From fd4cf79fcc4b5130ced8fd8c40378d3cec2e5fa8 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Wed, 12 Aug 2015 18:29:36 +0200 Subject: x86/mce: Remove the MCE ring for Action Optional errors Use unified genpool to save Action Optional error events and put Action Optional error handling in the same notification chain as MCE error decoding. Signed-off-by: Chen, Gong [ Fold in subsequent patch from Boris for early boot logging. ] Signed-off-by: Tony Luck [ Correct a lot. ] Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1439396985-12812-5-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar --- drivers/edac/i7core_edac.c | 2 +- drivers/edac/mce_amd.c | 2 +- drivers/edac/sb_edac.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/edac') diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 01087a38da22..13d77f4a892c 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -2424,7 +2424,7 @@ static int __init i7core_init(void) pci_rc = pci_register_driver(&i7core_driver); if (pci_rc >= 0) { - mce_register_decode_chain(&i7_mce_dec); + mce_register_decode_chain(&i7_mce_dec, true); return 0; } diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index 58586d59bf8e..aca31a237073 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -895,7 +895,7 @@ static int __init mce_amd_init(void) pr_info("MCE: In-kernel MCE decoding enabled.\n"); - mce_register_decode_chain(&amd_mce_dec_nb); + mce_register_decode_chain(&amd_mce_dec_nb, true); return 0; } diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index ca7831168298..5780e26c3e58 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -2591,7 +2591,7 @@ static int __init sbridge_init(void) pci_rc = pci_register_driver(&sbridge_driver); if (pci_rc >= 0) { - mce_register_decode_chain(&sbridge_mce_dec); + mce_register_decode_chain(&sbridge_mce_dec, true); if (get_edac_report_status() == EDAC_REPORTING_DISABLED) sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n"); return 0; -- cgit v1.2.3 From eef4dfa0cb83899c782935ac5345532f47073cea Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 12 Aug 2015 18:29:38 +0200 Subject: x86/mce: Kill drain_mcelog_buffer() This used to flush out MCEs logged during early boot and which were in the MCA registers from a previous system run. No need for that now, since we've moved to a genpool. Suggested-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1439396985-12812-7-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mce.h | 2 +- arch/x86/kernel/cpu/mcheck/mce.c | 44 ++-------------------------------------- drivers/acpi/acpi_extlog.c | 2 +- drivers/edac/i7core_edac.c | 2 +- drivers/edac/mce_amd.c | 2 +- drivers/edac/sb_edac.c | 2 +- 6 files changed, 7 insertions(+), 47 deletions(-) (limited to 'drivers/edac') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index dfaa4de1dbb4..982dfc3679ad 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -140,7 +140,7 @@ struct mce_vendor_flags { extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; -extern void mce_register_decode_chain(struct notifier_block *nb, bool drain); +extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); #include diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 9568bb55bfe2..32b586ee006a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -199,55 +199,15 @@ void mce_log(struct mce *mce) set_bit(0, &mce_need_notify); } -static void drain_mcelog_buffer(void) -{ - unsigned int next, i, prev = 0; - - next = ACCESS_ONCE(mcelog.next); - - do { - struct mce *m; - - /* drain what was logged during boot */ - for (i = prev; i < next; i++) { - unsigned long start = jiffies; - unsigned retries = 1; - - m = &mcelog.entry[i]; - - while (!m->finished) { - if (time_after_eq(jiffies, start + 2*retries)) - retries++; - - cpu_relax(); - - if (!m->finished && retries >= 4) { - pr_err("skipping error being logged currently!\n"); - break; - } - } - smp_rmb(); - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - } - - memset(mcelog.entry + prev, 0, (next - prev) * sizeof(*m)); - prev = next; - next = cmpxchg(&mcelog.next, prev, 0); - } while (next != prev); -} - static struct notifier_block mce_srao_nb; -void mce_register_decode_chain(struct notifier_block *nb, bool drain) +void mce_register_decode_chain(struct notifier_block *nb) { /* Ensure SRAO notifier has the highest priority in the decode chain. */ if (nb != &mce_srao_nb && nb->priority == INT_MAX) nb->priority -= 1; atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); - - if (drain) - drain_mcelog_buffer(); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -2028,7 +1988,7 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); - mce_register_decode_chain(&mce_srao_nb, false); + mce_register_decode_chain(&mce_srao_nb); mcheck_vendor_init_severity(); INIT_WORK(&mce_work, mce_process_work); diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 07e012e74c1b..b3842ffc19ba 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -286,7 +286,7 @@ static int __init extlog_init(void) */ old_edac_report_status = get_edac_report_status(); set_edac_report_status(EDAC_REPORTING_DISABLED); - mce_register_decode_chain(&extlog_mce_dec, true); + mce_register_decode_chain(&extlog_mce_dec); /* enable OS to be involved to take over management from BIOS */ ((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN; diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 13d77f4a892c..01087a38da22 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -2424,7 +2424,7 @@ static int __init i7core_init(void) pci_rc = pci_register_driver(&i7core_driver); if (pci_rc >= 0) { - mce_register_decode_chain(&i7_mce_dec, true); + mce_register_decode_chain(&i7_mce_dec); return 0; } diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index aca31a237073..58586d59bf8e 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -895,7 +895,7 @@ static int __init mce_amd_init(void) pr_info("MCE: In-kernel MCE decoding enabled.\n"); - mce_register_decode_chain(&amd_mce_dec_nb, true); + mce_register_decode_chain(&amd_mce_dec_nb); return 0; } diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 5780e26c3e58..ca7831168298 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -2591,7 +2591,7 @@ static int __init sbridge_init(void) pci_rc = pci_register_driver(&sbridge_driver); if (pci_rc >= 0) { - mce_register_decode_chain(&sbridge_mce_dec, true); + mce_register_decode_chain(&sbridge_mce_dec); if (get_edac_report_status() == EDAC_REPORTING_DISABLED) sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n"); return 0; -- cgit v1.2.3 From 6c36dfe949187dc2729abfad4b083758ac5c2e0e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 12 Aug 2015 18:29:45 +0200 Subject: x86/ras: Move AMD MCE injector to arch/x86/ras/ This is an x86-specific module and would benefit from being closer to the arch code. Move it there. Update copyright while at it. Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Link: http://lkml.kernel.org/r/1439396985-12812-14-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/Makefile | 2 + arch/x86/ras/Kconfig | 11 ++ arch/x86/ras/Makefile | 2 + arch/x86/ras/mce_amd_inj.c | 375 +++++++++++++++++++++++++++++++++++++++++++++ drivers/edac/Kconfig | 10 -- drivers/edac/Makefile | 1 - drivers/edac/mce_amd_inj.c | 375 --------------------------------------------- drivers/ras/Kconfig | 3 + 8 files changed, 393 insertions(+), 386 deletions(-) create mode 100644 arch/x86/ras/Kconfig create mode 100644 arch/x86/ras/Makefile create mode 100644 arch/x86/ras/mce_amd_inj.c delete mode 100644 drivers/edac/mce_amd_inj.c (limited to 'drivers/edac') diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 118e6debc483..0f38418719ab 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -212,6 +212,8 @@ drivers-$(CONFIG_PM) += arch/x86/power/ drivers-$(CONFIG_FB) += arch/x86/video/ +drivers-$(CONFIG_RAS) += arch/x86/ras/ + #### # boot loader support. Several targets are kept for legacy purposes diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig new file mode 100644 index 000000000000..10fea5fc821e --- /dev/null +++ b/arch/x86/ras/Kconfig @@ -0,0 +1,11 @@ +config AMD_MCE_INJ + tristate "Simple MCE injection interface for AMD processors" + depends on RAS && EDAC_DECODE_MCE && DEBUG_FS + default n + help + This is a simple debugfs interface to inject MCEs and test different + aspects of the MCE handling code. + + WARNING: Do not even assume this interface is staying stable! + + diff --git a/arch/x86/ras/Makefile b/arch/x86/ras/Makefile new file mode 100644 index 000000000000..dd2c98b84037 --- /dev/null +++ b/arch/x86/ras/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_AMD_MCE_INJ) += mce_amd_inj.o + diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c new file mode 100644 index 000000000000..17e35b5bf779 --- /dev/null +++ b/arch/x86/ras/mce_amd_inj.c @@ -0,0 +1,375 @@ +/* + * A simple MCE injection facility for testing different aspects of the RAS + * code. This driver should be built as module so that it can be loaded + * on production kernels for testing purposes. + * + * This file may be distributed under the terms of the GNU General Public + * License version 2. + * + * Copyright (c) 2010-15: Borislav Petkov + * Advanced Micro Devices Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kernel/cpu/mcheck/mce-internal.h" + +/* + * Collect all the MCi_XXX settings + */ +static struct mce i_mce; +static struct dentry *dfs_inj; + +static u8 n_banks; + +#define MAX_FLAG_OPT_SIZE 3 + +enum injection_type { + SW_INJ = 0, /* SW injection, simply decode the error */ + HW_INJ, /* Trigger a #MC */ + N_INJ_TYPES, +}; + +static const char * const flags_options[] = { + [SW_INJ] = "sw", + [HW_INJ] = "hw", + NULL +}; + +/* Set default injection to SW_INJ */ +static enum injection_type inj_type = SW_INJ; + +#define MCE_INJECT_SET(reg) \ +static int inj_##reg##_set(void *data, u64 val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + m->reg = val; \ + return 0; \ +} + +MCE_INJECT_SET(status); +MCE_INJECT_SET(misc); +MCE_INJECT_SET(addr); + +#define MCE_INJECT_GET(reg) \ +static int inj_##reg##_get(void *data, u64 *val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + *val = m->reg; \ + return 0; \ +} + +MCE_INJECT_GET(status); +MCE_INJECT_GET(misc); +MCE_INJECT_GET(addr); + +DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); + +/* + * Caller needs to be make sure this cpu doesn't disappear + * from under us, i.e.: get_cpu/put_cpu. + */ +static int toggle_hw_mce_inject(unsigned int cpu, bool enable) +{ + u32 l, h; + int err; + + err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); + if (err) { + pr_err("%s: error reading HWCR\n", __func__); + return err; + } + + enable ? (l |= BIT(18)) : (l &= ~BIT(18)); + + err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); + if (err) + pr_err("%s: error writing HWCR\n", __func__); + + return err; +} + +static int __set_inj(const char *buf) +{ + int i; + + for (i = 0; i < N_INJ_TYPES; i++) { + if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { + inj_type = i; + return 0; + } + } + return -EINVAL; +} + +static ssize_t flags_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE]; + int n; + + n = sprintf(buf, "%s\n", flags_options[inj_type]); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static ssize_t flags_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE], *__buf; + int err; + size_t ret; + + if (cnt > MAX_FLAG_OPT_SIZE) + cnt = MAX_FLAG_OPT_SIZE; + + ret = cnt; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt - 1] = 0; + + /* strip whitespace */ + __buf = strstrip(buf); + + err = __set_inj(__buf); + if (err) { + pr_err("%s: Invalid flags value: %s\n", __func__, __buf); + return err; + } + + *ppos += ret; + + return ret; +} + +static const struct file_operations flags_fops = { + .read = flags_read, + .write = flags_write, + .llseek = generic_file_llseek, +}; + +/* + * On which CPU to inject? + */ +MCE_INJECT_GET(extcpu); + +static int inj_extcpu_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= nr_cpu_ids || !cpu_online(val)) { + pr_err("%s: Invalid CPU: %llu\n", __func__, val); + return -EINVAL; + } + m->extcpu = val; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); + +static void trigger_mce(void *info) +{ + asm volatile("int $18"); +} + +static void do_inject(void) +{ + u64 mcg_status = 0; + unsigned int cpu = i_mce.extcpu; + u8 b = i_mce.bank; + + if (i_mce.misc) + i_mce.status |= MCI_STATUS_MISCV; + + if (inj_type == SW_INJ) { + mce_inject_log(&i_mce); + return; + } + + /* prep MCE global settings for the injection */ + mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; + + if (!(i_mce.status & MCI_STATUS_PCC)) + mcg_status |= MCG_STATUS_RIPV; + + get_online_cpus(); + if (!cpu_online(cpu)) + goto err; + + toggle_hw_mce_inject(cpu, true); + + wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, + (u32)mcg_status, (u32)(mcg_status >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + + toggle_hw_mce_inject(cpu, false); + + smp_call_function_single(cpu, trigger_mce, NULL, 0); + +err: + put_online_cpus(); + +} + +/* + * This denotes into which bank we're injecting and triggers + * the injection, at the same time. + */ +static int inj_bank_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= n_banks) { + pr_err("Non-existent MCE bank: %llu\n", val); + return -EINVAL; + } + + m->bank = val; + do_inject(); + + return 0; +} + +MCE_INJECT_GET(bank); + +DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); + +static const char readme_msg[] = +"Description of the files and their usages:\n" +"\n" +"Note1: i refers to the bank number below.\n" +"Note2: See respective BKDGs for the exact bit definitions of the files below\n" +"as they mirror the hardware registers.\n" +"\n" +"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" +"\t attributes of the error which caused the MCE.\n" +"\n" +"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" +"\t used for error thresholding purposes and its validity is indicated by\n" +"\t MCi_STATUS[MiscV].\n" +"\n" +"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" +"\t associated with the error.\n" +"\n" +"cpu:\t The CPU to inject the error on.\n" +"\n" +"bank:\t Specify the bank you want to inject the error into: the number of\n" +"\t banks in a processor varies and is family/model-specific, therefore, the\n" +"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" +"\t injection.\n" +"\n" +"flags:\t Injection type to be performed. Writing to this file will trigger a\n" +"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" +"\t for AMD processors.\n" +"\n" +"\t Allowed error injection types:\n" +"\t - \"sw\": Software error injection. Decode error to a human-readable \n" +"\t format only. Safe to use.\n" +"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" +"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" +"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" +"\t before injecting.\n" +"\n"; + +static ssize_t +inj_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static const struct file_operations readme_fops = { + .read = inj_readme_read, +}; + +static struct dfs_node { + char *name; + struct dentry *d; + const struct file_operations *fops; + umode_t perm; +} dfs_fls[] = { + { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, +}; + +static int __init init_mce_inject(void) +{ + int i; + u64 cap; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + n_banks = cap & MCG_BANKCNT_MASK; + + dfs_inj = debugfs_create_dir("mce-inject", NULL); + if (!dfs_inj) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) { + dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name, + dfs_fls[i].perm, + dfs_inj, + &i_mce, + dfs_fls[i].fops); + + if (!dfs_fls[i].d) + goto err_dfs_add; + } + + return 0; + +err_dfs_add: + while (--i >= 0) + debugfs_remove(dfs_fls[i].d); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; + + return -ENOMEM; +} + +static void __exit exit_mce_inject(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) + debugfs_remove(dfs_fls[i].d); + + memset(&dfs_fls, 0, sizeof(dfs_fls)); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; +} +module_init(init_mce_inject); +module_exit(exit_mce_inject); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Borislav Petkov "); +MODULE_AUTHOR("AMD Inc."); +MODULE_DESCRIPTION("MCE injection facility for RAS testing"); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 8677ead2a8e1..ef25000a5bc6 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -61,16 +61,6 @@ config EDAC_DECODE_MCE which occur really early upon boot, before the module infrastructure has been initialized. -config EDAC_MCE_INJ - tristate "Simple MCE injection interface" - depends on EDAC_DECODE_MCE && DEBUG_FS - default n - help - This is a simple debugfs interface to inject MCEs and test different - aspects of the MCE handling code. - - WARNING: Do not even assume this interface is staying stable! - config EDAC_MM_EDAC tristate "Main Memory EDAC (Error Detection And Correction) reporting" select RAS diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 28ef2a519f65..ae3c5f3ce405 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -17,7 +17,6 @@ edac_core-y += edac_pci.o edac_pci_sysfs.o endif obj-$(CONFIG_EDAC_GHES) += ghes_edac.o -obj-$(CONFIG_EDAC_MCE_INJ) += mce_amd_inj.o edac_mce_amd-y := mce_amd.o obj-$(CONFIG_EDAC_DECODE_MCE) += edac_mce_amd.o diff --git a/drivers/edac/mce_amd_inj.c b/drivers/edac/mce_amd_inj.c deleted file mode 100644 index 4c73e4d03d46..000000000000 --- a/drivers/edac/mce_amd_inj.c +++ /dev/null @@ -1,375 +0,0 @@ -/* - * A simple MCE injection facility for testing different aspects of the RAS - * code. This driver should be built as module so that it can be loaded - * on production kernels for testing purposes. - * - * This file may be distributed under the terms of the GNU General Public - * License version 2. - * - * Copyright (c) 2010-14: Borislav Petkov - * Advanced Micro Devices Inc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include "mce_amd.h" - -/* - * Collect all the MCi_XXX settings - */ -static struct mce i_mce; -static struct dentry *dfs_inj; - -static u8 n_banks; - -#define MAX_FLAG_OPT_SIZE 3 - -enum injection_type { - SW_INJ = 0, /* SW injection, simply decode the error */ - HW_INJ, /* Trigger a #MC */ - N_INJ_TYPES, -}; - -static const char * const flags_options[] = { - [SW_INJ] = "sw", - [HW_INJ] = "hw", - NULL -}; - -/* Set default injection to SW_INJ */ -static enum injection_type inj_type = SW_INJ; - -#define MCE_INJECT_SET(reg) \ -static int inj_##reg##_set(void *data, u64 val) \ -{ \ - struct mce *m = (struct mce *)data; \ - \ - m->reg = val; \ - return 0; \ -} - -MCE_INJECT_SET(status); -MCE_INJECT_SET(misc); -MCE_INJECT_SET(addr); - -#define MCE_INJECT_GET(reg) \ -static int inj_##reg##_get(void *data, u64 *val) \ -{ \ - struct mce *m = (struct mce *)data; \ - \ - *val = m->reg; \ - return 0; \ -} - -MCE_INJECT_GET(status); -MCE_INJECT_GET(misc); -MCE_INJECT_GET(addr); - -DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); - -/* - * Caller needs to be make sure this cpu doesn't disappear - * from under us, i.e.: get_cpu/put_cpu. - */ -static int toggle_hw_mce_inject(unsigned int cpu, bool enable) -{ - u32 l, h; - int err; - - err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); - if (err) { - pr_err("%s: error reading HWCR\n", __func__); - return err; - } - - enable ? (l |= BIT(18)) : (l &= ~BIT(18)); - - err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); - if (err) - pr_err("%s: error writing HWCR\n", __func__); - - return err; -} - -static int __set_inj(const char *buf) -{ - int i; - - for (i = 0; i < N_INJ_TYPES; i++) { - if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { - inj_type = i; - return 0; - } - } - return -EINVAL; -} - -static ssize_t flags_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[MAX_FLAG_OPT_SIZE]; - int n; - - n = sprintf(buf, "%s\n", flags_options[inj_type]); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); -} - -static ssize_t flags_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[MAX_FLAG_OPT_SIZE], *__buf; - int err; - size_t ret; - - if (cnt > MAX_FLAG_OPT_SIZE) - cnt = MAX_FLAG_OPT_SIZE; - - ret = cnt; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt - 1] = 0; - - /* strip whitespace */ - __buf = strstrip(buf); - - err = __set_inj(__buf); - if (err) { - pr_err("%s: Invalid flags value: %s\n", __func__, __buf); - return err; - } - - *ppos += ret; - - return ret; -} - -static const struct file_operations flags_fops = { - .read = flags_read, - .write = flags_write, - .llseek = generic_file_llseek, -}; - -/* - * On which CPU to inject? - */ -MCE_INJECT_GET(extcpu); - -static int inj_extcpu_set(void *data, u64 val) -{ - struct mce *m = (struct mce *)data; - - if (val >= nr_cpu_ids || !cpu_online(val)) { - pr_err("%s: Invalid CPU: %llu\n", __func__, val); - return -EINVAL; - } - m->extcpu = val; - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); - -static void trigger_mce(void *info) -{ - asm volatile("int $18"); -} - -static void do_inject(void) -{ - u64 mcg_status = 0; - unsigned int cpu = i_mce.extcpu; - u8 b = i_mce.bank; - - if (i_mce.misc) - i_mce.status |= MCI_STATUS_MISCV; - - if (inj_type == SW_INJ) { - amd_decode_mce(NULL, 0, &i_mce); - return; - } - - /* prep MCE global settings for the injection */ - mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; - - if (!(i_mce.status & MCI_STATUS_PCC)) - mcg_status |= MCG_STATUS_RIPV; - - get_online_cpus(); - if (!cpu_online(cpu)) - goto err; - - toggle_hw_mce_inject(cpu, true); - - wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, - (u32)mcg_status, (u32)(mcg_status >> 32)); - - wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), - (u32)i_mce.status, (u32)(i_mce.status >> 32)); - - wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), - (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); - - wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), - (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); - - toggle_hw_mce_inject(cpu, false); - - smp_call_function_single(cpu, trigger_mce, NULL, 0); - -err: - put_online_cpus(); - -} - -/* - * This denotes into which bank we're injecting and triggers - * the injection, at the same time. - */ -static int inj_bank_set(void *data, u64 val) -{ - struct mce *m = (struct mce *)data; - - if (val >= n_banks) { - pr_err("Non-existent MCE bank: %llu\n", val); - return -EINVAL; - } - - m->bank = val; - do_inject(); - - return 0; -} - -MCE_INJECT_GET(bank); - -DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); - -static const char readme_msg[] = -"Description of the files and their usages:\n" -"\n" -"Note1: i refers to the bank number below.\n" -"Note2: See respective BKDGs for the exact bit definitions of the files below\n" -"as they mirror the hardware registers.\n" -"\n" -"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" -"\t attributes of the error which caused the MCE.\n" -"\n" -"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" -"\t used for error thresholding purposes and its validity is indicated by\n" -"\t MCi_STATUS[MiscV].\n" -"\n" -"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" -"\t associated with the error.\n" -"\n" -"cpu:\t The CPU to inject the error on.\n" -"\n" -"bank:\t Specify the bank you want to inject the error into: the number of\n" -"\t banks in a processor varies and is family/model-specific, therefore, the\n" -"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" -"\t injection.\n" -"\n" -"flags:\t Injection type to be performed. Writing to this file will trigger a\n" -"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" -"\t for AMD processors.\n" -"\n" -"\t Allowed error injection types:\n" -"\t - \"sw\": Software error injection. Decode error to a human-readable \n" -"\t format only. Safe to use.\n" -"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" -"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" -"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" -"\t before injecting.\n" -"\n"; - -static ssize_t -inj_readme_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - return simple_read_from_buffer(ubuf, cnt, ppos, - readme_msg, strlen(readme_msg)); -} - -static const struct file_operations readme_fops = { - .read = inj_readme_read, -}; - -static struct dfs_node { - char *name; - struct dentry *d; - const struct file_operations *fops; - umode_t perm; -} dfs_fls[] = { - { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, -}; - -static int __init init_mce_inject(void) -{ - int i; - u64 cap; - - rdmsrl(MSR_IA32_MCG_CAP, cap); - n_banks = cap & MCG_BANKCNT_MASK; - - dfs_inj = debugfs_create_dir("mce-inject", NULL); - if (!dfs_inj) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) { - dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name, - dfs_fls[i].perm, - dfs_inj, - &i_mce, - dfs_fls[i].fops); - - if (!dfs_fls[i].d) - goto err_dfs_add; - } - - return 0; - -err_dfs_add: - while (--i >= 0) - debugfs_remove(dfs_fls[i].d); - - debugfs_remove(dfs_inj); - dfs_inj = NULL; - - return -ENOMEM; -} - -static void __exit exit_mce_inject(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) - debugfs_remove(dfs_fls[i].d); - - memset(&dfs_fls, 0, sizeof(dfs_fls)); - - debugfs_remove(dfs_inj); - dfs_inj = NULL; -} -module_init(init_mce_inject); -module_exit(exit_mce_inject); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Borislav Petkov "); -MODULE_AUTHOR("AMD Inc."); -MODULE_DESCRIPTION("MCE injection facility for RAS testing"); diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig index e5f0a43998d2..4c3c67d13254 100644 --- a/drivers/ras/Kconfig +++ b/drivers/ras/Kconfig @@ -29,4 +29,7 @@ menuconfig RAS data corruption. if RAS + +source arch/x86/ras/Kconfig + endif -- cgit v1.2.3