summary refs log tree commit diff
path: root/drivers/edac
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-10-29 15:16:01 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-10-29 15:16:01 -0700
commitb22b6beae6116e3a9c46ced312c626f6737a3fa6 (patch)
treec92228669e0444d91fd1445bc562351fd69b58cc /drivers/edac
parent53b7a3b7ec00f207c18e71f58ef2bca48635c622 (diff)
parentc1a92909dbc2090753ff6224971d9b8ae5f93c97 (diff)
downloadlinux-b22b6beae6116e3a9c46ced312c626f6737a3fa6.tar.gz
Merge tag 'armsoc-drivers' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM SoC driver updates from Arnd Bergmann:
 "The most noteworthy SoC driver changes this time include:

   - The TEE subsystem gains an in-kernel interface to access the TEE
     from device drivers.

   - The reset controller subsystem gains a driver for the Qualcomm
     Snapdragon 845 Power Domain Controller.

   - The Xilinx Zynq platform now has a firmware interface for its
     platform management unit. This contains a firmware "ioctl"
     interface that was a little controversial at first, but the version
     we merged solved that by not exposing arbitrary firmware calls to
     user space.

   - The Amlogic Meson platform gains a "canvas" driver that is used for
     video processing and shared between different high-level drivers.

  The rest is more of the usual, mostly related to SoC specific power
  management support and core drivers in drivers/soc:

   - Several Renesas SoCs (RZ/G1N, RZ/G2M, R-Car V3M, RZ/A2M) gain new
     features related to power and reset control.

   - The Mediatek mt8183 and mt6765 SoC platforms gain support for their
     respective power management chips.

   - A new driver for NXP i.MX8, which need a firmware interface for
     power management.

   - The SCPI firmware interface now contains support estimating power
     usage of performance states

   - The NVIDIA Tegra "pmc" driver gains a few new features, in
     particular a pinctrl interface for configuring the pads.

   - Lots of small changes for Qualcomm, in particular the "smem" device
     driver.

   - Some cleanups for the TI OMAP series related to their sysc
     controller.

  Additional cleanups and bugfixes in SoC specific drivers include the
  Meson, Keystone, NXP, AT91, Sunxi, Actions, and Tegra platforms"

* tag 'armsoc-drivers' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (129 commits)
  firmware: tegra: bpmp: Implement suspend/resume support
  drivers: clk: Add ZynqMP clock driver
  dt-bindings: clock: Add bindings for ZynqMP clock driver
  firmware: xilinx: Add zynqmp IOCTL API for device control
  Documentation: xilinx: Add documentation for eemi APIs
  MAINTAINERS: imx: include drivers/firmware/imx path
  firmware: imx: add misc svc support
  firmware: imx: add SCU firmware driver support
  reset: Fix potential use-after-free in __of_reset_control_get()
  dt-bindings: arm: fsl: add scu binding doc
  soc: fsl: qbman: add interrupt coalesce changing APIs
  soc: fsl: bman_portals: defer probe after bman's probe
  soc: fsl: qbman: Use last response to determine valid bit
  soc: fsl: qbman: Add 64 bit DMA addressing requirement to QBMan
  soc: fsl: qbman: replace CPU 0 with any online CPU in hotplug handlers
  soc: fsl: qbman: Check if CPU is offline when initializing portals
  reset: qcom: PDC Global (Power Domain Controller) reset controller
  dt-bindings: reset: Add PDC Global binding for SDM845 SoCs
  reset: Grammar s/more then once/more than once/
  bus: ti-sysc: Just use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS
  ...
Diffstat (limited to 'drivers/edac')
-rw-r--r--drivers/edac/Kconfig14
-rw-r--r--drivers/edac/Makefile1
-rw-r--r--drivers/edac/qcom_edac.c414
3 files changed, 429 insertions, 0 deletions
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 57304b2e989f..df9467eef32a 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -460,4 +460,18 @@ config EDAC_TI
 	  Support for error detection and correction on the
           TI SoCs.
 
