summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile4
-rw-r--r--kernel/audit.c62
-rw-r--r--kernel/audit.h10
-rw-r--r--kernel/audit_fsnotify.c6
-rw-r--r--kernel/audit_tree.c498
-rw-r--r--kernel/audit_watch.c6
-rw-r--r--kernel/auditsc.c150
-rw-r--r--kernel/cgroup/cgroup.c2
-rw-r--r--kernel/events/core.c4
-rw-r--r--kernel/events/hw_breakpoint.c2
-rw-r--r--kernel/fork.c9
-rw-r--r--kernel/irq/affinity.c176
-rw-r--r--kernel/irq/chip.c2
-rw-r--r--kernel/irq/devres.c4
-rw-r--r--kernel/irq/ipi.c4
-rw-r--r--kernel/irq/irq_sim.c23
-rw-r--r--kernel/irq/irqdesc.c28
-rw-r--r--kernel/irq/irqdomain.c4
-rw-r--r--kernel/irq/manage.c2
-rw-r--r--kernel/irq/matrix.c34
-rw-r--r--kernel/irq/msi.c8
-rw-r--r--kernel/irq/spurious.c6
-rw-r--r--kernel/kexec_file.c70
-rw-r--r--kernel/kprobes.c77
-rw-r--r--kernel/livepatch/patch.c4
-rw-r--r--kernel/livepatch/transition.c4
-rw-r--r--kernel/locking/lockdep.c78
-rw-r--r--kernel/locking/mutex-debug.c4
-rw-r--r--kernel/module.c137
-rw-r--r--kernel/module_signing.c3
-rw-r--r--kernel/panic.c6
-rw-r--r--kernel/power/Kconfig15
-rw-r--r--kernel/power/Makefile2
-rw-r--r--kernel/power/energy_model.c201
-rw-r--r--kernel/power/main.c15
-rw-r--r--kernel/power/qos.c15
-rw-r--r--kernel/printk/printk.c131
-rw-r--r--kernel/rcu/rcu.h4
-rw-r--r--kernel/rcu/rcutorture.c389
-rw-r--r--kernel/rcu/srcutiny.c120
-rw-r--r--kernel/rcu/srcutree.c489
-rw-r--r--kernel/rcu/sync.c25
-rw-r--r--kernel/rcu/tree.c114
-rw-r--r--kernel/rcu/tree.h18
-rw-r--r--kernel/rcu/tree_exp.h10
-rw-r--r--kernel/rcu/tree_plugin.h81
-rw-r--r--kernel/rcu/update.c9
-rw-r--r--kernel/sched/core.c8
-rw-r--r--kernel/sched/cpufreq.c5
-rw-r--r--kernel/sched/cpufreq_schedutil.c95
-rw-r--r--kernel/sched/cputime.c2
-rw-r--r--kernel/sched/deadline.c25
-rw-r--r--kernel/sched/debug.c2
-rw-r--r--kernel/sched/fair.c403
-rw-r--r--kernel/sched/isolation.c14
-rw-r--r--kernel/sched/membarrier.c6
-rw-r--r--kernel/sched/rt.c28
-rw-r--r--kernel/sched/sched.h97
-rw-r--r--kernel/sched/topology.c231
-rw-r--r--kernel/sys.c8
-rw-r--r--kernel/time/alarmtimer.c5
-rw-r--r--kernel/time/clockevents.c18
-rw-r--r--kernel/time/clocksource.c20
-rw-r--r--kernel/time/hrtimer.c19
-rw-r--r--kernel/time/itimer.c2
-rw-r--r--kernel/time/jiffies.c28
-rw-r--r--kernel/time/ntp.c1
-rw-r--r--kernel/time/posix-clock.c17
-rw-r--r--kernel/time/posix-stubs.c5
-rw-r--r--kernel/time/posix-timers.c25
-rw-r--r--kernel/time/sched_clock.c9
-rw-r--r--kernel/time/test_udelay.c10
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c4
-rw-r--r--kernel/time/tick-broadcast.c6
-rw-r--r--kernel/time/tick-common.c6
-rw-r--r--kernel/time/tick-oneshot.c6
-rw-r--r--kernel/time/tick-sched.c5
-rw-r--r--kernel/time/time.c13
-rw-r--r--kernel/time/timeconst.bc2
-rw-r--r--kernel/time/timeconv.c1
-rw-r--r--kernel/time/timecounter.c17
-rw-r--r--kernel/time/timekeeping.c15
-rw-r--r--kernel/time/timekeeping_debug.c26
-rw-r--r--kernel/time/timer.c3
-rw-r--r--kernel/time/timer_list.c7
-rw-r--r--kernel/torture.c34
-rw-r--r--kernel/trace/ftrace.c24
-rw-r--r--kernel/trace/ring_buffer.c12
-rw-r--r--kernel/trace/trace.c10
-rw-r--r--kernel/trace/trace_events_filter.c4
-rw-r--r--kernel/trace/trace_kprobe.c2
-rw-r--r--kernel/tracepoint.c4
-rw-r--r--kernel/workqueue.c8
93 files changed, 2750 insertions, 1607 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 7343b3a9bff0..9dc7f519129d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -76,9 +76,7 @@ obj-$(CONFIG_IKCONFIG) += configs.o
obj-$(CONFIG_SMP) += stop_machine.o
obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
-obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
-obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o audit_fsnotify.o
-obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
+obj-$(CONFIG_AUDITSYSCALL) += auditsc.o audit_watch.o audit_fsnotify.o audit_tree.o
obj-$(CONFIG_GCOV_KERNEL) += gcov/
obj-$(CONFIG_KCOV) += kcov.o
obj-$(CONFIG_KPROBES) += kprobes.o
diff --git a/kernel/audit.c b/kernel/audit.c
index 2a8058764aa6..632d36059556 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -60,7 +60,6 @@
#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/pid.h>
-#include <linux/slab.h>
#include <linux/audit.h>
@@ -400,7 +399,7 @@ static int audit_log_config_change(char *function_name, u32 new, u32 old,
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return rc;
- audit_log_format(ab, "%s=%u old=%u", function_name, new, old);
+ audit_log_format(ab, "%s=%u old=%u ", function_name, new, old);
audit_log_session_info(ab);
rc = audit_log_task_context(ab);
if (rc)
@@ -1067,7 +1066,7 @@ static void audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
*ab = audit_log_start(NULL, GFP_KERNEL, msg_type);
if (unlikely(!*ab))
return;
- audit_log_format(*ab, "pid=%d uid=%u", pid, uid);
+ audit_log_format(*ab, "pid=%d uid=%u ", pid, uid);
audit_log_session_info(*ab);
audit_log_task_context(*ab);
}
@@ -1096,10 +1095,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
if (audit_enabled == AUDIT_OFF)
return;
+
ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE);
if (!ab)
return;
- audit_log_task_info(ab, current);
+ audit_log_task_info(ab);
audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
audit_feature_names[which], !!old_feature, !!new_feature,
!!old_lock, !!new_lock, res);
@@ -2042,7 +2042,7 @@ void audit_log_session_info(struct audit_buffer *ab)
unsigned int sessionid = audit_get_sessionid(current);
uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current));
- audit_log_format(ab, " auid=%u ses=%u", auid, sessionid);
+ audit_log_format(ab, "auid=%u ses=%u", auid, sessionid);
}
void audit_log_key(struct audit_buffer *ab, char *key)
@@ -2058,11 +2058,13 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
{
int i;
- audit_log_format(ab, " %s=", prefix);
- CAP_FOR_EACH_U32(i) {
- audit_log_format(ab, "%08x",
- cap->cap[CAP_LAST_U32 - i]);
+ if (cap_isclear(*cap)) {
+ audit_log_format(ab, " %s=0", prefix);
+ return;
}
+ audit_log_format(ab, " %s=", prefix);
+ CAP_FOR_EACH_U32(i)
+ audit_log_format(ab, "%08x", cap->cap[CAP_LAST_U32 - i]);
}
static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
@@ -2177,22 +2179,21 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
}
/* log the audit_names record type */
- audit_log_format(ab, " nametype=");
switch(n->type) {
case AUDIT_TYPE_NORMAL:
- audit_log_format(ab, "NORMAL");
+ audit_log_format(ab, " nametype=NORMAL");
break;
case AUDIT_TYPE_PARENT:
- audit_log_format(ab, "PARENT");
+ audit_log_format(ab, " nametype=PARENT");
break;
case AUDIT_TYPE_CHILD_DELETE:
- audit_log_format(ab, "DELETE");
+ audit_log_format(ab, " nametype=DELETE");
break;
case AUDIT_TYPE_CHILD_CREATE:
- audit_log_format(ab, "CREATE");
+ audit_log_format(ab, " nametype=CREATE");
break;
default:
- audit_log_format(ab, "UNKNOWN");
+ audit_log_format(ab, " nametype=UNKNOWN");
break;
}
@@ -2247,15 +2248,15 @@ out_null:
audit_log_format(ab, " exe=(null)");
}
-struct tty_struct *audit_get_tty(struct task_struct *tsk)
+struct tty_struct *audit_get_tty(void)
{
struct tty_struct *tty = NULL;
unsigned long flags;
- spin_lock_irqsave(&tsk->sighand->siglock, flags);
- if (tsk->signal)
- tty = tty_kref_get(tsk->signal->tty);
- spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+ spin_lock_irqsave(&current->sighand->siglock, flags);
+ if (current->signal)
+ tty = tty_kref_get(current->signal->tty);
+ spin_unlock_irqrestore(&current->sighand->siglock, flags);
return tty;
}
@@ -2264,25 +2265,24 @@ void audit_put_tty(struct tty_struct *tty)
tty_kref_put(tty);
}
-void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
+void audit_log_task_info(struct audit_buffer *ab)
{
const struct cred *cred;
- char comm[sizeof(tsk->comm)];
+ char comm[sizeof(current->comm)];
struct tty_struct *tty;
if (!ab)
return;
- /* tsk == current */
cred = current_cred();
- tty = audit_get_tty(tsk);
+ tty = audit_get_tty();
audit_log_format(ab,
" ppid=%d pid=%d auid=%u uid=%u gid=%u"
" euid=%u suid=%u fsuid=%u"
" egid=%u sgid=%u fsgid=%u tty=%s ses=%u",
- task_ppid_nr(tsk),
- task_tgid_nr(tsk),
- from_kuid(&init_user_ns, audit_get_loginuid(tsk)),
+ task_ppid_nr(current),
+ task_tgid_nr(current),
+ from_kuid(&init_user_ns, audit_get_loginuid(current)),
from_kuid(&init_user_ns, cred->uid),
from_kgid(&init_user_ns, cred->gid),
from_kuid(&init_user_ns, cred->euid),
@@ -2292,11 +2292,11 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
from_kgid(&init_user_ns, cred->sgid),
from_kgid(&init_user_ns, cred->fsgid),
tty ? tty_name(tty) : "(none)",
- audit_get_sessionid(tsk));
+ audit_get_sessionid(current));
audit_put_tty(tty);
audit_log_format(ab, " comm=");
- audit_log_untrustedstring(ab, get_task_comm(comm, tsk));
- audit_log_d_path_exe(ab, tsk->mm);
+ audit_log_untrustedstring(ab, get_task_comm(comm, current));
+ audit_log_d_path_exe(ab, current->mm);
audit_log_task_context(ab);
}
EXPORT_SYMBOL(audit_log_task_info);
@@ -2317,7 +2317,7 @@ void audit_log_link_denied(const char *operation)
if (!ab)
return;
audit_log_format(ab, "op=%s", operation);
- audit_log_task_info(ab, current);
+ audit_log_task_info(ab);
audit_log_format(ab, " res=0");
audit_log_end(ab);
}
diff --git a/kernel/audit.h b/kernel/audit.h
index 214e14948370..91421679a168 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -210,6 +210,8 @@ struct audit_context {
extern bool audit_ever_enabled;
+extern void audit_log_session_info(struct audit_buffer *ab);
+
extern void audit_copy_inode(struct audit_names *name,
const struct dentry *dentry,
struct inode *inode);
@@ -262,11 +264,11 @@ extern struct audit_entry *audit_dupe_rule(struct audit_krule *old);
extern void audit_log_d_path_exe(struct audit_buffer *ab,
struct mm_struct *mm);
-extern struct tty_struct *audit_get_tty(struct task_struct *tsk);
+extern struct tty_struct *audit_get_tty(void);
extern void audit_put_tty(struct tty_struct *tty);
/* audit watch functions */
-#ifdef CONFIG_AUDIT_WATCH
+#ifdef CONFIG_AUDITSYSCALL
extern void audit_put_watch(struct audit_watch *watch);
extern void audit_get_watch(struct audit_watch *watch);
extern int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op);
@@ -299,9 +301,9 @@ extern int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark
#define audit_mark_compare(m, i, d) 0
#define audit_exe_compare(t, m) (-EINVAL)
#define audit_dupe_exe(n, o) (-EINVAL)
-#endif /* CONFIG_AUDIT_WATCH */
+#endif /* CONFIG_AUDITSYSCALL */
-#ifdef CONFIG_AUDIT_TREE
+#ifdef CONFIG_AUDITSYSCALL
extern struct audit_chunk *audit_tree_lookup(const struct inode *inode);
extern void audit_put_chunk(struct audit_chunk *chunk);
extern bool audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree);
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index fba78047fb37..cf4512a33675 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -130,10 +130,8 @@ static void audit_mark_log_rule_change(struct audit_fsnotify_mark *audit_mark, c
ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return;
- audit_log_format(ab, "auid=%u ses=%u op=%s",
- from_kuid(&init_user_ns, audit_get_loginuid(current)),
- audit_get_sessionid(current), op);
- audit_log_format(ab, " path=");
+ audit_log_session_info(ab);
+ audit_log_format(ab, " op=%s path=", op);
audit_log_untrustedstring(ab, audit_mark->path);
audit_log_key(ab, rule->filterkey);
audit_log_format(ab, " list=%d res=1", rule->listnr);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index ea43181cde4a..d4af4d97f847 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -24,9 +24,9 @@ struct audit_tree {
struct audit_chunk {
struct list_head hash;
- struct fsnotify_mark mark;
+ unsigned long key;
+ struct fsnotify_mark *mark;
struct list_head trees; /* with root here */
- int dead;
int count;
atomic_long_t refs;
struct rcu_head head;
@@ -37,13 +37,25 @@ struct audit_chunk {
} owners[];
};
+struct audit_tree_mark {
+ struct fsnotify_mark mark;
+ struct audit_chunk *chunk;
+};
+
static LIST_HEAD(tree_list);
static LIST_HEAD(prune_list);
static struct task_struct *prune_thread;
/*
- * One struct chunk is attached to each inode of interest.
- * We replace struct chunk on tagging/untagging.
+ * One struct chunk is attached to each inode of interest through
+ * audit_tree_mark (fsnotify mark). We replace struct chunk on tagging /
+ * untagging, the mark is stable as long as there is chunk attached. The
+ * association between mark and chunk is protected by hash_lock and
+ * audit_tree_group->mark_mutex. Thus as long as we hold
+ * audit_tree_group->mark_mutex and check that the mark is alive by
+ * FSNOTIFY_MARK_FLAG_ATTACHED flag check, we are sure the mark points to
+ * the current chunk.
+ *
* Rules have pointer to struct audit_tree.
* Rules have struct list_head rlist forming a list of rules over
* the same tree.
@@ -62,8 +74,12 @@ static struct task_struct *prune_thread;
* tree is refcounted; one reference for "some rules on rules_list refer to
* it", one for each chunk with pointer to it.
*
- * chunk is refcounted by embedded fsnotify_mark + .refs (non-zero refcount
- * of watch contributes 1 to .refs).
+ * chunk is refcounted by embedded .refs. Mark associated with the chunk holds
+ * one chunk reference. This reference is dropped either when a mark is going
+ * to be freed (corresponding inode goes away) or when chunk attached to the
+ * mark gets replaced. This reference must be dropped using
+ * audit_mark_put_chunk() to make sure the reference is dropped only after RCU
+ * grace period as it protects RCU readers of the hash table.
*
* node.index allows to get from node.list to containing chunk.
* MSB of that sucker is stolen to mark taggings that we might have to
@@ -72,6 +88,7 @@ static struct task_struct *prune_thread;
*/
static struct fsnotify_group *audit_tree_group;
+static struct kmem_cache *audit_tree_mark_cachep __read_mostly;
static struct audit_tree *alloc_tree(const char *s)
{
@@ -131,12 +148,43 @@ static void __put_chunk(struct rcu_head *rcu)
audit_put_chunk(chunk);
}
-static void audit_tree_destroy_watch(struct fsnotify_mark *entry)
+/*
+ * Drop reference to the chunk that was held by the mark. This is the reference
+ * that gets dropped after we've removed the chunk from the hash table and we
+ * use it to make sure chunk cannot be freed before RCU grace period expires.
+ */
+static void audit_mark_put_chunk(struct audit_chunk *chunk)
{
- struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark);
call_rcu(&chunk->head, __put_chunk);
}
+static inline struct audit_tree_mark *audit_mark(struct fsnotify_mark *mark)
+{
+ return container_of(mark, struct audit_tree_mark, mark);
+}
+
+static struct audit_chunk *mark_chunk(struct fsnotify_mark *mark)
+{
+ return audit_mark(mark)->chunk;
+}
+
+static void audit_tree_destroy_watch(struct fsnotify_mark *mark)
+{
+ kmem_cache_free(audit_tree_mark_cachep, audit_mark(mark));
+}
+
+static struct fsnotify_mark *alloc_mark(void)
+{
+ struct audit_tree_mark *amark;
+
+ amark = kmem_cache_zalloc(audit_tree_mark_cachep, GFP_KERNEL);
+ if (!amark)
+ return NULL;
+ fsnotify_init_mark(&amark->mark, audit_tree_group);
+ amark->mark.mask = FS_IN_IGNORED;
+ return &amark->mark;
+}
+
static struct audit_chunk *alloc_chunk(int count)
{
struct audit_chunk *chunk;
@@ -156,8 +204,6 @@ static struct audit_chunk *alloc_chunk(int count)
INIT_LIST_HEAD(&chunk->owners[i].list);
chunk->owners[i].index = i;
}
- fsnotify_init_mark(&chunk->mark, audit_tree_group);
- chunk->mark.mask = FS_IN_IGNORED;
return chunk;
}
@@ -172,36 +218,25 @@ static unsigned long inode_to_key(const struct inode *inode)
return (unsigned long)&inode->i_fsnotify_marks;
}
-/*
- * Function to return search key in our hash from chunk. Key 0 is special and
- * should never be present in the hash.
- */
-static unsigned long chunk_to_key(struct audit_chunk *chunk)
-{
- /*
- * We have a reference to the mark so it should be attached to a
- * connector.
- */
- if (WARN_ON_ONCE(!chunk->mark.connector))
- return 0;
- return (unsigned long)chunk->mark.connector->obj;
-}
-
static inline struct list_head *chunk_hash(unsigned long key)
{
unsigned long n = key / L1_CACHE_BYTES;
return chunk_hash_heads + n % HASH_SIZE;
}
-/* hash_lock & entry->lock is held by caller */
+/* hash_lock & mark->group->mark_mutex is held by caller */
static void insert_hash(struct audit_chunk *chunk)
{
- unsigned long key = chunk_to_key(chunk);
struct list_head *list;
- if (!(chunk->mark.flags & FSNOTIFY_MARK_FLAG_ATTACHED))
- return;
- list = chunk_hash(key);
+ /*
+ * Make sure chunk is fully initialized before making it visible in the
+ * hash. Pairs with a data dependency barrier in READ_ONCE() in
+ * audit_tree_lookup().
+ */
+ smp_wmb();
+ WARN_ON_ONCE(!chunk->key);
+ list = chunk_hash(chunk->key);
list_add_rcu(&chunk->hash, list);
}
@@ -213,7 +248,11 @@ struct audit_chunk *audit_tree_lookup(const struct inode *inode)
struct audit_chunk *p;
list_for_each_entry_rcu(p, list, hash) {
- if (chunk_to_key(p) == key) {
+ /*
+ * We use a data dependency barrier in READ_ONCE() to make sure
+ * the chunk we see is fully initialized.
+ */
+ if (READ_ONCE(p->key) == key) {
atomic_long_inc(&p->refs);
return p;
}
@@ -239,137 +278,159 @@ static struct audit_chunk *find_chunk(struct node *p)
return container_of(p, struct audit_chunk, owners[0]);
}
-static void untag_chunk(struct node *p)
+static void replace_mark_chunk(struct fsnotify_mark *mark,
+ struct audit_chunk *chunk)
+{
+ struct audit_chunk *old;
+
+ assert_spin_locked(&hash_lock);
+ old = mark_chunk(mark);
+ audit_mark(mark)->chunk = chunk;
+ if (chunk)
+ chunk->mark = mark;
+ if (old)
+ old->mark = NULL;
+}
+
+static void replace_chunk(struct audit_chunk *new, struct audit_chunk *old)
{
- struct audit_chunk *chunk = find_chunk(p);
- struct fsnotify_mark *entry = &chunk->mark;
- struct audit_chunk *new = NULL;
struct audit_tree *owner;
- int size = chunk->count - 1;
int i, j;
- fsnotify_get_mark(entry);
+ new->key = old->key;
+ list_splice_init(&old->trees, &new->trees);
+ list_for_each_entry(owner, &new->trees, same_root)
+ owner->root = new;
+ for (i = j = 0; j < old->count; i++, j++) {
+ if (!old->owners[j].owner) {
+ i--;
+ continue;
+ }
+ owner = old->owners[j].owner;
+ new->owners[i].owner = owner;
+ new->owners[i].index = old->owners[j].index - j + i;
+ if (!owner) /* result of earlier fallback */
+ continue;
+ get_tree(owner);
+ list_replace_init(&old->owners[j].list, &new->owners[i].list);
+ }
+ replace_mark_chunk(old->mark, new);
+ /*
+ * Make sure chunk is fully initialized before making it visible in the
+ * hash. Pairs with a data dependency barrier in READ_ONCE() in
+ * audit_tree_lookup().
+ */
+ smp_wmb();
+ list_replace_rcu(&old->hash, &new->hash);
+}
- spin_unlock(&hash_lock);
+static void remove_chunk_node(struct audit_chunk *chunk, struct node *p)
+{
+ struct audit_tree *owner = p->owner;
+
+ if (owner->root == chunk) {
+ list_del_init(&owner->same_root);
+ owner->root = NULL;
+ }
+ list_del_init(&p->list);
+ p->owner = NULL;
+ put_tree(owner);
+}
- if (size)
- new = alloc_chunk(size);
+static int chunk_count_trees(struct audit_chunk *chunk)
+{
+ int i;
+ int ret = 0;
- mutex_lock(&entry->group->mark_mutex);
- spin_lock(&entry->lock);
+ for (i = 0; i < chunk->count; i++)
+ if (chunk->owners[i].owner)
+ ret++;
+ return ret;
+}
+
+static void untag_chunk(struct audit_chunk *chunk, struct fsnotify_mark *mark)
+{
+ struct audit_chunk *new;
+ int size;
+
+ mutex_lock(&audit_tree_group->mark_mutex);
/*
- * mark_mutex protects mark from getting detached and thus also from
- * mark->connector->obj getting NULL.
+ * mark_mutex stabilizes chunk attached to the mark so we can check
+ * whether it didn't change while we've dropped hash_lock.
