[PATCH v6 RESEND 2/2] EDAC: Add EDAC driver for loongson memory controller

Zhao Qunqin posted 2 patches 1 month, 1 week ago
There is a newer version of this series
[PATCH v6 RESEND 2/2] EDAC: Add EDAC driver for loongson memory controller
Posted by Zhao Qunqin 1 month, 1 week ago
Reports single bit errors (CE) only.

Signed-off-by: Zhao Qunqin <zhaoqunqin@loongson.cn>
---
Changes in v6:
	- Change the Kconfig name to CONFIG_EDAC_LOONGSON

Changes in v5:
	- Drop the loongson_ prefix from all static functions.
	- Align function arguments on the opening brace.
	- Drop useless comments and useless wrapper. Drop side comments.
	- Reorder variable declarations.

Changes in v4:
	- None

Changes in v3:
	- Addressed review comments raised by Krzysztof and Huacai

Changes in v2:
	- Addressed review comments raised by Krzysztof

 MAINTAINERS                  |   1 +
 arch/loongarch/Kconfig       |   1 +
 drivers/edac/Kconfig         |   8 ++
 drivers/edac/Makefile        |   1 +
 drivers/edac/loongson_edac.c | 168 +++++++++++++++++++++++++++++++++++
 5 files changed, 179 insertions(+)
 create mode 100644 drivers/edac/loongson_edac.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 6cc8cfc8f..5b4526638 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13242,6 +13242,7 @@ M:	Zhao Qunqin <zhaoqunqin@loongson.cn>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/edac/loongson,ls3a5000-mc-edac.yaml
+F:	drivers/edac/loongson_edac.c
 
 LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI)
 M:	Sathya Prakash <sathya.prakash@broadcom.com>
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 70f169210..9c135f1a2 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -181,6 +181,7 @@ config LOONGARCH
 	select PCI_MSI_ARCH_FALLBACKS
 	select PCI_QUIRKS
 	select PERF_USE_VMALLOC
+	select EDAC_SUPPORT
 	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_ARCH_UNALIGN_ALLOW
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 81af6c344..1cf432102 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -564,5 +564,13 @@ config EDAC_VERSAL
 	  Support injecting both correctable and uncorrectable errors
 	  for debugging purposes.
 
+config EDAC_LOONGSON
+	tristate "Loongson Memory Controller"
+	depends on LOONGARCH || COMPILE_TEST
+	help
+	  Support for error detection and correction on the Loongson
+	  family memory controller. This driver reports single bit
+	  errors (CE) only. Loongson-3A5000/3C5000/3D5000/3C5000L/3A6000/3C6000
+	  are compatible.
 