+config EDAC_QCOM
+	tristate "QCOM EDAC Controller"
+	depends on ARCH_QCOM && QCOM_LLCC
+	help
+	  Support for error detection and correction on the
+	  Qualcomm Technologies, Inc. SoCs.
+
+	  This driver reports Single Bit Errors (SBEs) and Double Bit Errors (DBEs).
+	  As of now, it supports error reporting for Last Level Cache Controller (LLCC)
+	  of Tag RAM and Data RAM.
+
+	  For debugging issues having to do with stability and overall system
+	  health, you should probably say 'Y' here.
+
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 02b43a7d8c3e..716096d08ea0 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -77,3 +77,4 @@ obj-$(CONFIG_EDAC_ALTERA)		+= altera_edac.o
 obj-$(CONFIG_EDAC_SYNOPSYS)		+= synopsys_edac.o
 obj-$(CONFIG_EDAC_XGENE)		+= xgene_edac.o
 obj-$(CONFIG_EDAC_TI)			+= ti_edac.o
+obj-$(CONFIG_EDAC_QCOM)			+= qcom_edac.o
diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c
new file mode 100644
index 000000000000..82bd775124f2
--- /dev/null
+++ b/drivers/edac/qcom_edac.c
@@ -0,0 +1,414 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/edac.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/soc/qcom/llcc-qcom.h>
+
+#include "edac_mc.h"
+#include "edac_device.h"
+
+#define EDAC_LLCC                       "qcom_llcc"
+
+#define LLCC_ERP_PANIC_ON_UE            1
+
+#define TRP_SYN_REG_CNT                 6
+#define DRP_SYN_REG_CNT                 8
+
+#define LLCC_COMMON_STATUS0             0x0003000c
+#define LLCC_LB_CNT_MASK                GENMASK(31, 28)
+#define LLCC_LB_CNT_SHIFT               28
+
+/* Single & double bit syndrome register offsets */
+#define TRP_ECC_SB_ERR_SYN0             0x0002304c
+#define TRP_ECC_DB_ERR_SYN0             0x00020370
+#define DRP_ECC_SB_ERR_SYN0             0x0004204c
+#define DRP_ECC_DB_ERR_SYN0             0x00042070
+
+/* Error register offsets */
+#define TRP_ECC_ERROR_STATUS1           0x00020348
+#define TRP_ECC_ERROR_STATUS0           0x00020344
+#define DRP_ECC_ERROR_STATUS1           0x00042048
+#define DRP_ECC_ERROR_STATUS0           0x00042044
+
+/* TRP, DRP interrupt register offsets */
+#define DRP_INTERRUPT_STATUS            0x00041000
+#define TRP_INTERRUPT_0_STATUS          0x00020480
+#define DRP_INTERRUPT_CLEAR             0x00041008
+#define DRP_ECC_ERROR_CNTR_CLEAR        0x00040004
+#define TRP_INTERRUPT_0_CLEAR           0x00020484
+#define TRP_ECC_ERROR_CNTR_CLEAR        0x00020440
+
+/* Mask and shift macros */
+#define ECC_DB_ERR_COUNT_MASK           GENMASK(4, 0)
+#define ECC_DB_ERR_WAYS_MASK            GENMASK(31, 16)
+#define ECC_DB_ERR_WAYS_SHIFT           BIT(4)
+
+#define ECC_SB_ERR_COUNT_MASK           GENMASK(23, 16)
+#define ECC_SB_ERR_COUNT_SHIFT          BIT(4)
+#define ECC_SB_ERR_WAYS_MASK            GENMASK(15, 0)
+
+#define SB_ECC_ERROR                    BIT(0)
+#define DB_ECC_ERROR                    BIT(1)
+
+#define DRP_TRP_INT_CLEAR               GENMASK(1, 0)
+#define DRP_TRP_CNT_CLEAR               GENMASK(1, 0)
+
+/* Config registers offsets*/
+#define DRP_ECC_ERROR_CFG               0x00040000
+
+/* Tag RAM, Data RAM interrupt register offsets */
+#define CMN_INTERRUPT_0_ENABLE          0x0003001c
+#define CMN_INTERRUPT_2_ENABLE          0x0003003c
+#define TRP_INTERRUPT_0_ENABLE          0x00020488
+#define DRP_INTERRUPT_ENABLE            0x0004100c
+
+#define SB_ERROR_THRESHOLD              0x1
+#define SB_ERROR_THRESHOLD_SHIFT        24
+#define SB_DB_TRP_INTERRUPT_ENABLE      0x3
+#define TRP0_INTERRUPT_ENABLE           0x1
+#define DRP0_INTERRUPT_ENABLE           BIT(6)
+#define SB_DB_DRP_INTERRUPT_ENABLE      0x3
+
+enum {
+	LLCC_DRAM_CE = 0,
+	LLCC_DRAM_UE,
+	LLCC_TRAM_CE,
+	LLCC_TRAM_UE,
+};
+
+static const struct llcc_edac_reg_data edac_reg_data[] = {
+	[LLCC_DRAM_CE] = {
+		.name = "DRAM Single-bit",
+		.synd_reg = DRP_ECC_SB_ERR_SYN0,
+		.count_status_reg = DRP_ECC_ERROR_STATUS1,
+		.ways_status_reg = DRP_ECC_ERROR_STATUS0,
+		.reg_cnt = DRP_SYN_REG_CNT,
+		.count_mask = ECC_SB_ERR_COUNT_MASK,
+		.ways_mask = ECC_SB_ERR_WAYS_MASK,
+		.count_shift = ECC_SB_ERR_COUNT_SHIFT,
+	},
+	[LLCC_DRAM_UE] = {
+		.name = "DRAM Double-bit",
+		.synd_reg = DRP_ECC_DB_ERR_SYN0,
+		.count_status_reg = DRP_ECC_ERROR_STATUS1,
+		.ways_status_reg = DRP_ECC_ERROR_STATUS0,
+		.reg_cnt = DRP_SYN_REG_CNT,
+		.count_mask = ECC_DB_ERR_COUNT_MASK,
+		.ways_mask = ECC_DB_ERR_WAYS_MASK,
+		.ways_shift = ECC_DB_ERR_WAYS_SHIFT,
+	},
+	[LLCC_TRAM_CE] = {
+		.name = "TRAM Single-bit",
+		.synd_reg = TRP_ECC_SB_ERR_SYN0,
+		.count_status_reg = TRP_ECC_ERROR_STATUS1,
+		.ways_status_reg = TRP_ECC_ERROR_STATUS0,
+		.reg_cnt = TRP_SYN_REG_CNT,
+		.count_mask = ECC_SB_ERR_COUNT_MASK,
+		.ways_mask = ECC_SB_ERR_WAYS_MASK,
+		.count_shift = ECC_SB_ERR_COUNT_SHIFT,
+	},
+	[LLCC_TRAM_UE] = {
+		.name = "TRAM Double-bit",
+		.synd_reg = TRP_ECC_DB_ERR_SYN0,
+		.count_status_reg = TRP_ECC_ERROR_STATUS1,
+		.ways_status_reg = TRP_ECC_ERROR_STATUS0,
+		.reg_cnt = TRP_SYN_REG_CNT,
+		.count_mask = ECC_DB_ERR_COUNT_MASK,
+		.ways_mask = ECC_DB_ERR_WAYS_MASK,
+		.ways_shift = ECC_DB_ERR_WAYS_SHIFT,
+	},
+};
+
+static int qcom_llcc_core_setup(struct regmap *llcc_bcast_regmap)
+{
+	u32 sb_err_threshold;
+	int ret;
+
+	/*
+	 * Configure interrupt enable registers such that Tag, Data RAM related
+	 * interrupts are propagated to interrupt controller for servicing
+	 */
+	ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE,
+				 TRP0_INTERRUPT_ENABLE,
+				 TRP0_INTERRUPT_ENABLE);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(llcc_bcast_regmap, TRP_INTERRUPT_0_ENABLE,
+				 SB_DB_TRP_INTERRUPT_ENABLE,
+				 SB_DB_TRP_INTERRUPT_ENABLE);
+	if (ret)
+		return ret;
+
+	sb_err_threshold = (SB_ERROR_THRESHOLD << SB_ERROR_THRESHOLD_SHIFT);
+	ret = regmap_write(llcc_bcast_regmap, DRP_ECC_ERROR_CFG,
+			   sb_err_threshold);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE,
+				 DRP0_INTERRUPT_ENABLE,
+				 DRP0_INTERRUPT_ENABLE);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(llcc_bcast_regmap, DRP_INTERRUPT_ENABLE,
+			   SB_DB_DRP_INTERRUPT_ENABLE);
+	return ret;
+}
+
+/* Clear the error interrupt and counter registers */
+static int
+qcom_llcc_clear_error_status(int err_type, struct llcc_drv_data *drv)
+{
+	int ret = 0;
+
+	switch (err_type) {
+	case LLCC_DRAM_CE:
+	case LLCC_DRAM_UE:
+		ret = regmap_write(drv->bcast_regmap, DRP_INTERRUPT_CLEAR,
+				   DRP_TRP_INT_CLEAR);
+		if (ret)
+			return ret;
+
+		ret = regmap_write(drv->bcast_regmap, DRP_ECC_ERROR_CNTR_CLEAR,
+				   DRP_TRP_CNT_CLEAR);
+		if (ret)
+			return ret;
+		break;
+	case LLCC_TRAM_CE:
+	case LLCC_TRAM_UE:
+		ret = regmap_write(drv->bcast_regmap, TRP_INTERRUPT_0_CLEAR,
+				   DRP_TRP_INT_CLEAR);
+		if (ret)
+			return ret;
+
+		ret = regmap_write(drv->bcast_regmap, TRP_ECC_ERROR_CNTR_CLEAR,
+				   DRP_TRP_CNT_CLEAR);
+		if (ret)
+			return ret;
+		break;
+	default:
+		ret = -EINVAL;
+		edac_printk(KERN_CRIT, EDAC_LLCC, "Unexpected error type: %d\n",
+			    err_type);
+	}
+	return ret;
+}
+
+/* Dump Syndrome registers data for Tag RAM, Data RAM bit errors*/
+static int
+dump_syn_reg_values(struct llcc_drv_data *drv, u32 bank, int err_type)
+{
+	struct llcc_edac_reg_data reg_data = edac_reg_data[err_type];
+	int err_cnt, err_ways, ret, i;
+	u32 synd_reg, synd_val;
+
+	for (i = 0; i < reg_data.reg_cnt; i++) {
+		synd_reg = reg_data.synd_reg + (i * 4);
+		ret = regmap_read(drv->regmap, drv->offsets[bank] + synd_reg,
+				  &synd_val);
+		if (ret)
+			goto clear;
+
+		edac_printk(KERN_CRIT, EDAC_LLCC, "%s: ECC_SYN%d: 0x%8x\n",
+			    reg_data.name, i, synd_val);
+	}
+
+	ret = regmap_read(drv->regmap,
+			  drv->offsets[bank] + reg_data.count_status_reg,
+			  &err_cnt);
+	if (ret)
+		goto clear;
+
+	err_cnt &= reg_data.count_mask;
+	err_cnt >>= reg_data.count_shift;
+	edac_printk(KERN_CRIT, EDAC_LLCC, "%s: Error count: 0x%4x\n",
+		    reg_data.name, err_cnt);
+
+	ret = regmap_read(drv->regmap,
+			  drv->offsets[bank] + reg_data.ways_status_reg,
+			  &err_ways);
+	if (ret)
+		goto clear;
+
+	err_ways &= reg_data.ways_mask;
+	err_ways >>= reg_data.ways_shift;
+
+	edac_printk(KERN_CRIT, EDAC_LLCC, "%s: Error ways: 0x%4x\n",
+		    reg_data.name, err_ways);
+
+clear:
+	return qcom_llcc_clear_error_status(err_type, drv);
+}
+
+static int
+dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank)
+{
+	struct llcc_drv_data *drv = edev_ctl->pvt_info;
+	int ret;
+
+	ret = dump_syn_reg_values(drv, bank, err_type);
+	if (ret)
+		return ret;
+
+	switch (err_type) {
+	case LLCC_DRAM_CE:
+		edac_device_handle_ce(edev_ctl, 0, bank,
+				      "LLCC Data RAM correctable Error");
+		break;
+	case LLCC_DRAM_UE:
+		edac_device_handle_ue(edev_ctl, 0, bank,
+				      "LLCC Data RAM uncorrectable Error");
+		break;
+	case LLCC_TRAM_CE:
+		edac_device_handle_ce(edev_ctl, 0, bank,
+				      "LLCC Tag RAM correctable Error");
+		break;
+	case LLCC_TRAM_UE:
+		edac_device_handle_ue(edev_ctl, 0, bank,
+				      "LLCC Tag RAM uncorrectable Error");
+		break;
+	default:
+		ret = -EINVAL;
+		edac_printk(KERN_CRIT, EDAC_LLCC, "Unexpected error type: %d\n",
+			    err_type);
+	}
+
+	return ret;
+}
+
+static irqreturn_t
+llcc_ecc_irq_handler(int irq, void *edev_ctl)
+{
+	struct edac_device_ctl_info *edac_dev_ctl = edev_ctl;
+	struct llcc_drv_data *drv = edac_dev_ctl->pvt_info;
+	irqreturn_t irq_rc = IRQ_NONE;
+	u32 drp_error, trp_error, i;
+	bool irq_handled;
+	int ret;
+
+	/* Iterate over the banks and look for Tag RAM or Data RAM errors */
+	for (i = 0; i < drv->num_banks; i++) {
+		ret = regmap_read(drv->regmap,
+				  drv->offsets[i] + DRP_INTERRUPT_STATUS,
+				  &drp_error);
+
+		if (!ret && (drp_error & SB_ECC_ERROR)) {
+			edac_printk(KERN_CRIT, EDAC_LLCC,
+				    "Single Bit Error detected in Data RAM\n");
+			ret = dump_syn_reg(edev_ctl, LLCC_DRAM_CE, i);
+		} else if (!ret && (drp_error & DB_ECC_ERROR)) {
+			edac_printk(KERN_CRIT, EDAC_LLCC,
+				    "Double Bit Error detected in Data RAM\n");
+			ret = dump_syn_reg(edev_ctl, LLCC_DRAM_UE, i);
+		}
+		if (!ret)
+			irq_handled = true;
+
+		ret = regmap_read(drv->regmap,
+				  drv->offsets[i] + TRP_INTERRUPT_0_STATUS,
+				  &trp_error);
+
+		if (!ret && (trp_error & SB_ECC_ERROR)) {
+			edac_printk(KERN_CRIT, EDAC_LLCC,
+				    "Single Bit Error detected in Tag RAM\n");
+			ret = dump_syn_reg(edev_ctl, LLCC_TRAM_CE, i);
+		} else if (!ret && (trp_error & DB_ECC_ERROR)) {
+			edac_printk(KERN_CRIT, EDAC_LLCC,
+				    "Double Bit Error detected in Tag RAM\n");
+			ret = dump_syn_reg(edev_ctl, LLCC_TRAM_UE, i);
+		}
+		if (!ret)
+			irq_handled = true;
+	}
+
+	if (irq_handled)
+		irq_rc = IRQ_HANDLED;
+
+	return irq_rc;
+}
+
+static int qcom_llcc_edac_probe(struct platform_device *pdev)
+{
+	struct llcc_drv_data *llcc_driv_data = pdev->dev.platform_data;
+	struct edac_device_ctl_info *edev_ctl;
+	struct device *dev = &pdev->dev;
+	int ecc_irq;
+	int rc;
+
+	rc = qcom_llcc_core_setup(llcc_driv_data->bcast_regmap);
+	if (rc)
+		return rc;
+
+	/* Allocate edac control info */
+	edev_ctl = edac_device_alloc_ctl_info(0, "qcom-llcc", 1, "bank",
+					      llcc_driv_data->num_banks, 1,
+					      NULL, 0,
+					      edac_device_alloc_index());
+
+	if (!edev_ctl)
+		return -ENOMEM;
+
+	edev_ctl->dev = dev;
+	edev_ctl->mod_name = dev_name(dev);
+	edev_ctl->dev_name = dev_name(dev);
+	edev_ctl->ctl_name = "llcc";
+	edev_ctl->panic_on_ue = LLCC_ERP_PANIC_ON_UE;
+	edev_ctl->pvt_info = llcc_driv_data;
+
+	rc = edac_device_add_device(edev_ctl);
+	if (rc)
+		goto out_mem;
+
+	platform_set_drvdata(pdev, edev_ctl);
+
+	/* Request for ecc irq */
+	ecc_irq = llcc_driv_data->ecc_irq;
+	if (ecc_irq < 0) {
+		rc = -ENODEV;
+		goto out_dev;
+	}
+	rc = devm_request_irq(dev, ecc_irq, llcc_ecc_irq_handler,
+			      IRQF_TRIGGER_HIGH, "llcc_ecc", edev_ctl);
+	if (rc)
+		goto out_dev;
+
+	return rc;
+
+out_dev:
+	edac_device_del_device(edev_ctl->dev);
+out_mem:
+	edac_device_free_ctl_info(edev_ctl);
+
+	return rc;
+}
+
+static int qcom_llcc_edac_remove(struct platform_device *pdev)
+{
+	struct edac_device_ctl_info *edev_ctl = dev_get_drvdata(&pdev->dev);
+
+	edac_device_del_device(edev_ctl->dev);
+	edac_device_free_ctl_info(edev_ctl);
+
+	return 0;
+}
+
+static struct platform_driver qcom_llcc_edac_driver = {
+	.probe = qcom_llcc_edac_probe,
+	.remove = qcom_llcc_edac_remove,
+	.driver = {
+		.name = "qcom_llcc_edac",
+	},
+};
+module_platform_driver(qcom_llcc_edac_driver);
+
+MODULE_DESCRIPTION("QCOM EDAC driver");
+MODULE_LICENSE("GPL v2");