*/
- if (chunk->dead || !(entry->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
- spin_unlock(&entry->lock);
- mutex_unlock(&entry->group->mark_mutex);
- if (new)
- fsnotify_put_mark(&new->mark);
- goto out;
- }
-
- owner = p->owner;
+ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) ||
+ mark_chunk(mark) != chunk)
+ goto out_mutex;
+ size = chunk_count_trees(chunk);
if (!size) {
- chunk->dead = 1;
spin_lock(&hash_lock);
list_del_init(&chunk->trees);
- if (owner->root == chunk)
- owner->root = NULL;
- list_del_init(&p->list);
list_del_rcu(&chunk->hash);
+ replace_mark_chunk(mark, NULL);
spin_unlock(&hash_lock);
- spin_unlock(&entry->lock);
- mutex_unlock(&entry->group->mark_mutex);
- fsnotify_destroy_mark(entry, audit_tree_group);
- goto out;
+ fsnotify_detach_mark(mark);
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ audit_mark_put_chunk(chunk);
+ fsnotify_free_mark(mark);
+ return;
}
+ new = alloc_chunk(size);
if (!new)
- goto Fallback;
+ goto out_mutex;
- if (fsnotify_add_mark_locked(&new->mark, entry->connector->obj,
- FSNOTIFY_OBJ_TYPE_INODE, 1)) {
- fsnotify_put_mark(&new->mark);
- goto Fallback;
- }
-
- chunk->dead = 1;
spin_lock(&hash_lock);
- list_replace_init(&chunk->trees, &new->trees);
- if (owner->root == chunk) {
- list_del_init(&owner->same_root);
- owner->root = NULL;
- }
-
- for (i = j = 0; j <= size; i++, j++) {
- struct audit_tree *s;
- if (&chunk->owners[j] == p) {
- list_del_init(&p->list);
- i--;
- continue;
- }
- s = chunk->owners[j].owner;
- new->owners[i].owner = s;
- new->owners[i].index = chunk->owners[j].index - j + i;
- if (!s) /* result of earlier fallback */
- continue;
- get_tree(s);
- list_replace_init(&chunk->owners[j].list, &new->owners[i].list);
- }
-
- list_replace_rcu(&chunk->hash, &new->hash);
- list_for_each_entry(owner, &new->trees, same_root)
- owner->root = new;
- spin_unlock(&hash_lock);
- spin_unlock(&entry->lock);
- mutex_unlock(&entry->group->mark_mutex);
- fsnotify_destroy_mark(entry, audit_tree_group);
- fsnotify_put_mark(&new->mark); /* drop initial reference */
- goto out;
-
-Fallback:
- // do the best we can
- spin_lock(&hash_lock);
- if (owner->root == chunk) {
- list_del_init(&owner->same_root);
- owner->root = NULL;
- }
- list_del_init(&p->list);
- p->owner = NULL;
- put_tree(owner);
+ /*
+ * This has to go last when updating chunk as once replace_chunk() is
+ * called, new RCU readers can see the new chunk.
+ */
+ replace_chunk(new, chunk);
spin_unlock(&hash_lock);
- spin_unlock(&entry->lock);
- mutex_unlock(&entry->group->mark_mutex);
-out:
- fsnotify_put_mark(entry);
- spin_lock(&hash_lock);
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ audit_mark_put_chunk(chunk);
+ return;
+
+out_mutex:
+ mutex_unlock(&audit_tree_group->mark_mutex);
}
+/* Call with group->mark_mutex held, releases it */
static int create_chunk(struct inode *inode, struct audit_tree *tree)
{
- struct fsnotify_mark *entry;
+ struct fsnotify_mark *mark;
struct audit_chunk *chunk = alloc_chunk(1);
- if (!chunk)
+
+ if (!chunk) {
+ mutex_unlock(&audit_tree_group->mark_mutex);
return -ENOMEM;
+ }
- entry = &chunk->mark;
- if (fsnotify_add_inode_mark(entry, inode, 0)) {
- fsnotify_put_mark(entry);
+ mark = alloc_mark();
+ if (!mark) {
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ kfree(chunk);
+ return -ENOMEM;
+ }
+
+ if (fsnotify_add_inode_mark_locked(mark, inode, 0)) {
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ fsnotify_put_mark(mark);
+ kfree(chunk);
return -ENOSPC;
}
- spin_lock(&entry->lock);
spin_lock(&hash_lock);
if (tree->goner) {
spin_unlock(&hash_lock);
- chunk->dead = 1;
- spin_unlock(&entry->lock);
- fsnotify_destroy_mark(entry, audit_tree_group);
- fsnotify_put_mark(entry);
+ fsnotify_detach_mark(mark);
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ fsnotify_free_mark(mark);
+ fsnotify_put_mark(mark);
+ kfree(chunk);
return 0;
}
+ replace_mark_chunk(mark, chunk);
chunk->owners[0].index = (1U << 31);
chunk->owners[0].owner = tree;
get_tree(tree);
@@ -378,35 +439,49 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
tree->root = chunk;
list_add(&tree->same_root, &chunk->trees);
}
+ chunk->key = inode_to_key(inode);
+ /*
+ * Inserting into the hash table has to go last as once we do that RCU
+ * readers can see the chunk.
+ */
insert_hash(chunk);
spin_unlock(&hash_lock);
- spin_unlock(&entry->lock);
- fsnotify_put_mark(entry); /* drop initial reference */
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ /*
+ * Drop our initial reference. When mark we point to is getting freed,
+ * we get notification through ->freeing_mark callback and cleanup
+ * chunk pointing to this mark.
+ */
+ fsnotify_put_mark(mark);
return 0;
}
/* the first tagged inode becomes root of tree */
static int tag_chunk(struct inode *inode, struct audit_tree *tree)
{
- struct fsnotify_mark *old_entry, *chunk_entry;
- struct audit_tree *owner;
+ struct fsnotify_mark *mark;
struct audit_chunk *chunk, *old;
struct node *p;
int n;
- old_entry = fsnotify_find_mark(&inode->i_fsnotify_marks,
- audit_tree_group);
- if (!old_entry)
+ mutex_lock(&audit_tree_group->mark_mutex);
+ mark = fsnotify_find_mark(&inode->i_fsnotify_marks, audit_tree_group);
+ if (!mark)
return create_chunk(inode, tree);
- old = container_of(old_entry, struct audit_chunk, mark);
-
+ /*
+ * Found mark is guaranteed to be attached and mark_mutex protects mark
+ * from getting detached and thus it makes sure there is chunk attached
+ * to the mark.
+ */
/* are we already there? */
spin_lock(&hash_lock);
+ old = mark_chunk(mark);
for (n = 0; n < old->count; n++) {
if (old->owners[n].owner == tree) {
spin_unlock(&hash_lock);
- fsnotify_put_mark(old_entry);
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ fsnotify_put_mark(mark);
return 0;
}
}
@@ -414,83 +489,38 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
chunk = alloc_chunk(old->count + 1);
if (!chunk) {
- fsnotify_put_mark(old_entry);
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ fsnotify_put_mark(mark);
return -ENOMEM;
}
- chunk_entry = &chunk->mark;
-
- mutex_lock(&old_entry->group->mark_mutex);
- spin_lock(&old_entry->lock);
- /*
- * mark_mutex protects mark from getting detached and thus also from
- * mark->connector->obj getting NULL.
- */
- if (!(old_entry->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
- /* old_entry is being shot, lets just lie */
- spin_unlock(&old_entry->lock);
- mutex_unlock(&old_entry->group->mark_mutex);
- fsnotify_put_mark(old_entry);
- fsnotify_put_mark(&chunk->mark);
- return -ENOENT;
- }
-
- if (fsnotify_add_mark_locked(chunk_entry, old_entry->connector->obj,
- FSNOTIFY_OBJ_TYPE_INODE, 1)) {
- spin_unlock(&old_entry->lock);
- mutex_unlock(&old_entry->group->mark_mutex);
- fsnotify_put_mark(chunk_entry);
- fsnotify_put_mark(old_entry);
- return -ENOSPC;
- }
-
- /* even though we hold old_entry->lock, this is safe since chunk_entry->lock could NEVER have been grabbed before */
- spin_lock(&chunk_entry->lock);
spin_lock(&hash_lock);
-
- /* we now hold old_entry->lock, chunk_entry->lock, and hash_lock */
if (tree->goner) {
spin_unlock(&hash_lock);
- chunk->dead = 1;
- spin_unlock(&chunk_entry->lock);
- spin_unlock(&old_entry->lock);
- mutex_unlock(&old_entry->group->mark_mutex);
-
- fsnotify_destroy_mark(chunk_entry, audit_tree_group);
-
- fsnotify_put_mark(chunk_entry);
- fsnotify_put_mark(old_entry);
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ fsnotify_put_mark(mark);
+ kfree(chunk);
return 0;
}
- list_replace_init(&old->trees, &chunk->trees);
- for (n = 0, p = chunk->owners; n < old->count; n++, p++) {
- struct audit_tree *s = old->owners[n].owner;
- p->owner = s;
- p->index = old->owners[n].index;
- if (!s) /* result of fallback in untag */
- continue;
- get_tree(s);
- list_replace_init(&old->owners[n].list, &p->list);
- }
+ p = &chunk->owners[chunk->count - 1];
p->index = (chunk->count - 1) | (1U<<31);
p->owner = tree;
get_tree(tree);
list_add(&p->list, &tree->chunks);
- list_replace_rcu(&old->hash, &chunk->hash);
- list_for_each_entry(owner, &chunk->trees, same_root)
- owner->root = chunk;
- old->dead = 1;
if (!tree->root) {
tree->root = chunk;
list_add(&tree->same_root, &chunk->trees);
}
+ /*
+ * This has to go last when updating chunk as once replace_chunk() is
+ * called, new RCU readers can see the new chunk.
+ */
+ replace_chunk(chunk, old);
spin_unlock(&hash_lock);
- spin_unlock(&chunk_entry->lock);
- spin_unlock(&old_entry->lock);
- mutex_unlock(&old_entry->group->mark_mutex);
- fsnotify_destroy_mark(old_entry, audit_tree_group);
- fsnotify_put_mark(chunk_entry); /* drop initial reference */
- fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */
+ mutex_unlock(&audit_tree_group->mark_mutex);
+ fsnotify_put_mark(mark); /* pair to fsnotify_find_mark */
+ audit_mark_put_chunk(old);
+
return 0;
}
@@ -503,8 +533,7 @@ static void audit_tree_log_remove_rule(struct audit_krule *rule)
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return;
- audit_log_format(ab, "op=remove_rule");
- audit_log_format(ab, " dir=");
+ audit_log_format(ab, "op=remove_rule dir=");
audit_log_untrustedstring(ab, rule->tree->pathname);
audit_log_key(ab, rule->filterkey);
audit_log_format(ab, " list=%d res=1", rule->listnr);
@@ -534,22 +563,48 @@ static void kill_rules(struct audit_tree *tree)
}
/*
- * finish killing struct audit_tree
+ * Remove tree from chunks. If 'tagged' is set, remove tree only from tagged
+ * chunks. The function expects tagged chunks are all at the beginning of the
+ * chunks list.
*/
-static void prune_one(struct audit_tree *victim)
+static void prune_tree_chunks(struct audit_tree *victim, bool tagged)
{
spin_lock(&hash_lock);
while (!list_empty(&victim->chunks)) {
struct node *p;
+ struct audit_chunk *chunk;
+ struct fsnotify_mark *mark;
+
+ p = list_first_entry(&victim->chunks, struct node, list);
+ /* have we run out of marked? */
+ if (tagged && !(p->index & (1U<<31)))
+ break;
+ chunk = find_chunk(p);
+ mark = chunk->mark;
+ remove_chunk_node(chunk, p);
+ /* Racing with audit_tree_freeing_mark()? */
+ if (!mark)
+ continue;
+ fsnotify_get_mark(mark);
+ spin_unlock(&hash_lock);
- p = list_entry(victim->chunks.next, struct node, list);
+ untag_chunk(chunk, mark);
+ fsnotify_put_mark(mark);
- untag_chunk(p);
+ spin_lock(&hash_lock);
}
spin_unlock(&hash_lock);
put_tree(victim);
}
+/*
+ * finish killing struct audit_tree
+ */
+static void prune_one(struct audit_tree *victim)
+{
+ prune_tree_chunks(victim, false);
+}
+
/* trim the uncommitted chunks from tree */
static void trim_marked(struct audit_tree *tree)
@@ -569,18 +624,11 @@ static void trim_marked(struct audit_tree *tree)
list_add(p, &tree->chunks);
}
}
+ spin_unlock(&hash_lock);
- while (!list_empty(&tree->chunks)) {
- struct node *node;
-
- node = list_entry(tree->chunks.next, struct node, list);
-
- /* have we run out of marked? */
- if (!(node->index & (1U<<31)))
- break;
+ prune_tree_chunks(tree, true);
- untag_chunk(node);
- }
+ spin_lock(&hash_lock);
if (!tree->root && !tree->goner) {
tree->goner = 1;
spin_unlock(&hash_lock);
@@ -661,7 +709,7 @@ void audit_trim_trees(void)
/* this could be NULL if the watch is dying else where... */
node->index |= 1U<<31;
if (iterate_mounts(compare_root,
- (void *)chunk_to_key(chunk),
+ (void *)(chunk->key),
root_mnt))
node->index &= ~(1U<<31);
}
@@ -959,10 +1007,6 @@ static void evict_chunk(struct audit_chunk *chunk)
int need_prune = 0;
int n;
- if (chunk->dead)
- return;
-
- chunk->dead = 1;
mutex_lock(&audit_filter_mutex);
spin_lock(&hash_lock);
while (!list_empty(&chunk->trees)) {
@@ -999,17 +1043,27 @@ static int audit_tree_handle_event(struct fsnotify_group *group,
return 0;
}
-static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify_group *group)
+static void audit_tree_freeing_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group)
{
- struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark);
+ struct audit_chunk *chunk;
- evict_chunk(chunk);
+ mutex_lock(&mark->group->mark_mutex);
+ spin_lock(&hash_lock);
+ chunk = mark_chunk(mark);
+ replace_mark_chunk(mark, NULL);
+ spin_unlock(&hash_lock);
+ mutex_unlock(&mark->group->mark_mutex);
+ if (chunk) {
+ evict_chunk(chunk);
+ audit_mark_put_chunk(chunk);
+ }
/*
* We are guaranteed to have at least one reference to the mark from
* either the inode or the caller of fsnotify_destroy_mark().
*/
- BUG_ON(refcount_read(&entry->refcnt) < 1);
+ BUG_ON(refcount_read(&mark->refcnt) < 1);
}
static const struct fsnotify_ops audit_tree_ops = {
@@ -1022,6 +1076,8 @@ static int __init audit_tree_init(void)
{
int i;
+ audit_tree_mark_cachep = KMEM_CACHE(audit_tree_mark, SLAB_PANIC);
+
audit_tree_group = fsnotify_alloc_group(&audit_tree_ops);
if (IS_ERR(audit_tree_group))
audit_panic("cannot initialize fsnotify group for rectree watches");
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 787c7afdf829..20ef9ba134b0 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -245,10 +245,8 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc
ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
if (!ab)
return;
- audit_log_format(ab, "auid=%u ses=%u op=%s",
- from_kuid(&init_user_ns, audit_get_loginuid(current)),
- audit_get_sessionid(current), op);
- audit_log_format(ab, " path=");
+ audit_log_session_info(ab);
+ audit_log_format(ab, "op=%s path=", op);
audit_log_untrustedstring(ab, w->path);
audit_log_key(ab, r->filterkey);
audit_log_format(ab, " list=%d res=1", r->listnr);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b2d1f043f17f..6593a5207fb0 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -200,7 +200,6 @@ static int audit_match_filetype(struct audit_context *ctx, int val)
* References in it _are_ dropped - at the same time we free/drop aux stuff.
*/
-#ifdef CONFIG_AUDIT_TREE
static void audit_set_auditable(struct audit_context *ctx)
{
if (!ctx->prio) {
@@ -245,12 +244,10 @@ static int grow_tree_refs(struct audit_context *ctx)
ctx->tree_count = 31;
return 1;
}
-#endif
static void unroll_tree_refs(struct audit_context *ctx,
struct audit_tree_refs *p, int count)
{
-#ifdef CONFIG_AUDIT_TREE
struct audit_tree_refs *q;
int n;
if (!p) {
@@ -274,7 +271,6 @@ static void unroll_tree_refs(struct audit_context *ctx,
}
ctx->trees = p;
ctx->tree_count = count;
-#endif
}
static void free_tree_refs(struct audit_context *ctx)
@@ -288,7 +284,6 @@ static void free_tree_refs(struct audit_context *ctx)
static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree)
{
-#ifdef CONFIG_AUDIT_TREE
struct audit_tree_refs *p;
int n;
if (!tree)
@@ -305,7 +300,6 @@ static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree)
if (audit_tree_match(p->c[n], tree))
return 1;
}
-#endif
return 0;
}
@@ -836,44 +830,6 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
rcu_read_unlock();
}
-/* Transfer the audit context pointer to the caller, clearing it in the tsk's struct */
-static inline struct audit_context *audit_take_context(struct task_struct *tsk,
- int return_valid,
- long return_code)
-{
- struct audit_context *context = tsk->audit_context;
-
- if (!context)
- return NULL;
- context->return_valid = return_valid;
-
- /*
- * we need to fix up the return code in the audit logs if the actual
- * return codes are later going to be fixed up by the arch specific
- * signal handlers
- *
- * This is actually a test for:
- * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) ||
- * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK)
- *
- * but is faster than a bunch of ||
- */
- if (unlikely(return_code <= -ERESTARTSYS) &&
- (return_code >= -ERESTART_RESTARTBLOCK) &&
- (return_code != -ENOIOCTLCMD))
- context->return_code = -EINTR;
- else
- context->return_code = return_code;
-
- if (context->in_syscall && !context->dummy) {
- audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
- audit_filter_inodes(tsk, context);
- }
-
- audit_set_context(tsk, NULL);
- return context;
-}
-
static inline void audit_proctitle_free(struct audit_context *context)
{
kfree(context->proctitle.value);
@@ -1107,7 +1063,7 @@ static void audit_log_execve_info(struct audit_context *context,
}
/* write as much as we can to the audit log */
- if (len_buf > 0) {
+ if (len_buf >= 0) {
/* NOTE: some magic numbers here - basically if we
* can't fit a reasonable amount of data into the
* existing audit buffer, flush it and start with
@@ -1302,15 +1258,18 @@ static inline int audit_proctitle_rtrim(char *proctitle, int len)
return len;
}
-static void audit_log_proctitle(struct task_struct *tsk,
- struct audit_context *context)
+static void audit_log_proctitle(void)
{
int res;
char *buf;
char *msg = "(null)";
int len = strlen(msg);
+ struct audit_context *context = audit_context();
struct audit_buffer *ab;
+ if (!context || context->dummy)
+ return;
+
ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE);
if (!ab)
return; /* audit_panic or being filtered */
@@ -1323,7 +1282,7 @@ static void audit_log_proctitle(struct task_struct *tsk,
if (!buf)
goto out;
/* Historically called this from procfs naming */
- res = get_cmdline(tsk, buf, MAX_PROCTITLE_AUDIT_LEN);
+ res = get_cmdline(current, buf, MAX_PROCTITLE_AUDIT_LEN);
if (res == 0) {
kfree(buf);
goto out;
@@ -1343,15 +1302,15 @@ out:
audit_log_end(ab);
}
-static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
+static void audit_log_exit(void)
{
int i, call_panic = 0;
+ struct audit_context *context = audit_context();
struct audit_buffer *ab;
struct audit_aux_data *aux;
struct audit_names *n;
- /* tsk == current */
- context->personality = tsk->personality;
+ context->personality = current->personality;
ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
if (!ab)
@@ -1373,7 +1332,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
context->argv[3],
context->name_count);
- audit_log_task_info(ab, tsk);
+ audit_log_task_info(ab);
audit_log_key(ab, context->filterkey);
audit_log_end(ab);
@@ -1462,7 +1421,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
audit_log_name(context, n, NULL, i++, &call_panic);
}
- audit_log_proctitle(tsk, context);
+ audit_log_proctitle();
/* Send end of event record to help user space know we are finished */
ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
@@ -1480,22 +1439,31 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
*/
void __audit_free(struct task_struct *tsk)
{
- struct audit_context *context;
+ struct audit_context *context = tsk->audit_context;
- context = audit_take_context(tsk, 0, 0);
if (!context)
return;
- /* Check for system calls that do not go through the exit
- * function (e.g., exit_group), then free context block.
- * We use GFP_ATOMIC here because we might be doing this
- * in the context of the idle thread */
- /* that can happen only if we are called from do_exit() */
- if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
- audit_log_exit(context, tsk);
+ /* We are called either by do_exit() or the fork() error handling code;
+ * in the former case tsk == current and in the latter tsk is a
+ * random task_struct that doesn't doesn't have any meaningful data we
+ * need to log via audit_log_exit().
+ */
+ if (tsk == current && !context->dummy && context->in_syscall) {
+ context->return_valid = 0;
+ context->return_code = 0;
+
+ audit_filter_syscall(tsk, context,
+ &audit_filter_list[AUDIT_FILTER_EXIT]);
+ audit_filter_inodes(tsk, context);
+ if (context->current_state == AUDIT_RECORD_CONTEXT)
+ audit_log_exit();
+ }
+
if (!list_empty(&context->killed_trees))
audit_kill_trees(&context->killed_trees);
+ audit_set_context(tsk, NULL);
audit_free_context(context);
}
@@ -1565,17 +1533,40 @@ void __audit_syscall_exit(int success, long return_code)
{
struct audit_context *context;
- if (success)
- success = AUDITSC_SUCCESS;
- else
- success = AUDITSC_FAILURE;
-
- context = audit_take_context(current, success, return_code);
+ context = audit_context();
if (!context)
return;
- if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
- audit_log_exit(context, current);
+ if (!context->dummy && context->in_syscall) {
+ if (success)
+ context->return_valid = AUDITSC_SUCCESS;
+ else
+ context->return_valid = AUDITSC_FAILURE;
+
+ /*
+ * we need to fix up the return code in the audit logs if the
+ * actual return codes are later going to be fixed up by the
+ * arch specific signal handlers
+ *
+ * This is actually a test for:
+ * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) ||
+ * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK)
+ *
+ * but is faster than a bunch of ||
+ */
+ if (unlikely(return_code <= -ERESTARTSYS) &&
+ (return_code >= -ERESTART_RESTARTBLOCK) &&
+ (return_code != -ENOIOCTLCMD))
+ context->return_code = -EINTR;
+ else
+ context->return_code = return_code;
+
+ audit_filter_syscall(current, context,
+ &audit_filter_list[AUDIT_FILTER_EXIT]);
+ audit_filter_inodes(current, context);
+ if (context->current_state == AUDIT_RECORD_CONTEXT)
+ audit_log_exit();
+ }
context->in_syscall = 0;
context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
@@ -1597,12 +1588,10 @@ void __audit_syscall_exit(int success, long return_code)
kfree(context->filterkey);
context->filterkey = NULL;
}
- audit_set_context(current, context);
}
static inline void handle_one(const struct inode *inode)
{
-#ifdef CONFIG_AUDIT_TREE
struct audit_context *context;
struct audit_tree_refs *p;
struct audit_chunk *chunk;
@@ -1627,12 +1616,10 @@ static inline void handle_one(const struct inode *inode)
return;
}
put_tree_ref(context, chunk);
-#endif
}
static void handle_path(const struct dentry *dentry)
{
-#ifdef CONFIG_AUDIT_TREE
struct audit_context *context;
struct audit_tree_refs *p;
const struct dentry *d, *parent;
@@ -1685,7 +1672,6 @@ retry:
return;
}
rcu_read_unlock();
-#endif
}
static struct audit_names *audit_alloc_name(struct audit_context *context,
@@ -2035,7 +2021,7 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
uid = from_kuid(&init_user_ns, task_uid(current));
oldloginuid = from_kuid(&init_user_ns, koldloginuid);
loginuid = from_kuid(&init_user_ns, kloginuid),
- tty = audit_get_tty(current);
+ tty = audit_get_tty();
audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid);
audit_log_task_context(ab);
@@ -2056,7 +2042,6 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
*/
int audit_set_loginuid(kuid_t loginuid)
{
- struct task_struct *task = current;
unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET;
kuid_t oldloginuid;
int rc;
@@ -2075,8 +2060,8 @@ int audit_set_loginuid(kuid_t loginuid)
sessionid = (unsigned int)atomic_inc_return(&session_id);
}
- task->sessionid = sessionid;
- task->loginuid = loginuid;
+ current->sessionid = sessionid;
+ current->loginuid = loginuid;
out:
audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
return rc;
@@ -2513,10 +2498,9 @@ void audit_seccomp_actions_logged(const char *names, const char *old_names,
if (unlikely(!ab))
return;
- audit_log_format(ab, "op=seccomp-logging");
- audit_log_format(ab, " actions=%s", names);
- audit_log_format(ab, " old-actions=%s", old_names);
- audit_log_format(ab, " res=%d", res);
+ audit_log_format(ab,
+ "op=seccomp-logging actions=%s old-actions=%s res=%d",
+ names, old_names, res);
audit_log_end(ab);
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 6aaf5dd5383b..7a8429f8e280 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5343,7 +5343,7 @@ int __init cgroup_init(void)
cgroup_rstat_boot();
/*
- * The latency of the synchronize_sched() is too high for cgroups,
+ * The latency of the synchronize_rcu() is too high for cgroups,
* avoid it at the cost of forcing all readers into the slow path.
