Implement MCE recovery for the data load error path and assorted cleanups.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/string.h>
-#include <linux/sysdev.h>
+#include <linux/device.h>
#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/ctype.h>
static DEFINE_PER_CPU(struct mce, mces_seen);
static int cpu_missing;
-/*
- * CPU/chipset specific EDAC code can register a notifier call here to print
- * MCE errors in a human-readable form.
- */
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
-EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
-
/* MCA banks polled by the period polling timer for corrected events */
DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
static DEFINE_PER_CPU(struct work_struct, mce_work);
+/*
+ * CPU/chipset specific EDAC code can register a notifier call here to print
+ * MCE errors in a human-readable form.
+ */
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+
/* Do initial initialization of a struct mce */
void mce_setup(struct mce *m)
{
m->time = get_seconds();
m->cpuvendor = boot_cpu_data.x86_vendor;
m->cpuid = cpuid_eax(1);
-#ifdef CONFIG_SMP
m->socketid = cpu_data(m->extcpu).phys_proc_id;
-#endif
m->apicid = cpu_data(m->extcpu).initial_apicid;
rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
}
set_bit(0, &mce_need_notify);
}
+static void drain_mcelog_buffer(void)
+{
+ unsigned int next, i, prev = 0;
+
+ next = rcu_dereference_check_mce(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("MCE: 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);
+}
+
+
+void mce_register_decode_chain(struct notifier_block *nb)
+{
+ atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+ drain_mcelog_buffer();
+}
+EXPORT_SYMBOL_GPL(mce_register_decode_chain);
+
+void mce_unregister_decode_chain(struct notifier_block *nb)
+{
+ atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+}
+EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
+
static void print_mce(struct mce *m)
{
int ret = 0;
irq_work_queue(&__get_cpu_var(mce_irq_work));
}
+ /*
+ * Read ADDR and MISC registers.
+ */
+ static void mce_read_aux(struct mce *m, int i)
+ {
+ if (m->status & MCI_STATUS_MISCV)
+ m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
+ if (m->status & MCI_STATUS_ADDRV) {
+ m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+
+ /*
+ * Mask the reported address by the reported granularity.
+ */
+ if (mce_ser && (m->status & MCI_STATUS_MISCV)) {
+ u8 shift = MCI_MISC_ADDR_LSB(m->misc);
+ m->addr >>= shift;
+ m->addr <<= shift;
+ }
+ }
+ }
+
DEFINE_PER_CPU(unsigned, mce_poll_count);
/*
(m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)))
continue;
- if (m.status & MCI_STATUS_MISCV)
- m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
- if (m.status & MCI_STATUS_ADDRV)
- m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+ mce_read_aux(&m, i);
if (!(flags & MCP_TIMESTAMP))
m.tsc = 0;
}
}
+ /*
+ * Need to save faulting physical address associated with a process
+ * in the machine check handler some place where we can grab it back
+ * later in mce_notify_process()
+ */
+ #define MCE_INFO_MAX 16
+
+ struct mce_info {
+ atomic_t inuse;
+ struct task_struct *t;
+ __u64 paddr;
+ } mce_info[MCE_INFO_MAX];
+
+ static void mce_save_info(__u64 addr)
+ {
+ struct mce_info *mi;
+
+ for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) {
+ if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
+ mi->t = current;
+ mi->paddr = addr;
+ return;
+ }
+ }
+
+ mce_panic("Too many concurrent recoverable errors", NULL, NULL);
+ }
+
+ static struct mce_info *mce_find_info(void)
+ {
+ struct mce_info *mi;
+
+ for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++)
+ if (atomic_read(&mi->inuse) && mi->t == current)
+ return mi;
+ return NULL;
+ }
+
+ static void mce_clear_info(struct mce_info *mi)
+ {
+ atomic_set(&mi->inuse, 0);
+ }
+
/*
* The actual machine check handler. This only handles real
* exceptions when something got corrupted coming in through int 18.
barrier();
/*
- * When no restart IP must always kill or panic.
+ * When no restart IP might need to kill or panic.
+ * Assume the worst for now, but if we find the
+ * severity is MCE_AR_SEVERITY we have other options.
*/
if (!(m.mcgstatus & MCG_STATUS_RIPV))
kill_it = 1;
continue;
}
- /*
- * Kill on action required.
- */
- if (severity == MCE_AR_SEVERITY)
- kill_it = 1;
-
- if (m.status & MCI_STATUS_MISCV)
- m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i));
- if (m.status & MCI_STATUS_ADDRV)
- m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i));
+ mce_read_aux(&m, i);
/*
* Action optional error. Queue address for later processing.
}
}
+ /* mce_clear_state will clear *final, save locally for use later */
+ m = *final;
+
if (!no_way_out)
mce_clear_state(toclear);
no_way_out = worst >= MCE_PANIC_SEVERITY;
/*
- * If we have decided that we just CAN'T continue, and the user
- * has not set tolerant to an insane level, give up and die.
- *
- * This is mainly used in the case when the system doesn't
- * support MCE broadcasting or it has been disabled.
+ * At insane "tolerant" levels we take no action. Otherwise
+ * we only die if we have no other choice. For less serious
+ * issues we try to recover, or limit damage to the current
+ * process.
*/
- if (no_way_out && tolerant < 3)
- mce_panic("Fatal machine check on current CPU", final, msg);
-
- /*
- * If the error seems to be unrecoverable, something should be
- * done. Try to kill as little as possible. If we can kill just
- * one task, do that. If the user has set the tolerance very
- * high, don't try to do anything at all.
- */
-
- if (kill_it && tolerant < 3)
- force_sig(SIGBUS, current);
-
- /* notify userspace ASAP */
- set_thread_flag(TIF_MCE_NOTIFY);
+ if (tolerant < 3) {
+ if (no_way_out)
+ mce_panic("Fatal machine check on current CPU", &m, msg);
+ if (worst == MCE_AR_SEVERITY) {
+ /* schedule action before return to userland */
+ mce_save_info(m.addr);
+ set_thread_flag(TIF_MCE_NOTIFY);
+ } else if (kill_it) {
+ force_sig(SIGBUS, current);
+ }
+ }
if (worst > 0)
mce_report_event(regs);
}
EXPORT_SYMBOL_GPL(do_machine_check);
- /* dummy to break dependency. actual code is in mm/memory-failure.c */
- void __attribute__((weak)) memory_failure(unsigned long pfn, int vector)
+ #ifndef CONFIG_MEMORY_FAILURE
+ int memory_failure(unsigned long pfn, int vector, int flags)
{
- printk(KERN_ERR "Action optional memory failure at %lx ignored\n", pfn);
+ /* mce_severity() should not hand us an ACTION_REQUIRED error */
+ BUG_ON(flags & MF_ACTION_REQUIRED);
+ printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n"
+ "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn);
+
+ return 0;
}
+ #endif
/*
- * Called after mce notification in process context. This code
- * is allowed to sleep. Call the high level VM handler to process
- * any corrupted pages.
- * Assume that the work queue code only calls this one at a time
- * per CPU.
- * Note we don't disable preemption, so this code might run on the wrong
- * CPU. In this case the event is picked up by the scheduled work queue.
- * This is merely a fast path to expedite processing in some common
- * cases.
+ * Called in process context that interrupted by MCE and marked with
+ * TIF_MCE_NOTIFY, just before returning to erroneous userland.
+ * This code is allowed to sleep.
+ * Attempt possible recovery such as calling the high level VM handler to
+ * process any corrupted pages, and kill/signal current process if required.
+ * Action required errors are handled here.
*/
void mce_notify_process(void)
{
unsigned long pfn;
- mce_notify_irq();
- while (mce_ring_get(&pfn))
- memory_failure(pfn, MCE_VECTOR);
+ struct mce_info *mi = mce_find_info();
+
+ if (!mi)
+ mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL);
+ pfn = mi->paddr >> PAGE_SHIFT;
+
+ clear_thread_flag(TIF_MCE_NOTIFY);
+
+ pr_err("Uncorrected hardware memory error in user-access at %llx",
+ mi->paddr);
+ if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+ pr_err("Memory error not recovered");
+ force_sig(SIGBUS, current);
+ }
+ mce_clear_info(mi);
}
+ /*
+ * Action optional processing happens here (picking up
+ * from the list of faulting pages that do_machine_check()
+ * placed into the "ring").
+ */
static void mce_process_work(struct work_struct *dummy)
{
- mce_notify_process();
+ unsigned long pfn;
+
+ while (mce_ring_get(&pfn))
+ memory_failure(pfn, MCE_VECTOR, 0);
}
#ifdef CONFIG_X86_MCE_INTEL
/* Not more than two messages every minute */
static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
- clear_thread_flag(TIF_MCE_NOTIFY);
-
if (test_and_clear_bit(0, &mce_need_notify)) {
/* wake processes polling /dev/mcelog */
wake_up_interruptible(&mce_chrdev_wait);
};
/*
- * mce_sysdev: Sysfs support
+ * mce_device: Sysfs support
*/
static void mce_cpu_restart(void *data)
__mcheck_cpu_init_timer();
}
-static struct sysdev_class mce_sysdev_class = {
+static struct bus_type mce_subsys = {
.name = "machinecheck",
+ .dev_name = "machinecheck",
};
-DEFINE_PER_CPU(struct sys_device, mce_sysdev);
+struct device *mce_device[CONFIG_NR_CPUS];
__cpuinitdata
void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
-static inline struct mce_bank *attr_to_bank(struct sysdev_attribute *attr)
+static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
{
return container_of(attr, struct mce_bank, attr);
}
-static ssize_t show_bank(struct sys_device *s, struct sysdev_attribute *attr,
+static ssize_t show_bank(struct device *s, struct device_attribute *attr,
char *buf)
{
return sprintf(buf, "%llx\n", attr_to_bank(attr)->ctl);
}
-static ssize_t set_bank(struct sys_device *s, struct sysdev_attribute *attr,
+static ssize_t set_bank(struct device *s, struct device_attribute *attr,
const char *buf, size_t size)
{
u64 new;
}
static ssize_t
-show_trigger(struct sys_device *s, struct sysdev_attribute *attr, char *buf)
+show_trigger(struct device *s, struct device_attribute *attr, char *buf)
{
strcpy(buf, mce_helper);
strcat(buf, "\n");
return strlen(mce_helper) + 1;
}
-static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
+static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
const char *buf, size_t siz)
{
char *p;
return strlen(mce_helper) + !!p;
}
-static ssize_t set_ignore_ce(struct sys_device *s,
- struct sysdev_attribute *attr,
+static ssize_t set_ignore_ce(struct device *s,
+ struct device_attribute *attr,
const char *buf, size_t size)
{
u64 new;
return size;
}
-static ssize_t set_cmci_disabled(struct sys_device *s,
- struct sysdev_attribute *attr,
+static ssize_t set_cmci_disabled(struct device *s,
+ struct device_attribute *attr,
const char *buf, size_t size)
{
u64 new;
return size;
}
-static ssize_t store_int_with_restart(struct sys_device *s,
- struct sysdev_attribute *attr,
+static ssize_t store_int_with_restart(struct device *s,
+ struct device_attribute *attr,
const char *buf, size_t size)
{
- ssize_t ret = sysdev_store_int(s, attr, buf, size);
+ ssize_t ret = device_store_int(s, attr, buf, size);
mce_restart();
return ret;
}
-static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger);
-static SYSDEV_INT_ATTR(tolerant, 0644, tolerant);
-static SYSDEV_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
-static SYSDEV_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);
+static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
+static DEVICE_INT_ATTR(tolerant, 0644, tolerant);
+static DEVICE_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
+static DEVICE_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);
-static struct sysdev_ext_attribute attr_check_interval = {
- _SYSDEV_ATTR(check_interval, 0644, sysdev_show_int,
- store_int_with_restart),
+static struct dev_ext_attribute dev_attr_check_interval = {
+ __ATTR(check_interval, 0644, device_show_int, store_int_with_restart),
&check_interval
};
-static struct sysdev_ext_attribute attr_ignore_ce = {
- _SYSDEV_ATTR(ignore_ce, 0644, sysdev_show_int, set_ignore_ce),
+static struct dev_ext_attribute dev_attr_ignore_ce = {
+ __ATTR(ignore_ce, 0644, device_show_int, set_ignore_ce),
&mce_ignore_ce
};
-static struct sysdev_ext_attribute attr_cmci_disabled = {
- _SYSDEV_ATTR(cmci_disabled, 0644, sysdev_show_int, set_cmci_disabled),
+static struct dev_ext_attribute dev_attr_cmci_disabled = {
+ __ATTR(cmci_disabled, 0644, device_show_int, set_cmci_disabled),
&mce_cmci_disabled
};
-static struct sysdev_attribute *mce_sysdev_attrs[] = {
- &attr_tolerant.attr,
- &attr_check_interval.attr,
- &attr_trigger,
- &attr_monarch_timeout.attr,
- &attr_dont_log_ce.attr,
- &attr_ignore_ce.attr,
- &attr_cmci_disabled.attr,
+static struct device_attribute *mce_device_attrs[] = {
+ &dev_attr_tolerant.attr,
+ &dev_attr_check_interval.attr,
+ &dev_attr_trigger,
+ &dev_attr_monarch_timeout.attr,
+ &dev_attr_dont_log_ce.attr,
+ &dev_attr_ignore_ce.attr,
+ &dev_attr_cmci_disabled.attr,
NULL
};
-static cpumask_var_t mce_sysdev_initialized;
+static cpumask_var_t mce_device_initialized;
+
+static void mce_device_release(struct device *dev)
+{
+ kfree(dev);
+}
-/* Per cpu sysdev init. All of the cpus still share the same ctrl bank: */
-static __cpuinit int mce_sysdev_create(unsigned int cpu)
+/* Per cpu device init. All of the cpus still share the same ctrl bank: */
+static __cpuinit int mce_device_create(unsigned int cpu)
{
- struct sys_device *sysdev = &per_cpu(mce_sysdev, cpu);
+ struct device *dev;
int err;
int i, j;
if (!mce_available(&boot_cpu_data))
return -EIO;
- memset(&sysdev->kobj, 0, sizeof(struct kobject));
- sysdev->id = cpu;
- sysdev->cls = &mce_sysdev_class;
+ dev = kzalloc(sizeof *dev, GFP_KERNEL);
+ if (!dev)
+ return -ENOMEM;
+ dev->id = cpu;
+ dev->bus = &mce_subsys;
+ dev->release = &mce_device_release;
- err = sysdev_register(sysdev);
+ err = device_register(dev);
if (err)
return err;
- for (i = 0; mce_sysdev_attrs[i]; i++) {
- err = sysdev_create_file(sysdev, mce_sysdev_attrs[i]);
+ for (i = 0; mce_device_attrs[i]; i++) {
+ err = device_create_file(dev, mce_device_attrs[i]);
if (err)
goto error;
}
for (j = 0; j < banks; j++) {
- err = sysdev_create_file(sysdev, &mce_banks[j].attr);
+ err = device_create_file(dev, &mce_banks[j].attr);
if (err)
goto error2;
}
- cpumask_set_cpu(cpu, mce_sysdev_initialized);
+ cpumask_set_cpu(cpu, mce_device_initialized);
+ mce_device[cpu] = dev;
return 0;
error2:
while (--j >= 0)
- sysdev_remove_file(sysdev, &mce_banks[j].attr);
+ device_remove_file(dev, &mce_banks[j].attr);
error:
while (--i >= 0)
- sysdev_remove_file(sysdev, mce_sysdev_attrs[i]);
+ device_remove_file(dev, mce_device_attrs[i]);
- sysdev_unregister(sysdev);
+ device_unregister(dev);
return err;
}
-static __cpuinit void mce_sysdev_remove(unsigned int cpu)
+static __cpuinit void mce_device_remove(unsigned int cpu)
{
- struct sys_device *sysdev = &per_cpu(mce_sysdev, cpu);
+ struct device *dev = mce_device[cpu];
int i;
- if (!cpumask_test_cpu(cpu, mce_sysdev_initialized))
+ if (!cpumask_test_cpu(cpu, mce_device_initialized))
return;
- for (i = 0; mce_sysdev_attrs[i]; i++)
- sysdev_remove_file(sysdev, mce_sysdev_attrs[i]);
+ for (i = 0; mce_device_attrs[i]; i++)
+ device_remove_file(dev, mce_device_attrs[i]);
for (i = 0; i < banks; i++)
- sysdev_remove_file(sysdev, &mce_banks[i].attr);
+ device_remove_file(dev, &mce_banks[i].attr);
- sysdev_unregister(sysdev);
- cpumask_clear_cpu(cpu, mce_sysdev_initialized);
+ device_unregister(dev);
+ cpumask_clear_cpu(cpu, mce_device_initialized);
+ mce_device[cpu] = NULL;
}
/* Make sure there are no machine checks on offlined CPUs. */
switch (action) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- mce_sysdev_create(cpu);
+ mce_device_create(cpu);
if (threshold_cpu_callback)
threshold_cpu_callback(action, cpu);
break;
case CPU_DEAD_FROZEN:
if (threshold_cpu_callback)
threshold_cpu_callback(action, cpu);
- mce_sysdev_remove(cpu);
+ mce_device_remove(cpu);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
for (i = 0; i < banks; i++) {
struct mce_bank *b = &mce_banks[i];
- struct sysdev_attribute *a = &b->attr;
+ struct device_attribute *a = &b->attr;
sysfs_attr_init(&a->attr);
a->attr.name = b->attrname;
if (!mce_available(&boot_cpu_data))
return -EIO;
- zalloc_cpumask_var(&mce_sysdev_initialized, GFP_KERNEL);
+ zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
mce_init_banks();
- err = sysdev_class_register(&mce_sysdev_class);
+ err = subsys_system_register(&mce_subsys, NULL);
if (err)
return err;
for_each_online_cpu(i) {
- err = mce_sysdev_create(i);
+ err = mce_device_create(i);
if (err)
return err;
}
/*
- * drivers/base/memory.c - basic Memory class support
+ * Memory subsystem support
*
* Written by Matt Tolentino <matthew.e.tolentino@intel.com>
* Dave Hansen <haveblue@us.ibm.com>
* SPARSEMEM should be contained here, or in mm/memory_hotplug.c.
*/
-#include <linux/sysdev.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/topology.h>
return section_nr / sections_per_block;
}
-static struct sysdev_class memory_sysdev_class = {
+static struct bus_type memory_subsys = {
.name = MEMORY_CLASS_NAME,
-};
-
-static const char *memory_uevent_name(struct kset *kset, struct kobject *kobj)
-{
- return MEMORY_CLASS_NAME;
-}
-
-static int memory_uevent(struct kset *kset, struct kobject *obj,
- struct kobj_uevent_env *env)
-{
- int retval = 0;
-
- return retval;
-}
-
-static const struct kset_uevent_ops memory_uevent_ops = {
- .name = memory_uevent_name,
- .uevent = memory_uevent,
+ .dev_name = MEMORY_CLASS_NAME,
};
static BLOCKING_NOTIFIER_HEAD(memory_chain);
{
int error;
- memory->sysdev.cls = &memory_sysdev_class;
- memory->sysdev.id = memory->start_section_nr / sections_per_block;
+ memory->dev.bus = &memory_subsys;
+ memory->dev.id = memory->start_section_nr / sections_per_block;
- error = sysdev_register(&memory->sysdev);
+ error = device_register(&memory->dev);
return error;
}
static void
unregister_memory(struct memory_block *memory)
{
- BUG_ON(memory->sysdev.cls != &memory_sysdev_class);
+ BUG_ON(memory->dev.bus != &memory_subsys);
/* drop the ref. we got in remove_memory_block() */
- kobject_put(&memory->sysdev.kobj);
- sysdev_unregister(&memory->sysdev);
+ kobject_put(&memory->dev.kobj);
+ device_unregister(&memory->dev);
}
unsigned long __weak memory_block_size_bytes(void)
* uses.
*/
-static ssize_t show_mem_start_phys_index(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_start_phys_index(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
unsigned long phys_index;
phys_index = mem->start_section_nr / sections_per_block;
return sprintf(buf, "%08lx\n", phys_index);
}
-static ssize_t show_mem_end_phys_index(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_end_phys_index(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
unsigned long phys_index;
phys_index = mem->end_section_nr / sections_per_block;
/*
* Show whether the section of memory is likely to be hot-removable
*/
-static ssize_t show_mem_removable(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_removable(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
unsigned long i, pfn;
int ret = 1;
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
for (i = 0; i < sections_per_block; i++) {
pfn = section_nr_to_pfn(mem->start_section_nr + i);
/*
* online, offline, going offline, etc.
*/
-static ssize_t show_mem_state(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_mem_state(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
ssize_t len = 0;
/*
ret = memory_block_action(mem->start_section_nr, to_state);
- if (ret)
+ if (ret) {
mem->state = from_state_req;
- else
- mem->state = to_state;
+ goto out;
+ }
+ mem->state = to_state;
+ switch (mem->state) {
+ case MEM_OFFLINE:
+ kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE);
+ break;
+ case MEM_ONLINE:
+ kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE);
+ break;
+ default:
+ break;
+ }
out:
mutex_unlock(&mem->state_mutex);
return ret;
}
static ssize_t
-store_mem_state(struct sys_device *dev,
- struct sysdev_attribute *attr, const char *buf, size_t count)
+store_mem_state(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
{
struct memory_block *mem;
int ret = -EINVAL;
- mem = container_of(dev, struct memory_block, sysdev);
+ mem = container_of(dev, struct memory_block, dev);
if (!strncmp(buf, "online", min((int)count, 6)))
ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
* s.t. if I offline all of these sections I can then
* remove the physical device?
*/
-static ssize_t show_phys_device(struct sys_device *dev,
- struct sysdev_attribute *attr, char *buf)
+static ssize_t show_phys_device(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct memory_block *mem =
- container_of(dev, struct memory_block, sysdev);
+ container_of(dev, struct memory_block, dev);
return sprintf(buf, "%d\n", mem->phys_device);
}
-static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
-static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
-static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
-static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
-static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);
+static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static DEVICE_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
+static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);
+static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);
+static DEVICE_ATTR(removable, 0444, show_mem_removable, NULL);
#define mem_create_simple_file(mem, attr_name) \
- sysdev_create_file(&mem->sysdev, &attr_##attr_name)
+ device_create_file(&mem->dev, &dev_attr_##attr_name)
#define mem_remove_simple_file(mem, attr_name) \
- sysdev_remove_file(&mem->sysdev, &attr_##attr_name)
+ device_remove_file(&mem->dev, &dev_attr_##attr_name)
/*
* Block size attribute stuff
*/
static ssize_t
-print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr,
+print_block_size(struct device *dev, struct device_attribute *attr,
char *buf)
{
return sprintf(buf, "%lx\n", get_memory_block_size());
}
-static SYSDEV_CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL);
+static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL);
static int block_size_init(void)
{
- return sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &attr_block_size_bytes.attr);
+ return device_create_file(memory_subsys.dev_root,
+ &dev_attr_block_size_bytes);
}
/*
*/
#ifdef CONFIG_ARCH_MEMORY_PROBE
static ssize_t
-memory_probe_store(struct class *class, struct class_attribute *attr,
+memory_probe_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
u64 phys_addr;
out:
return ret;
}
-static CLASS_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
+static DEVICE_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
static int memory_probe_init(void)
{
- return sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &class_attr_probe.attr);
+ return device_create_file(memory_subsys.dev_root, &dev_attr_probe);
}
#else
static inline int memory_probe_init(void)
/* Soft offline a page */
static ssize_t
-store_soft_offline_page(struct class *class,
- struct class_attribute *attr,
+store_soft_offline_page(struct device *dev,
+ struct device_attribute *attr,
const char *buf, size_t count)
{
int ret;
/* Forcibly offline a page, including killing processes. */
static ssize_t
-store_hard_offline_page(struct class *class,
- struct class_attribute *attr,
+store_hard_offline_page(struct device *dev,
+ struct device_attribute *attr,
const char *buf, size_t count)
{
int ret;
if (strict_strtoull(buf, 0, &pfn) < 0)
return -EINVAL;
pfn >>= PAGE_SHIFT;
- ret = __memory_failure(pfn, 0, 0);
+ ret = memory_failure(pfn, 0, 0);
return ret ? ret : count;
}
-static CLASS_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
-static CLASS_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);
+static DEVICE_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
+static DEVICE_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);
static __init int memory_fail_init(void)
{
int err;
- err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &class_attr_soft_offline_page.attr);
+ err = device_create_file(memory_subsys.dev_root,
+ &dev_attr_soft_offline_page);
if (!err)
- err = sysfs_create_file(&memory_sysdev_class.kset.kobj,
- &class_attr_hard_offline_page.attr);
+ err = device_create_file(memory_subsys.dev_root,
+ &dev_attr_hard_offline_page);
return err;
}
#else
return 0;
}
+/*
+ * A reference for the returned object is held and the reference for the
+ * hinted object is released.
+ */
struct memory_block *find_memory_block_hinted(struct mem_section *section,
struct memory_block *hint)
{
- struct kobject *kobj;
- struct sys_device *sysdev;
- struct memory_block *mem;
- char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
int block_id = base_memory_block_id(__section_nr(section));
+ struct device *hintdev = hint ? &hint->dev : NULL;
+ struct device *dev;
- kobj = hint ? &hint->sysdev.kobj : NULL;
-
- /*
- * This only works because we know that section == sysdev->id
- * slightly redundant with sysdev_register()
- */
- sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id);
-
- kobj = kset_find_obj_hinted(&memory_sysdev_class.kset, name, kobj);
- if (!kobj)
+ dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
+ if (hint)
+ put_device(&hint->dev);
+ if (!dev)
return NULL;
-
- sysdev = container_of(kobj, struct sys_device, kobj);
- mem = container_of(sysdev, struct memory_block, sysdev);
-
- return mem;
+ return container_of(dev, struct memory_block, dev);
}
/*
* this gets to be a real problem, we can always use a radix
* tree or something here.
*
- * This could be made generic for all sysdev classes.
+ * This could be made generic for all device subsystems.
*/
struct memory_block *find_memory_block(struct mem_section *section)
{
mem = find_memory_block(section);
if (mem) {
mem->section_count++;
- kobject_put(&mem->sysdev.kobj);
+ kobject_put(&mem->dev.kobj);
} else
ret = init_memory_block(&mem, section, state);
unregister_memory(mem);
kfree(mem);
} else
- kobject_put(&mem->sysdev.kobj);
+ kobject_put(&mem->dev.kobj);
mutex_unlock(&mem_sysfs_mutex);
return 0;
int err;
unsigned long block_sz;
- memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops;
- ret = sysdev_class_register(&memory_sysdev_class);
+ ret = subsys_system_register(&memory_subsys, NULL);
if (ret)
goto out;
extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, unsigned long * zones_size,
unsigned long zone_start_pfn, unsigned long *zholes_size);
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
/*
- * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
+ * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its
* zones, allocate the backing mem_map and account for memory holes in a more
* architecture independent manner. This is a substitute for creating the
* zone_sizes[] and zholes_size[] arrays and passing them to
* free_area_init_node()
*
* An architecture is expected to register range of page frames backed by
- * physical memory with add_active_range() before calling
+ * physical memory with memblock_add[_node]() before calling
* free_area_init_nodes() passing in the PFN each zone ends at. At a basic
* usage, an architecture is expected to do something like
*
* unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
* max_highmem_pfn};
* for_each_valid_physical_page_range()
- * add_active_range(node_id, start_pfn, end_pfn)
+ * memblock_add_node(base, size, nid)
* free_area_init_nodes(max_zone_pfns);
*
- * If the architecture guarantees that there are no holes in the ranges
- * registered with add_active_range(), free_bootmem_active_regions()
- * will call free_bootmem_node() for each registered physical page range.
- * Similarly sparse_memory_present_with_active_regions() calls
- * memory_present() for each range when SPARSEMEM is enabled.
+ * free_bootmem_with_active_regions() calls free_bootmem_node() for each
+ * registered physical page range. Similarly
+ * sparse_memory_present_with_active_regions() calls memory_present() for
+ * each range when SPARSEMEM is enabled.
*
* See mm/page_alloc.c for more information on each function exposed by
- * CONFIG_ARCH_POPULATES_NODE_MAP
+ * CONFIG_HAVE_MEMBLOCK_NODE_MAP.
*/
extern void free_area_init_nodes(unsigned long *max_zone_pfn);
-extern void add_active_range(unsigned int nid, unsigned long start_pfn,
- unsigned long end_pfn);
-extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
- unsigned long end_pfn);
-extern void remove_all_active_ranges(void);
-void sort_node_map(void);
unsigned long node_map_pfn_alignment(void);
unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
unsigned long end_pfn);
unsigned long max_low_pfn);
int add_from_early_node_map(struct range *range, int az,
int nr_range, int nid);
-u64 __init find_memory_core_early(int nid, u64 size, u64 align,
- u64 goal, u64 limit);
-typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
-extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
extern void sparse_memory_present_with_active_regions(int nid);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
-#if !defined(CONFIG_ARCH_POPULATES_NODE_MAP) && \
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
!defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
static inline int __early_pfn_to_nid(unsigned long pfn)
{
return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
}
+/* Look up the first VMA which exactly match the interval vm_start ... vm_end */
+static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
+ unsigned long vm_start, unsigned long vm_end)
+{
+ struct vm_area_struct *vma = find_vma(mm, vm_start);
+
+ if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end))
+ vma = NULL;
+
+ return vma;
+}
+
#ifdef CONFIG_MMU
pgprot_t vm_get_page_prot(unsigned long vm_flags);
#else
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_DEBUG_PAGEALLOC
-extern int debug_pagealloc_enabled;
-
extern void kernel_map_pages(struct page *page, int numpages, int enable);
-
-static inline void enable_debug_pagealloc(void)
-{
- debug_pagealloc_enabled = 1;
-}
#ifdef CONFIG_HIBERNATION
extern bool kernel_page_present(struct page *page);
#endif /* CONFIG_HIBERNATION */
#else
static inline void
kernel_map_pages(struct page *page, int numpages, int enable) {}
-static inline void enable_debug_pagealloc(void)
-{
-}
#ifdef CONFIG_HIBERNATION
static inline bool kernel_page_present(struct page *page) { return true; }
#endif /* CONFIG_HIBERNATION */
enum mf_flags {
MF_COUNT_INCREASED = 1 << 0,
+ MF_ACTION_REQUIRED = 1 << 1,
};
- extern void memory_failure(unsigned long pfn, int trapno);
- extern int __memory_failure(unsigned long pfn, int trapno, int flags);
+ extern int memory_failure(unsigned long pfn, int trapno, int flags);
extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
extern int unpoison_memory(unsigned long pfn);
extern int sysctl_memory_failure_early_kill;
unsigned int pages_per_huge_page);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+extern unsigned int _debug_guardpage_minorder;
+
+static inline unsigned int debug_guardpage_minorder(void)
+{
+ return _debug_guardpage_minorder;
+}
+
+static inline bool page_is_guard(struct page *page)
+{
+ return test_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+#else
+static inline unsigned int debug_guardpage_minorder(void) { return 0; }
+static inline bool page_is_guard(struct page *page) { return false; }
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */
EXPORT_SYMBOL_GPL(hwpoison_filter);
/*
- * Send all the processes who have the page mapped an ``action optional''
- * signal.
+ * Send all the processes who have the page mapped a signal.
+ * ``action optional'' if they are not immediately affected by the error
+ * ``action required'' if error happened in current execution context
*/
- static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
- unsigned long pfn, struct page *page)
+ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
+ unsigned long pfn, struct page *page, int flags)
{
struct siginfo si;
int ret;
printk(KERN_ERR
- "MCE %#lx: Killing %s:%d early due to hardware memory corruption\n",
+ "MCE %#lx: Killing %s:%d due to hardware memory corruption\n",
pfn, t->comm, t->pid);
si.si_signo = SIGBUS;
si.si_errno = 0;
- si.si_code = BUS_MCEERR_AO;
si.si_addr = (void *)addr;
#ifdef __ARCH_SI_TRAPNO
si.si_trapno = trapno;
#endif
si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
- /*
- * Don't use force here, it's convenient if the signal
- * can be temporarily blocked.
- * This could cause a loop when the user sets SIGBUS
- * to SIG_IGN, but hopefully no one will do that?
- */
- ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */
+
+ if ((flags & MF_ACTION_REQUIRED) && t == current) {
+ si.si_code = BUS_MCEERR_AR;
+ ret = force_sig_info(SIGBUS, &si, t);
+ } else {
+ /*
+ * Don't use force here, it's convenient if the signal
+ * can be temporarily blocked.
+ * This could cause a loop when the user sets SIGBUS
+ * to SIG_IGN, but hopefully no one will do that?
+ */
+ si.si_code = BUS_MCEERR_AO;
+ ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */
+ }
if (ret < 0)
printk(KERN_INFO "MCE: Error sending signal to %s:%d: %d\n",
t->comm, t->pid, ret);
* Also when FAIL is set do a force kill because something went
* wrong earlier.
*/
- static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
- int fail, struct page *page, unsigned long pfn)
+ static void kill_procs(struct list_head *to_kill, int doit, int trapno,
+ int fail, struct page *page, unsigned long pfn,
+ int flags)
{
struct to_kill *tk, *next;
* check for that, but we need to tell the
* process anyways.
*/
- else if (kill_proc_ao(tk->tsk, tk->addr, trapno,
- pfn, page) < 0)
+ else if (kill_proc(tk->tsk, tk->addr, trapno,
+ pfn, page, flags) < 0)
printk(KERN_ERR
"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
pfn, tk->tsk->comm, tk->tsk->pid);
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
- int trapno)
+ int trapno, int flags)
{
enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
* use a more force-full uncatchable kill to prevent
* any accesses to the poisoned memory.
*/
- kill_procs_ao(&tokill, !!PageDirty(ppage), trapno,
- ret != SWAP_SUCCESS, p, pfn);
+ kill_procs(&tokill, !!PageDirty(ppage), trapno,
+ ret != SWAP_SUCCESS, p, pfn, flags);
return ret;
}
ClearPageHWPoison(hpage + i);
}
- int __memory_failure(unsigned long pfn, int trapno, int flags)
+ /**
+ * memory_failure - Handle memory failure of a page.
+ * @pfn: Page Number of the corrupted page
+ * @trapno: Trap number reported in the signal to user space.
+ * @flags: fine tune action taken
+ *
+ * This function is called by the low level machine check code
+ * of an architecture when it detects hardware memory corruption
+ * of a page. It tries its best to recover, which includes
+ * dropping pages, killing processes etc.
+ *
+ * The function is primarily of use for corruptions that
+ * happen outside the current execution context (e.g. when
+ * detected by a background scrubber)
+ *
+ * Must run in process context (e.g. a work queue) with interrupts
+ * enabled and no spinlocks hold.
+ */
+ int memory_failure(unsigned long pfn, int trapno, int flags)
{
struct page_state *ps;
struct page *p;
* Now take care of user space mappings.
* Abort on fail: __delete_from_page_cache() assumes unmapped page.
*/
- if (hwpoison_user_mappings(p, pfn, trapno) != SWAP_SUCCESS) {
+ if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
res = -EBUSY;
goto out;
unlock_page(hpage);
return res;
}
- EXPORT_SYMBOL_GPL(__memory_failure);
-
- /**
- * memory_failure - Handle memory failure of a page.
- * @pfn: Page Number of the corrupted page
- * @trapno: Trap number reported in the signal to user space.
- *
- * This function is called by the low level machine check code
- * of an architecture when it detects hardware memory corruption
- * of a page. It tries its best to recover, which includes
- * dropping pages, killing processes etc.
- *
- * The function is primarily of use for corruptions that
- * happen outside the current execution context (e.g. when
- * detected by a background scrubber)
- *
- * Must run in process context (e.g. a work queue) with interrupts
- * enabled and no spinlocks hold.
- */
- void memory_failure(unsigned long pfn, int trapno)
- {
- __memory_failure(pfn, trapno, 0);
- }
+ EXPORT_SYMBOL_GPL(memory_failure);
#define MEMORY_FAILURE_FIFO_ORDER 4
#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER)
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
if (!gotten)
break;
- __memory_failure(entry.pfn, entry.trapno, entry.flags);
+ memory_failure(entry.pfn, entry.trapno, entry.flags);
}
}
page_is_file_cache(page));
list_add(&page->lru, &pagelist);
ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
- 0, true);
+ 0, MIGRATE_SYNC);
if (ret) {
putback_lru_pages(&pagelist);
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",