCES_UE PPC_REG_VAL(19, 1)
#define SDRAM_ECCES_BKNER_MASK PPC_REG_VAL(21, 0x3)
#define SDRAM_ECCES_BK0ER PPC_REG_VAL(20, 1)
#define SDRAM_ECCES_BK1ER PPC_REG_VAL(21, 1)
#endif /* __PPC4XX_EDAC_H */
......@@ -29,6 +29,8 @@
/* Static vars */
static LIST_HEAD(sbridge_edac_list);
static char sb_msg[256];
static char sb_msg_full[512];
/*
* Alter this version for the module when modifications are made
......@@ -3079,7 +3081,6 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
struct mem_ctl_info *new_mci;
struct sbridge_pvt *pvt = mci->pvt_info;
enum hw_event_mc_err_type tp_event;
char *optype, msg[256], msg_full[512];
bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0);
bool overflow = GET_BITFIELD(m->status, 62, 62);
bool uncorrected_error = GET_BITFIELD(m->status, 61, 61);
......@@ -3095,10 +3096,10 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
* aligned address reported by patrol scrubber.
*/
u32 lsb = GET_BITFIELD(m->misc, 0, 5);
char *optype, *area_type = "DRAM";
long channel_mask, first_channel;
u8 rank = 0xff, socket, ha;
int rc, dimm;
char *area_type = "DRAM";
if (pvt->info.type != SANDY_BRIDGE)
recoverable = true;
......@@ -3168,32 +3169,32 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
channel = knl_channel_remap(m->bank == 16, channel);
channel_mask = 1 << channel;
snprintf(msg, sizeof(msg),
"%s%s err_code:%04x:%04x channel:%d (DIMM_%c)",
overflow ? " OVERFLOW" : "",
(uncorrected_error && recoverable)
? " recoverable" : " ",
mscod, errcode, channel, A + channel);
snprintf(sb_msg, sizeof(sb_msg),
"%s%s err_code:%04x:%04x channel:%d (DIMM_%c)",
overflow ? " OVERFLOW" : "",
(uncorrected_error && recoverable)
? " recoverable" : " ",
mscod, errcode, channel, A + channel);
edac_mc_handle_error(tp_event, mci, core_err_cnt,
m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0,
channel, 0, -1,
optype, msg);
optype, sb_msg);
}
return;
} else if (lsb < 12) {
rc = get_memory_error_data(mci, m->addr, &socket, &ha,
&channel_mask, &rank,
&area_type, msg);
&area_type, sb_msg);
} else {
rc = get_memory_error_data_from_mce(mci, m, &socket, &ha,
&channel_mask, msg);
&channel_mask, sb_msg);
}
if (rc < 0)
goto err_parsing;
new_mci = get_mci_for_node_id(socket, ha);
if (!new_mci) {
strcpy(msg, "Error: socket got corrupted!");
strscpy(sb_msg, "Error: socket got corrupted!");
goto err_parsing;
}
mci = new_mci;
......@@ -3218,7 +3219,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
*/
if (!pvt->is_lockstep && !pvt->is_cur_addr_mirrored && !pvt->is_close_pg)
channel = first_channel;
snprintf(msg_full, sizeof(msg_full),
snprintf(sb_msg_full, sizeof(sb_msg_full),
"%s%s area:%s err_code:%04x:%04x socket:%d ha:%d channel_mask:%ld rank:%d %s",
overflow ? " OVERFLOW" : "",
(uncorrected_error && recoverable) ? " recoverable" : "",
......@@ -3226,9 +3227,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
mscod, errcode,
socket, ha,
channel_mask,
rank, msg);
rank, sb_msg);
edac_dbg(0, "%s\n", msg_full);
edac_dbg(0, "%s\n", sb_msg_full);
/* FIXME: need support for channel mask */
......@@ -3239,12 +3240,12 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
edac_mc_handle_error(tp_event, mci, core_err_cnt,
m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0,
channel, dimm, -1,
optype, msg_full);
optype, sb_msg_full);
return;
err_parsing:
edac_mc_handle_error(tp_event, mci, core_err_cnt, 0, 0, 0,
-1, -1, -1,
msg, "");
sb_msg, "");
}
......
......@@ -587,54 +587,6 @@ static struct notifier_block skx_mce_dec = {
.priority = MCE_PRIO_EDAC,
};
#ifdef CONFIG_EDAC_DEBUG
/*
* Debug feature.
* Exercise the address decode logic by writing an address to
* /sys/kernel/debug/edac/skx_test/addr.
*/
static struct dentry *skx_test;
static int debugfs_u64_set(void *data, u64 val)
{
struct mce m;
pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
memset(&m, 0, sizeof(m));
/* ADDRV + MemRd + Unknown channel */
m.status = MCI_STATUS_ADDRV + 0x90;
/* One corrected error */
m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
m.addr = val;
skx_mce_check_error(NULL, 0, &m);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
static void setup_skx_debug(void)
{
skx_test = edac_debugfs_create_dir("skx_test");
if (!skx_test)
return;
if (!edac_debugfs_create_file("addr", 0200, skx_test,
NULL, &fops_u64_wo)) {
debugfs_remove(skx_test);
skx_test = NULL;
}
}
static void teardown_skx_debug(void)
{
debugfs_remove_recursive(skx_test);
}
#else
static inline void setup_skx_debug(void) {}
static inline void teardown_skx_debug(void) {}
#endif /*CONFIG_EDAC_DEBUG*/
/*
* skx_init:
* make sure we are running on the correct cpu model
......@@ -728,7 +680,7 @@ static int __init skx_init(void)
/* Ensure that the OPSTATE is set correctly for POLL or NMI */
opstate_init();
setup_skx_debug();
skx_setup_debug("skx_test");
mce_register_decode_chain(&skx_mce_dec);
......@@ -742,7 +694,7 @@ static void __exit skx_exit(void)
{
edac_dbg(2, "\n");
mce_unregister_decode_chain(&skx_mce_dec);
teardown_skx_debug();
skx_teardown_debug();
if (nvdimm_count)
skx_adxl_put();
skx_remove();
......
......@@ -363,7 +363,7 @@ int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
if (imc->hbm_mc) {
banks = 32;
mtype = MEM_HBM2;
} else if (cfg->support_ddr5 && (amap & 0x8)) {
} else if (cfg->support_ddr5) {
banks = 32;
mtype = MEM_DDR5;
} else {
......@@ -739,6 +739,53 @@ void skx_remove(void)
}
EXPORT_SYMBOL_GPL(skx_remove);
#ifdef CONFIG_EDAC_DEBUG
/*
* Debug feature.
* Exercise the address decode logic by writing an address to
* /sys/kernel/debug/edac/{skx,i10nm}_test/addr.
*/
static struct dentry *skx_test;
static int debugfs_u64_set(void *data, u64 val)
{
struct mce m;
pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
memset(&m, 0, sizeof(m));
/* ADDRV + MemRd + Unknown channel */
m.status = MCI_STATUS_ADDRV + 0x90;
/* One corrected error */
m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
m.addr = val;
skx_mce_check_error(NULL, 0, &m);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
void skx_setup_debug(const char *name)
{
skx_test = edac_debugfs_create_dir(name);
if (!skx_test)
return;
if (!edac_debugfs_create_file("addr", 0200, skx_test,
NULL, &fops_u64_wo)) {
debugfs_remove(skx_test);
skx_test = NULL;
}
}
EXPORT_SYMBOL_GPL(skx_setup_debug);
void skx_teardown_debug(void)
{
debugfs_remove_recursive(skx_test);
}
EXPORT_SYMBOL_GPL(skx_teardown_debug);
#endif /*CONFIG_EDAC_DEBUG*/
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Tony Luck");
MODULE_DESCRIPTION("MC Driver for Intel server processors");
......@@ -259,4 +259,12 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
void skx_remove(void);
#ifdef CONFIG_EDAC_DEBUG
void skx_setup_debug(const char *name);
void skx_teardown_debug(void);
#else
static inline void skx_setup_debug(const char *name) {}
static inline void skx_teardown_debug(void) {}
#endif
#endif /* _SKX_COMM_EDAC_H */
......@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/spinlock.h>
#include <linux/sizes.h>
#include <linux/interrupt.h>
#include <linux/of.h>
......@@ -337,6 +338,7 @@ struct synps_edac_priv {
* @get_mtype: Get mtype.
* @get_dtype: Get dtype.
* @get_ecc_state: Get ECC state.
* @get_mem_info: Get EDAC memory info
* @quirks: To differentiate IPs.
*/
struct synps_platform_data {
......@@ -344,6 +346,9 @@ struct synps_platform_data {
enum mem_type (*get_mtype)(const void __iomem *base);
enum dev_type (*get_dtype)(const void __iomem *base);
bool (*get_ecc_state)(void __iomem *base);
#ifdef CONFIG_EDAC_DEBUG
u64 (*get_mem_info)(struct synps_edac_priv *priv);
#endif
int quirks;
};
......@@ -402,6 +407,25 @@ static int zynq_get_error_info(struct synps_edac_priv *priv)
return 0;
}
#ifdef CONFIG_EDAC_DEBUG
/**
* zynqmp_get_mem_info - Get the current memory info.
* @priv: DDR memory controller private instance data.
*
* Return: host interface address.
*/
static u64 zynqmp_get_mem_info(struct synps_edac_priv *priv)
{
u64 hif_addr = 0, linear_addr;
linear_addr = priv->poison_addr;
if (linear_addr >= SZ_32G)
linear_addr = linear_addr - SZ_32G + SZ_2G;
hif_addr = linear_addr >> 3;
return hif_addr;
}
#endif
/**
* zynqmp_get_error_info - Get the current ECC error info.
* @priv: DDR memory controller private instance data.