*/
rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 84530ab358c3..67ecac337374 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5541,7 +5541,7 @@ out_put:
static const struct vm_operations_struct perf_mmap_vmops = {
.open = perf_mmap_open,
- .close = perf_mmap_close, /* non mergable */
+ .close = perf_mmap_close, /* non mergeable */
.fault = perf_mmap_fault,
.page_mkwrite = perf_mmap_fault,
};
@@ -9918,7 +9918,7 @@ static void account_event(struct perf_event *event)
* call the perf scheduling hooks before proceeding to
* install events that need them.
*/
- synchronize_sched();
+ synchronize_rcu();
}
/*
* Now that we have waited for the sync_sched(), allow further
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index d6b56180827c..5befb338a18d 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -238,7 +238,7 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
}
/*
- * Contraints to check before allowing this new breakpoint counter:
+ * Constraints to check before allowing this new breakpoint counter:
*
* == Non-pinned counter == (Considered as pinned for now)
*
diff --git a/kernel/fork.c b/kernel/fork.c
index 07cddff89c7b..e2a5156bc9c3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -240,8 +240,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
* free_thread_stack() can be called in interrupt context,
* so cache the vm_struct.
*/
- if (stack)
+ if (stack) {
tsk->stack_vm_area = find_vm_area(stack);
+ tsk->stack = stack;
+ }
return stack;
#else
struct page *page = alloc_pages_node(node, THREADINFO_GFP,
@@ -288,7 +290,10 @@ static struct kmem_cache *thread_stack_cache;
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+ unsigned long *stack;
+ stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+ tsk->stack = stack;
+ return stack;
}
static void free_thread_stack(struct task_struct *tsk)
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f4f29b9d90ee..45b68b4ea48b 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -94,15 +94,15 @@ static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask,
return nodes;
}
-static int irq_build_affinity_masks(const struct irq_affinity *affd,
- int startvec, int numvecs,
- cpumask_var_t *node_to_cpumask,
- const struct cpumask *cpu_mask,
- struct cpumask *nmsk,
- struct cpumask *masks)
+static int __irq_build_affinity_masks(const struct irq_affinity *affd,
+ int startvec, int numvecs, int firstvec,
+ cpumask_var_t *node_to_cpumask,
+ const struct cpumask *cpu_mask,
+ struct cpumask *nmsk,
+ struct irq_affinity_desc *masks)
{
int n, nodes, cpus_per_vec, extra_vecs, done = 0;
- int last_affv = affd->pre_vectors + numvecs;
+ int last_affv = firstvec + numvecs;
int curvec = startvec;
nodemask_t nodemsk = NODE_MASK_NONE;
@@ -117,12 +117,13 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
*/
if (numvecs <= nodes) {
for_each_node_mask(n, nodemsk) {
- cpumask_copy(masks + curvec, node_to_cpumask[n]);
- if (++done == numvecs)
- break;
+ cpumask_or(&masks[curvec].mask,
+ &masks[curvec].mask,
+ node_to_cpumask[n]);
if (++curvec == last_affv)
- curvec = affd->pre_vectors;
+ curvec = firstvec;
}
+ done = numvecs;
goto out;
}
@@ -130,7 +131,7 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
int ncpus, v, vecs_to_assign, vecs_per_node;
/* Spread the vectors per node */
- vecs_per_node = (numvecs - (curvec - affd->pre_vectors)) / nodes;
+ vecs_per_node = (numvecs - (curvec - firstvec)) / nodes;
/* Get the cpus on this node which are in the mask */
cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
@@ -151,14 +152,15 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
cpus_per_vec++;
--extra_vecs;
}
- irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
+ irq_spread_init_one(&masks[curvec].mask, nmsk,
+ cpus_per_vec);
}
done += v;
if (done >= numvecs)
break;
if (curvec >= last_affv)
- curvec = affd->pre_vectors;
+ curvec = firstvec;
--nodes;
}
@@ -166,20 +168,77 @@ out:
return done;
}
+/*
+ * build affinity in two stages:
+ * 1) spread present CPU on these vectors
+ * 2) spread other possible CPUs on these vectors
+ */
+static int irq_build_affinity_masks(const struct irq_affinity *affd,
+ int startvec, int numvecs, int firstvec,
+ cpumask_var_t *node_to_cpumask,
+ struct irq_affinity_desc *masks)
+{
+ int curvec = startvec, nr_present, nr_others;
+ int ret = -ENOMEM;
+ cpumask_var_t nmsk, npresmsk;
+
+ if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
+ return ret;
+
+ if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
+ goto fail;
+
+ ret = 0;
+ /* Stabilize the cpumasks */
+ get_online_cpus();
+ build_node_to_cpumask(node_to_cpumask);
+
+ /* Spread on present CPUs starting from affd->pre_vectors */
+ nr_present = __irq_build_affinity_masks(affd, curvec, numvecs,
+ firstvec, node_to_cpumask,
+ cpu_present_mask, nmsk, masks);
+
+ /*
+ * Spread on non present CPUs starting from the next vector to be
+ * handled. If the spreading of present CPUs already exhausted the
+ * vector space, assign the non present CPUs to the already spread
+ * out vectors.
+ */
+ if (nr_present >= numvecs)
+ curvec = firstvec;
+ else
+ curvec = firstvec + nr_present;
+ cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
+ nr_others = __irq_build_affinity_masks(affd, curvec, numvecs,
+ firstvec, node_to_cpumask,
+ npresmsk, nmsk, masks);
+ put_online_cpus();
+
+ if (nr_present < numvecs)
+ WARN_ON(nr_present + nr_others < numvecs);
+
+ free_cpumask_var(npresmsk);
+
+ fail:
+ free_cpumask_var(nmsk);
+ return ret;
+}
+
/**
* irq_create_affinity_masks - Create affinity masks for multiqueue spreading
* @nvecs: The total number of vectors
* @affd: Description of the affinity requirements
*
- * Returns the masks pointer or NULL if allocation failed.
+ * Returns the irq_affinity_desc pointer or NULL if allocation failed.
*/
-struct cpumask *
+struct irq_affinity_desc *
irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
{
int affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
int curvec, usedvecs;
- cpumask_var_t nmsk, npresmsk, *node_to_cpumask;
- struct cpumask *masks = NULL;
+ cpumask_var_t *node_to_cpumask;
+ struct irq_affinity_desc *masks = NULL;
+ int i, nr_sets;
/*
* If there aren't any vectors left after applying the pre/post
@@ -188,15 +247,9 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
if (nvecs == affd->pre_vectors + affd->post_vectors)
return NULL;
- if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
- return NULL;
-
- if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
- goto outcpumsk;
-
node_to_cpumask = alloc_node_to_cpumask();
if (!node_to_cpumask)
- goto outnpresmsk;
+ return NULL;
masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
if (!masks)
@@ -204,32 +257,29 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
/* Fill out vectors at the beginning that don't need affinity */
for (curvec = 0; curvec < affd->pre_vectors; curvec++)
- cpumask_copy(masks + curvec, irq_default_affinity);
-
- /* Stabilize the cpumasks */
- get_online_cpus();
- build_node_to_cpumask(node_to_cpumask);
-
- /* Spread on present CPUs starting from affd->pre_vectors */
- usedvecs = irq_build_affinity_masks(affd, curvec, affvecs,
- node_to_cpumask, cpu_present_mask,
- nmsk, masks);
-
+ cpumask_copy(&masks[curvec].mask, irq_default_affinity);
/*
- * Spread on non present CPUs starting from the next vector to be
- * handled. If the spreading of present CPUs already exhausted the
- * vector space, assign the non present CPUs to the already spread
- * out vectors.
+ * Spread on present CPUs starting from affd->pre_vectors. If we
+ * have multiple sets, build each sets affinity mask separately.
*/
- if (usedvecs >= affvecs)
- curvec = affd->pre_vectors;
- else
- curvec = affd->pre_vectors + usedvecs;
- cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
- usedvecs += irq_build_affinity_masks(affd, curvec, affvecs,
- node_to_cpumask, npresmsk,
- nmsk, masks);
- put_online_cpus();
+ nr_sets = affd->nr_sets;
+ if (!nr_sets)
+ nr_sets = 1;
+
+ for (i = 0, usedvecs = 0; i < nr_sets; i++) {
+ int this_vecs = affd->sets ? affd->sets[i] : affvecs;
+ int ret;
+
+ ret = irq_build_affinity_masks(affd, curvec, this_vecs,
+ curvec, node_to_cpumask, masks);
+ if (ret) {
+ kfree(masks);
+ masks = NULL;
+ goto outnodemsk;
+ }
+ curvec += this_vecs;
+ usedvecs += this_vecs;
+ }
/* Fill out vectors at the end that don't need affinity */
if (usedvecs >= affvecs)
@@ -237,14 +287,14 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
else
curvec = affd->pre_vectors + usedvecs;
for (; curvec < nvecs; curvec++)
- cpumask_copy(masks + curvec, irq_default_affinity);
+ cpumask_copy(&masks[curvec].mask, irq_default_affinity);
+
+ /* Mark the managed interrupts */
+ for (i = affd->pre_vectors; i < nvecs - affd->post_vectors; i++)
+ masks[i].is_managed = 1;
outnodemsk:
free_node_to_cpumask(node_to_cpumask);
-outnpresmsk:
- free_cpumask_var(npresmsk);
-outcpumsk:
- free_cpumask_var(nmsk);
return masks;
}
@@ -258,13 +308,21 @@ int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity
{
int resv = affd->pre_vectors + affd->post_vectors;
int vecs = maxvec - resv;
- int ret;
+ int set_vecs;
if (resv > minvec)
return 0;
- get_online_cpus();
- ret = min_t(int, cpumask_weight(cpu_possible_mask), vecs) + resv;
- put_online_cpus();
- return ret;
+ if (affd->nr_sets) {
+ int i;
+
+ for (i = 0, set_vecs = 0; i < affd->nr_sets; i++)
+ set_vecs += affd->sets[i];
+ } else {
+ get_online_cpus();
+ set_vecs = cpumask_weight(cpu_possible_mask);
+ put_online_cpus();
+ }
+
+ return resv + min(set_vecs, vecs);
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a2b3d9de999c..34e969069488 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -929,7 +929,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
break;
/*
* Bail out if the outer chip is not set up
- * and the interrrupt supposed to be started
+ * and the interrupt supposed to be started
* right away.
*/
if (WARN_ON(is_chained))
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index 6a682c229e10..5d5378ea0afe 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -169,7 +169,7 @@ static void devm_irq_desc_release(struct device *dev, void *res)
* @cnt: Number of consecutive irqs to allocate
* @node: Preferred node on which the irq descriptor should be allocated
* @owner: Owning module (can be NULL)
- * @affinity: Optional pointer to an affinity mask array of size @cnt
+ * @affinity: Optional pointer to an irq_affinity_desc array of size @cnt
* which hints where the irq descriptors should be allocated
* and which default affinities to use
*
@@ -179,7 +179,7 @@ static void devm_irq_desc_release(struct device *dev, void *res)
*/
int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
unsigned int cnt, int node, struct module *owner,
- const struct cpumask *affinity)
+ const struct irq_affinity_desc *affinity)
{
struct irq_desc_devres *dr;
int base;
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index 8b778e37dc6d..43e3d1be622c 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -56,7 +56,7 @@ int irq_reserve_ipi(struct irq_domain *domain,
unsigned int next;
/*
- * The IPI requires a seperate HW irq on each CPU. We require
+ * The IPI requires a separate HW irq on each CPU. We require
* that the destination mask is consecutive. If an
* implementation needs to support holes, it can reserve
* several IPI ranges.
@@ -172,7 +172,7 @@ irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu)
/*
* Get the real hardware irq number if the underlying implementation
- * uses a seperate irq per cpu. If the underlying implementation uses
+ * uses a separate irq per cpu. If the underlying implementation uses
* a single hardware irq for all cpus then the IPI send mechanism
* needs to take care of the cpu destinations.
*/
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index dd20d0d528d4..98a20e1594ce 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -34,9 +34,20 @@ static struct irq_chip irq_sim_irqchip = {
static void irq_sim_handle_irq(struct irq_work *work)
{
struct irq_sim_work_ctx *work_ctx;
+ unsigned int offset = 0;
+ struct irq_sim *sim;
+ int irqnum;
work_ctx = container_of(work, struct irq_sim_work_ctx, work);
- handle_simple_irq(irq_to_desc(work_ctx->irq));
+ sim = container_of(work_ctx, struct irq_sim, work_ctx);
+
+ while (!bitmap_empty(work_ctx->pending, sim->irq_count)) {
+ offset = find_next_bit(work_ctx->pending,
+ sim->irq_count, offset);
+ clear_bit(offset, work_ctx->pending);
+ irqnum = irq_sim_irqnum(sim, offset);
+ handle_simple_irq(irq_to_desc(irqnum));
+ }
}
/**
@@ -63,6 +74,13 @@ int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs)
return sim->irq_base;
}
+ sim->work_ctx.pending = bitmap_zalloc(num_irqs, GFP_KERNEL);
+ if (!sim->work_ctx.pending) {
+ kfree(sim->irqs);
+ irq_free_descs(sim->irq_base, num_irqs);
+ return -ENOMEM;
+ }
+
for (i = 0; i < num_irqs; i++) {
sim->irqs[i].irqnum = sim->irq_base + i;
sim->irqs[i].enabled = false;
@@ -89,6 +107,7 @@ EXPORT_SYMBOL_GPL(irq_sim_init);
void irq_sim_fini(struct irq_sim *sim)
{
irq_work_sync(&sim->work_ctx.work);
+ bitmap_free(sim->work_ctx.pending);
irq_free_descs(sim->irq_base, sim->irq_count);
kfree(sim->irqs);
}
@@ -143,7 +162,7 @@ EXPORT_SYMBOL_GPL(devm_irq_sim_init);
void irq_sim_fire(struct irq_sim *sim, unsigned int offset)
{
if (sim->irqs[offset].enabled) {
- sim->work_ctx.irq = irq_sim_irqnum(sim, offset);
+ set_bit(offset, sim->work_ctx.pending);
irq_work_queue(&sim->work_ctx.work);
}
}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 578d0e5f1b5b..ee062b7939d3 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -449,30 +449,34 @@ static void free_desc(unsigned int irq)
}
static int alloc_descs(unsigned int start, unsigned int cnt, int node,
- const struct cpumask *affinity, struct module *owner)
+ const struct irq_affinity_desc *affinity,
+ struct module *owner)
{
- const struct cpumask *mask = NULL;
struct irq_desc *desc;
- unsigned int flags;
int i;
/* Validate affinity mask(s) */
if (affinity) {
- for (i = 0, mask = affinity; i < cnt; i++, mask++) {
- if (cpumask_empty(mask))
+ for (i = 0; i < cnt; i++, i++) {
+ if (cpumask_empty(&affinity[i].mask))
return -EINVAL;
}
}
- flags = affinity ? IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN : 0;
- mask = NULL;
-
for (i = 0; i < cnt; i++) {
+ const struct cpumask *mask = NULL;
+ unsigned int flags = 0;
+
if (affinity) {
- node = cpu_to_node(cpumask_first(affinity));
- mask = affinity;
+ if (affinity->is_managed) {
+ flags = IRQD_AFFINITY_MANAGED |
+ IRQD_MANAGED_SHUTDOWN;
+ }
+ mask = &affinity->mask;
+ node = cpu_to_node(cpumask_first(mask));
affinity++;
}
+
desc = alloc_desc(start + i, node, flags, mask, owner);
if (!desc)
goto err;
@@ -575,7 +579,7 @@ static void free_desc(unsigned int irq)
}
static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
- const struct cpumask *affinity,
+ const struct irq_affinity_desc *affinity,
struct module *owner)
{
u32 i;
@@ -705,7 +709,7 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
*/
int __ref
__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
- struct module *owner, const struct cpumask *affinity)
+ struct module *owner, const struct irq_affinity_desc *affinity)
{
int start, ret;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 3366d11c3e02..8b0be4bd6565 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -969,7 +969,7 @@ const struct irq_domain_ops irq_domain_simple_ops = {
EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
- int node, const struct cpumask *affinity)
+ int node, const struct irq_affinity_desc *affinity)
{
unsigned int hint;
@@ -1281,7 +1281,7 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
*/
int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
unsigned int nr_irqs, int node, void *arg,
- bool realloc, const struct cpumask *affinity)
+ bool realloc, const struct irq_affinity_desc *affinity)
{
int i, ret, virq;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9dbdccab3b6a..a4888ce4667a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -915,7 +915,7 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
#endif
/*
- * Interrupts which are not explicitely requested as threaded
+ * Interrupts which are not explicitly requested as threaded
* interrupts rely on the implicit bh/preempt disable of the hard irq
* context. So we need to disable bh here to avoid deadlocks and other
* side effects.
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 1f0985adf193..30cc217b8631 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -14,6 +14,7 @@ struct cpumap {
unsigned int available;
unsigned int allocated;
unsigned int managed;
+ unsigned int managed_allocated;
bool initialized;
bool online;
unsigned long alloc_map[IRQ_MATRIX_SIZE];
@@ -145,6 +146,27 @@ static unsigned int matrix_find_best_cpu(struct irq_matrix *m,
return best_cpu;
}
+/* Find the best CPU which has the lowest number of managed IRQs allocated */
+static unsigned int matrix_find_best_cpu_managed(struct irq_matrix *m,
+ const struct cpumask *msk)
+{
+ unsigned int cpu, best_cpu, allocated = UINT_MAX;
+ struct cpumap *cm;
+
+ best_cpu = UINT_MAX;
+
+ for_each_cpu(cpu, msk) {
+ cm = per_cpu_ptr(m->maps, cpu);
+
+ if (!cm->online || cm->managed_allocated > allocated)
+ continue;
+
+ best_cpu = cpu;
+ allocated = cm->managed_allocated;
+ }
+ return best_cpu;
+}
+
/**
* irq_matrix_assign_system - Assign system wide entry in the matrix
* @m: Matrix pointer
@@ -269,7 +291,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk,
if (cpumask_empty(msk))
return -EINVAL;
- cpu = matrix_find_best_cpu(m, msk);
+ cpu = matrix_find_best_cpu_managed(m, msk);
if (cpu == UINT_MAX)
return -ENOSPC;
@@ -282,6 +304,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk,
return -ENOSPC;
set_bit(bit, cm->alloc_map);
cm->allocated++;
+ cm->managed_allocated++;
m->total_allocated++;
*mapped_cpu = cpu;
trace_irq_matrix_alloc_managed(bit, cpu, m, cm);
@@ -395,6 +418,8 @@ void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
clear_bit(bit, cm->alloc_map);
cm->allocated--;
+ if(managed)
+ cm->managed_allocated--;
if (cm->online)
m->total_allocated--;
@@ -464,13 +489,14 @@ void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind)
seq_printf(sf, "Total allocated: %6u\n", m->total_allocated);
seq_printf(sf, "System: %u: %*pbl\n", nsys, m->matrix_bits,
m->system_map);
- seq_printf(sf, "%*s| CPU | avl | man | act | vectors\n", ind, " ");
+ seq_printf(sf, "%*s| CPU | avl | man | mac | act | vectors\n", ind, " ");
cpus_read_lock();
for_each_online_cpu(cpu) {
struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
- seq_printf(sf, "%*s %4d %4u %4u %4u %*pbl\n", ind, " ",
- cpu, cm->available, cm->managed, cm->allocated,
+ seq_printf(sf, "%*s %4d %4u %4u %4u %4u %*pbl\n", ind, " ",
+ cpu, cm->available, cm->managed,
+ cm->managed_allocated, cm->allocated,
m->matrix_bits, cm->alloc_map);
}
cpus_read_unlock();
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 4ca2fd46645d..ad26fbcfbfc8 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -23,11 +23,11 @@
* @nvec: The number of vectors used in this entry
* @affinity: Optional pointer to an affinity mask array size of @nvec
*
- * If @affinity is not NULL then a an affinity array[@nvec] is allocated
- * and the affinity masks from @affinity are copied.
+ * If @affinity is not NULL then an affinity array[@nvec] is allocated
+ * and the affinity masks and flags from @affinity are copied.
*/
-struct msi_desc *
-alloc_msi_entry(struct device *dev, int nvec, const struct cpumask *affinity)
+struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
+ const struct irq_affinity_desc *affinity)
{
struct msi_desc *desc;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index d867d6ddafdd..6d2fa6914b30 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -66,7 +66,7 @@ static int try_one_irq(struct irq_desc *desc, bool force)
raw_spin_lock(&desc->lock);
/*
- * PER_CPU, nested thread interrupts and interrupts explicitely
+ * PER_CPU, nested thread interrupts and interrupts explicitly
* marked polled are excluded from polling.
*/
if (irq_settings_is_per_cpu(desc) ||
@@ -76,7 +76,7 @@ static int try_one_irq(struct irq_desc *desc, bool force)
/*
* Do not poll disabled interrupts unless the spurious
- * disabled poller asks explicitely.
+ * disabled poller asks explicitly.
*/
if (irqd_irq_disabled(&desc->irq_data) && !force)
goto out;
@@ -292,7 +292,7 @@ void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret)
* So in case a thread is woken, we just note the fact and
* defer the analysis to the next hardware interrupt.
*
- * The threaded handlers store whether they sucessfully
+ * The threaded handlers store whether they successfully
* handled an interrupt and we check whether that number
* changed versus the last invocation.
*
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 35cf0ad29718..f1d0e00a3971 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -16,6 +16,7 @@
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/kexec.h>
+#include <linux/memblock.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/fs.h>
@@ -76,7 +77,7 @@ void * __weak arch_kexec_kernel_image_load(struct kimage *image)
return kexec_image_load_default(image);
}
-static int kexec_image_post_load_cleanup_default(struct kimage *image)
+int kexec_image_post_load_cleanup_default(struct kimage *image)
{
if (!image->fops || !image->fops->cleanup)
return 0;
@@ -499,8 +500,60 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
return locate_mem_hole_bottom_up(start, end, kbuf);
}
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
+{
+ return 0;
+}
+#else
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
+{
+ int ret = 0;
+ u64 i;
+ phys_addr_t mstart, mend;
+ struct resource res = { };
+
+ if (kbuf->image->type == KEXEC_TYPE_CRASH)
+ return func(&crashk_res, kbuf);
+
+ if (kbuf->top_down) {
+ for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ /*
+ * In memblock, end points to the first byte after the
+ * range while in kexec, end points to the last byte
+ * in the range.
+ */
+ res.start = mstart;
+ res.end = mend - 1;
+ ret = func(&res, kbuf);
+ if (ret)
+ break;
+ }
+ } else {
+ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ /*
+ * In memblock, end points to the first byte after the
+ * range while in kexec, end points to the last byte
+ * in the range.
+ */
+ res.start = mstart;
+ res.end = mend - 1;
+ ret = func(&res, kbuf);
+ if (ret)
+ break;
+ }
+ }
+
+ return ret;
+}
+#endif
+
/**
- * arch_kexec_walk_mem - call func(data) on free memory regions
+ * kexec_walk_resources - call func(data) on free memory regions
* @kbuf: Context info for the search. Also passed to @func.
* @func: Function to call for each memory region.
*
@@ -508,8 +561,8 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
* and that value will be returned. If all free regions are visited without
* func returning non-zero, then zero will be returned.
*/
-int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
- int (*func)(struct resource *, void *))
+static int kexec_walk_resources(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
{
if (kbuf->image->type == KEXEC_TYPE_CRASH)
return walk_iomem_res_desc(crashk_res.desc,
@@ -532,7 +585,14 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
{
int ret;
- ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback);
+ /* Arch knows where to place */
+ if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
+ return 0;
+
+ if (IS_ENABLED(CONFIG_ARCH_DISCARD_MEMBLOCK))
+ ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
+ else
+ ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback);
return ret == 1 ? 0 : -EADDRNOTAVAIL;
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 90e98e233647..f4ddfdd2d07e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -229,7 +229,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
struct kprobe_insn_page *kip, *next;
/* Ensure no-one is interrupted on the garbages */
- synchronize_sched();
+ synchronize_rcu();
list_for_each_entry_safe(kip, next, &c->pages, list) {
int i;
@@ -1382,7 +1382,7 @@ out:
if (ret) {
ap->flags |= KPROBE_FLAG_DISABLED;
list_del_rcu(&p->list);
- synchronize_sched();
+ synchronize_rcu();
}
}
}
@@ -1597,7 +1597,7 @@ int register_kprobe(struct kprobe *p)
ret = arm_kprobe(p);
if (ret) {
hlist_del_rcu(&p->hlist);
- synchronize_sched();
+ synchronize_rcu();
goto out;
}
}
@@ -1776,7 +1776,7 @@ void unregister_kprobes(struct kprobe **kps, int num)
kps[i]->addr = NULL;
mutex_unlock(&kprobe_mutex);
- synchronize_sched();
+ synchronize_rcu();
for (i = 0; i < num; i++)
if (kps[i]->addr)
__unregister_kprobe_bottom(kps[i]);
@@ -1966,7 +1966,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
rps[i]->kp.addr = NULL;
mutex_unlock(&kprobe_mutex);
- synchronize_sched();
+ synchronize_rcu();
for (i = 0; i < num; i++) {
if (rps[i]->kp.addr) {
__unregister_kprobe_bottom(&rps[i]->kp);
@@ -2093,6 +2093,47 @@ void dump_kprobe(struct kprobe *kp)
}
NOKPROBE_SYMBOL(dump_kprobe);
+int kprobe_add_ksym_blacklist(unsigned long entry)
+{
+ struct kprobe_blacklist_entry *ent;
+ unsigned long offset = 0, size = 0;
+
+ if (!kernel_text_address(entry) ||
+ !kallsyms_lookup_size_offset(entry, &size, &offset))
+ return -EINVAL;
+
+ ent = kmalloc(sizeof(*ent), GFP_KERNEL);
+ if (!ent)
+ return -ENOMEM;
+ ent->start_addr = entry;
+ ent->end_addr = entry + size;
+ INIT_LIST_HEAD(&ent->list);
+ list_add_tail(&ent->list, &kprobe_blacklist);
+
+ return (int)size;
+}
+
+/* Add all symbols in given area into kprobe blacklist */
+int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
+{
+ unsigned long entry;
+ int ret = 0;
+
+ for (entry = start; entry < end; entry += ret) {
+ ret = kprobe_add_ksym_blacklist(entry);
+ if (ret < 0)
+ return ret;
+ if (ret == 0) /* In case of alias symbol */
+ ret = 1;
+ }
+ return 0;
+}
+
+int __init __weak arch_populate_kprobe_blacklist(void)
+{
+ return 0;
+}
+
/*
* Lookup and populate the kprobe_blacklist.
*
@@ -2104,26 +2145,24 @@ NOKPROBE_SYMBOL(dump_kprobe);
static int __init populate_kprobe_blacklist(unsigned long *start,
unsigned long *end)
{
+ unsigned long entry;
unsigned long *iter;
- struct kprobe_blacklist_entry *ent;
- unsigned long entry, offset = 0, size = 0;
+ int ret;
for (iter = start; iter < end; iter++) {
entry = arch_deref_entry_point((void *)*iter);
-
- if (!kernel_text_address(entry) ||
- !kallsyms_lookup_size_offset(entry, &size, &offset))
+ ret = kprobe_add_ksym_blacklist(entry);
+ if (ret == -EINVAL)
continue;
-
- ent = kmalloc(sizeof(*ent), GFP_KERNEL);
- if (!ent)
- return -ENOMEM;
- ent->start_addr = entry;
- ent->end_addr = entry + size;
- INIT_LIST_HEAD(&ent->list);
- list_add_tail(&ent->list, &kprobe_blacklist);
+ if (ret < 0)
+ return ret;
}
- return 0;
+
+ /* Symbols in __kprobes_text are blacklisted */
+ ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start,
+ (unsigned long)__kprobes_text_end);
+
+ return ret ? : arch_populate_kprobe_blacklist();
}
/* Module notifier call back, checking kprobes on the module */
diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
index 82d584225dc6..7702cb4064fc 100644
--- a/kernel/livepatch/patch.c
+++ b/kernel/livepatch/patch.c
@@ -61,7 +61,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
ops = container_of(fops, struct klp_ops, fops);
/*
- * A variant of synchronize_sched() is used to allow patching functions
+ * A variant of synchronize_rcu() is used to allow patching functions
* where RCU is not watching, see klp_synchronize_transition().
*/
preempt_disable_notrace();
@@ -72,7 +72,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
/*
* func should never be NULL because preemption should be disabled here
* and unregister_ftrace_function() does the equivalent of a
- * synchronize_sched() before the func_stack removal.
+ * synchronize_rcu() before the func_stack removal.
*/
if (WARN_ON_ONCE(!func))
goto unlock;
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 5bc349805e03..304d5eb8a98c 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -52,7 +52,7 @@ static DECLARE_DELAYED_WORK(klp_transition_work, klp_transition_work_fn);
/*
* This function is just a stub to implement a hard force
- * of synchronize_sched(). This requires synchronizing
+ * of synchronize_rcu(). This requires synchronizing
* tasks even in userspace and idle.
*/
static void klp_sync(struct work_struct *work)
@@ -175,7 +175,7 @@ void klp_cancel_transition(void)
void klp_update_patch_state(struct task_struct *task)
{
/*
- * A variant of synchronize_sched() is used to allow patching functions
+ * A variant of synchronize_rcu() is used to allow patching functions
* where RCU is not watching, see klp_synchronize_transition().
*/
preempt_disable_notrace();
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 1efada2dd9dd..95932333a48b 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -138,6 +138,9 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
* get freed - this significantly simplifies the debugging code.
*/
unsigned long nr_lock_classes;
+#ifndef CONFIG_DEBUG_LOCKDEP
+static
+#endif
struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
static inline struct lock_class *hlock_class(struct held_lock *hlock)
@@ -626,7 +629,8 @@ static int static_obj(void *obj)
/*
* To make lock name printouts unique, we calculate a unique
- * class->name_version generation counter:
+ * class->name_version generation counter. The caller must hold the graph
+ * lock.
*/
static int count_matching_names(struct lock_class *new_class)
{
@@ -636,7 +640,7 @@ static int count_matching_names(struct lock_class *new_class)
if (!new_class->name)
return 0;
- list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
+ list_for_each_entry(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))
@@ -789,7 +793,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
class->key = key;
class->name = lock->name;
class->subclass = subclass;
- INIT_LIST_HEAD(&class->lock_entry);
INIT_LIST_HEAD(&class->locks_before);
INIT_LIST_HEAD(&class->locks_after);
class->name_version = count_matching_names(class);
@@ -801,7 +804,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
/*
* Add it to the global list of classes:
*/
- list_add_tail_rcu(&class->lock_entry, &all_lock_classes);
+ list_add_tail(&class->lock_entry, &all_lock_classes);
if (verbose(class)) {
graph_unlock();
@@ -3088,7 +3091,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
/*
* Initialize a lock instance's lock-class mapping info:
*/
-static void __lockdep_init_map(struct lockdep_map *lock, const char *name,
+void lockdep_init_map(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, int subclass)
{
int i;
@@ -3144,12 +3147,6 @@ static void __lockdep_init_map(struct lockdep_map *lock, const char *name,
raw_local_irq_restore(flags);
}
}
-
-void lockdep_init_map(struct lockdep_map *lock, const char *name,
- struct lock_class_key *key, int subclass)
-{
- __lockdep_init_map(lock, name, key, subclass);
-}
EXPORT_SYMBOL_GPL(lockdep_init_map);
struct lock_class_key __lockdep_no_validate__;
@@ -4126,6 +4123,9 @@ void lockdep_reset(void)
raw_local_irq_restore(flags);
}
+/*
+ * Remove all references to a lock class. The caller must hold the graph lock.
+ */
static void zap_class(struct lock_class *class)
{
int i;
@@ -4142,7 +4142,7 @@ static void zap_class(struct lock_class *class)
* Unhash the class and remove it from the all_lock_classes list:
*/
hlist_del_rcu(&class->hash_entry);
- list_del_rcu(&class->lock_entry);
+ list_del(&class->lock_entry);
RCU_INIT_POINTER(class->key, NULL);
RCU_INIT_POINTER(class->name, NULL);
@@ -4195,7 +4195,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
*
* sync_sched() is sufficient because the read-side is IRQ disable.
*/
- synchronize_sched();
+ synchronize_rcu();
/*
* XXX at this point we could return the resources to the pool;
@@ -4204,15 +4204,36 @@ void lockdep_free_key_range(void *start, unsigned long size)
*/
}
-void lockdep_reset_lock(struct lockdep_map *lock)
+/*
+ * Check whether any element of the @lock->class_cache[] array refers to a
+ * registered lock class. The caller must hold either the graph lock or the
+ * RCU read lock.
+ */
+static bool lock_class_cache_is_registered(struct lockdep_map *lock)
{
struct lock_class *class;
struct hlist_head *head;
- unsigned long flags;
int i, j;
- int locked;
+
+ for (i = 0; i < CLASSHASH_SIZE; i++) {
+ head = classhash_table + i;
+ hlist_for_each_entry_rcu(class, head, hash_entry) {
+ for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
+ if (lock->class_cache[j] == class)
+ return true;
+ }
+ }
+ return false;
+}
+
+void lockdep_reset_lock(struct lockdep_map *lock)
+{
+ struct lock_class *class;
+ unsigned long flags;
+ int j, locked;
raw_local_irq_save(flags);
+ locked = graph_lock();
/*
* Remove all classes this lock might have:
@@ -4229,25 +4250,14 @@ void lockdep_reset_lock(struct lockdep_map *lock)
* Debug check: in the end all mapped classes should
* be gone.
*/
- locked = graph_lock();
- for (i = 0; i < CLASSHASH_SIZE; i++) {
- head = classhash_table + i;
- hlist_for_each_entry_rcu(class, head, hash_entry) {
- int match = 0;
-
- for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
- match |= class == lock->class_cache[j];
-
- if (unlikely(match)) {
- if (debug_locks_off_graph_unlock()) {
- /*
- * We all just reset everything, how did it match?
- */
- WARN_ON(1);
- }
- goto out_restore;
- }
+ if (unlikely(lock_class_cache_is_registered(lock))) {
+ if (debug_locks_off_graph_unlock()) {
+ /*
+ * We all just reset everything, how did it match?
+ */
+ WARN_ON(1);
}
+ goto out_restore;
}
if (locked)
graph_unlock();
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 9aa713629387..771d4ca96dda 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -36,7 +36,7 @@ void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter)
void debug_mutex_wake_waiter(struct mutex *lock, struct mutex_waiter *waiter)
{
- SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+ lockdep_assert_held(&lock->wait_lock);
DEBUG_LOCKS_WARN_ON(list_empty(&lock->wait_list));
DEBUG_LOCKS_WARN_ON(waiter->magic != waiter);
DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
@@ -51,7 +51,7 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
struct task_struct *task)
{
- SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
+ lockdep_assert_held(&lock->wait_lock);
/* Mark the current thread as blocked on the lock: */
task->blocked_on = waiter;
diff --git a/kernel/module.c b/kernel/module.c
index 06ec68f08387..d46c7814a00e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -495,9 +495,9 @@ struct find_symbol_arg {
const struct kernel_symbol *sym;
};
-static bool check_symbol(const struct symsearch *syms,
- struct module *owner,
- unsigned int symnum, void *data)
+static bool check_exported_symbol(const struct symsearch *syms,
+ struct module *owner,
+ unsigned int symnum, void *data)
{
struct find_symbol_arg *fsa = data;
@@ -555,9 +555,9 @@ static int cmp_name(const void *va, const void *vb)
return strcmp(a, kernel_symbol_name(b));
}
-static bool find_symbol_in_section(const struct symsearch *syms,
- struct module *owner,
- void *data)
+static bool find_exported_symbol_in_section(const struct symsearch *syms,
+ struct module *owner,
+ void *data)
{
struct find_symbol_arg *fsa = data;
struct kernel_symbol *sym;
@@ -565,13 +565,14 @@ static bool find_symbol_in_section(const struct symsearch *syms,
sym = bsearch(fsa->name, syms->start, syms->stop - syms->start,
sizeof(struct kernel_symbol), cmp_name);
- if (sym != NULL && check_symbol(syms, owner, sym - syms->start, data))
+ if (sym != NULL && check_exported_symbol(syms, owner,
+ sym - syms->start, data))
return true;
return false;
}
-/* Find a symbol and return it, along with, (optional) crc and
+/* Find an exported symbol and return it, along with, (optional) crc and
* (optional) module which owns it. Needs preempt disabled or module_mutex. */
const struct kernel_symbol *find_symbol(const char *name,
struct module **owner,
@@ -585,7 +586,7 @@ const struct kernel_symbol *find_symbol(const char *name,
fsa.gplok = gplok;
fsa.warn = warn;
- if (each_symbol_section(find_symbol_in_section, &fsa)) {
+ if (each_symbol_section(find_exported_symbol_in_section, &fsa)) {
if (owner)
*owner = fsa.owner;
if (crc)
@@ -2159,7 +2160,7 @@ static void free_module(struct module *mod)
/* Remove this module from bug list, this uses list_del_rcu */
module_bug_cleanup(mod);
/* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */
- synchronize_sched();
+ synchronize_rcu();
mutex_unlock(&module_mutex);
/* This may be empty, but that's OK */
@@ -2198,7 +2199,7 @@ EXPORT_SYMBOL_GPL(__symbol_get);
*
* You must hold the module_mutex.
*/
-static int verify_export_symbols(struct module *mod)
+static int verify_exported_symbols(struct module *mod)
{
unsigned int i;
struct module *owner;
@@ -2519,10 +2520,10 @@ static void free_modinfo(struct module *mod)
#ifdef CONFIG_KALLSYMS
-/* lookup symbol in given range of kernel_symbols */
-static const struct kernel_symbol *lookup_symbol(const char *name,
- const struct kernel_symbol *start,
- const struct kernel_symbol *stop)
+/* Lookup exported symbol in given range of kernel_symbols */
+static const struct kernel_symbol *lookup_exported_symbol(const char *name,
+ const struct kernel_symbol *start,
+ const struct kernel_symbol *stop)
{
return bsearch(name, start, stop - start,
sizeof(struct kernel_symbol), cmp_name);
@@ -2533,9 +2534,10 @@ static int is_exported(const char *name, unsigned long value,
{
const struct kernel_symbol *ks;
if (!mod)
- ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab);
+ ks = lookup_exported_symbol(name, __start___ksymtab, __stop___ksymtab);
else
- ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms);
+ ks = lookup_exported_symbol(name, mod->syms, mod->syms + mod->num_syms);
+
return ks != NULL && kernel_symbol_value(ks) == value;
}
@@ -2682,7 +2684,7 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
/* Set types up while we still have access to sections. */
for (i = 0; i < mod->kallsyms->num_symtab; i++)
- mod->kallsyms->symtab[i].st_info
+ mod->kallsyms->symtab[i].st_size
= elf_type(&mod->kallsyms->symtab[i], info);
/* Now populate the cut down core kallsyms for after init. */
@@ -3512,15 +3514,15 @@ static noinline int do_init_module(struct module *mod)
/*
* We want to free module_init, but be aware that kallsyms may be
* walking this with preempt disabled. In all the failure paths, we
- * call synchronize_sched(), but we don't want to slow down the success
+ * call synchronize_rcu(), but we don't want to slow down the success
* path, so use actual RCU here.
* Note that module_alloc() on most architectures creates W+X page
* mappings which won't be cleaned up until do_free_init() runs. Any
* code such as mark_rodata_ro() which depends on those mappings to
* be cleaned up needs to sync with the queued work - ie
- * rcu_barrier_sched()
+ * rcu_barrier()
*/
- call_rcu_sched(&freeinit->rcu, do_free_init);
+ call_rcu(&freeinit->rcu, do_free_init);
mutex_unlock(&module_mutex);
wake_up_all(&module_wq);
@@ -3531,7 +3533,7 @@ fail_free_freeinit:
fail:
/* Try to protect us from buggy refcounters. */
mod->state = MODULE_STATE_GOING;
- synchronize_sched();
+ synchronize_rcu();
module_put(mod);
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_GOING, mod);
@@ -3597,7 +3599,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
mutex_lock(&module_mutex);
/* Find duplicate symbols (must be called under lock). */
- err = verify_export_symbols(mod);
+ err = verify_exported_symbols(mod);
if (err < 0)
goto out;
@@ -3824,7 +3826,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
ddebug_cleanup:
ftrace_release_mod(mod);
dynamic_debug_remove(mod, info->debug);
- synchronize_sched();
+ synchronize_rcu();
kfree(mod->args);
free_arch_cleanup:
module_arch_cleanup(mod);
@@ -3839,7 +3841,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
mod_tree_remove(mod);
wake_up_all(&module_wq);
/* Wait for RCU-sched synchronizing before releasing mod->list. */
- synchronize_sched();
+ synchronize_rcu();
mutex_unlock(&module_mutex);
free_module:
/* Free lock-classes; relies on the preceding sync_rcu() */
@@ -3916,18 +3918,22 @@ static inline int is_arm_mapping_symbol(const char *str)
&& (str[2] == '\0' || str[2] == '.');
}
-static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum)
+static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum)
{
return kallsyms->strtab + kallsyms->symtab[symnum].st_name;
}
-static const char *get_ksymbol(struct module *mod,
- unsigned long addr,
- unsigned long *size,
- unsigned long *offset)
+/*
+ * Given a module and address, find the corresponding symbol and return its name
+ * while providing its size and offset if needed.
+ */
+static const char *find_kallsyms_symbol(struct module *mod,
+ unsigned long addr,
+ unsigned long *size,
+ unsigned long *offset)
{
unsigned int i, best = 0;
- unsigned long nextval;
+ unsigned long nextval, bestval;
struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
/* At worse, next value is at end of module */
@@ -3936,34 +3942,40 @@ static const char *get_ksymbol(struct module *mod,
else
nextval = (unsigned long)mod->core_layout.base+mod->core_layout.text_size;
+ bestval = kallsyms_symbol_value(&kallsyms->symtab[best]);
+
/* Scan for closest preceding symbol, and next symbol. (ELF
starts real symbols at 1). */
for (i = 1; i < kallsyms->num_symtab; i++) {
- if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
+ const Elf_Sym *sym = &kallsyms->symtab[i];
+ unsigned long thisval = kallsyms_symbol_value(sym);
+
+ if (sym->st_shndx == SHN_UNDEF)
continue;
/* We ignore unnamed symbols: they're uninformative
* and inserted at a whim. */
- if (*symname(kallsyms, i) == '\0'
- || is_arm_mapping_symbol(symname(kallsyms, i)))
+ if (*kallsyms_symbol_name(kallsyms, i) == '\0'
+ || is_arm_mapping_symbol(kallsyms_symbol_name(kallsyms, i)))
continue;
- if (kallsyms->symtab[i].st_value <= addr
- && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value)
+ if (thisval <= addr && thisval > bestval) {
best = i;
- if (kallsyms->symtab[i].st_value > addr
- && kallsyms->symtab[i].st_value < nextval)
- nextval = kallsyms->symtab[i].st_value;
+ bestval = thisval;
+ }
+ if (thisval > addr && thisval < nextval)
+ nextval = thisval;
}
if (!best)
return NULL;
if (size)
- *size = nextval - kallsyms->symtab[best].st_value;
+ *size = nextval - bestval;
if (offset)
- *offset = addr - kallsyms->symtab[best].st_value;
- return symname(kallsyms, best);
+ *offset = addr - bestval;
+
+ return kallsyms_symbol_name(kallsyms, best);
}
void * __weak dereference_module_function_descriptor(struct module *mod,
@@ -3988,7 +4000,8 @@ const char *module_address_lookup(unsigned long addr,
if (mod) {
if (modname)
*modname = mod->name;
- ret = get_ksymbol(mod, addr, size, offset);
+
+ ret = find_kallsyms_symbol(mod, addr, size, offset);
}
/* Make a copy in here where it's safe */
if (ret) {
@@ -4011,9 +4024,10 @@ int lookup_module_symbol_name(unsigned long addr, char *symname)
if (within_module(addr, mod)) {
const char *sym;
- sym = get_ksymbol(mod, addr, NULL, NULL);
+ sym = find_kallsyms_symbol(mod, addr, NULL, NULL);
if (!sym)
goto out;
+
strlcpy(symname, sym, KSYM_NAME_LEN);
preempt_enable();
return 0;
@@ -4036,7 +4050,7 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size,
if (within_module(addr, mod)) {
const char *sym;
- sym = get_ksymbol(mod, addr, size, offset);
+ sym = find_kallsyms_symbol(mod, addr, size, offset);
if (!sym)
goto out;
if (modname)
@@ -4065,9 +4079,11 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
continue;
kallsyms = rcu_dereference_sched(mod->kallsyms);
if (symnum < kallsyms->num_symtab) {
- *value = kallsyms->symtab[symnum].st_value;
- *type = kallsyms->symtab[symnum].st_info;
- strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN);
+ const Elf_Sym *sym = &kallsyms->symtab[symnum];
+
+ *value = kallsyms_symbol_value(sym);
+ *type = sym->st_size;
+ strlcpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN);
strlcpy(module_name, mod->name, MODULE_NAME_LEN);
*exported = is_exported(name, *value, mod);
preempt_enable();
@@ -4079,15 +4095,19 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
return -ERANGE;
}
-static unsigned long mod_find_symname(struct module *mod, const char *name)
+/* Given a module and name of symbol, find and return the symbol's value */
+static unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name)
{
unsigned int i;
struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
- for (i = 0; i < kallsyms->num_symtab; i++)
- if (strcmp(name, symname(kallsyms, i)) == 0 &&
- kallsyms->symtab[i].st_shndx != SHN_UNDEF)
- return kallsyms->symtab[i].st_value;
+ for (i = 0; i < kallsyms->num_symtab; i++) {
+ const Elf_Sym *sym = &kallsyms->symtab[i];
+
+ if (strcmp(name, kallsyms_symbol_name(kallsyms, i)) == 0 &&
+ sym->st_shndx != SHN_UNDEF)
+ return kallsyms_symbol_value(sym);
+ }
return 0;
}
@@ -4102,12 +4122,12 @@ unsigned long module_kallsyms_lookup_name(const char *name)
preempt_disable();
if ((colon = strnchr(name, MODULE_NAME_LEN, ':')) != NULL) {
if ((mod = find_module_all(name, colon - name, false)) != NULL)
- ret = mod_find_symname(mod, colon+1);
+ ret = find_kallsyms_symbol_value(mod, colon+1);
} else {
list_for_each_entry_rcu(mod, &modules, list) {
if (mod->state == MODULE_STATE_UNFORMED)
continue;
- if ((ret = mod_find_symname(mod, name)) != 0)
+ if ((ret = find_kallsyms_symbol_value(mod, name)) != 0)
break;
}
}
@@ -4132,12 +4152,13 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
if (mod->state == MODULE_STATE_UNFORMED)
continue;
for (i = 0; i < kallsyms->num_symtab; i++) {
+ const Elf_Sym *sym = &kallsyms->symtab[i];
- if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
+ if (sym->st_shndx == SHN_UNDEF)
continue;
- ret = fn(data, symname(kallsyms, i),
- mod, kallsyms->symtab[i].st_value);
+ ret = fn(data, kallsyms_symbol_name(kallsyms, i),
+ mod, kallsyms_symbol_value(sym));
if (ret != 0)
return ret;
}
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index f2075ce8e4b3..6b9a926fd86b 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -83,6 +83,7 @@ int mod_verify_sig(const void *mod, struct load_info *info)
}
return verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len,
- NULL, VERIFYING_MODULE_SIGNATURE,
+ VERIFY_USE_SECONDARY_KEYRING,
+ VERIFYING_MODULE_SIGNATURE,
NULL, NULL);
}
diff --git a/kernel/panic.c b/kernel/panic.c
index f6d549a29a5c..d10c340c43b0 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -14,6 +14,7 @@
#include <linux/kmsg_dump.h>
#include <linux/kallsyms.h>
#include <linux/notifier.h>
+#include <linux/vt_kern.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/ftrace.h>
@@ -237,7 +238,10 @@ void panic(const char *fmt, ...)
if (_crash_kexec_post_notifiers)
__crash_kexec(NULL);
- bust_spinlocks(0);
+#ifdef CONFIG_VT
+ unblank_screen();
+#endif
+ console_unblank();
/*
* We may have ended up stopping the CPU holding the lock (in
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 3a6c2f87699e..f8fe57d1022e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -298,3 +298,18 @@ config PM_GENERIC_DOMAINS_OF
config CPU_PM
bool
+
+config ENERGY_MODEL
+ bool "Energy Model for CPUs"
+ depends on SMP
+ depends on CPU_FREQ
+ default n
+ help
+ Several subsystems (thermal and/or the task scheduler for example)
+ can leverage information about the energy consumed by CPUs to make
+ smarter decisions. This config option enables the framework from
+ which subsystems can access the energy models.
+
+ The exact usage of the energy model is subsystem-dependent.
+
+ If in doubt, say N.
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index a3f79f0eef36..e7e47d9be1e5 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -15,3 +15,5 @@ obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o
obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
+
+obj-$(CONFIG_ENERGY_MODEL) += energy_model.o
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
new file mode 100644
index 000000000000..d9dc2c38764a
--- /dev/null
+++ b/kernel/power/energy_model.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Energy Model of CPUs
+ *
+ * Copyright (c) 2018, Arm ltd.
+ * Written by: Quentin Perret, Arm ltd.
+ */
+
+#define pr_fmt(fmt) "energy_model: " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/energy_model.h>
+#include <linux/sched/topology.h>
+#include <linux/slab.h>
+
+/* Mapping of each CPU to the performance domain to which it belongs. */
+static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
+
+/*
+ * Mutex serializing the registrations of performance domains and letting
+ * callbacks defined by drivers sleep.
+ */
+static DEFINE_MUTEX(em_pd_mutex);
+
+static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
+ struct em_data_callback *cb)
+{
+ unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
+ unsigned long power, freq, prev_freq = 0;
+ int i, ret, cpu = cpumask_first(span);
+ struct em_cap_state *table;
+ struct em_perf_domain *pd;
+ u64 fmax;
+
+ if (!cb->active_power)
+ return NULL;
+
+ pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
+ if (!pd)
+ return NULL;
+
+ table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
+ if (!table)
+ goto free_pd;
+
+ /* Build the list of capacity states for this performance domain */
+ for (i = 0, freq = 0; i < nr_states; i++, freq++) {
+ /*
+ * active_power() is a driver callback which ceils 'freq' to
+ * lowest capacity state of 'cpu' above 'freq' and updates
+ * 'power' and 'freq' accordingly.
+ */
+ ret = cb->active_power(&power, &freq, cpu);
+ if (ret) {
+ pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
+ goto free_cs_table;
+ }
+
+ /*
+ * We expect the driver callback to increase the frequency for
+ * higher capacity states.
+ */
+ if (freq <= prev_freq) {
+ pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
+ goto free_cs_table;
+ }
+
+ /*
+ * The power returned by active_state() is expected to be
+ * positive, in milli-watts and to fit into 16 bits.
+ */
+ if (!power || power > EM_CPU_MAX_POWER) {
+ pr_err("pd%d: invalid power: %lu\n", cpu, power);
+ goto free_cs_table;
+ }
+
+ table[i].power = power;
+ table[i].frequency = prev_freq = freq;
+
+ /*
+ * The hertz/watts efficiency ratio should decrease as the
+ * frequency grows on sane platforms. But this isn't always
+ * true in practice so warn the user if a higher OPP is more
+ * power efficient than a lower one.
+ */
+ opp_eff = freq / power;
+ if (opp_eff >= prev_opp_eff)
+ pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
+ cpu, i, i - 1);
+ prev_opp_eff = opp_eff;
+ }
+
+ /* Compute the cost of each capacity_state. */
+ fmax = (u64) table[nr_states - 1].frequency;
+ for (i = 0; i < nr_states; i++) {
+ table[i].cost = div64_u64(fmax * table[i].power,
+ table[i].frequency);
+ }
+
+ pd->table = table;
+ pd->nr_cap_states = nr_states;
+ cpumask_copy(to_cpumask(pd->cpus), span);
+
+ return pd;
+
+free_cs_table:
+ kfree(table);
+free_pd:
+ kfree(pd);
+
+ return NULL;
+}
+
+/**
+ * em_cpu_get() - Return the performance domain for a CPU
+ * @cpu : CPU to find the performance domain for
+ *
+ * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_perf_domain *em_cpu_get(int cpu)
+{
+ return READ_ONCE(per_cpu(em_data, cpu));
+}
+EXPORT_SYMBOL_GPL(em_cpu_get);
+
+/**
+ * em_register_perf_domain() - Register the Energy Model of a performance domain
+ * @span : Mask of CPUs in the performance domain
+ * @nr_states : Number of capacity states to register
+ * @cb : Callback functions providing the data of the Energy Model
+ *
+ * Create Energy Model tables for a performance domain using the callbacks
+ * defined in cb.
+ *
+ * If multiple clients register the same performance domain, all but the first
+ * registration will be ignored.
+ *
+ * Return 0 on success
+ */
+int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
+ struct em_data_callback *cb)
+{
+ unsigned long cap, prev_cap = 0;
+ struct em_perf_domain *pd;
+ int cpu, ret = 0;
+
+ if (!span || !nr_states || !cb)
+ return -EINVAL;
+
+ /*
+ * Use a mutex to serialize the registration of performance domains and
+ * let the driver-defined callback functions sleep.
+ */
+ mutex_lock(&em_pd_mutex);
+
+ for_each_cpu(cpu, span) {
+ /* Make sure we don't register again an existing domain. */
+ if (READ_ONCE(per_cpu(em_data, cpu))) {
+ ret = -EEXIST;
+ goto unlock;
+ }
+
+ /*
+ * All CPUs of a domain must have the same micro-architecture
+ * since they all share the same table.
+ */
+ cap = arch_scale_cpu_capacity(NULL, cpu);
+ if (prev_cap && prev_cap != cap) {
+ pr_err("CPUs of %*pbl must have the same capacity\n",
+ cpumask_pr_args(span));
+ ret = -EINVAL;
+ goto unlock;
+ }
+ prev_cap = cap;
+ }
+
+ /* Create the performance domain and add it to the Energy Model. */
+ pd = em_create_pd(span, nr_states, cb);
+ if (!pd) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ for_each_cpu(cpu, span) {
+ /*
+ * The per-cpu array can be read concurrently from em_cpu_get().
+ * The barrier enforces the ordering needed to make sure readers
+ * can only access well formed em_perf_domain structs.
+ */
+ smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
+ }
+
+ pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
+unlock:
+ mutex_unlock(&em_pd_mutex);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(em_register_perf_domain);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 35b50823d83b..98e76cad128b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -318,23 +318,12 @@ static int suspend_stats_show(struct seq_file *s, void *unused)
return 0;
}
-
-static int suspend_stats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, suspend_stats_show, NULL);
-}
-
-static const struct file_operations suspend_stats_operations = {
- .open = suspend_stats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(suspend_stats);
static int __init pm_debugfs_init(void)
{
debugfs_create_file("suspend_stats", S_IFREG | S_IRUGO,
- NULL, NULL, &suspend_stats_operations);
+ NULL, NULL, &suspend_stats_fops);
return 0;
}
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 86d72ffb811b..b7a82502857a 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -184,7 +184,7 @@ static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
c->target_value = value;
}
-static int pm_qos_dbg_show_requests(struct seq_file *s, void *unused)
+static int pm_qos_debug_show(struct seq_file *s, void *unused)
{
struct pm_qos_object *qos = (struct pm_qos_object *)s->private;
struct pm_qos_constraints *c;
@@ -245,18 +245,7 @@ out:
return 0;
}
-static int pm_qos_dbg_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pm_qos_dbg_show_requests,
- inode->i_private);
-}
-
-static const struct file_operations pm_qos_debug_fops = {
- .open = pm_qos_dbg_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(pm_qos_debug);
/**
* pm_qos_update_target - manages the constraints list and calls the notifiers
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 1b2a029360b7..1306fe0c1dc6 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -403,6 +403,7 @@ DECLARE_WAIT_QUEUE_HEAD(log_wait);
static u64 syslog_seq;
static u32 syslog_idx;
static size_t syslog_partial;
+static bool syslog_time;
/* index and sequence number of the first record stored in the buffer */
static u64 log_first_seq;
@@ -752,6 +753,19 @@ struct devkmsg_user {
char buf[CONSOLE_EXT_LOG_MAX];
};
+static __printf(3, 4) __cold
+int devkmsg_emit(int facility, int level, const char *fmt, ...)
+{
+ va_list args;
+ int r;
+
+ va_start(args, fmt);
+ r = vprintk_emit(facility, level, NULL, 0, fmt, args);
+ va_end(args);
+
+ return r;
+}
+
static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
{
char *buf, *line;
@@ -810,7 +824,7 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
}
}
- printk_emit(facility, level, NULL, 0, "%s", line);
+ devkmsg_emit(facility, level, "%s", line);
kfree(buf);
return ret;
}
@@ -1213,50 +1227,39 @@ static inline void boot_delay_msec(int level)
static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME);
module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
-static size_t print_time(u64 ts, char *buf)
+static size_t print_syslog(unsigned int level, char *buf)
{
- unsigned long rem_nsec;
-
- if (!printk_time)
- return 0;
-
- rem_nsec = do_div(ts, 1000000000);
+ return sprintf(buf, "<%u>", level);
+}
- if (!buf)
- return snprintf(NULL, 0, "[%5lu.000000] ", (unsigned long)ts);
+static size_t print_time(u64 ts, char *buf)
+{
+ unsigned long rem_nsec = do_div(ts, 1000000000);
return sprintf(buf, "[%5lu.%06lu] ",
(unsigned long)ts, rem_nsec / 1000);
}
-static size_t print_prefix(const struct printk_log *msg, bool syslog, char *buf)
+static size_t print_prefix(const struct printk_log *msg, bool syslog,
+ bool time, char *buf)
{
size_t len = 0;
- unsigned int prefix = (msg->facility << 3) | msg->level;
-
- if (syslog) {
- if (buf) {
- len += sprintf(buf, "<%u>", prefix);
- } else {
- len += 3;
- if (prefix > 999)
- len += 3;
- else if (prefix > 99)
- len += 2;
- else if (prefix > 9)
- len++;
- }
- }
- len += print_time(msg->ts_nsec, buf ? buf + len : NULL);
+ if (syslog)
+ len = print_syslog((msg->facility << 3) | msg->level, buf);
+ if (time)
+ len += print_time(msg->ts_nsec, buf + len);
return len;
}
-static size_t msg_print_text(const struct printk_log *msg, bool syslog, char *buf, size_t size)
+static size_t msg_print_text(const struct printk_log *msg, bool syslog,
+ bool time, char *buf, size_t size)
{
const char *text = log_text(msg);
size_t text_size = msg->text_len;
size_t len = 0;
+ char prefix[PREFIX_MAX];
+ const size_t prefix_len = print_prefix(msg, syslog, time, prefix);
do {
const char *next = memchr(text, '\n', text_size);
@@ -1271,19 +1274,17 @@ static size_t msg_print_text(const struct printk_log *msg, bool syslog, char *bu
}
if (buf) {
- if (print_prefix(msg, syslog, NULL) +
- text_len + 1 >= size - len)
+ if (prefix_len + text_len + 1 >= size - len)
break;
- len += print_prefix(msg, syslog, buf + len);
+ memcpy(buf + len, prefix, prefix_len);
+ len += prefix_len;
memcpy(buf + len, text, text_len);
len += text_len;
buf[len++] = '\n';
} else {
/* SYSLOG_ACTION_* buffer size only calculation */
- len += print_prefix(msg, syslog, NULL);
- len += text_len;
- len++;
+ len += prefix_len + text_len + 1;
}
text = next;
@@ -1318,9 +1319,17 @@ static int syslog_print(char __user *buf, int size)
break;
}
+ /*
+ * To keep reading/counting partial line consistent,
+ * use printk_time value as of the beginning of a line.
+ */
+ if (!syslog_partial)
+ syslog_time = printk_time;
+
skip = syslog_partial;
msg = log_from_idx(syslog_idx);
- n = msg_print_text(msg, true, text, LOG_LINE_MAX + PREFIX_MAX);
+ n = msg_print_text(msg, true, syslog_time, text,
+ LOG_LINE_MAX + PREFIX_MAX);
if (n - syslog_partial <= size) {
/* message fits into buffer, move forward */
syslog_idx = log_next(syslog_idx);
@@ -1360,11 +1369,13 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
u64 next_seq;
u64 seq;
u32 idx;
+ bool time;
text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
if (!text)
return -ENOMEM;
+ time = printk_time;
logbuf_lock_irq();
/*
* Find first record that fits, including all following records,
@@ -1375,7 +1386,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
while (seq < log_next_seq) {
struct printk_log *msg = log_from_idx(idx);
- len += msg_print_text(msg, true, NULL, 0);
+ len += msg_print_text(msg, true, time, NULL, 0);
idx = log_next(idx);
seq++;
}
@@ -1386,7 +1397,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
while (len > size && seq < log_next_seq) {
struct printk_log *msg = log_from_idx(idx);
- len -= msg_print_text(msg, true, NULL, 0);
+ len -= msg_print_text(msg, true, time, NULL, 0);
idx = log_next(idx);
seq++;
}
@@ -1397,14 +1408,9 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
len = 0;
while (len >= 0 && seq < next_seq) {
struct printk_log *msg = log_from_idx(idx);
- int textlen;
+ int textlen = msg_print_text(msg, true, time, text,
+ LOG_LINE_MAX + PREFIX_MAX);
- textlen = msg_print_text(msg, true, text,
- LOG_LINE_MAX + PREFIX_MAX);
- if (textlen < 0) {
- len = textlen;
- break;
- }
idx = log_next(idx);
seq++;
@@ -1528,11 +1534,14 @@ int do_syslog(int type, char __user *buf, int len, int source)
} else {
u64 seq = syslog_seq;
u32 idx = syslog_idx;
+ bool time = syslog_partial ? syslog_time : printk_time;
while (seq < log_next_seq) {
struct printk_log *msg = log_from_idx(idx);
- error += msg_print_text(msg, true, NULL, 0);
+ error += msg_print_text(msg, true, time, NULL,
+ 0);
+ time = printk_time;
idx = log_next(idx);
seq++;
}
@@ -1935,21 +1944,6 @@ asmlinkage int vprintk(const char *fmt, va_list args)
}
EXPORT_SYMBOL(vprintk);
-asmlinkage int printk_emit(int facility, int level,
- const char *dict, size_t dictlen,
- const char *fmt, ...)
-{
- va_list args;
- int r;
-
- va_start(args, fmt);
- r = vprintk_emit(facility, level, dict, dictlen, fmt, args);
- va_end(args);
-
- return r;
-}
-EXPORT_SYMBOL(printk_emit);
-
int vprintk_default(const char *fmt, va_list args)
{
int r;
@@ -2005,6 +1999,7 @@ EXPORT_SYMBOL(printk);
#define LOG_LINE_MAX 0
#define PREFIX_MAX 0
+#define printk_time false
static u64 syslog_seq;
static u32 syslog_idx;
@@ -2028,8 +2023,8 @@ static void console_lock_spinning_enable(void) { }
static int console_lock_spinning_disable_and_check(void) { return 0; }
static void call_console_drivers(const char *ext_text, size_t ext_len,
const char *text, size_t len) {}
-static size_t msg_print_text(const struct printk_log *msg,
- bool syslog, char *buf, size_t size) { return 0; }
+static size_t msg_print_text(const struct printk_log *msg, bool syslog,
+ bool time, char *buf, size_t size) { return 0; }
static bool suppress_message_printing(int level) { return false; }
#endif /* CONFIG_PRINTK */
@@ -2387,8 +2382,7 @@ skip:
len += msg_print_text(msg,
console_msg_format & MSG_FORMAT_SYSLOG,
- text + len,
- sizeof(text) - len);
+ printk_time, text + len, sizeof(text) - len);
if (nr_ext_console_drivers) {
ext_len = msg_print_ext_header(ext_text,
sizeof(ext_text),
@@ -3112,7 +3106,7 @@ bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog,
goto out;
msg = log_from_idx(dumper->cur_idx);
- l = msg_print_text(msg, syslog, line, size);
+ l = msg_print_text(msg, syslog, printk_time, line, size);
dumper->cur_idx = log_next(dumper->cur_idx);
dumper->cur_seq++;
@@ -3183,6 +3177,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
u32 next_idx;
size_t l = 0;
bool ret = false;
+ bool time = printk_time;
if (!dumper->active)
goto out;
@@ -3206,7 +3201,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
while (seq < dumper->next_seq) {
struct printk_log *msg = log_from_idx(idx);
- l += msg_print_text(msg, true, NULL, 0);
+ l += msg_print_text(msg, true, time, NULL, 0);
idx = log_next(idx);
seq++;
}
@@ -3217,7 +3212,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
while (l > size && seq < dumper->next_seq) {
struct printk_log *msg = log_from_idx(idx);
- l -= msg_print_text(msg, true, NULL, 0);
+ l -= msg_print_text(msg, true, time, NULL, 0);
idx = log_next(idx);
seq++;
}
@@ -3230,7 +3225,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
while (seq < dumper->next_seq) {
struct printk_log *msg = log_from_idx(idx);
- l += msg_print_text(msg, syslog, buf + l, size - l);
+ l += msg_print_text(msg, syslog, time, buf + l, size - l);
idx = log_next(idx);
seq++;
}
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 2866166863f0..a393e24a9195 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -526,12 +526,14 @@ srcu_batches_completed(struct srcu_struct *sp) { return 0; }
static inline void rcu_force_quiescent_state(void) { }
static inline void show_rcu_gp_kthreads(void) { }
static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
+static inline void rcu_fwd_progress_check(unsigned long j) { }
#else /* #ifdef CONFIG_TINY_RCU */
unsigned long rcu_get_gp_seq(void);
unsigned long rcu_exp_batches_completed(void);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
void show_rcu_gp_kthreads(void);
int rcu_get_gp_kthreads_prio(void);
+void rcu_fwd_progress_check(unsigned long j);
void rcu_force_quiescent_state(void);
extern struct workqueue_struct *rcu_gp_wq;
extern struct workqueue_struct *rcu_par_gp_wq;
@@ -539,8 +541,10 @@ extern struct workqueue_struct *rcu_par_gp_wq;
#ifdef CONFIG_RCU_NOCB_CPU
bool rcu_is_nocb_cpu(int cpu);
+void rcu_bind_current_to_nocb(void);
#else
static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
+static inline void rcu_bind_current_to_nocb(void) { }
#endif
#endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 210c77460365..f6e85faa4ff4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -56,6 +56,7 @@
#include <linux/vmalloc.h>
#include <linux/sched/debug.h>
#include <linux/sched/sysctl.h>
+#include <linux/oom.h>
#include "rcu.h"
@@ -80,13 +81,6 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@jos
/* Must be power of two minus one. */
#define RCUTORTURE_RDR_MAX_SEGS (RCUTORTURE_RDR_MAX_LOOPS + 3)
-torture_param(int, cbflood_inter_holdoff, HZ,
- "Holdoff between floods (jiffies)");
-torture_param(int, cbflood_intra_holdoff, 1,
- "Holdoff between bursts (jiffies)");
-torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
-torture_param(int, cbflood_n_per_burst, 20000,
- "# callbacks per burst in flood");
torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
"Extend readers by disabling bh (1), irqs (2), or preempt (4)");
torture_param(int, fqs_duration, 0,
@@ -138,12 +132,10 @@ module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, srcu, ...)");
static int nrealreaders;
-static int ncbflooders;
static struct task_struct *writer_task;
static struct task_struct **fakewriter_tasks;
static struct task_struct **reader_tasks;
static struct task_struct *stats_task;
-static struct task_struct **cbflood_task;
static struct task_struct *fqs_task;
static struct task_struct *boost_tasks[NR_CPUS];
static struct task_struct *stall_task;
@@ -181,7 +173,6 @@ static long n_rcu_torture_boosts;
static atomic_long_t n_rcu_torture_timers;
static long n_barrier_attempts;
static long n_barrier_successes; /* did rcu_barrier test succeed? */
-static atomic_long_t n_cbfloods;
static struct list_head rcu_torture_removed;
static int rcu_torture_writer_state;
@@ -259,6 +250,8 @@ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */
static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
+static bool rcu_fwd_cb_nodelay; /* Short rcu_torture_delay() delays. */
+
/*
* Allocate an element from the rcu_tortures pool.
*/
@@ -348,7 +341,8 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
* period, and we want a long delay occasionally to trigger
* force_quiescent_state. */
- if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
+ if (!rcu_fwd_cb_nodelay &&
+ !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
started = cur_ops->get_gp_seq();
ts = rcu_trace_clock_local();
if (preempt_count() & (SOFTIRQ_MASK | HARDIRQ_MASK))
@@ -870,59 +864,6 @@ checkwait: stutter_wait("rcu_torture_boost");
return 0;
}
-static void rcu_torture_cbflood_cb(struct rcu_head *rhp)
-{
-}
-
-/*
- * RCU torture callback-flood kthread. Repeatedly induces bursts of calls
- * to call_rcu() or analogous, increasing the probability of occurrence
- * of callback-overflow corner cases.
- */
-static int
-rcu_torture_cbflood(void *arg)
-{
- int err = 1;
- int i;
- int j;
- struct rcu_head *rhp;
-
- if (cbflood_n_per_burst > 0 &&
- cbflood_inter_holdoff > 0 &&
- cbflood_intra_holdoff > 0 &&
- cur_ops->call &&
- cur_ops->cb_barrier) {
- rhp = vmalloc(array3_size(cbflood_n_burst,
- cbflood_n_per_burst,
- sizeof(*rhp)));
- err = !rhp;
- }
- if (err) {
- VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM");
- goto wait_for_stop;
- }
- VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started");
- do {
- schedule_timeout_interruptible(cbflood_inter_holdoff);
- atomic_long_inc(&n_cbfloods);
- WARN_ON(signal_pending(current));
- for (i = 0; i < cbflood_n_burst; i++) {
- for (j = 0; j < cbflood_n_per_burst; j++) {
- cur_ops->call(&rhp[i * cbflood_n_per_burst + j],
- rcu_torture_cbflood_cb);
- }
- schedule_timeout_interruptible(cbflood_intra_holdoff);
- WARN_ON(signal_pending(current));
- }
- cur_ops->cb_barrier();
- stutter_wait("rcu_torture_cbflood");
- } while (!torture_must_stop());
- vfree(rhp);
-wait_for_stop:
- torture_kthread_stopping("rcu_torture_cbflood");
- return 0;
-}
-
/*
* RCU torture force-quiescent-state kthread. Repeatedly induces
* bursts of calls to force_quiescent_state(), increasing the probability
@@ -1457,11 +1398,10 @@ rcu_torture_stats_print(void)
n_rcu_torture_boosts,
atomic_long_read(&n_rcu_torture_timers));
torture_onoff_stats();
- pr_cont("barrier: %ld/%ld:%ld ",
+ pr_cont("barrier: %ld/%ld:%ld\n",
n_barrier_successes,
n_barrier_attempts,
n_rcu_torture_barrier_error);
- pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods));
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
if (atomic_read(&n_rcu_torture_mberror) != 0 ||
@@ -1674,8 +1614,90 @@ static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp)
cur_ops->call(&fcsp->rh, rcu_torture_fwd_prog_cb);
}
-/* Carry out grace-period forward-progress testing. */
-static int rcu_torture_fwd_prog(void *args)
+/* State for continuous-flood RCU callbacks. */
+struct rcu_fwd_cb {
+ struct rcu_head rh;
+ struct rcu_fwd_cb *rfc_next;
+ int rfc_gps;
+};
+static DEFINE_SPINLOCK(rcu_fwd_lock);
+static struct rcu_fwd_cb *rcu_fwd_cb_head;
+static struct rcu_fwd_cb **rcu_fwd_cb_tail = &rcu_fwd_cb_head;
+static long n_launders_cb;
+static unsigned long rcu_fwd_startat;
+static bool rcu_fwd_emergency_stop;
+#define MAX_FWD_CB_JIFFIES (8 * HZ) /* Maximum CB test duration. */
+#define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */
+#define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */
+#define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */
+static long n_launders_hist[2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)];
+
+static void rcu_torture_fwd_cb_hist(void)
+{
+ int i;
+ int j;
+
+ for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
+ if (n_launders_hist[i] > 0)
+ break;
+ pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
+ __func__, jiffies - rcu_fwd_startat);
+ for (j = 0; j <= i; j++)
+ pr_cont(" %ds/%d: %ld",
+ j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j]);
+ pr_cont("\n");
+}
+
+/* Callback function for continuous-flood RCU callbacks. */
+static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
+{
+ unsigned long flags;
+ int i;
+ struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh);
+ struct rcu_fwd_cb **rfcpp;
+
+ rfcp->rfc_next = NULL;
+ rfcp->rfc_gps++;
+ spin_lock_irqsave(&rcu_fwd_lock, flags);
+ rfcpp = rcu_fwd_cb_tail;
+ rcu_fwd_cb_tail = &rfcp->rfc_next;
+ WRITE_ONCE(*rfcpp, rfcp);
+ WRITE_ONCE(n_launders_cb, n_launders_cb + 1);
+ i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
+ if (i >= ARRAY_SIZE(n_launders_hist))
+ i = ARRAY_SIZE(n_launders_hist) - 1;
+ n_launders_hist[i]++;
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+}
+
+/*
+ * Free all callbacks on the rcu_fwd_cb_head list, either because the
+ * test is over or because we hit an OOM event.
+ */
+static unsigned long rcu_torture_fwd_prog_cbfree(void)
+{
+ unsigned long flags;
+ unsigned long freed = 0;
+ struct rcu_fwd_cb *rfcp;
+
+ for (;;) {
+ spin_lock_irqsave(&rcu_fwd_lock, flags);
+ rfcp = rcu_fwd_cb_head;
+ if (!rfcp)
+ break;
+ rcu_fwd_cb_head = rfcp->rfc_next;
+ if (!rcu_fwd_cb_head)
+ rcu_fwd_cb_tail = &rcu_fwd_cb_head;
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ kfree(rfcp);
+ freed++;
+ }
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ return freed;
+}
+
+/* Carry out need_resched()/cond_resched() forward-progress testing. */
+static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
{
unsigned long cver;
unsigned long dur;
@@ -1686,56 +1708,186 @@ static int rcu_torture_fwd_prog(void *args)
int sd4;
bool selfpropcb = false;
unsigned long stopat;
- int tested = 0;
- int tested_tries = 0;
static DEFINE_TORTURE_RANDOM(trs);
- VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started");
- if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
- set_user_nice(current, MAX_NICE);
if (cur_ops->call && cur_ops->sync && cur_ops->cb_barrier) {
init_rcu_head_on_stack(&fcs.rh);
selfpropcb = true;
}
+
+ /* Tight loop containing cond_resched(). */
+ if (selfpropcb) {
+ WRITE_ONCE(fcs.stop, 0);
+ cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb);
+ }
+ cver = READ_ONCE(rcu_torture_current_version);
+ gps = cur_ops->get_gp_seq();
+ sd = cur_ops->stall_dur() + 1;
+ sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
+ dur = sd4 + torture_random(&trs) % (sd - sd4);
+ WRITE_ONCE(rcu_fwd_startat, jiffies);
+ stopat = rcu_fwd_startat + dur;
+ while (time_before(jiffies, stopat) &&
+ !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+ idx = cur_ops->readlock();
+ udelay(10);
+ cur_ops->readunlock(idx);
+ if (!fwd_progress_need_resched || need_resched())
+ cond_resched();
+ }
+ (*tested_tries)++;
+ if (!time_before(jiffies, stopat) &&
+ !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+ (*tested)++;
+ cver = READ_ONCE(rcu_torture_current_version) - cver;
+ gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+ WARN_ON(!cver && gps < 2);
+ pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
+ }
+ if (selfpropcb) {
+ WRITE_ONCE(fcs.stop, 1);
+ cur_ops->sync(); /* Wait for running CB to complete. */
+ cur_ops->cb_barrier(); /* Wait for queued callbacks. */
+ }
+
+ if (selfpropcb) {
+ WARN_ON(READ_ONCE(fcs.stop) != 2);
+ destroy_rcu_head_on_stack(&fcs.rh);
+ }
+}
+
+/* Carry out call_rcu() forward-progress testing. */
+static void rcu_torture_fwd_prog_cr(void)
+{
+ unsigned long cver;
+ unsigned long gps;
+ int i;
+ long n_launders;
+ long n_launders_cb_snap;
+ long n_launders_sa;
+ long n_max_cbs;
+ long n_max_gps;
+ struct rcu_fwd_cb *rfcp;
+ struct rcu_fwd_cb *rfcpn;
+ unsigned long stopat;
+ unsigned long stoppedat;
+
+ if (READ_ONCE(rcu_fwd_emergency_stop))
+ return; /* Get out of the way quickly, no GP wait! */
+
+ /* Loop continuously posting RCU callbacks. */
+ WRITE_ONCE(rcu_fwd_cb_nodelay, true);
+ cur_ops->sync(); /* Later readers see above write. */
+ WRITE_ONCE(rcu_fwd_startat, jiffies);
+ stopat = rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
+ n_launders = 0;
+ n_launders_cb = 0;
+ n_launders_sa = 0;
+ n_max_cbs = 0;
+ n_max_gps = 0;
+ for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
+ n_launders_hist[i] = 0;
+ cver = READ_ONCE(rcu_torture_current_version);
+ gps = cur_ops->get_gp_seq();
+ while (time_before(jiffies, stopat) &&
+ !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
+ rfcp = READ_ONCE(rcu_fwd_cb_head);
+ rfcpn = NULL;
+ if (rfcp)
+ rfcpn = READ_ONCE(rfcp->rfc_next);
+ if (rfcpn) {
+ if (rfcp->rfc_gps >= MIN_FWD_CB_LAUNDERS &&
+ ++n_max_gps >= MIN_FWD_CBS_LAUNDERED)
+ break;
+ rcu_fwd_cb_head = rfcpn;
+ n_launders++;
+ n_launders_sa++;
+ } else {
+ rfcp = kmalloc(sizeof(*rfcp), GFP_KERNEL);
+ if (WARN_ON_ONCE(!rfcp)) {
+ schedule_timeout_interruptible(1);
+ continue;
+ }
+ n_max_cbs++;
+ n_launders_sa = 0;
+ rfcp->rfc_gps = 0;
+ }
+ cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
+ cond_resched();
+ }
+ stoppedat = jiffies;
+ n_launders_cb_snap = READ_ONCE(n_launders_cb);
+ cver = READ_ONCE(rcu_torture_current_version) - cver;
+ gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+ cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
+ (void)rcu_torture_fwd_prog_cbfree();
+
+ WRITE_ONCE(rcu_fwd_cb_nodelay, false);
+ if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop)) {
+ WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED);
+ pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n",
+ __func__,
+ stoppedat - rcu_fwd_startat, jiffies - stoppedat,
+ n_launders + n_max_cbs - n_launders_cb_snap,
+ n_launders, n_launders_sa,
+ n_max_gps, n_max_cbs, cver, gps);
+ rcu_torture_fwd_cb_hist();
+ }
+}
+
+
+/*
+ * OOM notifier, but this only prints diagnostic information for the
+ * current forward-progress test.
+ */
+static int rcutorture_oom_notify(struct notifier_block *self,
+ unsigned long notused, void *nfreed)
+{
+ WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
+ __func__);
+ rcu_torture_fwd_cb_hist();
+ rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2));
+ WRITE_ONCE(rcu_fwd_emergency_stop, true);
+ smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ rcu_barrier();
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ rcu_barrier();
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ smp_mb(); /* Frees before return to avoid redoing OOM. */
+ (*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */
+ pr_info("%s returning after OOM processing.\n", __func__);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block rcutorture_oom_nb = {
+ .notifier_call = rcutorture_oom_notify
+};
+
+/* Carry out grace-period forward-progress testing. */
+static int rcu_torture_fwd_prog(void *args)
+{
+ int tested = 0;
+ int tested_tries = 0;
+
+ VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started");
+ rcu_bind_current_to_nocb();
+ if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
+ set_user_nice(current, MAX_NICE);
do {
schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
- if (selfpropcb) {
- WRITE_ONCE(fcs.stop, 0);
- cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb);
- }
- cver = READ_ONCE(rcu_torture_current_version);
- gps = cur_ops->get_gp_seq();
- sd = cur_ops->stall_dur() + 1;
- sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
- dur = sd4 + torture_random(&trs) % (sd - sd4);
- stopat = jiffies + dur;
- while (time_before(jiffies, stopat) && !torture_must_stop()) {
- idx = cur_ops->readlock();
- udelay(10);
- cur_ops->readunlock(idx);
- if (!fwd_progress_need_resched || need_resched())
- cond_resched();
- }
- tested_tries++;
- if (!time_before(jiffies, stopat) && !torture_must_stop()) {
- tested++;
- cver = READ_ONCE(rcu_torture_current_version) - cver;
- gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
- WARN_ON(!cver && gps < 2);
- pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
- }
- if (selfpropcb) {
- WRITE_ONCE(fcs.stop, 1);
- cur_ops->sync(); /* Wait for running CB to complete. */
- cur_ops->cb_barrier(); /* Wait for queued callbacks. */
- }
+ WRITE_ONCE(rcu_fwd_emergency_stop, false);
+ register_oom_notifier(&rcutorture_oom_nb);
+ rcu_torture_fwd_prog_nr(&tested, &tested_tries);
+ rcu_torture_fwd_prog_cr();
+ unregister_oom_notifier(&rcutorture_oom_nb);
+
/* Avoid slow periods, better to test when busy. */
stutter_wait("rcu_torture_fwd_prog");
} while (!torture_must_stop());
- if (selfpropcb) {
- WARN_ON(READ_ONCE(fcs.stop) != 2);
- destroy_rcu_head_on_stack(&fcs.rh);
- }
/* Short runs might not contain a valid forward-progress attempt. */
WARN_ON(!tested && tested_tries >= 5);
pr_alert("%s: tested %d tested_tries %d\n", __func__, tested, tested_tries);
@@ -1748,7 +1900,8 @@ static int __init rcu_torture_fwd_prog_init(void)
{
if (!fwd_progress)
return 0; /* Not requested, so don't do it. */
- if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0) {
+ if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 ||
+ cur_ops == &rcu_busted_ops) {
VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, unsupported by RCU flavor under test");
return 0;
}
@@ -1968,8 +2121,6 @@ rcu_torture_cleanup(void)
cur_ops->name, gp_seq, flags);
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
- for (i = 0; i < ncbflooders; i++)
- torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
if (rcu_torture_can_boost())
cpuhp_remove_state(rcutor_hp);
@@ -2252,24 +2403,6 @@ rcu_torture_init(void)
goto unwind;
if (object_debug)
rcu_test_debug_objects();
- if (cbflood_n_burst > 0) {
- /* Create the cbflood threads */
- ncbflooders = (num_online_cpus() + 3) / 4;
- cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task),
- GFP_KERNEL);
- if (!cbflood_task) {
- VERBOSE_TOROUT_ERRSTRING("out of memory");
- firsterr = -ENOMEM;
- goto unwind;
- }
- for (i = 0; i < ncbflooders; i++) {
- firsterr = torture_create_kthread(rcu_torture_cbflood,
- NULL,
- cbflood_task[i]);
- if (firsterr)
- goto unwind;
- }
- }
torture_init_end();
return 0;
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index b46e6683f8c9..32dfd6522548 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -37,30 +37,30 @@ int rcu_scheduler_active __read_mostly;
static LIST_HEAD(srcu_boot_list);
static bool srcu_init_done;
-static int init_srcu_struct_fields(struct srcu_struct *sp)
+static int init_srcu_struct_fields(struct srcu_struct *ssp)
{
- sp->srcu_lock_nesting[0] = 0;
- sp->srcu_lock_nesting[1] = 0;
- init_swait_queue_head(&sp->srcu_wq);
- sp->srcu_cb_head = NULL;
- sp->srcu_cb_tail = &sp->srcu_cb_head;
- sp->srcu_gp_running = false;
- sp->srcu_gp_waiting = false;
- sp->srcu_idx = 0;
- INIT_WORK(&sp->srcu_work, srcu_drive_gp);
- INIT_LIST_HEAD(&sp->srcu_work.entry);
+ ssp->srcu_lock_nesting[0] = 0;
+ ssp->srcu_lock_nesting[1] = 0;
+ init_swait_queue_head(&ssp->srcu_wq);
+ ssp->srcu_cb_head = NULL;
+ ssp->srcu_cb_tail = &ssp->srcu_cb_head;
+ ssp->srcu_gp_running = false;
+ ssp->srcu_gp_waiting = false;
+ ssp->srcu_idx = 0;
+ INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
+ INIT_LIST_HEAD(&ssp->srcu_work.entry);
return 0;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+int __init_srcu_struct(struct srcu_struct *ssp, const char *name,
struct lock_class_key *key)
{
/* Don't re-initialize a lock while it is held. */
- debug_check_no_locks_freed((void *)sp, sizeof(*sp));
- lockdep_init_map(&sp->dep_map, name, key, 0);
- return init_srcu_struct_fields(sp);
+ debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
+ lockdep_init_map(&ssp->dep_map, name, key, 0);
+ return init_srcu_struct_fields(ssp);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);
@@ -68,15 +68,15 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
/*
* init_srcu_struct - initialize a sleep-RCU structure
- * @sp: structure to initialize.
+ * @ssp: structure to initialize.
*
* Must invoke this on a given srcu_struct before passing that srcu_struct
* to any other function. Each srcu_struct represents a separate domain
* of SRCU protection.
*/
-int init_srcu_struct(struct srcu_struct *sp)
+int init_srcu_struct(struct srcu_struct *ssp)
{
- return init_srcu_struct_fields(sp);
+ return init_srcu_struct_fields(ssp);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);
@@ -84,22 +84,22 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
/*
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @sp: structure to clean up.
+ * @ssp: structure to clean up.
*
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
-void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
+void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
{
- WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
+ WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
if (quiesced)
- WARN_ON(work_pending(&sp->srcu_work));
+ WARN_ON(work_pending(&ssp->srcu_work));
else
- flush_work(&sp->srcu_work);
- WARN_ON(sp->srcu_gp_running);
- WARN_ON(sp->srcu_gp_waiting);
- WARN_ON(sp->srcu_cb_head);
- WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail);
+ flush_work(&ssp->srcu_work);
+ WARN_ON(ssp->srcu_gp_running);
+ WARN_ON(ssp->srcu_gp_waiting);
+ WARN_ON(ssp->srcu_cb_head);
+ WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
}
EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
@@ -107,13 +107,13 @@ EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
* Removes the count for the old reader from the appropriate element of
* the srcu_struct.
*/
-void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
{
- int newval = sp->srcu_lock_nesting[idx] - 1;
+ int newval = ssp->srcu_lock_nesting[idx] - 1;
- WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
- if (!newval && READ_ONCE(sp->srcu_gp_waiting))
- swake_up_one(&sp->srcu_wq);
+ WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
+ if (!newval && READ_ONCE(ssp->srcu_gp_waiting))
+ swake_up_one(&ssp->srcu_wq);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -127,24 +127,24 @@ void srcu_drive_gp(struct work_struct *wp)
int idx;
struct rcu_head *lh;
struct rcu_head *rhp;
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
- sp = container_of(wp, struct srcu_struct, srcu_work);
- if (sp->srcu_gp_running || !READ_ONCE(sp->srcu_cb_head))
+ ssp = container_of(wp, struct srcu_struct, srcu_work);
+ if (ssp->srcu_gp_running || !READ_ONCE(ssp->srcu_cb_head))
return; /* Already running or nothing to do. */
/* Remove recently arrived callbacks and wait for readers. */
- WRITE_ONCE(sp->srcu_gp_running, true);
+ WRITE_ONCE(ssp->srcu_gp_running, true);
local_irq_disable();
- lh = sp->srcu_cb_head;
- sp->srcu_cb_head = NULL;
- sp->srcu_cb_tail = &sp->srcu_cb_head;
+ lh = ssp->srcu_cb_head;
+ ssp->srcu_cb_head = NULL;
+ ssp->srcu_cb_tail = &ssp->srcu_cb_head;
local_irq_enable();
- idx = sp->srcu_idx;
- WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
- WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
- swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
- WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+ idx = ssp->srcu_idx;
+ WRITE_ONCE(ssp->srcu_idx, !ssp->srcu_idx);
+ WRITE_ONCE(ssp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
+ swait_event_exclusive(ssp->srcu_wq, !READ_ONCE(ssp->srcu_lock_nesting[idx]));
+ WRITE_ONCE(ssp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
/* Invoke the callbacks we removed above. */
while (lh) {
@@ -161,9 +161,9 @@ void srcu_drive_gp(struct work_struct *wp)
* at interrupt level, but the ->srcu_gp_running checks will
* straighten that out.
*/
- WRITE_ONCE(sp->srcu_gp_running, false);
- if (READ_ONCE(sp->srcu_cb_head))
- schedule_work(&sp->srcu_work);
+ WRITE_ONCE(ssp->srcu_gp_running, false);
+ if (READ_ONCE(ssp->srcu_cb_head))
+ schedule_work(&ssp->srcu_work);
}
EXPORT_SYMBOL_GPL(srcu_drive_gp);
@@ -171,7 +171,7 @@ EXPORT_SYMBOL_GPL(srcu_drive_gp);
* Enqueue an SRCU callback on the specified srcu_struct structure,
* initiating grace-period processing if it is not already running.
*/
-void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
rcu_callback_t func)
{
unsigned long flags;
@@ -179,14 +179,14 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
rhp->func = func;
rhp->next = NULL;
local_irq_save(flags);
- *sp->srcu_cb_tail = rhp;
- sp->srcu_cb_tail = &rhp->next;
+ *ssp->srcu_cb_tail = rhp;
+ ssp->srcu_cb_tail = &rhp->next;
local_irq_restore(flags);
- if (!READ_ONCE(sp->srcu_gp_running)) {
+ if (!READ_ONCE(ssp->srcu_gp_running)) {
if (likely(srcu_init_done))
- schedule_work(&sp->srcu_work);
- else if (list_empty(&sp->srcu_work.entry))
- list_add(&sp->srcu_work.entry, &srcu_boot_list);
+ schedule_work(&ssp->srcu_work);
+ else if (list_empty(&ssp->srcu_work.entry))
+ list_add(&ssp->srcu_work.entry, &srcu_boot_list);
}
}
EXPORT_SYMBOL_GPL(call_srcu);
@@ -194,13 +194,13 @@ EXPORT_SYMBOL_GPL(call_srcu);
/*
* synchronize_srcu - wait for prior SRCU read-side critical-section completion
*/
-void synchronize_srcu(struct srcu_struct *sp)
+void synchronize_srcu(struct srcu_struct *ssp)
{
struct rcu_synchronize rs;
init_rcu_head_on_stack(&rs.head);
init_completion(&rs.completion);
- call_srcu(sp, &rs.head, wakeme_after_rcu);
+ call_srcu(ssp, &rs.head, wakeme_after_rcu);
wait_for_completion(&rs.completion);
destroy_rcu_head_on_stack(&rs.head);
}
@@ -219,13 +219,13 @@ void __init rcu_scheduler_starting(void)
*/
void __init srcu_init(void)
{
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
srcu_init_done = true;
while (!list_empty(&srcu_boot_list)) {
- sp = list_first_entry(&srcu_boot_list,
+ ssp = list_first_entry(&srcu_boot_list,
struct srcu_struct, srcu_work.entry);
- list_del_init(&sp->srcu_work.entry);
- schedule_work(&sp->srcu_work);
+ list_del_init(&ssp->srcu_work.entry);
+ schedule_work(&ssp->srcu_work);
}
}
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index a8846ed7f352..3600d88d8956 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -56,7 +56,7 @@ static LIST_HEAD(srcu_boot_list);
static bool __read_mostly srcu_init_done;
static void srcu_invoke_callbacks(struct work_struct *work);
-static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
+static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
static void process_srcu(struct work_struct *work);
/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
@@ -92,7 +92,7 @@ do { \
* srcu_read_unlock() running against them. So if the is_static parameter
* is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
*/
-static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
+static void init_srcu_struct_nodes(struct srcu_struct *ssp, bool is_static)
{
int cpu;
int i;
@@ -103,13 +103,13 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
struct srcu_node *snp_first;
/* Work out the overall tree geometry. */
- sp->level[0] = &sp->node[0];
+ ssp->level[0] = &ssp->node[0];
for (i = 1; i < rcu_num_lvls; i++)
- sp->level[i] = sp->level[i - 1] + num_rcu_lvl[i - 1];
+ ssp->level[i] = ssp->level[i - 1] + num_rcu_lvl[i - 1];
rcu_init_levelspread(levelspread, num_rcu_lvl);
/* Each pass through this loop initializes one srcu_node structure. */
- srcu_for_each_node_breadth_first(sp, snp) {
+ srcu_for_each_node_breadth_first(ssp, snp) {
spin_lock_init(&ACCESS_PRIVATE(snp, lock));
WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
ARRAY_SIZE(snp->srcu_data_have_cbs));
@@ -120,17 +120,17 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
snp->srcu_gp_seq_needed_exp = 0;
snp->grplo = -1;
snp->grphi = -1;
- if (snp == &sp->node[0]) {
+ if (snp == &ssp->node[0]) {
/* Root node, special case. */
snp->srcu_parent = NULL;
continue;
}
/* Non-root node. */
- if (snp == sp->level[level + 1])
+ if (snp == ssp->level[level + 1])
level++;
- snp->srcu_parent = sp->level[level - 1] +
- (snp - sp->level[level]) /
+ snp->srcu_parent = ssp->level[level - 1] +
+ (snp - ssp->level[level]) /
levelspread[level - 1];
}
@@ -141,14 +141,14 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
ARRAY_SIZE(sdp->srcu_unlock_count));
level = rcu_num_lvls - 1;
- snp_first = sp->level[level];
+ snp_first = ssp->level[level];
for_each_possible_cpu(cpu) {
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
rcu_segcblist_init(&sdp->srcu_cblist);
sdp->srcu_cblist_invoking = false;
- sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
- sdp->srcu_gp_seq_needed_exp = sp->srcu_gp_seq;
+ sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq;
+ sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq;
sdp->mynode = &snp_first[cpu / levelspread[level]];
for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
if (snp->grplo < 0)
@@ -157,7 +157,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
}
sdp->cpu = cpu;
INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
- sdp->sp = sp;
+ sdp->ssp = ssp;
sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
if (is_static)
continue;
@@ -176,35 +176,35 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
* parameter is passed through to init_srcu_struct_nodes(), and
* also tells us that ->sda has already been wired up to srcu_data.
*/
-static int init_srcu_struct_fields(struct srcu_struct *sp, bool is_static)
+static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
{
- mutex_init(&sp->srcu_cb_mutex);
- mutex_init(&sp->srcu_gp_mutex);
- sp->srcu_idx = 0;
- sp->srcu_gp_seq = 0;
- sp->srcu_barrier_seq = 0;
- mutex_init(&sp->srcu_barrier_mutex);
- atomic_set(&sp->srcu_barrier_cpu_cnt, 0);
- INIT_DELAYED_WORK(&sp->work, process_srcu);
+ mutex_init(&ssp->srcu_cb_mutex);
+ mutex_init(&ssp->srcu_gp_mutex);
+ ssp->srcu_idx = 0;
+ ssp->srcu_gp_seq = 0;
+ ssp->srcu_barrier_seq = 0;
+ mutex_init(&ssp->srcu_barrier_mutex);
+ atomic_set(&ssp->srcu_barrier_cpu_cnt, 0);
+ INIT_DELAYED_WORK(&ssp->work, process_srcu);
if (!is_static)
- sp->sda = alloc_percpu(struct srcu_data);
- init_srcu_struct_nodes(sp, is_static);
- sp->srcu_gp_seq_needed_exp = 0;
- sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
- smp_store_release(&sp->srcu_gp_seq_needed, 0); /* Init done. */
- return sp->sda ? 0 : -ENOMEM;
+ ssp->sda = alloc_percpu(struct srcu_data);
+ init_srcu_struct_nodes(ssp, is_static);
+ ssp->srcu_gp_seq_needed_exp = 0;
+ ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
+ return ssp->sda ? 0 : -ENOMEM;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+int __init_srcu_struct(struct srcu_struct *ssp, const char *name,
struct lock_class_key *key)
{
/* Don't re-initialize a lock while it is held. */
- debug_check_no_locks_freed((void *)sp, sizeof(*sp));
- lockdep_init_map(&sp->dep_map, name, key, 0);
- spin_lock_init(&ACCESS_PRIVATE(sp, lock));
- return init_srcu_struct_fields(sp, false);
+ debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
+ lockdep_init_map(&ssp->dep_map, name, key, 0);
+ spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
+ return init_srcu_struct_fields(ssp, false);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);
@@ -212,16 +212,16 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
/**
* init_srcu_struct - initialize a sleep-RCU structure
- * @sp: structure to initialize.
+ * @ssp: structure to initialize.
*
* Must invoke this on a given srcu_struct before passing that srcu_struct
* to any other function. Each srcu_struct represents a separate domain
* of SRCU protection.
*/
-int init_srcu_struct(struct srcu_struct *sp)
+int init_srcu_struct(struct srcu_struct *ssp)
{
- spin_lock_init(&ACCESS_PRIVATE(sp, lock));
- return init_srcu_struct_fields(sp, false);
+ spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
+ return init_srcu_struct_fields(ssp, false);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);
@@ -231,37 +231,37 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
* First-use initialization of statically allocated srcu_struct
* structure. Wiring up the combining tree is more than can be
* done with compile-time initialization, so this check is added
- * to each update-side SRCU primitive. Use sp->lock, which -is-
+ * to each update-side SRCU primitive. Use ssp->lock, which -is-
* compile-time initialized, to resolve races involving multiple
* CPUs trying to garner first-use privileges.
*/
-static void check_init_srcu_struct(struct srcu_struct *sp)
+static void check_init_srcu_struct(struct srcu_struct *ssp)
{
unsigned long flags;
/* The smp_load_acquire() pairs with the smp_store_release(). */
- if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
+ if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq_needed))) /*^^^*/
return; /* Already initialized. */
- spin_lock_irqsave_rcu_node(sp, flags);
- if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ spin_lock_irqsave_rcu_node(ssp, flags);
+ if (!rcu_seq_state(ssp->srcu_gp_seq_needed)) {
+ spin_unlock_irqrestore_rcu_node(ssp, flags);
return;
}
- init_srcu_struct_fields(sp, true);
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ init_srcu_struct_fields(ssp, true);
+ spin_unlock_irqrestore_rcu_node(ssp, flags);
}
/*
* Returns approximate total of the readers' ->srcu_lock_count[] values
* for the rank of per-CPU counters specified by idx.
*/
-static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+ struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
}
@@ -272,13 +272,13 @@ static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
* Returns approximate total of the readers' ->srcu_unlock_count[] values
* for the rank of per-CPU counters specified by idx.
*/
-static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+ struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
}
@@ -289,11 +289,11 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
* Return true if the number of pre-existing readers is determined to
* be zero.
*/
-static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
+static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
{
unsigned long unlocks;
- unlocks = srcu_readers_unlock_idx(sp, idx);
+ unlocks = srcu_readers_unlock_idx(ssp, idx);
/*
* Make sure that a lock is always counted if the corresponding
@@ -329,25 +329,25 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
* of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient,
* especially on 64-bit systems.
*/
- return srcu_readers_lock_idx(sp, idx) == unlocks;
+ return srcu_readers_lock_idx(ssp, idx) == unlocks;
}
/**
* srcu_readers_active - returns true if there are readers. and false
* otherwise
- * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
+ * @ssp: which srcu_struct to count active readers (holding srcu_read_lock).
*
* Note that this is not an atomic primitive, and can therefore suffer
* severe errors when invoked on an active srcu_struct. That said, it
* can be useful as an error check at cleanup time.
*/
-static bool srcu_readers_active(struct srcu_struct *sp)
+static bool srcu_readers_active(struct srcu_struct *ssp)
{
int cpu;
unsigned long sum = 0;
for_each_possible_cpu(cpu) {
- struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+ struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
sum += READ_ONCE(cpuc->srcu_lock_count[0]);
sum += READ_ONCE(cpuc->srcu_lock_count[1]);
@@ -363,44 +363,44 @@ static bool srcu_readers_active(struct srcu_struct *sp)
* Return grace-period delay, zero if there are expedited grace
* periods pending, SRCU_INTERVAL otherwise.
*/
-static unsigned long srcu_get_delay(struct srcu_struct *sp)
+static unsigned long srcu_get_delay(struct srcu_struct *ssp)
{
- if (ULONG_CMP_LT(READ_ONCE(sp->srcu_gp_seq),
- READ_ONCE(sp->srcu_gp_seq_needed_exp)))
+ if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq),
+ READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
return 0;
return SRCU_INTERVAL;
}
/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
-void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
+void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
{
int cpu;
- if (WARN_ON(!srcu_get_delay(sp)))
+ if (WARN_ON(!srcu_get_delay(ssp)))
return; /* Just leak it! */
- if (WARN_ON(srcu_readers_active(sp)))
+ if (WARN_ON(srcu_readers_active(ssp)))
return; /* Just leak it! */
if (quiesced) {
- if (WARN_ON(delayed_work_pending(&sp->work)))
+ if (WARN_ON(delayed_work_pending(&ssp->work)))
return; /* Just leak it! */
} else {
- flush_delayed_work(&sp->work);
+ flush_delayed_work(&ssp->work);
}
for_each_possible_cpu(cpu)
if (quiesced) {
- if (WARN_ON(delayed_work_pending(&per_cpu_ptr(sp->sda, cpu)->work)))
+ if (WARN_ON(delayed_work_pending(&per_cpu_ptr(ssp->sda, cpu)->work)))
return; /* Just leak it! */
} else {
- flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ flush_delayed_work(&per_cpu_ptr(ssp->sda, cpu)->work);
}
- if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
- WARN_ON(srcu_readers_active(sp))) {
+ if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
+ WARN_ON(srcu_readers_active(ssp))) {
pr_info("%s: Active srcu_struct %p state: %d\n",
- __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+ __func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)));
return; /* Caller forgot to stop doing call_srcu()? */
}
- free_percpu(sp->sda);
- sp->sda = NULL;
+ free_percpu(ssp->sda);
+ ssp->sda = NULL;
}
EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
@@ -409,12 +409,12 @@ EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
* srcu_struct.
* Returns an index that must be passed to the matching srcu_read_unlock().
*/
-int __srcu_read_lock(struct srcu_struct *sp)
+int __srcu_read_lock(struct srcu_struct *ssp)
{
int idx;
- idx = READ_ONCE(sp->srcu_idx) & 0x1;
- this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+ idx = READ_ONCE(ssp->srcu_idx) & 0x1;
+ this_cpu_inc(ssp->sda->srcu_lock_count[idx]);
smp_mb(); /* B */ /* Avoid leaking the critical section. */
return idx;
}
@@ -425,10 +425,10 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
* element of the srcu_struct. Note that this may well be a different
* CPU than that which was incremented by the corresponding srcu_read_lock().
*/
-void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
{
smp_mb(); /* C */ /* Avoid leaking the critical section. */
- this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
+ this_cpu_inc(ssp->sda->srcu_unlock_count[idx]);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -444,20 +444,22 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
/*
* Start an SRCU grace period.
*/
-static void srcu_gp_start(struct srcu_struct *sp)
+static void srcu_gp_start(struct srcu_struct *ssp)
{
- struct srcu_data *sdp = this_cpu_ptr(sp->sda);
+ struct srcu_data *sdp = this_cpu_ptr(ssp->sda);
int state;
- lockdep_assert_held(&ACCESS_PRIVATE(sp, lock));
- WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+ lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
+ WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+ spin_lock_rcu_node(sdp); /* Interrupts already disabled. */
rcu_segcblist_advance(&sdp->srcu_cblist,
- rcu_seq_current(&sp->srcu_gp_seq));
+ rcu_seq_current(&ssp->srcu_gp_seq));
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&sp->srcu_gp_seq));
+ rcu_seq_snap(&ssp->srcu_gp_seq));
+ spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */
smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
- rcu_seq_start(&sp->srcu_gp_seq);
- state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+ rcu_seq_start(&ssp->srcu_gp_seq);
+ state = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}
@@ -511,7 +513,7 @@ static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
* just-completed grace period, the one corresponding to idx. If possible,
* schedule this invocation on the corresponding CPUs.
*/
-static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
+static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp,
unsigned long mask, unsigned long delay)
{
int cpu;
@@ -519,7 +521,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
if (!(mask & (1 << (cpu - snp->grplo))))
continue;
- srcu_schedule_cbs_sdp(per_cpu_ptr(sp->sda, cpu), delay);
+ srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
}
}
@@ -532,7 +534,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
* are initiating callback invocation. This allows the ->srcu_have_cbs[]
* array to have a finite number of elements.
*/
-static void srcu_gp_end(struct srcu_struct *sp)
+static void srcu_gp_end(struct srcu_struct *ssp)
{
unsigned long cbdelay;
bool cbs;
@@ -546,28 +548,28 @@ static void srcu_gp_end(struct srcu_struct *sp)
struct srcu_node *snp;
/* Prevent more than one additional grace period. */
- mutex_lock(&sp->srcu_cb_mutex);
+ mutex_lock(&ssp->srcu_cb_mutex);
/* End the current grace period. */
- spin_lock_irq_rcu_node(sp);
- idx = rcu_seq_state(sp->srcu_gp_seq);
+ spin_lock_irq_rcu_node(ssp);
+ idx = rcu_seq_state(ssp->srcu_gp_seq);
WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
- cbdelay = srcu_get_delay(sp);
- sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
- rcu_seq_end(&sp->srcu_gp_seq);
- gpseq = rcu_seq_current(&sp->srcu_gp_seq);
- if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq))
- sp->srcu_gp_seq_needed_exp = gpseq;
- spin_unlock_irq_rcu_node(sp);
- mutex_unlock(&sp->srcu_gp_mutex);
+ cbdelay = srcu_get_delay(ssp);
+ ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ rcu_seq_end(&ssp->srcu_gp_seq);
+ gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
+ if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
+ ssp->srcu_gp_seq_needed_exp = gpseq;
+ spin_unlock_irq_rcu_node(ssp);
+ mutex_unlock(&ssp->srcu_gp_mutex);
/* A new grace period can start at this point. But only one. */
/* Initiate callback invocation as needed. */
idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
- srcu_for_each_node_breadth_first(sp, snp) {
+ srcu_for_each_node_breadth_first(ssp, snp) {
spin_lock_irq_rcu_node(snp);
cbs = false;
- last_lvl = snp >= sp->level[rcu_num_lvls - 1];
+ last_lvl = snp >= ssp->level[rcu_num_lvls - 1];
if (last_lvl)
cbs = snp->srcu_have_cbs[idx] == gpseq;
snp->srcu_have_cbs[idx] = gpseq;
@@ -578,12 +580,12 @@ static void srcu_gp_end(struct srcu_struct *sp)
snp->srcu_data_have_cbs[idx] = 0;
spin_unlock_irq_rcu_node(snp);
if (cbs)
- srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
+ srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay);
/* Occasionally prevent srcu_data counter wrap. */
if (!(gpseq & counter_wrap_check) && last_lvl)
for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
spin_lock_irqsave_rcu_node(sdp, flags);
if (ULONG_CMP_GE(gpseq,
sdp->srcu_gp_seq_needed + 100))
@@ -596,18 +598,18 @@ static void srcu_gp_end(struct srcu_struct *sp)
}
/* Callback initiation done, allow grace periods after next. */
- mutex_unlock(&sp->srcu_cb_mutex);
+ mutex_unlock(&ssp->srcu_cb_mutex);
/* Start a new grace period if needed. */
- spin_lock_irq_rcu_node(sp);
- gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+ spin_lock_irq_rcu_node(ssp);
+ gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
if (!rcu_seq_state(gpseq) &&
- ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
- srcu_gp_start(sp);
- spin_unlock_irq_rcu_node(sp);
- srcu_reschedule(sp, 0);
+ ULONG_CMP_LT(gpseq, ssp->srcu_gp_seq_needed)) {
+ srcu_gp_start(ssp);
+ spin_unlock_irq_rcu_node(ssp);
+ srcu_reschedule(ssp, 0);
} else {
- spin_unlock_irq_rcu_node(sp);
+ spin_unlock_irq_rcu_node(ssp);
}
}
@@ -618,13 +620,13 @@ static void srcu_gp_end(struct srcu_struct *sp)
* but without expediting. To start a completely new grace period,
* whether expedited or not, use srcu_funnel_gp_start() instead.
*/
-static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
+static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp,
unsigned long s)
{
unsigned long flags;
for (; snp != NULL; snp = snp->srcu_parent) {
- if (rcu_seq_done(&sp->srcu_gp_seq, s) ||
+ if (rcu_seq_done(&ssp->srcu_gp_seq, s) ||
ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
return;
spin_lock_irqsave_rcu_node(snp, flags);
@@ -635,10 +637,10 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
spin_unlock_irqrestore_rcu_node(snp, flags);
}
- spin_lock_irqsave_rcu_node(sp, flags);
- if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
- sp->srcu_gp_seq_needed_exp = s;
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ spin_lock_irqsave_rcu_node(ssp, flags);
+ if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
+ ssp->srcu_gp_seq_needed_exp = s;
+ spin_unlock_irqrestore_rcu_node(ssp, flags);
}
/*
@@ -651,7 +653,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
* Note that this function also does the work of srcu_funnel_exp_start(),
* in some cases by directly invoking it.
*/
-static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
+static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
unsigned long s, bool do_norm)
{
unsigned long flags;
@@ -661,7 +663,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
/* Each pass through the loop does one level of the srcu_node tree. */
for (; snp != NULL; snp = snp->srcu_parent) {
- if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
+ if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != sdp->mynode)
return; /* GP already done and CBs recorded. */
spin_lock_irqsave_rcu_node(snp, flags);
if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
@@ -676,7 +678,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
return;
}
if (!do_norm)
- srcu_funnel_exp_start(sp, snp, s);
+ srcu_funnel_exp_start(ssp, snp, s);
return;
}
snp->srcu_have_cbs[idx] = s;
@@ -688,29 +690,29 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
}
/* Top of tree, must ensure the grace period will be started. */
- spin_lock_irqsave_rcu_node(sp, flags);
- if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
+ spin_lock_irqsave_rcu_node(ssp, flags);
+ if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed, s)) {
/*
* Record need for grace period s. Pair with load
* acquire setting up for initialization.
*/
- smp_store_release(&sp->srcu_gp_seq_needed, s); /*^^^*/
+ smp_store_release(&ssp->srcu_gp_seq_needed, s); /*^^^*/
}
- if (!do_norm && ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
- sp->srcu_gp_seq_needed_exp = s;
+ if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
+ ssp->srcu_gp_seq_needed_exp = s;
/* If grace period not already done and none in progress, start it. */
- if (!rcu_seq_done(&sp->srcu_gp_seq, s) &&
- rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) {
- WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
- srcu_gp_start(sp);
+ if (!rcu_seq_done(&ssp->srcu_gp_seq, s) &&
+ rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) {
+ WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
+ srcu_gp_start(ssp);
if (likely(srcu_init_done))
- queue_delayed_work(rcu_gp_wq, &sp->work,
- srcu_get_delay(sp));
- else if (list_empty(&sp->work.work.entry))
- list_add(&sp->work.work.entry, &srcu_boot_list);
+ queue_delayed_work(rcu_gp_wq, &ssp->work,
+ srcu_get_delay(ssp));
+ else if (list_empty(&ssp->work.work.entry))
+ list_add(&ssp->work.work.entry, &srcu_boot_list);
}
- spin_unlock_irqrestore_rcu_node(sp, flags);
+ spin_unlock_irqrestore_rcu_node(ssp, flags);
}
/*
@@ -718,12 +720,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
* loop an additional time if there is an expedited grace period pending.
* The caller must ensure that ->srcu_idx is not changed while checking.
*/
-static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
+static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
{
for (;;) {
- if (srcu_readers_active_idx_check(sp, idx))
+ if (srcu_readers_active_idx_check(ssp, idx))
return true;
- if (--trycount + !srcu_get_delay(sp) <= 0)
+ if (--trycount + !srcu_get_delay(ssp) <= 0)
return false;
udelay(SRCU_RETRY_CHECK_DELAY);
}
@@ -734,7 +736,7 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
* use the other rank of the ->srcu_(un)lock_count[] arrays. This allows
* us to wait for pre-existing readers in a starvation-free manner.
*/
-static void srcu_flip(struct srcu_struct *sp)
+static void srcu_flip(struct srcu_struct *ssp)
{
/*
* Ensure that if this updater saw a given reader's increment
@@ -746,7 +748,7 @@ static void srcu_flip(struct srcu_struct *sp)
*/
smp_mb(); /* E */ /* Pairs with B and C. */
- WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);
+ WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
/*
* Ensure that if the updater misses an __srcu_read_unlock()
@@ -779,7 +781,7 @@ static void srcu_flip(struct srcu_struct *sp)
* negligible when amoritized over that time period, and the extra latency
* of a needlessly non-expedited grace period is similarly negligible.
*/
-static bool srcu_might_be_idle(struct srcu_struct *sp)
+static bool srcu_might_be_idle(struct srcu_struct *ssp)
{
unsigned long curseq;
unsigned long flags;
@@ -788,7 +790,7 @@ static bool srcu_might_be_idle(struct srcu_struct *sp)
/* If the local srcu_data structure has callbacks, not idle. */
local_irq_save(flags);
- sdp = this_cpu_ptr(sp->sda);
+ sdp = this_cpu_ptr(ssp->sda);
if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
local_irq_restore(flags);
return false; /* Callbacks already present, so not idle. */
@@ -804,17 +806,17 @@ static bool srcu_might_be_idle(struct srcu_struct *sp)
/* First, see if enough time has passed since the last GP. */
t = ktime_get_mono_fast_ns();
if (exp_holdoff == 0 ||
- time_in_range_open(t, sp->srcu_last_gp_end,
- sp->srcu_last_gp_end + exp_holdoff))
+ time_in_range_open(t, ssp->srcu_last_gp_end,
+ ssp->srcu_last_gp_end + exp_holdoff))
return false; /* Too soon after last GP. */
/* Next, check for probable idleness. */
- curseq = rcu_seq_current(&sp->srcu_gp_seq);
+ curseq = rcu_seq_current(&ssp->srcu_gp_seq);
smp_mb(); /* Order ->srcu_gp_seq with ->srcu_gp_seq_needed. */
- if (ULONG_CMP_LT(curseq, READ_ONCE(sp->srcu_gp_seq_needed)))
+ if (ULONG_CMP_LT(curseq, READ_ONCE(ssp->srcu_gp_seq_needed)))
return false; /* Grace period in progress, so not idle. */
smp_mb(); /* Order ->srcu_gp_seq with prior access. */
- if (curseq != rcu_seq_current(&sp->srcu_gp_seq))
+ if (curseq != rcu_seq_current(&ssp->srcu_gp_seq))
return false; /* GP # changed, so not idle. */
return true; /* With reasonable probability, idle! */
}
@@ -854,16 +856,17 @@ static void srcu_leak_callback(struct rcu_head *rhp)
* srcu_read_lock(), and srcu_read_unlock() that are all passed the same
* srcu_struct structure.
*/
-void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
rcu_callback_t func, bool do_norm)
{
unsigned long flags;
+ int idx;
bool needexp = false;
bool needgp = false;
unsigned long s;
struct srcu_data *sdp;
- check_init_srcu_struct(sp);
+ check_init_srcu_struct(ssp);
if (debug_rcu_head_queue(rhp)) {
/* Probable double call_srcu(), so leak the callback. */
WRITE_ONCE(rhp->func, srcu_leak_callback);
@@ -871,13 +874,14 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
return;
}
rhp->func = func;
+ idx = srcu_read_lock(ssp);
local_irq_save(flags);
- sdp = this_cpu_ptr(sp->sda);
+ sdp = this_cpu_ptr(ssp->sda);
spin_lock_rcu_node(sdp);
rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
rcu_segcblist_advance(&sdp->srcu_cblist,
- rcu_seq_current(&sp->srcu_gp_seq));
- s = rcu_seq_snap(&sp->srcu_gp_seq);
+ rcu_seq_current(&ssp->srcu_gp_seq));
+ s = rcu_seq_snap(&ssp->srcu_gp_seq);
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
sdp->srcu_gp_seq_needed = s;
@@ -889,14 +893,15 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
}
spin_unlock_irqrestore_rcu_node(sdp, flags);
if (needgp)
- srcu_funnel_gp_start(sp, sdp, s, do_norm);
+ srcu_funnel_gp_start(ssp, sdp, s, do_norm);
else if (needexp)
- srcu_funnel_exp_start(sp, sdp->mynode, s);
+ srcu_funnel_exp_start(ssp, sdp->mynode, s);
+ srcu_read_unlock(ssp, idx);
}
/**
* call_srcu() - Queue a callback for invocation after an SRCU grace period
- * @sp: srcu_struct in queue the callback
+ * @ssp: srcu_struct in queue the callback
* @rhp: structure to be used for queueing the SRCU callback.
