#include <linux/debugfs.h>
#include <linux/irq_work.h>
#include <linux/export.h>
+#include <linux/jump_label.h>
#include <asm/processor.h>
#include <asm/traps.h>
if (m->misc)
pr_cont("MISC %llx ", m->misc);
+ if (mce_flags.smca) {
+ if (m->synd)
+ pr_cont("SYND %llx ", m->synd);
+ if (m->ipid)
+ pr_cont("IPID %llx ", m->ipid);
+ }
+
pr_cont("\n");
/*
* Note this output is parsed by external tools and old fields
static void mce_schedule_work(void)
{
- if (!mce_gen_pool_empty() && keventd_up())
+ if (!mce_gen_pool_empty())
schedule_work(&mce_work);
}
{
if (m->status & MCI_STATUS_MISCV)
m->misc = mce_rdmsrl(msr_ops.misc(i));
+
if (m->status & MCI_STATUS_ADDRV) {
m->addr = mce_rdmsrl(msr_ops.addr(i));
m->addr >>= shift;
m->addr <<= shift;
}
+
+ /*
+ * Extract [55:<lsb>] where lsb is the least significant
+ * *valid* bit of the address bits.
+ */
+ if (mce_flags.smca) {
+ u8 lsb = (m->addr >> 56) & 0x3f;
+
+ m->addr &= GENMASK_ULL(55, lsb);
+ }
+ }
+
+ if (mce_flags.smca) {
+ m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+
+ if (m->status & MCI_STATUS_SYNDV)
+ m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
}
}
if (c->x86 == 6 && c->x86_model == 45)
quirk_no_way_out = quirk_sandybridge_ifu;
- /*
- * MCG_CAP.MCG_SER_P is necessary but not sufficient to know
- * whether this processor will actually generate recoverable
- * machine checks. Check to see if this is an E7 model Xeon.
- * We can't do a model number check because E5 and E7 use the
- * same model number. E5 doesn't support recovery, E7 does.
- */
- if (mca_cfg.recovery || (mca_cfg.ser &&
- !strncmp(c->x86_model_id,
- "Intel(R) Xeon(R) CPU E7-", 24)))
- set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY);
}
if (cfg->monarch_timeout < 0)
cfg->monarch_timeout = 0;
* mce=bootlog Log MCEs from before booting. Disabled by default on AMD.
* mce=nobootlog Don't log MCEs from before booting.
* mce=bios_cmci_threshold Don't program the CMCI threshold
+ * mce=recovery force enable memcpy_mcsafe()
*/
static int __init mcheck_enable(char *str)
{
static int __init mcheck_debugfs_init(void) { return -EINVAL; }
#endif
+DEFINE_STATIC_KEY_FALSE(mcsafe_key);
+EXPORT_SYMBOL_GPL(mcsafe_key);
+
static int __init mcheck_late_init(void)
{
+ if (mca_cfg.recovery)
+ static_branch_inc(&mcsafe_key);
+
mcheck_debugfs_init();
/*
if (i > vc->vc_npar)
return i;
- if (vc->vc_par[i] == 5 && i < vc->vc_npar) {
- /* 256 colours -- ubiquitous */
+ if (vc->vc_par[i] == 5 && i + 1 <= vc->vc_npar) {
+ /* 256 colours */
i++;
rgb_from_256(vc->vc_par[i], &c);
- } else if (vc->vc_par[i] == 2 && i <= vc->vc_npar + 3) {
- /* 24 bit -- extremely rare */
+ } else if (vc->vc_par[i] == 2 && i + 3 <= vc->vc_npar) {
+ /* 24 bit */
c.r = vc->vc_par[i + 1];
c.g = vc->vc_par[i + 2];
c.b = vc->vc_par[i + 3];
(vc->vc_color & 0x0f);
break;
default:
+ if (vc->vc_par[i] >= 90 && vc->vc_par[i] <= 107) {
+ if (vc->vc_par[i] < 100)
+ vc->vc_intensity = 2;
+ vc->vc_par[i] -= 60;
+ }
if (vc->vc_par[i] >= 30 && vc->vc_par[i] <= 37)
vc->vc_color = color_table[vc->vc_par[i] - 30]
| (vc->vc_color & 0xf0);
pr_info("Console: switching ");
if (!deflt)
- printk("consoles %d-%d ", first+1, last+1);
+ printk(KERN_CONT "consoles %d-%d ", first+1, last+1);
if (j >= 0) {
struct vc_data *vc = vc_cons[j].d;
- printk("to %s %s %dx%d\n",
+ printk(KERN_CONT "to %s %s %dx%d\n",
vc->vc_can_do_color ? "colour" : "mono",
desc, vc->vc_cols, vc->vc_rows);
update_screen(vc);
}
} else
- printk("to %s\n", desc);
+ printk(KERN_CONT "to %s\n", desc);
retval = 0;
err:
*/
static void blank_screen_t(unsigned long dummy)
{
- if (unlikely(!keventd_up())) {
- mod_timer(&console_timer, jiffies + (blankinterval * HZ));
- return;
- }
blank_timer_expired = 1;
schedule_work(&console_work);
}
int execute_in_process_context(work_func_t fn, struct execute_work *);
extern bool flush_work(struct work_struct *work);
+extern bool cancel_work(struct work_struct *work);
extern bool cancel_work_sync(struct work_struct *work);
extern bool flush_delayed_work(struct delayed_work *dwork);
return queue_delayed_work(system_wq, dwork, delay);
}
- /**
- * keventd_up - is workqueue initialized yet?
- */
- static inline bool keventd_up(void)
- {
- return system_wq != NULL;
- }
-
#ifndef CONFIG_SMP
static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
{
int workqueue_offline_cpu(unsigned int cpu);
#endif
+ int __init workqueue_init_early(void);
+ int __init workqueue_init(void);
+
#endif
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
idr_init_cache();
+
+ /*
+ * Allow workqueue creation and work item queueing/cancelling
+ * early. Work item execution depends on kthreads and starts after
+ * workqueue_init().
+ */
+ workqueue_init_early();
+
rcu_init();
/* trace_printk() and trace points may be used after this */
}
WARN(msgbuf[0], "initcall %pF returned with %s\n", fn, msgbuf);
+ add_latent_entropy();
return ret;
}
smp_prepare_cpus(setup_max_cpus);
+ workqueue_init();
+
do_pre_smp_initcalls();
lockup_detector_init();
static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
module_param_named(power_efficient, wq_power_efficient, bool, 0444);
+ static bool wq_online; /* can kworkers be created yet? */
+
static bool wq_numa_enabled; /* unbound NUMA affinity enabled */
/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
};
int next_color;
+ if (WARN_ON(!wq_online))
+ return;
+
lock_map_acquire(&wq->lockdep_map);
lock_map_release(&wq->lockdep_map);
{
struct wq_barrier barr;
+ if (WARN_ON(!wq_online))
+ return false;
+
lock_map_acquire(&work->lockdep_map);
lock_map_release(&work->lockdep_map);
mark_work_canceling(work);
local_irq_restore(flags);
- flush_work(work);
+ /*
+ * This allows canceling during early boot. We know that @work
+ * isn't executing.
+ */
+ if (wq_online)
+ flush_work(work);
+
clear_work_data(work);
/*
}
EXPORT_SYMBOL(flush_delayed_work);
+static bool __cancel_work(struct work_struct *work, bool is_dwork)
+{
+ unsigned long flags;
+ int ret;
+
+ do {
+ ret = try_to_grab_pending(work, is_dwork, &flags);
+ } while (unlikely(ret == -EAGAIN));
+
+ if (unlikely(ret < 0))
+ return false;
+
+ set_work_pool_and_clear_pending(work, get_work_pool_id(work));
+ local_irq_restore(flags);
+ return ret;
+}
+
+/*
+ * See cancel_delayed_work()
+ */
+bool cancel_work(struct work_struct *work)
+{
+ return __cancel_work(work, false);
+}
+
/**
* cancel_delayed_work - cancel a delayed work
* @dwork: delayed_work to cancel
*/
bool cancel_delayed_work(struct delayed_work *dwork)
{
- unsigned long flags;
- int ret;
-
- do {
- ret = try_to_grab_pending(&dwork->work, true, &flags);
- } while (unlikely(ret == -EAGAIN));
-
- if (unlikely(ret < 0))
- return false;
-
- set_work_pool_and_clear_pending(&dwork->work,
- get_work_pool_id(&dwork->work));
- local_irq_restore(flags);
- return ret;
+ return __cancel_work(&dwork->work, true);
}
EXPORT_SYMBOL(cancel_delayed_work);
goto fail;
/* create and start the initial worker */
- if (!create_worker(pool))
+ if (wq_online && !create_worker(pool))
goto fail;
/* install */
{
struct workqueue_struct *wq = pwq->wq;
bool freezable = wq->flags & WQ_FREEZABLE;
+ unsigned long flags;
/* for @wq->saved_max_active */
lockdep_assert_held(&wq->mutex);
if (!freezable && pwq->max_active == wq->saved_max_active)
return;
- spin_lock_irq(&pwq->pool->lock);
+ /* this function can be called during early boot w/ irq disabled */
+ spin_lock_irqsave(&pwq->pool->lock, flags);
/*
* During [un]freezing, the caller is responsible for ensuring that
pwq->max_active = 0;
}
- spin_unlock_irq(&pwq->pool->lock);
+ spin_unlock_irqrestore(&pwq->pool->lock, flags);
}
/* initialize newly alloced @pwq which is associated with @wq and @pool */
for (i = 0; i < WORK_NR_COLORS; i++) {
if (WARN_ON(pwq->nr_in_flight[i])) {
mutex_unlock(&wq->mutex);
+ show_workqueue_state();
return;
}
}
WARN_ON(pwq->nr_active) ||
WARN_ON(!list_empty(&pwq->delayed_works))) {
mutex_unlock(&wq->mutex);
+ show_workqueue_state();
return;
}
}
* This function is called without any synchronization and @task
* could be in any state. Be careful with dereferences.
*/
- worker = probe_kthread_data(task);
+ worker = kthread_probe_data(task);
/*
* Carefully copy the associated workqueue's workfn and name. Keep
wq_numa_enabled = true;
}
- static int __init init_workqueues(void)
+ /**
+ * workqueue_init_early - early init for workqueue subsystem
+ *
+ * This is the first half of two-staged workqueue subsystem initialization
+ * and invoked as soon as the bare basics - memory allocation, cpumasks and
+ * idr are up. It sets up all the data structures and system workqueues
+ * and allows early boot code to create workqueues and queue/cancel work
+ * items. Actual work item execution starts only after kthreads can be
+ * created and scheduled right before early initcalls.
+ */
+ int __init workqueue_init_early(void)
{
int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
int i, cpu;
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
- wq_numa_init();
-
/* initialize CPU pools */
for_each_possible_cpu(cpu) {
struct worker_pool *pool;
}
}
- /* create the initial worker */
- for_each_online_cpu(cpu) {
- struct worker_pool *pool;
-
- for_each_cpu_worker_pool(pool, cpu) {
- pool->flags &= ~POOL_DISASSOCIATED;
- BUG_ON(!create_worker(pool));
- }
- }
-
/* create default unbound and ordered wq attrs */
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
!system_power_efficient_wq ||
!system_freezable_power_efficient_wq);
+ return 0;
+ }
+
+ /**
+ * workqueue_init - bring workqueue subsystem fully online
+ *
+ * This is the latter half of two-staged workqueue subsystem initialization
+ * and invoked as soon as kthreads can be created and scheduled.
+ * Workqueues have been created and work items queued on them, but there
+ * are no kworkers executing the work items yet. Populate the worker pools
+ * with the initial workers and enable future kworker creations.
+ */
+ int __init workqueue_init(void)
+ {
+ struct workqueue_struct *wq;
+ struct worker_pool *pool;
+ int cpu, bkt;
+
+ /*
+ * It'd be simpler to initialize NUMA in workqueue_init_early() but
+ * CPU to node mapping may not be available that early on some
+ * archs such as power and arm64. As per-cpu pools created
+ * previously could be missing node hint and unbound pools NUMA
+ * affinity, fix them up.
+ */
+ wq_numa_init();
+
+ mutex_lock(&wq_pool_mutex);
+
+ for_each_possible_cpu(cpu) {
+ for_each_cpu_worker_pool(pool, cpu) {
+ pool->node = cpu_to_node(cpu);
+ }
+ }
+
+ list_for_each_entry(wq, &workqueues, list)
+ wq_update_unbound_numa(wq, smp_processor_id(), true);
+
+ mutex_unlock(&wq_pool_mutex);
+
+ /* create the initial workers */
+ for_each_online_cpu(cpu) {
+ for_each_cpu_worker_pool(pool, cpu) {
+ pool->flags &= ~POOL_DISASSOCIATED;
+ BUG_ON(!create_worker(pool));
+ }
+ }
+
+ hash_for_each(unbound_pool_hash, bkt, pool, hash_node)
+ BUG_ON(!create_worker(pool));
+
+ wq_online = true;
wq_watchdog_init();
return 0;
}
- early_initcall(init_workqueues);
{
struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
- /*
- * When this gets called from do_initcalls via cpucache_init(),
- * init_workqueues() has already run, so keventd will be setup
- * at that time.
- */
- if (keventd_up() && reap_work->work.func == NULL) {
+ if (reap_work->work.func == NULL) {
init_reap_node(cpu);
INIT_DEFERRABLE_WORK(reap_work, cache_reap);
schedule_delayed_work_on(cpu, reap_work,
return 0;
}
+#if (defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)) || defined(CONFIG_SMP)
/*
* Allocates and initializes node for a node on each slab cache, used for
* either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node
return 0;
}
+#endif
static int setup_kmem_cache_node(struct kmem_cache *cachep,
int node, gfp_t gfp, bool force_change)
return ret;
}
+#ifdef CONFIG_SMP
+
static void cpuup_canceled(long cpu)
{
struct kmem_cache *cachep;
return -ENOMEM;
}
-static int cpuup_callback(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+int slab_prepare_cpu(unsigned int cpu)
{
- long cpu = (long)hcpu;
- int err = 0;
+ int err;
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- mutex_lock(&slab_mutex);
- err = cpuup_prepare(cpu);
- mutex_unlock(&slab_mutex);
- break;
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- start_cpu_timer(cpu);
- break;
-#ifdef CONFIG_HOTPLUG_CPU
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- /*
- * Shutdown cache reaper. Note that the slab_mutex is
- * held so that if cache_reap() is invoked it cannot do
- * anything expensive but will only modify reap_work
- * and reschedule the timer.
- */
- cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
- /* Now the cache_reaper is guaranteed to be not running. */
- per_cpu(slab_reap_work, cpu).work.func = NULL;
- break;
- case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- start_cpu_timer(cpu);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- /*
- * Even if all the cpus of a node are down, we don't free the
- * kmem_cache_node of any cache. This to avoid a race between
- * cpu_down, and a kmalloc allocation from another cpu for
- * memory from the node of the cpu going down. The node
- * structure is usually allocated from kmem_cache_create() and
- * gets destroyed at kmem_cache_destroy().
- */
- /* fall through */
+ mutex_lock(&slab_mutex);
+ err = cpuup_prepare(cpu);
+ mutex_unlock(&slab_mutex);
+ return err;
+}
+
+/*
+ * This is called for a failed online attempt and for a successful
+ * offline.
+ *
+ * Even if all the cpus of a node are down, we don't free the
+ * kmem_list3 of any cache. This to avoid a race between cpu_down, and
+ * a kmalloc allocation from another cpu for memory from the node of
+ * the cpu going down. The list3 structure is usually allocated from
+ * kmem_cache_create() and gets destroyed at kmem_cache_destroy().
+ */
+int slab_dead_cpu(unsigned int cpu)
+{
+ mutex_lock(&slab_mutex);
+ cpuup_canceled(cpu);
+ mutex_unlock(&slab_mutex);
+ return 0;
+}
#endif
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- mutex_lock(&slab_mutex);
- cpuup_canceled(cpu);
- mutex_unlock(&slab_mutex);
- break;
- }
- return notifier_from_errno(err);
+
+static int slab_online_cpu(unsigned int cpu)
+{
+ start_cpu_timer(cpu);
+ return 0;
}
-static struct notifier_block cpucache_notifier = {
- &cpuup_callback, NULL, 0
-};
+static int slab_offline_cpu(unsigned int cpu)
+{
+ /*
+ * Shutdown cache reaper. Note that the slab_mutex is held so
+ * that if cache_reap() is invoked it cannot do anything
+ * expensive but will only modify reap_work and reschedule the
+ * timer.
+ */
+ cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
+ /* Now the cache_reaper is guaranteed to be not running. */
+ per_cpu(slab_reap_work, cpu).work.func = NULL;
+ return 0;
+}
#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
/*
/* Done! */
slab_state = FULL;
- /*
- * Register a cpu startup notifier callback that initializes
- * cpu_cache_get for all new cpus
- */
- register_cpu_notifier(&cpucache_notifier);
-
#ifdef CONFIG_NUMA
/*
* Register a memory hotplug callback that initializes and frees
static int __init cpucache_init(void)
{
- int cpu;
+ int ret;
/*
* Register the timers that return unneeded pages to the page allocator
*/
- for_each_online_cpu(cpu)
- start_cpu_timer(cpu);
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SLAB online",
+ slab_online_cpu, slab_offline_cpu);
+ WARN_ON(ret < 0);
/* Done! */
slab_state = FULL;