Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757790Ab3J2AcU (ORCPT ); Mon, 28 Oct 2013 20:32:20 -0400 Received: from smtp.codeaurora.org ([198.145.11.231]:39811 "EHLO smtp.codeaurora.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756749Ab3J2Abf (ORCPT ); Mon, 28 Oct 2013 20:31:35 -0400 From: Stephen Boyd To: linux-edac@vger.kernel.org Cc: linux-kernel@vger.kernel.org, linux-arm-msm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Stepan Moskovchenko Subject: [PATCH 5/6] edac: Add support for Krait CPU cache error detection Date: Mon, 28 Oct 2013 17:31:29 -0700 Message-Id: <1383006690-6754-6-git-send-email-sboyd@codeaurora.org> X-Mailer: git-send-email 1.8.4.1.600.g3d092bf In-Reply-To: <1383006690-6754-1-git-send-email-sboyd@codeaurora.org> References: <1383006690-6754-1-git-send-email-sboyd@codeaurora.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 11094 Lines: 393 Add support for the Krait CPU cache error detection. This is a simplified version of the code originally written by Stepan Moskovchenko[1] ported to the EDAC device framework. [1] https://www.codeaurora.org/cgit/quic/la/kernel/msm/tree/arch/arm/mach-msm/cache_erp.c?h=msm-3.4 Cc: Stepan Moskovchenko Signed-off-by: Stephen Boyd --- drivers/edac/Kconfig | 8 ++ drivers/edac/Makefile | 2 + drivers/edac/krait_edac.c | 336 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 346 insertions(+) create mode 100644 drivers/edac/krait_edac.c diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 878f090..68f612d 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -368,4 +368,12 @@ config EDAC_OCTEON_PCI Support for error detection and correction on the Cavium Octeon family of SOCs. +config EDAC_KRAIT_CACHE + tristate "Krait L1/L2 Cache" + depends on EDAC_MM_EDAC && ARCH_MSM + select KRAIT_L2_ACCESSORS + help + Support for error detection and correction on the + Krait L1/L2 cache controller. + endif # EDAC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 4154ed6..b6ea505 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -64,3 +64,5 @@ obj-$(CONFIG_EDAC_OCTEON_PC) += octeon_edac-pc.o obj-$(CONFIG_EDAC_OCTEON_L2C) += octeon_edac-l2c.o obj-$(CONFIG_EDAC_OCTEON_LMC) += octeon_edac-lmc.o obj-$(CONFIG_EDAC_OCTEON_PCI) += octeon_edac-pci.o + +obj-$(CONFIG_EDAC_KRAIT_CACHE) += krait_edac.o diff --git a/drivers/edac/krait_edac.c b/drivers/edac/krait_edac.c new file mode 100644 index 0000000..89380a1 --- /dev/null +++ b/drivers/edac/krait_edac.c @@ -0,0 +1,336 @@ +/* Copyright (c) 2012-2013, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "edac_core.h" + +#define CESR_DCTPE BIT(0) +#define CESR_DCDPE BIT(1) +#define CESR_ICTPE BIT(2) +#define CESR_ICDPE BIT(3) +#define CESR_DCTE (BIT(4) | BIT(5)) +#define CESR_ICTE (BIT(6) | BIT(7)) +#define CESR_TLBMH BIT(16) +#define CESR_I_MASK 0x000000cc +/* Print a message for everything but TLB MH events */ +#define CESR_PRINT_MASK 0x000000ff + +#define L2ESR 0x204 +#define L2ESR_MPDCD BIT(0) +#define L2ESR_MPSLV BIT(1) +#define L2ESR_TSESB BIT(2) +#define L2ESR_TSEDB BIT(3) +#define L2ESR_DSESB BIT(4) +#define L2ESR_DSEDB BIT(5) +#define L2ESR_MSE BIT(6) +#define L2ESR_MPLDREXNOK BIT(8) +#define L2ESR_CPU_MASK 0xf +#define L2ESR_CPU_SHIFT 16 +#define L2ESR_SP BIT(20) + +#define L2ESYNR0 0x208 +#define L2ESYNR1 0x209 +#define L2EAR0 0x20c +#define L2EAR1 0x20d + +struct krait_edac { + int l1_irq; + struct edac_device_ctl_info * __percpu *edev; + struct notifier_block notifier; +}; + +struct krait_edac_error { + const char * const msg; + void (*func)(struct edac_device_ctl_info *edac_dev, + int inst_nr, int block_nr, const char *msg); +}; + +static unsigned int read_cesr(void) +{ + unsigned int cesr; + + asm volatile ("mrc p15, 7, %0, c15, c0, 1" : "=r" (cesr)); + return cesr; +} + +static void write_cesr(unsigned int cesr) +{ + asm volatile ("mcr p15, 7, %0, c15, c0, 1" : : "r" (cesr)); +} + +static unsigned int read_cesynr(void) +{ + unsigned int cesynr; + + asm volatile ("mrc p15, 7, %0, c15, c0, 3" : "=r" (cesynr)); + return cesynr; +} + +static irqreturn_t krait_l1_irq(int irq, void *dev_id) +{ + struct edac_device_ctl_info *edac = dev_id; + unsigned int cesr = read_cesr(); + unsigned int i_cesynr, d_cesynr; + unsigned int cpu = smp_processor_id(); + int print_regs = cesr & CESR_PRINT_MASK; + int i; + static const struct krait_edac_error errors[] = { + { "D-cache tag parity error", edac_device_handle_ue }, + { "D-cache data parity error", edac_device_handle_ue }, + { "I-cache tag parity error", edac_device_handle_ce }, + { "I-cache data parity error", edac_device_handle_ce }, + { "D-cache tag timing error", edac_device_handle_ue }, + { "D-cache data timing error", edac_device_handle_ue }, + { "I-cache tag timing error", edac_device_handle_ce }, + { "I-cache data timing error", edac_device_handle_ce } + }; + + if (print_regs) { + pr_alert("L1 / TLB Error detected on CPU %d!\n", cpu); + pr_alert("CESR = 0x%08x\n", cesr); + pr_alert("MIDR = 0x%08x\n", read_cpuid_id()); + } + + for (i = 0; i < ARRAY_SIZE(errors); i++) + if (BIT(i) & cesr) + errors[i].func(edac, cpu, 0, errors[i].msg); + + if (cesr & CESR_TLBMH) { + asm ("mcr p15, 0, r0, c8, c7, 0"); + edac_device_handle_ce(edac, cpu, 0, "TLB Multi-Hit error"); + } + + if (cesr & (CESR_ICTPE | CESR_ICDPE | CESR_ICTE)) { + i_cesynr = read_cesynr(); + pr_alert("I-side CESYNR = 0x%08x\n", i_cesynr); + write_cesr(CESR_I_MASK); + + /* + * Clear the I-side bits from the captured CESR value so that we + * don't accidentally clear any new I-side errors when we do + * the CESR write-clear operation. + */ + cesr &= ~CESR_I_MASK; + } + + if (cesr & (CESR_DCTPE | CESR_DCDPE | CESR_DCTE)) { + d_cesynr = read_cesynr(); + pr_alert("D-side CESYNR = 0x%08x\n", d_cesynr); + } + + /* Clear the interrupt bits we processed */ + write_cesr(cesr); + + return IRQ_HANDLED; +} + +static irqreturn_t krait_l2_irq(int irq, void *dev_id) +{ + struct edac_device_ctl_info *edac = dev_id; + unsigned int l2esr; + unsigned int l2esynr0; + unsigned int l2esynr1; + unsigned int l2ear0; + unsigned int l2ear1; + unsigned long cpu; + int i; + static const struct krait_edac_error errors[] = { + { "master port decode error", edac_device_handle_ce }, + { "master port slave error", edac_device_handle_ce }, + { "tag soft error, single-bit", edac_device_handle_ce }, + { "tag soft error, double-bit", edac_device_handle_ue }, + { "data soft error, single-bit", edac_device_handle_ce }, + { "data soft error, double-bit", edac_device_handle_ue }, + { "modified soft error", edac_device_handle_ce }, + { "slave port exclusive monitor not available", + edac_device_handle_ue}, + { "master port LDREX received Normal OK response", + edac_device_handle_ce }, + }; + + l2esr = get_l2_indirect_reg(L2ESR); + pr_alert("Error detected!\n"); + pr_alert("L2ESR = 0x%08x\n", l2esr); + + if (l2esr & (L2ESR_TSESB | L2ESR_TSEDB | L2ESR_MSE | L2ESR_SP)) { + l2esynr0 = get_l2_indirect_reg(L2ESYNR0); + l2esynr1 = get_l2_indirect_reg(L2ESYNR1); + l2ear0 = get_l2_indirect_reg(L2EAR0); + l2ear1 = get_l2_indirect_reg(L2EAR1); + + pr_alert("L2ESYNR0 = 0x%08x\n", l2esynr0); + pr_alert("L2ESYNR1 = 0x%08x\n", l2esynr1); + pr_alert("L2EAR0 = 0x%08x\n", l2ear0); + pr_alert("L2EAR1 = 0x%08x\n", l2ear1); + } + + cpu = (l2esr >> L2ESR_CPU_SHIFT) & L2ESR_CPU_MASK; + cpu = __ffs(cpu); + if (cpu) + cpu--; + for (i = 0; i < ARRAY_SIZE(errors); i++) + if (BIT(i) & l2esr) + errors[i].func(edac, cpu, 1, errors[i].msg); + + set_l2_indirect_reg(L2ESR, l2esr); + + return IRQ_HANDLED; +} + +static void enable_l1_irq(void *info) +{ + const struct krait_edac *k = info; + + enable_percpu_irq(k->l1_irq, IRQ_TYPE_LEVEL_HIGH); +} + +static void disable_l1_irq(void *info) +{ + const struct krait_edac *k = info; + + disable_percpu_irq(k->l1_irq); +} + +static int +krait_edac_notify(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + struct krait_edac *p = container_of(nfb, struct krait_edac, notifier); + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + enable_l1_irq(p); + break; + + case CPU_DYING: + disable_l1_irq(p); + break; + } + return NOTIFY_OK; +} + +static int krait_edac_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct edac_device_ctl_info *edev; + struct krait_edac *p; + int l1_irq, l2_irq; + int ret; + int cpu; + + l1_irq = platform_get_irq(pdev, 0); + if (l1_irq < 0) + return l1_irq; + + l2_irq = platform_get_irq(pdev, 1); + if (l2_irq < 0) + return l2_irq; + + p = devm_kzalloc(dev, sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + platform_set_drvdata(pdev, p); + p->l1_irq = l1_irq; + + p->edev = alloc_percpu(struct edac_device_ctl_info *); + if (!p->edev) + return -ENOMEM; + + edev = edac_device_alloc_ctl_info(0, "cpu", num_possible_cpus(), + "L", 2, 1, NULL, 0, + edac_device_alloc_index()); + if (!edev) { + ret = -ENOMEM; + goto err_alloc; + } + + edev->dev = dev; + edev->mod_name = dev_name(dev); + edev->dev_name = dev_name(dev); + edev->ctl_name = "cache"; + + for_each_possible_cpu(cpu) + *per_cpu_ptr(p->edev, cpu) = edev; + + ret = edac_device_add_device(edev); + if (ret) + goto err_add; + + ret = request_percpu_irq(l1_irq, krait_l1_irq, "[edac] L1 err", + p->edev); + if (ret) + goto err_l1_irq; + + ret = devm_request_irq(dev, l2_irq, krait_l2_irq, 0, "[edac] L2 err", + edev); + if (ret) + goto err_l2_irq; + + p->notifier.notifier_call = krait_edac_notify; + register_hotcpu_notifier(&p->notifier); + on_each_cpu(enable_l1_irq, p, true); + + return 0; +err_l2_irq: + free_percpu_irq(p->l1_irq, p->edev); +err_l1_irq: + edac_device_del_device(dev); +err_add: + edac_device_free_ctl_info(edev); +err_alloc: + free_percpu(p->edev); + return ret; +} + +static int krait_edac_remove(struct platform_device *pdev) +{ + struct krait_edac *p = platform_get_drvdata(pdev); + + unregister_hotcpu_notifier(&p->notifier); + on_each_cpu(disable_l1_irq, p, true); + free_percpu_irq(p->l1_irq, p->edev); + edac_device_del_device(&pdev->dev); + edac_device_free_ctl_info(*__this_cpu_ptr(p->edev)); + free_percpu(p->edev); + + return 0; +} + +static const struct of_device_id krait_edac_match_table[] = { + { .compatible = "qcom,krait-cache-erp" }, + { } +}; +MODULE_DEVICE_TABLE(of, krait_edac_match_table); + +static struct platform_driver krait_edac_driver = { + .probe = krait_edac_probe, + .remove = krait_edac_remove, + .driver = { + .name = "krait_edac", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(krait_edac_match_table), + }, +}; +module_platform_driver(krait_edac_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Krait CPU cache error reporting driver"); +MODULE_ALIAS("platform:krait_edac"); -- The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/