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index faf310eec..f8bdbc895 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -88,3 +88,4 @@ obj-$(CONFIG_EDAC_DMC520)		+= dmc520_edac.o
 obj-$(CONFIG_EDAC_NPCM)			+= npcm_edac.o
 obj-$(CONFIG_EDAC_ZYNQMP)		+= zynqmp_edac.o
 obj-$(CONFIG_EDAC_VERSAL)		+= versal_edac.o
+obj-$(CONFIG_EDAC_LOONGSON)		+= loongson_edac.o
diff --git a/drivers/edac/loongson_edac.c b/drivers/edac/loongson_edac.c
new file mode 100644
index 000000000..2721dfba5
--- /dev/null
+++ b/drivers/edac/loongson_edac.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Loongson Technology Corporation Limited.
+ */
+
+#include <linux/edac.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+
+#include "edac_module.h"
+
+enum ecc_index {
+	ECC_SET = 0,
+	ECC_RESERVED,
+	ECC_COUNT,
+	ECC_CS_COUNT,
+	ECC_CODE,
+	ECC_ADDR,
+	ECC_DATA0,
+	ECC_DATA1,
+	ECC_DATA2,
+	ECC_DATA3,
+};
+
+struct loongson_edac_pvt {
+	u64 *ecc_base;
+	int last_ce_count;
+};
+
+static int read_ecc(struct mem_ctl_info *mci)
+{
+	struct loongson_edac_pvt *pvt = mci->pvt_info;
+	u64 ecc;
+	int cs;
+
+	if (!pvt->ecc_base)
+		return pvt->last_ce_count;
+
+	ecc = pvt->ecc_base[ECC_CS_COUNT];
+	/* cs0 -- cs3 */
+	cs = ecc & 0xff;
+	cs += (ecc >> 8) & 0xff;
+	cs += (ecc >> 16) & 0xff;
+	cs += (ecc >> 24) & 0xff;
+
+	return cs;
+}
+
+static void edac_check(struct mem_ctl_info *mci)
+{
+	struct loongson_edac_pvt *pvt = mci->pvt_info;
+	int new, add;
+
+	new = read_ecc(mci);
+	add = new - pvt->last_ce_count;
+	pvt->last_ce_count = new;
+	if (add <= 0)
+		return;
+
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, add,
+			     0, 0, 0, 0, 0, -1, "error", "");
+	edac_mc_printk(mci, KERN_INFO, "add: %d", add);
+}
+
+static int get_dimm_config(struct mem_ctl_info *mci)
+{
+	struct dimm_info *dimm;
+	u32 size, npages;
+
+	/* size not used */
+	size = -1;
+	npages = MiB_TO_PAGES(size);
+
+	dimm = edac_get_dimm(mci, 0, 0, 0);
+	dimm->nr_pages = npages;
+	snprintf(dimm->label, sizeof(dimm->label),
+		 "MC#%uChannel#%u_DIMM#%u", mci->mc_idx, 0, 0);
+	dimm->grain = 8;
+
+	return 0;
+}
+
+static void pvt_init(struct mem_ctl_info *mci, u64 *vbase)
+{
+	struct loongson_edac_pvt *pvt = mci->pvt_info;
+
+	pvt->ecc_base = vbase;
+	pvt->last_ce_count = read_ecc(mci);
+}
+
+static int edac_probe(struct platform_device *pdev)
+{
+	struct edac_mc_layer layers[2];
+	struct loongson_edac_pvt *pvt;
+	struct mem_ctl_info *mci;
+	u64 *vbase;
+	int ret;
+
+	vbase = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(vbase))
+		return PTR_ERR(vbase);
+
+	/* allocate a new MC control structure */
+	layers[0].type = EDAC_MC_LAYER_CHANNEL;
+	layers[0].size = 1;
+	layers[0].is_virt_csrow = false;
+	layers[1].type = EDAC_MC_LAYER_SLOT;
+	layers[1].size = 1;
+	layers[1].is_virt_csrow = true;
+	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(*pvt));
+	if (mci == NULL)
+		return -ENOMEM;
+
+	mci->mc_idx = edac_device_alloc_index();
+	mci->mtype_cap = MEM_FLAG_RDDR4;
+	mci->edac_ctl_cap = EDAC_FLAG_NONE;
+	mci->edac_cap = EDAC_FLAG_NONE;
+	mci->mod_name = "loongson_edac.c";
+	mci->ctl_name = "loongson_edac_ctl";
+	mci->dev_name = "loongson_edac_dev";
+	mci->ctl_page_to_phys = NULL;
+	mci->pdev = &pdev->dev;
+	mci->error_desc.grain = 8;
+	/* Set the function pointer to an actual operation function */
+	mci->edac_check = edac_check;
+
+	pvt_init(mci, vbase);
+	get_dimm_config(mci);
+
+	ret = edac_mc_add_mc(mci);
+	if (ret) {
+		edac_dbg(0, "MC: failed edac_mc_add_mc()\n");
+		edac_mc_free(mci);
+		return ret;
+	}
+	edac_op_state = EDAC_OPSTATE_POLL;
+
+	return 0;
+}
+
+static void edac_remove(struct platform_device *pdev)
+{
+	struct mem_ctl_info *mci = edac_mc_del_mc(&pdev->dev);
+
+	if (mci)
+		edac_mc_free(mci);
+}
+
+static const struct of_device_id loongson_edac_of_match[] = {
+	{ .compatible = "loongson,ls3a5000-mc-edac", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, loongson_edac_of_match);
+
+static struct platform_driver loongson_edac_driver = {
+	.probe		= edac_probe,
+	.remove		= edac_remove,
+	.driver		= {
+		.name	= "loongson-mc-edac",
+		.of_match_table = loongson_edac_of_match,
+	},
+};
+module_platform_driver(loongson_edac_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Zhao Qunqin <zhaoqunqin@loongson.cn>");
+MODULE_DESCRIPTION("EDAC driver for loongson memory controller");
-- 
2.43.0
Re: [PATCH v6 RESEND 2/2] EDAC: Add EDAC driver for loongson memory controller
Posted by kernel test robot 1 month, 1 week ago
Hi Zhao,

kernel test robot noticed the following build warnings:

[auto build test WARNING on 61124f42dcaa30f58a8b47a2b69ddb80260677c7]

url:    https://github.com/intel-lab-lkp/linux/commits/Zhao-Qunqin/dt-bindings-EDAC-for-ls3a5000-memory-controller/20241018-094803
base:   61124f42dcaa30f58a8b47a2b69ddb80260677c7
patch link:    https://lore.kernel.org/r/20241018014542.27283-3-zhaoqunqin%40loongson.cn
patch subject: [PATCH v6 RESEND 2/2] EDAC: Add EDAC driver for loongson memory controller
config: arm64-randconfig-r113-20241019 (https://download.01.org/0day-ci/archive/20241020/202410200949.GpnHSLfV-lkp@intel.com/config)
compiler: aarch64-linux-gcc (GCC) 14.1.0
reproduce: (https://download.01.org/0day-ci/archive/20241020/202410200949.GpnHSLfV-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202410200949.GpnHSLfV-lkp@intel.com/

sparse warnings: (new ones prefixed by >>)
>> drivers/edac/loongson_edac.c:100:15: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected unsigned long long [usertype] *vbase @@     got void [noderef] __iomem * @@
   drivers/edac/loongson_edac.c:100:15: sparse:     expected unsigned long long [usertype] *vbase
   drivers/edac/loongson_edac.c:100:15: sparse:     got void [noderef] __iomem *

vim +100 drivers/edac/loongson_edac.c

    91	
    92	static int edac_probe(struct platform_device *pdev)
    93	{
    94		struct edac_mc_layer layers[2];
    95		struct loongson_edac_pvt *pvt;
    96		struct mem_ctl_info *mci;
    97		u64 *vbase;
    98		int ret;
    99	
 > 100		vbase = devm_platform_ioremap_resource(pdev, 0);
   101		if (IS_ERR(vbase))
   102			return PTR_ERR(vbase);
   103	
   104		/* allocate a new MC control structure */
   105		layers[0].type = EDAC_MC_LAYER_CHANNEL;
   106		layers[0].size = 1;
   107		layers[0].is_virt_csrow = false;
   108		layers[1].type = EDAC_MC_LAYER_SLOT;
   109		layers[1].size = 1;
   110		layers[1].is_virt_csrow = true;
   111		mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(*pvt));
   112		if (mci == NULL)
   113			return -ENOMEM;
   114	
   115		mci->mc_idx = edac_device_alloc_index();
   116		mci->mtype_cap = MEM_FLAG_RDDR4;
   117		mci->edac_ctl_cap = EDAC_FLAG_NONE;
   118		mci->edac_cap = EDAC_FLAG_NONE;
   119		mci->mod_name = "loongson_edac.c";
   120		mci->ctl_name = "loongson_edac_ctl";
   121		mci->dev_name = "loongson_edac_dev";
   122		mci->ctl_page_to_phys = NULL;
   123		mci->pdev = &pdev->dev;
   124		mci->error_desc.grain = 8;
   125		/* Set the function pointer to an actual operation function */
   126		mci->edac_check = edac_check;
   127	
   128		pvt_init(mci, vbase);
   129		get_dimm_config(mci);
   130	
   131		ret = edac_mc_add_mc(mci);
   132		if (ret) {
   133			edac_dbg(0, "MC: failed edac_mc_add_mc()\n");
   134			edac_mc_free(mci);
   135			return ret;
   136		}
   137		edac_op_state = EDAC_OPSTATE_POLL;
   138	
   139		return 0;
   140	}
   141	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki