summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cpuset.c9
-rw-r--r--kernel/events/core.c12
-rw-r--r--kernel/irq/manage.c7
-rw-r--r--kernel/irq/pm.c7
-rw-r--r--kernel/livepatch/core.c43
-rw-r--r--kernel/locking/lockdep.c81
-rw-r--r--kernel/locking/rtmutex.c1
-rw-r--r--kernel/module.c31
-rw-r--r--kernel/power/snapshot.c21
-rw-r--r--kernel/printk/console_cmdline.h2
-rw-r--r--kernel/printk/printk.c1
-rw-r--r--kernel/sched/core.c17
-rw-r--r--kernel/sched/fair.c12
-rw-r--r--kernel/sched/idle.c54
-rw-r--r--kernel/sys.c3
-rw-r--r--kernel/sysctl.c8
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c11
-rw-r--r--kernel/trace/ftrace.c40
-rw-r--r--kernel/workqueue.c56
19 files changed, 303 insertions, 113 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1d1fe9361d29..fc7f4748d34a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -548,9 +548,6 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
rcu_read_lock();
cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
- if (cp == root_cs)
- continue;
-
/* skip the whole subtree if @cp doesn't have any CPU */
if (cpumask_empty(cp->cpus_allowed)) {
pos_css = css_rightmost_descendant(pos_css);
@@ -873,7 +870,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
* If it becomes empty, inherit the effective mask of the
* parent, which is guaranteed to have some CPUs.
*/
- if (cpumask_empty(new_cpus))
+ if (cgroup_on_dfl(cp->css.cgroup) && cpumask_empty(new_cpus))
cpumask_copy(new_cpus, parent->effective_cpus);
/* Skip the whole subtree if the cpumask remains the same. */
@@ -1129,7 +1126,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
* If it becomes empty, inherit the effective mask of the
* parent, which is guaranteed to have some MEMs.
*/
- if (nodes_empty(*new_mems))
+ if (cgroup_on_dfl(cp->css.cgroup) && nodes_empty(*new_mems))
*new_mems = parent->effective_mems;
/* Skip the whole subtree if the nodemask remains the same. */
@@ -1979,7 +1976,9 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
spin_lock_irq(&callback_lock);
cs->mems_allowed = parent->mems_allowed;
+ cs->effective_mems = parent->mems_allowed;
cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+ cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
spin_unlock_irq(&callback_lock);
out_unlock:
mutex_unlock(&cpuset_mutex);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f04daabfd1cf..2fabc0627165 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3591,7 +3591,7 @@ static void put_event(struct perf_event *event)
ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
WARN_ON_ONCE(ctx->parent_ctx);
perf_remove_from_context(event, true);
- mutex_unlock(&ctx->mutex);
+ perf_event_ctx_unlock(event, ctx);
_free_event(event);
}
@@ -4574,6 +4574,13 @@ static void perf_pending_event(struct irq_work *entry)
{
struct perf_event *event = container_of(entry,
struct perf_event, pending);
+ int rctx;
+
+ rctx = perf_swevent_get_recursion_context();
+ /*
+ * If we 'fail' here, that's OK, it means recursion is already disabled
+ * and we won't recurse 'further'.
+ */
if (event->pending_disable) {
event->pending_disable = 0;
@@ -4584,6 +4591,9 @@ static void perf_pending_event(struct irq_work *entry)
event->pending_wakeup = 0;
perf_event_wakeup(event);
}
+
+ if (rctx >= 0)
+ perf_swevent_put_recursion_context(rctx);
}
/*
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 196a06fbc122..886d09e691d5 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1474,8 +1474,13 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
* otherwise we'll have trouble later trying to figure out
* which interrupt is which (messes up the interrupt freeing
* logic etc).
+ *
+ * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
+ * it cannot be set along with IRQF_NO_SUSPEND.
*/
- if ((irqflags & IRQF_SHARED) && !dev_id)
+ if (((irqflags & IRQF_SHARED) && !dev_id) ||
+ (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
+ ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
return -EINVAL;
desc = irq_to_desc(irq);
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 3ca532592704..5204a6d1b985 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -43,9 +43,12 @@ void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action)
if (action->flags & IRQF_NO_SUSPEND)
desc->no_suspend_depth++;
+ else if (action->flags & IRQF_COND_SUSPEND)
+ desc->cond_suspend_depth++;
WARN_ON_ONCE(desc->no_suspend_depth &&
- desc->no_suspend_depth != desc->nr_actions);
+ (desc->no_suspend_depth +
+ desc->cond_suspend_depth) != desc->nr_actions);
}
/*
@@ -61,6 +64,8 @@ void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action)
if (action->flags & IRQF_NO_SUSPEND)
desc->no_suspend_depth--;
+ else if (action->flags & IRQF_COND_SUSPEND)
+ desc->cond_suspend_depth--;
}
static bool suspend_device_irq(struct irq_desc *desc, int irq)
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index ff7f47d026ac..3f9f1d6b4c2e 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -89,16 +89,28 @@ static bool klp_is_object_loaded(struct klp_object *obj)
/* sets obj->mod if object is not vmlinux and module is found */
static void klp_find_object_module(struct klp_object *obj)
{
+ struct module *mod;
+
if (!klp_is_module(obj))
return;
mutex_lock(&module_mutex);
/*
- * We don't need to take a reference on the module here because we have
- * the klp_mutex, which is also taken by the module notifier. This
- * prevents any module from unloading until we release the klp_mutex.
+ * We do not want to block removal of patched modules and therefore
+ * we do not take a reference here. The patches are removed by
+ * a going module handler instead.
+ */
+ mod = find_module(obj->name);
+ /*
+ * Do not mess work of the module coming and going notifiers.
+ * Note that the patch might still be needed before the going handler
+ * is called. Module functions can be called even in the GOING state
+ * until mod->exit() finishes. This is especially important for
+ * patches that modify semantic of the functions.
*/
- obj->mod = find_module(obj->name);
+ if (mod && mod->klp_alive)
+ obj->mod = mod;
+
mutex_unlock(&module_mutex);
}
@@ -248,11 +260,12 @@ static int klp_find_external_symbol(struct module *pmod, const char *name,
/* first, check if it's an exported symbol */
preempt_disable();
sym = find_symbol(name, NULL, NULL, true, true);
- preempt_enable();
if (sym) {
*addr = sym->value;
+ preempt_enable();
return 0;
}
+ preempt_enable();
/* otherwise check if it's in another .o within the patch module */
return klp_find_object_symbol(pmod->name, name, addr);
@@ -314,12 +327,12 @@ static void notrace klp_ftrace_handler(unsigned long ip,
rcu_read_lock();
func = list_first_or_null_rcu(&ops->func_stack, struct klp_func,
stack_node);
- rcu_read_unlock();
-
if (WARN_ON_ONCE(!func))
- return;
+ goto unlock;
klp_arch_set_pc(regs, (unsigned long)func->new_func);
+unlock:
+ rcu_read_unlock();
}
static int klp_disable_func(struct klp_func *func)
@@ -731,7 +744,7 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
func->state = KLP_DISABLED;
return kobject_init_and_add(&func->kobj, &klp_ktype_func,
- obj->kobj, func->old_name);
+ obj->kobj, "%s", func->old_name);
}
/* parts of the initialization that is done only when the object is loaded */
@@ -766,6 +779,7 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj)
return -EINVAL;
obj->state = KLP_DISABLED;
+ obj->mod = NULL;
klp_find_object_module(obj);
@@ -807,7 +821,7 @@ static int klp_init_patch(struct klp_patch *patch)
patch->state = KLP_DISABLED;
ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch,
- klp_root_kobj, patch->mod->name);
+ klp_root_kobj, "%s", patch->mod->name);
if (ret)
goto unlock;
@@ -960,6 +974,15 @@ static int klp_module_notify(struct notifier_block *nb, unsigned long action,
mutex_lock(&klp_mutex);
+ /*
+ * Each module has to know that the notifier has been called.
+ * We never know what module will get patched by a new patch.
+ */
+ if (action == MODULE_STATE_COMING)
+ mod->klp_alive = true;
+ else /* MODULE_STATE_GOING */
+ mod->klp_alive = false;
+
list_for_each_entry(patch, &klp_patches, list) {
for (obj = patch->objs; obj->funcs; obj++) {
if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 88d0d4420ad2..ba77ab5f64dd 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -633,7 +633,7 @@ static int count_matching_names(struct lock_class *new_class)
if (!new_class->name)
return 0;
- list_for_each_entry(class, &all_lock_classes, lock_entry) {
+ list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
if (new_class->key - new_class->subclass == class->key)
return class->name_version;
if (class->name && !strcmp(class->name, new_class->name))
@@ -700,10 +700,12 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
hash_head = classhashentry(key);
/*
- * We can walk the hash lockfree, because the hash only
- * grows, and we are careful when adding entries to the end:
+ * We do an RCU walk of the hash, see lockdep_free_key_range().
*/
- list_for_each_entry(class, hash_head, hash_entry) {
+ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+ return NULL;
+
+ list_for_each_entry_rcu(class, hash_head, hash_entry) {
if (class->key == key) {
/*
* Huh! same key, different name? Did someone trample
@@ -728,7 +730,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
struct lockdep_subclass_key *key;
struct list_head *hash_head;
struct lock_class *class;
- unsigned long flags;
+
+ DEBUG_LOCKS_WARN_ON(!irqs_disabled());
class = look_up_lock_class(lock, subclass);
if (likely(class))
@@ -750,28 +753,26 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
key = lock->key->subkeys + subclass;
hash_head = classhashentry(key);
- raw_local_irq_save(flags);
if (!graph_lock()) {
- raw_local_irq_restore(flags);
return NULL;
}
/*
* We have to do the hash-walk again, to avoid races
* with another CPU:
*/
- list_for_each_entry(class, hash_head, hash_entry)
+ list_for_each_entry_rcu(class, hash_head, hash_entry) {
if (class->key == key)
goto out_unlock_set;
+ }
+
/*
* Allocate a new key from the static array, and add it to
* the hash:
*/
if (nr_lock_classes >= MAX_LOCKDEP_KEYS) {
if (!debug_locks_off_graph_unlock()) {
- raw_local_irq_restore(flags);
return NULL;
}
- raw_local_irq_restore(flags);
print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!");
dump_stack();
@@ -798,7 +799,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
if (verbose(class)) {
graph_unlock();
- raw_local_irq_restore(flags);
printk("\nnew class %p: %s", class->key, class->name);
if (class->name_version > 1)
@@ -806,15 +806,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
printk("\n");
dump_stack();
- raw_local_irq_save(flags);
if (!graph_lock()) {
- raw_local_irq_restore(flags);
return NULL;
}
}
out_unlock_set:
graph_unlock();
- raw_local_irq_restore(flags);
out_set_class_cache:
if (!subclass || force)
@@ -870,11 +867,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
entry->distance = distance;
entry->trace = *trace;
/*
- * Since we never remove from the dependency list, the list can
- * be walked lockless by other CPUs, it's only allocation
- * that must be protected by the spinlock. But this also means
- * we must make new entries visible only once writes to the
- * entry become visible - hence the RCU op:
+ * Both allocation and removal are done under the graph lock; but
+ * iteration is under RCU-sched; see look_up_lock_class() and
+ * lockdep_free_key_range().
*/
list_add_tail_rcu(&entry->entry, head);
@@ -1025,7 +1020,9 @@ static int __bfs(struct lock_list *source_entry,
else
head = &lock->class->locks_before;
- list_for_each_entry(entry, head, entry) {
+ DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
+ list_for_each_entry_rcu(entry, head, entry) {
if (!lock_accessed(entry)) {
unsigned int cq_depth;
mark_lock_accessed(entry, lock);
@@ -2022,7 +2019,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
* We can walk it lock-free, because entries only get added
* to the hash:
*/
- list_for_each_entry(chain, hash_head, entry) {
+ list_for_each_entry_rcu(chain, hash_head, entry) {
if (chain->chain_key == chain_key) {
cache_hit:
debug_atomic_inc(chain_lookup_hits);
@@ -2996,8 +2993,18 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
if (unlikely(!debug_locks))
return;
- if (subclass)
+ if (subclass) {
+ unsigned long flags;
+
+ if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+ return;
+
+ raw_local_irq_save(flags);
+ current->lockdep_recursion = 1;
register_lock_class(lock, subclass, 1);
+ current->lockdep_recursion = 0;
+ raw_local_irq_restore(flags);
+ }
}
EXPORT_SYMBOL_GPL(lockdep_init_map);
@@ -3887,9 +3894,17 @@ static inline int within(const void *addr, void *start, unsigned long size)
return addr >= start && addr < start + size;
}
+/*
+ * Used in module.c to remove lock classes from memory that is going to be
+ * freed; and possibly re-used by other modules.
+ *
+ * We will have had one sync_sched() before getting here, so we're guaranteed
+ * nobody will look up these exact classes -- they're properly dead but still
+ * allocated.
+ */
void lockdep_free_key_range(void *start, unsigned long size)
{
- struct lock_class *class, *next;
+ struct lock_class *class;
struct list_head *head;
unsigned long flags;
int i;
@@ -3905,7 +3920,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
head = classhash_table + i;
if (list_empty(head))
continue;
- list_for_each_entry_safe(class, next, head, hash_entry) {
+ list_for_each_entry_rcu(class, head, hash_entry) {
if (within(class->key, start, size))
zap_class(class);
else if (within(class->name, start, size))
@@ -3916,11 +3931,25 @@ void lockdep_free_key_range(void *start, unsigned long size)
if (locked)
graph_unlock();
raw_local_irq_restore(flags);
+
+ /*
+ * Wait for any possible iterators from look_up_lock_class() to pass
+ * before continuing to free the memory they refer to.
+ *
+ * sync_sched() is sufficient because the read-side is IRQ disable.
+ */
+ synchronize_sched();
+
+ /*
+ * XXX at this point we could return the resources to the pool;
+ * instead we leak them. We would need to change to bitmap allocators
+ * instead of the linear allocators we have now.
+ */
}
void lockdep_reset_lock(struct lockdep_map *lock)
{
- struct lock_class *class, *next;
+ struct lock_class *class;
struct list_head *head;
unsigned long flags;
int i, j;
@@ -3948,7 +3977,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
head = classhash_table + i;
if (list_empty(head))
continue;
- list_for_each_entry_safe(class, next, head, hash_entry) {
+ list_for_each_entry_rcu(class, head, hash_entry) {
int match = 0;
for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index c0b8e9db6b2e..b73279367087 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1193,6 +1193,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
if (unlikely(ret)) {
+ __set_current_state(TASK_RUNNING);
if (rt_mutex_has_waiters(lock))
remove_waiter(lock, &waiter);
rt_mutex_handle_deadlock(ret, chwalk, &waiter);
diff --git a/kernel/module.c b/kernel/module.c
index b34813f725e9..ec53f594e9c9 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -56,7 +56,6 @@
#include <linux/async.h>
#include <linux/percpu.h>
#include <linux/kmemleak.h>
-#include <linux/kasan.h>
#include <linux/jump_label.h>
#include <linux/pfn.h>
#include <linux/bsearch.h>
@@ -1814,7 +1813,6 @@ static void unset_module_init_ro_nx(struct module *mod) { }
void __weak module_memfree(void *module_region)
{
vfree(module_region);
- kasan_module_free(module_region);
}
void __weak module_arch_cleanup(struct module *mod)
@@ -1867,7 +1865,7 @@ static void free_module(struct module *mod)
kfree(mod->args);
percpu_modfree(mod);
- /* Free lock-classes: */
+ /* Free lock-classes; relies on the preceding sync_rcu(). */
lockdep_free_key_range(mod->module_core, mod->core_size);
/* Finally, free the core (containing the module structure) */
@@ -2313,11 +2311,13 @@ static void layout_symtab(struct module *mod, struct load_info *info)
info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);
info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym);
mod->core_size += strtab_size;
+ mod->core_size = debug_align(mod->core_size);
/* Put string table section at end of init part of module. */
strsect->sh_flags |= SHF_ALLOC;
strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect,
info->index.str) | INIT_OFFSET_MASK;
+ mod->init_size = debug_align(mod->init_size);
pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
}
@@ -2479,6 +2479,23 @@ static int elf_header_check(struct load_info *info)
return 0;
}
+#define COPY_CHUNK_SIZE (16*PAGE_SIZE)
+
+static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned long len)
+{
+ do {
+ unsigned long n = min(len, COPY_CHUNK_SIZE);
+
+ if (copy_from_user(dst, usrc, n) != 0)
+ return -EFAULT;
+ cond_resched();
+ dst += n;
+ usrc += n;
+ len -= n;
+ } while (len);
+ return 0;
+}
+
/* Sets info->hdr and info->len. */
static int copy_module_from_user(const void __user *umod, unsigned long len,
struct load_info *info)
@@ -2498,7 +2515,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
if (!info->hdr)
return -ENOMEM;
- if (copy_from_user(info->hdr, umod, info->len) != 0) {
+ if (copy_chunked_from_user(info->hdr, umod, info->len) != 0) {
vfree(info->hdr);
return -EFAULT;
}
@@ -3349,9 +3366,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
module_bug_cleanup(mod);
mutex_unlock(&module_mutex);
- /* Free lock-classes: */
- lockdep_free_key_range(mod->module_core, mod->core_size);
-
/* we can't deallocate the module until we clear memory protection */
unset_module_init_ro_nx(mod);
unset_module_core_ro_nx(mod);
@@ -3375,6 +3389,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
synchronize_rcu();
mutex_unlock(&module_mutex);
free_module:
+ /* Free lock-classes; relies on the preceding sync_rcu() */
+ lockdep_free_key_range(mod->module_core, mod->core_size);
+
module_deallocate(mod, info);
free_copy:
free_copy(info);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index c24d5a23bf93..5235dd4e1e2f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -955,25 +955,6 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
}
}
-static bool is_nosave_page(unsigned long pfn)
-{
- struct nosave_region *region;
-
- list_for_each_entry(region, &nosave_regions, list) {
- if (pfn >= region->start_pfn && pfn < region->end_pfn) {
- pr_err("PM: %#010llx in e820 nosave region: "
- "[mem %#010llx-%#010llx]\n",
- (unsigned long long) pfn << PAGE_SHIFT,
- (unsigned long long) region->start_pfn << PAGE_SHIFT,
- ((unsigned long long) region->end_pfn << PAGE_SHIFT)
- - 1);
- return true;
- }
- }
-
- return false;
-}
-
/**
* create_basic_memory_bitmaps - create bitmaps needed for marking page
* frames that should not be saved and free page frames. The pointers
@@ -2042,7 +2023,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm)
do {
pfn = memory_bm_next_pfn(bm);
if (likely(pfn != BM_END_OF_MAP)) {
- if (likely(pfn_valid(pfn)) && !is_nosave_page(pfn))
+ if (likely(pfn_valid(pfn)))
swsusp_set_page_free(pfn_to_page(pfn));
else
return -EFAULT;
diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h
index cbd69d842341..2ca4a8b5fe57 100644
--- a/kernel/printk/console_cmdline.h
+++ b/kernel/printk/console_cmdline.h
@@ -3,7 +3,7 @@
struct console_cmdline
{
- char name[8]; /* Name of the driver */
+ char name[16]; /* Name of the driver */
int index; /* Minor dev. to use */
char *options; /* Options for the driver */
#ifdef CONFIG_A11Y_BRAILLE_CONSOLE
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 01cfd69c54c6..bb0635bd74f2 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2464,6 +2464,7 @@ void register_console(struct console *newcon)
for (i = 0, c = console_cmdline;
i < MAX_CMDLINECONSOLES && c->name[0];
i++, c++) {
+ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
if (strcmp(c->name, newcon->name) != 0)
continue;
if (newcon->index >= 0 &&
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f0f831e8a345..3d5f6f6d14c2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -996,6 +996,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
rq_clock_skip_update(rq, true);
}
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+ atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
#ifdef CONFIG_SMP
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
@@ -1026,10 +1033,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
trace_sched_migrate_task(p, new_cpu);
if (task_cpu(p) != new_cpu) {
+ struct task_migration_notifier tmn;
+
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+
+ tmn.task = p;
+ tmn.from_cpu = task_cpu(p);
+ tmn.to_cpu = new_cpu;
+
+ atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
}
__set_task_cpu(p, new_cpu);
@@ -3034,6 +3049,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
} else {
if (dl_prio(oldprio))
p->dl.dl_boosted = 0;
+ if (rt_prio(oldprio))
+ p->rt.timeout = 0;
p->sched_class = &fair_sched_class;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce18f3c097a..241213be507c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1609,9 +1609,11 @@ static void update_task_scan_period(struct task_struct *p,
/*
* If there were no record hinting faults then either the task is
* completely idle or all activity is areas that are not of interest
- * to automatic numa balancing. Scan slower
+ * to automatic numa balancing. Related to that, if there were failed
+ * migration then it implies we are migrating too quickly or the local
+ * node is overloaded. In either case, scan slower
*/
- if (local + shared == 0) {
+ if (local + shared == 0 || p->numa_faults_locality[2]) {
p->numa_scan_period = min(p->numa_scan_period_max,
p->numa_scan_period << 1);
@@ -2080,6 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
if (migrated)
p->numa_pages_migrated += pages;
+ if (flags & TNF_MIGRATE_FAIL)
+ p->numa_faults_locality[2] += pages;
p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
@@ -2161,8 +2165,10 @@ void task_numa_work(struct callback_head *work)
vma = mm->mmap;
}
for (; vma; vma = vma->vm_next) {
- if (!vma_migratable(vma) || !vma_policy_mof(vma))
+ if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
+ is_vm_hugetlb_page(vma)) {
continue;
+ }
/*
* Shared library pages mapped by multiple processes are not
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 94b2d7b88a27..80014a178342 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -82,6 +82,7 @@ static void cpuidle_idle_call(void)
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
unsigned int broadcast;
+ bool reflect;
/*
* Check if the idle task must be rescheduled. If it is the
@@ -105,6 +106,9 @@ static void cpuidle_idle_call(void)
*/
rcu_idle_enter();
+ if (cpuidle_not_available(drv, dev))
+ goto use_default;
+
/*
* Suspend-to-idle ("freeze") is a system state in which all user space
* has been frozen, all I/O devices have been suspended and the only
@@ -115,30 +119,24 @@ static void cpuidle_idle_call(void)
* until a proper wakeup interrupt happens.
*/
if (idle_should_freeze()) {
- cpuidle_enter_freeze();
- local_irq_enable();
- goto exit_idle;
- }
+ entered_state = cpuidle_enter_freeze(drv, dev);
+ if (entered_state >= 0) {
+ local_irq_enable();
+ goto exit_idle;
+ }
- /*
- * Ask the cpuidle framework to choose a convenient idle state.
- * Fall back to the default arch idle method on errors.
- */
- next_state = cpuidle_select(drv, dev);
- if (next_state < 0) {
-use_default:
+ reflect = false;
+ next_state = cpuidle_find_deepest_state(drv, dev);
+ } else {
+ reflect = true;
/*
- * We can't use the cpuidle framework, let's use the default
- * idle routine.
+ * Ask the cpuidle framework to choose a convenient idle state.
*/
- if (current_clr_polling_and_test())
- local_irq_enable();
- else
- arch_cpu_idle();
-
- goto exit_idle;
+ next_state = cpuidle_select(drv, dev);
}
-
+ /* Fall back to the default arch idle method on errors. */
+ if (next_state < 0)
+ goto use_default;
/*
* The idle task must be scheduled, it is pointless to
@@ -183,7 +181,8 @@ use_default:
/*
* Give the governor an opportunity to reflect on the outcome
*/
- cpuidle_reflect(dev, entered_state);
+ if (reflect)
+ cpuidle_reflect(dev, entered_state);
exit_idle:
__current_set_polling();
@@ -196,6 +195,19 @@ exit_idle:
rcu_idle_exit();
start_critical_timings();
+ return;
+
+use_default:
+ /*
+ * We can't use the cpuidle framework, let's use the default
+ * idle routine.
+ */
+ if (current_clr_polling_and_test())
+ local_irq_enable();
+ else
+ arch_cpu_idle();
+
+ goto exit_idle;
}
/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 667b2e62fad2..a03d9cd23ed7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1108,6 +1108,7 @@ DECLARE_RWSEM(uts_sem);
/*
* Work around broken programs that cannot handle "Linux 3.0".
* Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
+ * And we map 4.x to 2.6.60+x, so 4.0 would be 2.6.60.
*/
static int override_release(char __user *release, size_t len)
{
@@ -1127,7 +1128,7 @@ static int override_release(char __user *release, size_t len)
break;
rest++;
}
- v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
+ v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60;
copy = clamp_t(size_t, len, 1, sizeof(buf));
copy = scnprintf(buf, copy, "2.6.%u%s", v, rest);
ret = copy_to_user(release, buf, copy + 1);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 88ea2d6e0031..ce410bb9f2e1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1228,6 +1228,14 @@ static struct ctl_table vm_table[] = {
.extra1 = &zero,
},
{
+ .procname = "dirtytime_expire_seconds",
+ .data = &dirtytime_expire_interval,
+ .maxlen = sizeof(dirty_expire_interval),
+ .mode = 0644,
+ .proc_handler = dirtytime_interval_handler,
+ .extra1 = &zero,
+ },
+ {
.procname = "nr_pdflush_threads",
.mode = 0444 /* read-only */,
.proc_handler = pdflush_proc_obsolete,
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index eb682d5c697c..6aac4beedbbe 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode,
*/
static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
{
+ int bc_moved;
/*
* We try to cancel the timer first. If the callback is on
* flight on some other cpu then we let it handle it. If we
@@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
* restart the timer because we are in the callback, but we
* can set the expiry time and let the callback return
* HRTIMER_RESTART.
+ *
+ * Since we are in the idle loop at this point and because
+ * hrtimer_{start/cancel} functions call into tracing,
+ * calls to these functions must be bound within RCU_NONIDLE.
*/
- if (hrtimer_try_to_cancel(&bctimer) >= 0) {
- hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+ RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
+ !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
+ 0);
+ if (bc_moved) {
/* Bind the "device" to the cpu */
bc->bound_on = smp_processor_id();
} else if (bc->bound_on == smp_processor_id()) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 45e5cb143d17..4f228024055b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1059,6 +1059,12 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int ftrace_graph_active;
+#else
+# define ftrace_graph_active 0
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE
static struct ftrace_ops *removed_ops;
@@ -2041,8 +2047,12 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
if (!ftrace_rec_count(rec))
rec->flags = 0;
else
- /* Just disable the record (keep REGS state) */
- rec->flags &= ~FTRACE_FL_ENABLED;
+ /*
+ * Just disable the record, but keep the ops TRAMP
+ * and REGS states. The _EN flags must be disabled though.
+ */
+ rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN |
+ FTRACE_FL_REGS_EN);
}
return FTRACE_UPDATE_MAKE_NOP;
@@ -2688,24 +2698,36 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
static void ftrace_startup_sysctl(void)
{
+ int command;
+
if (unlikely(ftrace_disabled))
return;
/* Force update next time */
saved_ftrace_func = NULL;
/* ftrace_start_up is true if we want ftrace running */
- if (ftrace_start_up)
- ftrace_run_update_code(FTRACE_UPDATE_CALLS);
+ if (ftrace_start_up) {
+ command = FTRACE_UPDATE_CALLS;
+ if (ftrace_graph_active)
+ command |= FTRACE_START_FUNC_RET;
+ ftrace_startup_enable(command);
+ }
}
static void ftrace_shutdown_sysctl(void)
{
+ int command;
+
if (unlikely(ftrace_disabled))
return;
/* ftrace_start_up is true if ftrace is running */
- if (ftrace_start_up)
- ftrace_run_update_code(FTRACE_DISABLE_CALLS);
+ if (ftrace_start_up) {
+ command = FTRACE_DISABLE_CALLS;
+ if (ftrace_graph_active)
+ command |= FTRACE_STOP_FUNC_RET;
+ ftrace_run_update_code(command);
+ }
}
static cycle_t ftrace_update_time;
@@ -5558,12 +5580,12 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
if (ftrace_enabled) {
- ftrace_startup_sysctl();
-
/* we are starting ftrace again */
if (ftrace_ops_list != &ftrace_list_end)
update_ftrace_function();
+ ftrace_startup_sysctl();
+
} else {
/* stopping ftrace calls (just send to ftrace_stub) */
ftrace_trace_function = ftrace_stub;
@@ -5590,8 +5612,6 @@ static struct ftrace_ops graph_ops = {
ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash)
};
-static int ftrace_graph_active;
-
int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
{
return 0;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f28849394791..41ff75b478c6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2728,19 +2728,57 @@ bool flush_work(struct work_struct *work)
}
EXPORT_SYMBOL_GPL(flush_work);
+struct cwt_wait {
+ wait_queue_t wait;
+ struct work_struct *work;
+};
+
+static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+ struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
+
+ if (cwait->work != key)
+ return 0;
+ return autoremove_wake_function(wait, mode, sync, key);
+}
+
static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
{
+ static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq);
unsigned long flags;
int ret;
do {
ret = try_to_grab_pending(work, is_dwork, &flags);
/*
- * If someone else is canceling, wait for the same event it
- * would be waiting for before retrying.
+ * If someone else is already canceling, wait for it to
+ * finish. flush_work() doesn't work for PREEMPT_NONE
+ * because we may get scheduled between @work's completion
+ * and the other canceling task resuming and clearing
+ * CANCELING - flush_work() will return false immediately
+ * as @work is no longer busy, try_to_grab_pending() will
+ * return -ENOENT as @work is still being canceled and the
+ * other canceling task won't be able to clear CANCELING as
+ * we're hogging the CPU.
+ *
+ * Let's wait for completion using a waitqueue. As this
+ * may lead to the thundering herd problem, use a custom
+ * wake function which matches @work along with exclusive
+ * wait and wakeup.
*/
- if (unlikely(ret == -ENOENT))
- flush_work(work);
+ if (unlikely(ret == -ENOENT)) {
+ struct cwt_wait cwait;
+
+ init_wait(&cwait.wait);
+ cwait.wait.func = cwt_wakefn;
+ cwait.work = work;
+
+ prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait,
+ TASK_UNINTERRUPTIBLE);
+ if (work_is_canceling(work))
+ schedule();
+ finish_wait(&cancel_waitq, &cwait.wait);
+ }
} while (unlikely(ret < 0));
/* tell other tasks trying to grab @work to back off */
@@ -2749,6 +2787,16 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
flush_work(work);
clear_work_data(work);
+
+ /*
+ * Paired with prepare_to_wait() above so that either
+ * waitqueue_active() is visible here or !work_is_canceling() is
+ * visible there.
+ */
+ smp_mb();
+ if (waitqueue_active(&cancel_waitq))
+ __wake_up(&cancel_waitq, TASK_NORMAL, 1, work);
+
return ret;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-16 00:14:22 +0000