......@@ -922,6 +946,9 @@ static const struct synps_platform_data zynqmp_edac_def = {
.get_mtype = zynqmp_get_mtype,
.get_dtype = zynqmp_get_dtype,
.get_ecc_state = zynqmp_get_ecc_state,
#ifdef CONFIG_EDAC_DEBUG
.get_mem_info = zynqmp_get_mem_info,
#endif
.quirks = (DDR_ECC_INTR_SUPPORT
#ifdef CONFIG_EDAC_DEBUG
| DDR_ECC_DATA_POISON_SUPPORT
......@@ -975,10 +1002,16 @@ MODULE_DEVICE_TABLE(of, synps_edac_match);
static void ddr_poison_setup(struct synps_edac_priv *priv)
{
int col = 0, row = 0, bank = 0, bankgrp = 0, rank = 0, regval;
const struct synps_platform_data *p_data;
int index;
ulong hif_addr = 0;
hif_addr = priv->poison_addr >> 3;
p_data = priv->p_data;
if (p_data->get_mem_info)
hif_addr = p_data->get_mem_info(priv);
else
hif_addr = priv->poison_addr >> 3;
for (index = 0; index < DDR_MAX_ROW_SHIFT; index++) {
if (priv->row_shift[index])
......
......@@ -19,3 +19,7 @@ config AMD_ATL
Enable this option if using DRAM ECC on Zen-based systems
and OS-based error handling.
config AMD_ATL_PRM
depends on AMD_ATL && ACPI_PRMT
def_bool y
......@@ -15,4 +15,6 @@ amd_atl-y += map.o
amd_atl-y += system.o
amd_atl-y += umc.o
amd_atl-$(CONFIG_AMD_ATL_PRM) += prm.o
obj-$(CONFIG_AMD_ATL) += amd_atl.o
......@@ -282,6 +282,16 @@ unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err);
u64 add_base_and_hole(struct addr_ctx *ctx, u64 addr);
u64 remove_base_and_hole(struct addr_ctx *ctx, u64 addr);
#ifdef CONFIG_AMD_ATL_PRM
unsigned long prm_umc_norm_to_sys_addr(u8 socket_id, u64 umc_bank_inst_id, unsigned long addr);
#else
static inline unsigned long prm_umc_norm_to_sys_addr(u8 socket_id, u64 umc_bank_inst_id,
unsigned long addr)
{
return -ENODEV;
}
#endif
/*
* Make a gap in @data that is @num_bits long starting at @bit_num.
* e.g. data = 11111111'b
......
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* AMD Address Translation Library
*
* prm.c : Plumbing code for ACPI Platform Runtime Mechanism (PRM)
*
* Information on AMD PRM modules and handlers including the GUIDs and buffer
* structures used here are defined in the AMD ACPI Porting Guide in the
* chapter "Platform Runtime Mechanism Table (PRMT)"
*
* Copyright (c) 2024, Advanced Micro Devices, Inc.
* All Rights Reserved.
*
* Author: John Allen <john.allen@amd.com>
*/
#include "internal.h"
#include <linux/prmt.h>
/*
* PRM parameter buffer - normalized to system physical address, as described
* in the "PRM Parameter Buffer" section of the AMD ACPI Porting Guide.
*/
struct norm_to_sys_param_buf {
u64 norm_addr;
u8 socket;
u64 bank_id;
void *out_buf;
} __packed;
static const guid_t norm_to_sys_guid = GUID_INIT(0xE7180659, 0xA65D, 0x451D,
0x92, 0xCD, 0x2B, 0x56, 0xF1,
0x2B, 0xEB, 0xA6);
unsigned long prm_umc_norm_to_sys_addr(u8 socket_id, u64 bank_id, unsigned long addr)
{
struct norm_to_sys_param_buf p_buf;
unsigned long ret_addr;
int ret;
p_buf.norm_addr = addr;
p_buf.socket = socket_id;
p_buf.bank_id = bank_id;
p_buf.out_buf = &ret_addr;
ret = acpi_call_prm_handler(norm_to_sys_guid, &p_buf);
if (!ret)
return ret_addr;
if (ret == -ENODEV)
pr_debug("PRM module/handler not available\n");
else
pr_notice_once("PRM address translation failed\n");
return ret;
}
......@@ -401,9 +401,14 @@ unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err)
u8 coh_st_inst_id = get_coh_st_inst_id(err);
unsigned long addr = get_addr(err->addr);
u8 die_id = get_die_id(err);
unsigned long ret_addr;
pr_debug("socket_id=0x%x die_id=0x%x coh_st_inst_id=0x%x addr=0x%016lx",
socket_id, die_id, coh_st_inst_id, addr);
ret_addr = prm_umc_norm_to_sys_addr(socket_id, err->ipid, addr);
if (!IS_ERR_VALUE(ret_addr))
return ret_addr;
return norm_to_sys_addr(socket_id, die_id, coh_st_inst_id, addr);
}
......@@ -2,6 +2,11 @@
#ifdef CONFIG_ACPI_PRMT
void init_prmt(void);
int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer);
#else
static inline void init_prmt(void) { }
static inline int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer)
{
return -EOPNOTSUPP;
}
#endif
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment