config X86_MCE
bool "Machine Check / overheating reporting"
+ select GENERIC_ALLOCATOR
default y
---help---
Machine Check support allows the processor to notify the
drivers-$(CONFIG_FB) += arch/x86/video/
+drivers-$(CONFIG_RAS) += arch/x86/ras/
+
####
# boot loader support. Several targets are kept for legacy purposes
#ifdef CONFIG_X86_MCE
int mcheck_init(void);
void mcheck_cpu_init(struct cpuinfo_x86 *c);
+void mcheck_cpu_clear(struct cpuinfo_x86 *c);
void mcheck_vendor_init_severity(void);
#else
static inline int mcheck_init(void) { return 0; }
static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
+static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {}
static inline void mcheck_vendor_init_severity(void) {}
#endif
#ifdef CONFIG_X86_MCE_INTEL
void mce_intel_feature_init(struct cpuinfo_x86 *c);
+void mce_intel_feature_clear(struct cpuinfo_x86 *c);
void cmci_clear(void);
void cmci_reenable(void);
void cmci_rediscover(void);
void cmci_recheck(void);
-void lmce_clear(void);
-void lmce_enable(void);
#else
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
+static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { }
static inline void cmci_clear(void) {}
static inline void cmci_reenable(void) {}
static inline void cmci_rediscover(void) {}
static inline void cmci_recheck(void) {}
-static inline void lmce_clear(void) {}
-static inline void lmce_enable(void) {}
#endif
#ifdef CONFIG_X86_MCE_AMD
__u64 time; /* wall time_t when error was detected */
__u8 cpuvendor; /* cpu vendor as encoded in system.h */
__u8 inject_flags; /* software inject flags */
- __u16 pad;
+ __u8 severity;
+ __u8 usable_addr;
__u32 cpuid; /* CPUID 1 EAX */
__u8 cs; /* code segment */
__u8 bank; /* machine check bank */
-obj-y = mce.o mce-severity.o
+obj-y = mce.o mce-severity.o mce-genpool.o
obj-$(CONFIG_X86_ANCIENT_MCE) += winchip.o p5.o
obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o
m.addr = mem_err->physical_addr;
mce_log(&m);
- mce_notify_irq();
}
EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
--- /dev/null
+/*
+ * MCE event pool management in MCE context
+ *
+ * Copyright (C) 2015 Intel Corp.
+ * Author: Chen, Gong <gong.chen@linux.intel.com>
+ *
+ * This file is licensed under GPLv2.
+ */
+#include <linux/smp.h>
+#include <linux/mm.h>
+#include <linux/genalloc.h>
+#include <linux/llist.h>
+#include "mce-internal.h"
+
+/*
+ * printk() is not safe in MCE context. This is a lock-less memory allocator
+ * used to save error information organized in a lock-less list.
+ *
+ * This memory pool is only to be used to save MCE records in MCE context.
+ * MCE events are rare, so a fixed size memory pool should be enough. Use
+ * 2 pages to save MCE events for now (~80 MCE records at most).
+ */
+#define MCE_POOLSZ (2 * PAGE_SIZE)
+
+static struct gen_pool *mce_evt_pool;
+static LLIST_HEAD(mce_event_llist);
+static char gen_pool_buf[MCE_POOLSZ];
+
+void mce_gen_pool_process(void)
+{
+ struct llist_node *head;
+ struct mce_evt_llist *node;
+ struct mce *mce;
+
+ head = llist_del_all(&mce_event_llist);
+ if (!head)
+ return;
+
+ head = llist_reverse_order(head);
+ llist_for_each_entry(node, head, llnode) {
+ mce = &node->mce;
+ atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+ gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
+ }
+}
+
+bool mce_gen_pool_empty(void)
+{
+ return llist_empty(&mce_event_llist);
+}
+
+int mce_gen_pool_add(struct mce *mce)
+{
+ struct mce_evt_llist *node;
+
+ if (!mce_evt_pool)
+ return -EINVAL;
+
+ node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node));
+ if (!node) {
+ pr_warn_ratelimited("MCE records pool full!\n");
+ return -ENOMEM;
+ }
+
+ memcpy(&node->mce, mce, sizeof(*mce));
+ llist_add(&node->llnode, &mce_event_llist);
+
+ return 0;
+}
+
+static int mce_gen_pool_create(void)
+{
+ struct gen_pool *tmpp;
+ int ret = -ENOMEM;
+
+ tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1);
+ if (!tmpp)
+ goto out;
+
+ ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1);
+ if (ret) {
+ gen_pool_destroy(tmpp);
+ goto out;
+ }
+
+ mce_evt_pool = tmpp;
+
+out:
+ return ret;
+}
+
+int mce_gen_pool_init(void)
+{
+ /* Just init mce_gen_pool once. */
+ if (mce_evt_pool)
+ return 0;
+
+ return mce_gen_pool_create();
+}
MCE_PANIC_SEVERITY,
};
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
#define ATTR_LEN 16
#define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */
char attrname[ATTR_LEN]; /* attribute name */
};
+struct mce_evt_llist {
+ struct llist_node llnode;
+ struct mce mce;
+};
+
+void mce_gen_pool_process(void);
+bool mce_gen_pool_empty(void);
+int mce_gen_pool_add(struct mce *mce);
+int mce_gen_pool_init(void);
+
extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
struct dentry *mce_get_debugfs_dir(void);
return -EINVAL;
}
#endif
+
+void mce_inject_log(struct mce *m);
static DEFINE_MUTEX(mce_chrdev_read_mutex);
-#define rcu_dereference_check_mce(p) \
+#define mce_log_get_idx_check(p) \
({ \
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
!lockdep_is_held(&mce_chrdev_read_mutex), \
- "suspicious rcu_dereference_check_mce() usage"); \
+ "suspicious mce_log_get_idx_check() usage"); \
smp_load_acquire(&(p)); \
})
*/
mce_banks_t mce_banks_ce_disabled;
-static DEFINE_PER_CPU(struct work_struct, mce_work);
+static struct work_struct mce_work;
+static struct irq_work mce_irq_work;
static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
+static int mce_usable_address(struct mce *m);
/*
* CPU/chipset specific EDAC code can register a notifier call here to print
* MCE errors in a human-readable form.
*/
-static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
/* Do initial initialization of a struct mce */
void mce_setup(struct mce *m)
/* Emit the trace record: */
trace_mce_record(mce);
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+ if (!mce_gen_pool_add(mce))
+ irq_work_queue(&mce_irq_work);
mce->finished = 0;
wmb();
for (;;) {
- entry = rcu_dereference_check_mce(mcelog.next);
+ entry = mce_log_get_idx_check(mcelog.next);
for (;;) {
/*
set_bit(0, &mce_need_notify);
}
-static void drain_mcelog_buffer(void)
+void mce_inject_log(struct mce *m)
{
- 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);
+ mutex_lock(&mce_chrdev_read_mutex);
+ mce_log(m);
+ mutex_unlock(&mce_chrdev_read_mutex);
}
+EXPORT_SYMBOL_GPL(mce_inject_log);
+static struct notifier_block mce_srao_nb;
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);
- drain_mcelog_buffer();
}
EXPORT_SYMBOL_GPL(mce_register_decode_chain);
}
}
-/*
- * Simple lockless ring to communicate PFNs from the exception handler with the
- * process context work function. This is vastly simplified because there's
- * only a single reader and a single writer.
- */
-#define MCE_RING_SIZE 16 /* we use one entry less */
-
-struct mce_ring {
- unsigned short start;
- unsigned short end;
- unsigned long ring[MCE_RING_SIZE];
-};
-static DEFINE_PER_CPU(struct mce_ring, mce_ring);
-
-/* Runs with CPU affinity in workqueue */
-static int mce_ring_empty(void)
-{
- struct mce_ring *r = this_cpu_ptr(&mce_ring);
-
- return r->start == r->end;
-}
-
-static int mce_ring_get(unsigned long *pfn)
-{
- struct mce_ring *r;
- int ret = 0;
-
- *pfn = 0;
- get_cpu();
- r = this_cpu_ptr(&mce_ring);
- if (r->start == r->end)
- goto out;
- *pfn = r->ring[r->start];
- r->start = (r->start + 1) % MCE_RING_SIZE;
- ret = 1;
-out:
- put_cpu();
- return ret;
-}
-
-/* Always runs in MCE context with preempt off */
-static int mce_ring_add(unsigned long pfn)
-{
- struct mce_ring *r = this_cpu_ptr(&mce_ring);
- unsigned next;
-
- next = (r->end + 1) % MCE_RING_SIZE;
- if (next == r->start)
- return -1;
- r->ring[r->end] = pfn;
- wmb();
- r->end = next;
- return 0;
-}
-
int mce_available(struct cpuinfo_x86 *c)
{
if (mca_cfg.disabled)
static void mce_schedule_work(void)
{
- if (!mce_ring_empty())
- schedule_work(this_cpu_ptr(&mce_work));
+ if (!mce_gen_pool_empty() && keventd_up())
+ schedule_work(&mce_work);
}
-static DEFINE_PER_CPU(struct irq_work, mce_irq_work);
-
static void mce_irq_work_cb(struct irq_work *entry)
{
mce_notify_irq();
return;
}
- irq_work_queue(this_cpu_ptr(&mce_irq_work));
+ irq_work_queue(&mce_irq_work);
+}
+
+static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct mce *mce = (struct mce *)data;
+ unsigned long pfn;
+
+ if (!mce)
+ return NOTIFY_DONE;
+
+ if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) {
+ pfn = mce->addr >> PAGE_SHIFT;
+ memory_failure(pfn, MCE_VECTOR, 0);
+ }
+
+ return NOTIFY_OK;
}
+static struct notifier_block mce_srao_nb = {
+ .notifier_call = srao_decode_notifier,
+ .priority = INT_MAX,
+};
/*
* Read ADDR and MISC registers.
*/
if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) {
if (m.status & MCI_STATUS_ADDRV) {
- mce_ring_add(m.addr >> PAGE_SHIFT);
- mce_schedule_work();
+ m.severity = severity;
+ m.usable_addr = mce_usable_address(&m);
+
+ if (!mce_gen_pool_add(&m))
+ mce_schedule_work();
}
}
mce_read_aux(&m, i);
- /*
- * Action optional error. Queue address for later processing.
- * When the ring overflows we just ignore the AO error.
- * RED-PEN add some logging mechanism when
- * usable_address or mce_add_ring fails.
- * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0
- */
- if (severity == MCE_AO_SEVERITY && mce_usable_address(&m))
- mce_ring_add(m.addr >> PAGE_SHIFT);
+ /* assuming valid severity level != 0 */
+ m.severity = severity;
+ m.usable_addr = mce_usable_address(&m);
mce_log(&m);
/*
* Action optional processing happens here (picking up
* from the list of faulting pages that do_machine_check()
- * placed into the "ring").
+ * placed into the genpool).
*/
static void mce_process_work(struct work_struct *dummy)
{
- unsigned long pfn;
-
- while (mce_ring_get(&pfn))
- memory_failure(pfn, MCE_VECTOR, 0);
+ mce_gen_pool_process();
}
#ifdef CONFIG_X86_MCE_INTEL
}
}
+static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
+{
+ switch (c->x86_vendor) {
+ case X86_VENDOR_INTEL:
+ mce_intel_feature_clear(c);
+ break;
+ default:
+ break;
+ }
+}
+
static void mce_start_timer(unsigned int cpu, struct timer_list *t)
{
unsigned long iv = check_interval * HZ;
return;
}
+ if (mce_gen_pool_init()) {
+ mca_cfg.disabled = true;
+ pr_emerg("Couldn't allocate MCE records pool!\n");
+ return;
+ }
+
machine_check_vector = do_machine_check;
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
__mcheck_cpu_init_timer();
- INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
- init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
+}
+
+/*
+ * Called for each booted CPU to clear some machine checks opt-ins
+ */
+void mcheck_cpu_clear(struct cpuinfo_x86 *c)
+{
+ if (mca_cfg.disabled)
+ return;
+
+ if (!mce_available(c))
+ return;
+
+ /*
+ * Possibly to clear general settings generic to x86
+ * __mcheck_cpu_clear_generic(c);
+ */
+ __mcheck_cpu_clear_vendor(c);
+
}
/*
goto out;
}
- next = rcu_dereference_check_mce(mcelog.next);
+ next = mce_log_get_idx_check(mcelog.next);
/* Only supports full reads right now */
err = -EINVAL;
int __init mcheck_init(void)
{
mcheck_intel_therm_init();
+ mce_register_decode_chain(&mce_srao_nb);
mcheck_vendor_init_severity();
+ INIT_WORK(&mce_work, mce_process_work);
+ init_irq_work(&mce_irq_work, mce_irq_work_cb);
+
return 0;
}
return 0;
}
-late_initcall(mcheck_debugfs_init);
+#else
+static int __init mcheck_debugfs_init(void) { return -EINVAL; }
#endif
+
+static int __init mcheck_late_init(void)
+{
+ mcheck_debugfs_init();
+
+ /*
+ * Flush out everything that has been logged during early boot, now that
+ * everything has been initialized (workqueues, decoders, ...).
+ */
+ mce_schedule_work();
+
+ return 0;
+}
+late_initcall(mcheck_late_init);
per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
}
+static void cmci_toggle_interrupt_mode(bool on)
+{
+ unsigned long flags, *owned;
+ int bank;
+ u64 val;
+
+ raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ owned = this_cpu_ptr(mce_banks_owned);
+ for_each_set_bit(bank, owned, MAX_NR_BANKS) {
+ rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+
+ if (on)
+ val |= MCI_CTL2_CMCI_EN;
+ else
+ val &= ~MCI_CTL2_CMCI_EN;
+
+ wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ }
+ raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
unsigned long cmci_intel_adjust_timer(unsigned long interval)
{
if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
*/
if (!atomic_read(&cmci_storm_on_cpus)) {
__this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
- cmci_reenable();
+ cmci_toggle_interrupt_mode(true);
cmci_recheck();
}
return CMCI_POLL_INTERVAL;
}
}
-static void cmci_storm_disable_banks(void)
-{
- unsigned long flags, *owned;
- int bank;
- u64 val;
-
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
- owned = this_cpu_ptr(mce_banks_owned);
- for_each_set_bit(bank, owned, MAX_NR_BANKS) {
- rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
- val &= ~MCI_CTL2_CMCI_EN;
- wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
- }
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
-
static bool cmci_storm_detect(void)
{
unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
if (cnt <= CMCI_STORM_THRESHOLD)
return false;
- cmci_storm_disable_banks();
+ cmci_toggle_interrupt_mode(false);
__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
r = atomic_add_return(1, &cmci_storm_on_cpus);
mce_timer_kick(CMCI_STORM_INTERVAL);
return;
machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
- mce_notify_irq();
}
/*
cmci_recheck();
}
-void intel_init_lmce(void)
+static void intel_init_lmce(void)
{
u64 val;
wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
}
+static void intel_clear_lmce(void)
+{
+ u64 val;
+
+ if (!lmce_supported())
+ return;
+
+ rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+ val &= ~MCG_EXT_CTL_LMCE_EN;
+ wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
+}
+
void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
intel_init_thermal(c);
intel_init_cmci();
intel_init_lmce();
}
+
+void mce_intel_feature_clear(struct cpuinfo_x86 *c)
+{
+ intel_clear_lmce();
+}
#include <asm/debugreg.h>
#include <asm/nmi.h>
#include <asm/tlbflush.h>
+#include <asm/mce.h>
/*
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
*/
set_cpu_online(smp_processor_id(), false);
disable_local_APIC();
+ mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
for (;;)
halt();
#include <asm/proto.h>
#include <asm/apic.h>
#include <asm/nmi.h>
+#include <asm/mce.h>
#include <asm/trace/irq_vectors.h>
/*
* Some notes on x86 processor bugs affecting SMP operation:
finish:
local_irq_save(flags);
disable_local_APIC();
+ mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
local_irq_restore(flags);
}
--- /dev/null
+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!
+
+
--- /dev/null
+obj-$(CONFIG_AMD_MCE_INJ) += mce_amd_inj.o
+
--- /dev/null
+/*
+ * 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 <bp@alien8.de>
+ * Advanced Micro Devices Inc.
+ */
+
+#include <linux/kobject.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <asm/mce.h>
+
+#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 <bp@alien8.de>");
+MODULE_AUTHOR("AMD Inc.");
+MODULE_DESCRIPTION("MCE injection facility for RAS testing");
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
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
+++ /dev/null
-/*
- * 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 <bp@alien8.de>
- * Advanced Micro Devices Inc.
- */
-
-#include <linux/kobject.h>
-#include <linux/debugfs.h>
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/string.h>
-#include <linux/uaccess.h>
-#include <asm/mce.h>
-
-#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 <bp@alien8.de>");
-MODULE_AUTHOR("AMD Inc.");
-MODULE_DESCRIPTION("MCE injection facility for RAS testing");
-config RAS
- bool
+menuconfig RAS
+ bool "Reliability, Availability and Serviceability (RAS) features"
+ help
+ Reliability, availability and serviceability (RAS) is a computer
+ hardware engineering term. Computers designed with higher levels
+ of RAS have a multitude of features that protect data integrity
+ and help them stay available for long periods of time without
+ failure.
+
+ Reliability can be defined as the probability that the system will
+ produce correct outputs up to some given time. Reliability is
+ enhanced by features that help to avoid, detect and repair hardware
+ faults.
+
+ Availability is the probability a system is operational at a given
+ time, i.e. the amount of time a device is actually operating as the
+ percentage of total time it should be operating.
+
+ Serviceability or maintainability is the simplicity and speed with
+ which a system can be repaired or maintained; if the time to repair
+ a failed system increases, then availability will decrease.
+
+ Note that Reliability and Availability are distinct concepts:
+ Reliability is a measure of the ability of a system to function
+ correctly, including avoiding data corruption, whereas Availability
+ measures how often it is available for use, even though it may not
+ be functioning correctly. For example, a server may run forever and
+ so have ideal availability, but may be unreliable, with frequent
+ data corruption.
+
+if RAS
+
+source arch/x86/ras/Kconfig
+
+endif
projects / linux-2.6-microblaze.git / commitdiff