* @func: function to be invoked after the SRCU grace period
*
@@ -911,21 +916,21 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
* The callback will be invoked from process context, but must nevertheless
* be fast and must not block.
*/
-void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
rcu_callback_t func)
{
- __call_srcu(sp, rhp, func, true);
+ __call_srcu(ssp, rhp, func, true);
}
EXPORT_SYMBOL_GPL(call_srcu);
/*
* Helper function for synchronize_srcu() and synchronize_srcu_expedited().
*/
-static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
+static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm)
{
struct rcu_synchronize rcu;
- RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
+ RCU_LOCKDEP_WARN(lock_is_held(&ssp->dep_map) ||
lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
@@ -934,10 +939,10 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return;
might_sleep();
- check_init_srcu_struct(sp);
+ check_init_srcu_struct(ssp);
init_completion(&rcu.completion);
init_rcu_head_on_stack(&rcu.head);
- __call_srcu(sp, &rcu.head, wakeme_after_rcu, do_norm);
+ __call_srcu(ssp, &rcu.head, wakeme_after_rcu, do_norm);
wait_for_completion(&rcu.completion);
destroy_rcu_head_on_stack(&rcu.head);
@@ -953,7 +958,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
/**
* synchronize_srcu_expedited - Brute-force SRCU grace period
- * @sp: srcu_struct with which to synchronize.
+ * @ssp: srcu_struct with which to synchronize.
*
* Wait for an SRCU grace period to elapse, but be more aggressive about
* spinning rather than blocking when waiting.
@@ -961,15 +966,15 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
* Note that synchronize_srcu_expedited() has the same deadlock and
* memory-ordering properties as does synchronize_srcu().
*/
-void synchronize_srcu_expedited(struct srcu_struct *sp)
+void synchronize_srcu_expedited(struct srcu_struct *ssp)
{
- __synchronize_srcu(sp, rcu_gp_is_normal());
+ __synchronize_srcu(ssp, rcu_gp_is_normal());
}
EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
/**
* synchronize_srcu - wait for prior SRCU read-side critical-section completion
- * @sp: srcu_struct with which to synchronize.
+ * @ssp: srcu_struct with which to synchronize.
*
* Wait for the count to drain to zero of both indexes. To avoid the
* possible starvation of synchronize_srcu(), it waits for the count of
@@ -1011,12 +1016,12 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
* SRCU must also provide it. Note that detecting idleness is heuristic
* and subject to both false positives and negatives.
*/
-void synchronize_srcu(struct srcu_struct *sp)
+void synchronize_srcu(struct srcu_struct *ssp)
{
- if (srcu_might_be_idle(sp) || rcu_gp_is_expedited())
- synchronize_srcu_expedited(sp);
+ if (srcu_might_be_idle(ssp) || rcu_gp_is_expedited())
+ synchronize_srcu_expedited(ssp);
else
- __synchronize_srcu(sp, true);
+ __synchronize_srcu(ssp, true);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
@@ -1026,36 +1031,36 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
static void srcu_barrier_cb(struct rcu_head *rhp)
{
struct srcu_data *sdp;
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
- sp = sdp->sp;
- if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
- complete(&sp->srcu_barrier_completion);
+ ssp = sdp->ssp;
+ if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
+ complete(&ssp->srcu_barrier_completion);
}
/**
* srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
- * @sp: srcu_struct on which to wait for in-flight callbacks.
+ * @ssp: srcu_struct on which to wait for in-flight callbacks.
*/
-void srcu_barrier(struct srcu_struct *sp)
+void srcu_barrier(struct srcu_struct *ssp)
{
int cpu;
struct srcu_data *sdp;
- unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);
+ unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq);
- check_init_srcu_struct(sp);
- mutex_lock(&sp->srcu_barrier_mutex);
- if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
+ check_init_srcu_struct(ssp);
+ mutex_lock(&ssp->srcu_barrier_mutex);
+ if (rcu_seq_done(&ssp->srcu_barrier_seq, s)) {
smp_mb(); /* Force ordering following return. */
- mutex_unlock(&sp->srcu_barrier_mutex);
+ mutex_unlock(&ssp->srcu_barrier_mutex);
return; /* Someone else did our work for us. */
}
- rcu_seq_start(&sp->srcu_barrier_seq);
- init_completion(&sp->srcu_barrier_completion);
+ rcu_seq_start(&ssp->srcu_barrier_seq);
+ init_completion(&ssp->srcu_barrier_completion);
/* Initial count prevents reaching zero until all CBs are posted. */
- atomic_set(&sp->srcu_barrier_cpu_cnt, 1);
+ atomic_set(&ssp->srcu_barrier_cpu_cnt, 1);
/*
* Each pass through this loop enqueues a callback, but only
@@ -1066,39 +1071,39 @@ void srcu_barrier(struct srcu_struct *sp)
* grace period as the last callback already in the queue.
*/
for_each_possible_cpu(cpu) {
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
spin_lock_irq_rcu_node(sdp);
- atomic_inc(&sp->srcu_barrier_cpu_cnt);
+ atomic_inc(&ssp->srcu_barrier_cpu_cnt);
sdp->srcu_barrier_head.func = srcu_barrier_cb;
debug_rcu_head_queue(&sdp->srcu_barrier_head);
if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
&sdp->srcu_barrier_head, 0)) {
debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
- atomic_dec(&sp->srcu_barrier_cpu_cnt);
+ atomic_dec(&ssp->srcu_barrier_cpu_cnt);
}
spin_unlock_irq_rcu_node(sdp);
}
/* Remove the initial count, at which point reaching zero can happen. */
- if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
- complete(&sp->srcu_barrier_completion);
- wait_for_completion(&sp->srcu_barrier_completion);
+ if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
+ complete(&ssp->srcu_barrier_completion);
+ wait_for_completion(&ssp->srcu_barrier_completion);
- rcu_seq_end(&sp->srcu_barrier_seq);
- mutex_unlock(&sp->srcu_barrier_mutex);
+ rcu_seq_end(&ssp->srcu_barrier_seq);
+ mutex_unlock(&ssp->srcu_barrier_mutex);
}
EXPORT_SYMBOL_GPL(srcu_barrier);
/**
* srcu_batches_completed - return batches completed.
- * @sp: srcu_struct on which to report batch completion.
+ * @ssp: srcu_struct on which to report batch completion.
*
* Report the number of batches, correlated with, but not necessarily
* precisely the same as, the number of grace periods that have elapsed.
*/
-unsigned long srcu_batches_completed(struct srcu_struct *sp)
+unsigned long srcu_batches_completed(struct srcu_struct *ssp)
{
- return sp->srcu_idx;
+ return ssp->srcu_idx;
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);
@@ -1107,11 +1112,11 @@ EXPORT_SYMBOL_GPL(srcu_batches_completed);
* to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
* completed in that state.
*/
-static void srcu_advance_state(struct srcu_struct *sp)
+static void srcu_advance_state(struct srcu_struct *ssp)
{
int idx;
- mutex_lock(&sp->srcu_gp_mutex);
+ mutex_lock(&ssp->srcu_gp_mutex);
/*
* Because readers might be delayed for an extended period after
@@ -1123,47 +1128,47 @@ static void srcu_advance_state(struct srcu_struct *sp)
* The load-acquire ensures that we see the accesses performed
* by the prior grace period.
*/
- idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
+ idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq)); /* ^^^ */
if (idx == SRCU_STATE_IDLE) {
- spin_lock_irq_rcu_node(sp);
- if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
- WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
- spin_unlock_irq_rcu_node(sp);
- mutex_unlock(&sp->srcu_gp_mutex);
+ spin_lock_irq_rcu_node(ssp);
+ if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
+ WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq));
+ spin_unlock_irq_rcu_node(ssp);
+ mutex_unlock(&ssp->srcu_gp_mutex);
return;
}
- idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+ idx = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
if (idx == SRCU_STATE_IDLE)
- srcu_gp_start(sp);
- spin_unlock_irq_rcu_node(sp);
+ srcu_gp_start(ssp);
+ spin_unlock_irq_rcu_node(ssp);
if (idx != SRCU_STATE_IDLE) {
- mutex_unlock(&sp->srcu_gp_mutex);
+ mutex_unlock(&ssp->srcu_gp_mutex);
return; /* Someone else started the grace period. */
}
}
- if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
- idx = 1 ^ (sp->srcu_idx & 1);
- if (!try_check_zero(sp, idx, 1)) {
- mutex_unlock(&sp->srcu_gp_mutex);
+ if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
+ idx = 1 ^ (ssp->srcu_idx & 1);
+ if (!try_check_zero(ssp, idx, 1)) {
+ mutex_unlock(&ssp->srcu_gp_mutex);
return; /* readers present, retry later. */
}
- srcu_flip(sp);
- rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
+ srcu_flip(ssp);
+ rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
}
- if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
+ if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
/*
* SRCU read-side critical sections are normally short,
* so check at least twice in quick succession after a flip.
*/
- idx = 1 ^ (sp->srcu_idx & 1);
- if (!try_check_zero(sp, idx, 2)) {
- mutex_unlock(&sp->srcu_gp_mutex);
+ idx = 1 ^ (ssp->srcu_idx & 1);
+ if (!try_check_zero(ssp, idx, 2)) {
+ mutex_unlock(&ssp->srcu_gp_mutex);
return; /* readers present, retry later. */
}
- srcu_gp_end(sp); /* Releases ->srcu_gp_mutex. */
+ srcu_gp_end(ssp); /* Releases ->srcu_gp_mutex. */
}
}
@@ -1179,14 +1184,14 @@ static void srcu_invoke_callbacks(struct work_struct *work)
struct rcu_cblist ready_cbs;
struct rcu_head *rhp;
struct srcu_data *sdp;
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
sdp = container_of(work, struct srcu_data, work.work);
- sp = sdp->sp;
+ ssp = sdp->ssp;
rcu_cblist_init(&ready_cbs);
spin_lock_irq_rcu_node(sdp);
rcu_segcblist_advance(&sdp->srcu_cblist,
- rcu_seq_current(&sp->srcu_gp_seq));
+ rcu_seq_current(&ssp->srcu_gp_seq));
if (sdp->srcu_cblist_invoking ||
!rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
spin_unlock_irq_rcu_node(sdp);
@@ -1212,7 +1217,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
spin_lock_irq_rcu_node(sdp);
rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&sp->srcu_gp_seq));
+ rcu_seq_snap(&ssp->srcu_gp_seq));
sdp->srcu_cblist_invoking = false;
more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
spin_unlock_irq_rcu_node(sdp);
@@ -1224,24 +1229,24 @@ static void srcu_invoke_callbacks(struct work_struct *work)
* Finished one round of SRCU grace period. Start another if there are
* more SRCU callbacks queued, otherwise put SRCU into not-running state.
*/
-static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
+static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
{
bool pushgp = true;
- spin_lock_irq_rcu_node(sp);
- if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
- if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
+ spin_lock_irq_rcu_node(ssp);
+ if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
+ if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq))) {
/* All requests fulfilled, time to go idle. */
pushgp = false;
}
- } else if (!rcu_seq_state(sp->srcu_gp_seq)) {
+ } else if (!rcu_seq_state(ssp->srcu_gp_seq)) {
/* Outstanding request and no GP. Start one. */
- srcu_gp_start(sp);
+ srcu_gp_start(ssp);
}
- spin_unlock_irq_rcu_node(sp);
+ spin_unlock_irq_rcu_node(ssp);
if (pushgp)
- queue_delayed_work(rcu_gp_wq, &sp->work, delay);
+ queue_delayed_work(rcu_gp_wq, &ssp->work, delay);
}
/*
@@ -1249,41 +1254,41 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
*/
static void process_srcu(struct work_struct *work)
{
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
- sp = container_of(work, struct srcu_struct, work.work);
+ ssp = container_of(work, struct srcu_struct, work.work);
- srcu_advance_state(sp);
- srcu_reschedule(sp, srcu_get_delay(sp));
+ srcu_advance_state(ssp);
+ srcu_reschedule(ssp, srcu_get_delay(ssp));
}
void srcutorture_get_gp_data(enum rcutorture_type test_type,
- struct srcu_struct *sp, int *flags,
+ struct srcu_struct *ssp, int *flags,
unsigned long *gp_seq)
{
if (test_type != SRCU_FLAVOR)
return;
*flags = 0;
- *gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
+ *gp_seq = rcu_seq_current(&ssp->srcu_gp_seq);
}
EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
-void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
+void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
{
int cpu;
int idx;
unsigned long s0 = 0, s1 = 0;
- idx = sp->srcu_idx & 0x1;
+ idx = ssp->srcu_idx & 0x1;
pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
- tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
+ tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), idx);
for_each_possible_cpu(cpu) {
unsigned long l0, l1;
unsigned long u0, u1;
long c0, c1;
struct srcu_data *sdp;
- sdp = per_cpu_ptr(sp->sda, cpu);
+ sdp = per_cpu_ptr(ssp->sda, cpu);
u0 = sdp->srcu_unlock_count[!idx];
u1 = sdp->srcu_unlock_count[idx];
@@ -1318,14 +1323,14 @@ early_initcall(srcu_bootup_announce);
void __init srcu_init(void)
{
- struct srcu_struct *sp;
+ struct srcu_struct *ssp;
srcu_init_done = true;
while (!list_empty(&srcu_boot_list)) {
- sp = list_first_entry(&srcu_boot_list, struct srcu_struct,
+ ssp = list_first_entry(&srcu_boot_list, struct srcu_struct,
work.work.entry);
- check_init_srcu_struct(sp);
- list_del_init(&sp->work.work.entry);
- queue_work(rcu_gp_wq, &sp->work.work);
+ check_init_srcu_struct(ssp);
+ list_del_init(&ssp->work.work.entry);
+ queue_work(rcu_gp_wq, &ssp->work.work);
}
}
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index 3f943efcf61c..be10036fa621 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -44,15 +44,15 @@ static const struct {
__INIT_HELD(rcu_read_lock_held)
},
[RCU_SCHED_SYNC] = {
- .sync = synchronize_sched,
- .call = call_rcu_sched,
- .wait = rcu_barrier_sched,
+ .sync = synchronize_rcu,
+ .call = call_rcu,
+ .wait = rcu_barrier,
__INIT_HELD(rcu_read_lock_sched_held)
},
[RCU_BH_SYNC] = {
- .sync = synchronize_rcu_bh,
- .call = call_rcu_bh,
- .wait = rcu_barrier_bh,
+ .sync = synchronize_rcu,
+ .call = call_rcu,
+ .wait = rcu_barrier,
__INIT_HELD(rcu_read_lock_bh_held)
},
};
@@ -125,8 +125,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
rsp->gp_state = GP_PENDING;
spin_unlock_irq(&rsp->rss_lock);
- BUG_ON(need_wait && need_sync);
-
+ WARN_ON_ONCE(need_wait && need_sync);
if (need_sync) {
gp_ops[rsp->gp_type].sync();
rsp->gp_state = GP_PASSED;
@@ -139,7 +138,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
* Nobody has yet been allowed the 'fast' path and thus we can
* avoid doing any sync(). The callback will get 'dropped'.
*/
- BUG_ON(rsp->gp_state != GP_PASSED);
+ WARN_ON_ONCE(rsp->gp_state != GP_PASSED);
}
}
@@ -166,8 +165,8 @@ static void rcu_sync_func(struct rcu_head *rhp)
struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
unsigned long flags;
- BUG_ON(rsp->gp_state != GP_PASSED);
- BUG_ON(rsp->cb_state == CB_IDLE);
+ WARN_ON_ONCE(rsp->gp_state != GP_PASSED);
+ WARN_ON_ONCE(rsp->cb_state == CB_IDLE);
spin_lock_irqsave(&rsp->rss_lock, flags);
if (rsp->gp_count) {
@@ -225,7 +224,7 @@ void rcu_sync_dtor(struct rcu_sync *rsp)
{
int cb_state;
- BUG_ON(rsp->gp_count);
+ WARN_ON_ONCE(rsp->gp_count);
spin_lock_irq(&rsp->rss_lock);
if (rsp->cb_state == CB_REPLAY)
@@ -235,6 +234,6 @@ void rcu_sync_dtor(struct rcu_sync *rsp)
if (cb_state != CB_IDLE) {
gp_ops[rsp->gp_type].wait();
- BUG_ON(rsp->cb_state != CB_IDLE);
+ WARN_ON_ONCE(rsp->cb_state != CB_IDLE);
}
}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 121f833acd04..9180158756d2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -207,6 +207,19 @@ static int rcu_gp_in_progress(void)
return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq));
}
+/*
+ * Return the number of callbacks queued on the specified CPU.
+ * Handles both the nocbs and normal cases.
+ */
+static long rcu_get_n_cbs_cpu(int cpu)
+{
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+ if (rcu_segcblist_is_enabled(&rdp->cblist)) /* Online normal CPU? */
+ return rcu_segcblist_n_cbs(&rdp->cblist);
+ return rcu_get_n_cbs_nocb_cpu(rdp); /* Works for offline, too. */
+}
+
void rcu_softirq_qs(void)
{
rcu_qs();
@@ -500,16 +513,29 @@ void rcu_force_quiescent_state(void)
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
+ * Convert a ->gp_state value to a character string.
+ */
+static const char *gp_state_getname(short gs)
+{
+ if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
+ return "???";
+ return gp_state_names[gs];
+}
+
+/*
* Show the state of the grace-period kthreads.
*/
void show_rcu_gp_kthreads(void)
{
int cpu;
+ unsigned long j;
struct rcu_data *rdp;
struct rcu_node *rnp;
- pr_info("%s: wait state: %d ->state: %#lx\n", rcu_state.name,
- rcu_state.gp_state, rcu_state.gp_kthread->state);
+ j = jiffies - READ_ONCE(rcu_state.gp_activity);
+ pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n",
+ rcu_state.name, gp_state_getname(rcu_state.gp_state),
+ rcu_state.gp_state, rcu_state.gp_kthread->state, j);
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
continue;
@@ -891,12 +917,12 @@ void rcu_irq_enter_irqson(void)
}
/**
- * rcu_is_watching - see if RCU thinks that the current CPU is idle
+ * rcu_is_watching - see if RCU thinks that the current CPU is not idle
*
* Return true if RCU is watching the running CPU, which means that this
* CPU can safely enter RCU read-side critical sections. In other words,
- * if the current CPU is in its idle loop and is neither in an interrupt
- * or NMI handler, return true.
+ * if the current CPU is not in its idle loop or is in an interrupt or
+ * NMI handler, return true.
*/
bool notrace rcu_is_watching(void)
{
@@ -1143,16 +1169,6 @@ static void record_gp_stall_check_time(void)
}
/*
- * Convert a ->gp_state value to a character string.
- */
-static const char *gp_state_getname(short gs)
-{
- if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
- return "???";
- return gp_state_names[gs];
-}
-
-/*
* Complain about starvation of grace-period kthread.
*/
static void rcu_check_gp_kthread_starvation(void)
@@ -1262,8 +1278,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data,
- cpu)->cblist);
+ totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
@@ -1323,8 +1338,7 @@ static void print_cpu_stall(void)
raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data,
- cpu)->cblist);
+ totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
jiffies - rcu_state.gp_start,
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
@@ -1986,7 +2000,8 @@ static void rcu_gp_cleanup(void)
WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
- gp_duration = jiffies - rcu_state.gp_start;
+ rcu_state.gp_end = jiffies;
+ gp_duration = rcu_state.gp_end - rcu_state.gp_start;
if (gp_duration > rcu_state.gp_max)
rcu_state.gp_max = gp_duration;
@@ -2032,9 +2047,9 @@ static void rcu_gp_cleanup(void)
rnp = rcu_get_root();
raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */
- /* Declare grace period done. */
- rcu_seq_end(&rcu_state.gp_seq);
+ /* Declare grace period done, trace first to use old GP number. */
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
+ rcu_seq_end(&rcu_state.gp_seq);
rcu_state.gp_state = RCU_GP_IDLE;
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(&rcu_data);
@@ -2600,10 +2615,10 @@ static void force_quiescent_state(void)
* This function checks for grace-period requests that fail to motivate
* RCU to come out of its idle mode.
*/
-static void
-rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp)
+void
+rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+ const unsigned long gpssdelay)
{
- const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
unsigned long flags;
unsigned long j;
struct rcu_node *rnp_root = rcu_get_root();
@@ -2655,6 +2670,48 @@ rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp)
}
/*
+ * Do a forward-progress check for rcutorture. This is normally invoked
+ * due to an OOM event. The argument "j" gives the time period during
+ * which rcutorture would like progress to have been made.
+ */
+void rcu_fwd_progress_check(unsigned long j)
+{
+ unsigned long cbs;
+ int cpu;
+ unsigned long max_cbs = 0;
+ int max_cpu = -1;
+ struct rcu_data *rdp;
+
+ if (rcu_gp_in_progress()) {
+ pr_info("%s: GP age %lu jiffies\n",
+ __func__, jiffies - rcu_state.gp_start);
+ show_rcu_gp_kthreads();
+ } else {
+ pr_info("%s: Last GP end %lu jiffies ago\n",
+ __func__, jiffies - rcu_state.gp_end);
+ preempt_disable();
+ rdp = this_cpu_ptr(&rcu_data);
+ rcu_check_gp_start_stall(rdp->mynode, rdp, j);
+ preempt_enable();
+ }
+ for_each_possible_cpu(cpu) {
+ cbs = rcu_get_n_cbs_cpu(cpu);
+ if (!cbs)
+ continue;
+ if (max_cpu < 0)
+ pr_info("%s: callbacks", __func__);
+ pr_cont(" %d: %lu", cpu, cbs);
+ if (cbs <= max_cbs)
+ continue;
+ max_cbs = cbs;
+ max_cpu = cpu;
+ }
+ if (max_cpu >= 0)
+ pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
+
+/*
* This does the RCU core processing work for the specified rcu_data
* structures. This may be called only from the CPU to whom the rdp
* belongs.
@@ -2690,7 +2747,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
local_irq_restore(flags);
}
- rcu_check_gp_start_stall(rnp, rdp);
+ rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
/* If there are callbacks ready, invoke them. */
if (rcu_segcblist_ready_cbs(&rdp->cblist))
@@ -2826,7 +2883,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
* Very early boot, before rcu_init(). Initialize if needed
* and then drop through to queue the callback.
*/
- BUG_ON(cpu != -1);
+ WARN_ON_ONCE(cpu != -1);
WARN_ON_ONCE(!rcu_is_watching());
if (rcu_segcblist_empty(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist);
@@ -3485,7 +3542,8 @@ static int __init rcu_spawn_gp_kthread(void)
rcu_scheduler_fully_active = 1;
t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name);
- BUG_ON(IS_ERR(t));
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__))
+ return 0;
rnp = rcu_get_root();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rcu_state.gp_kthread = t;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 703e19ff532d..d90b02b53c0e 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -57,7 +57,7 @@ struct rcu_node {
/* some rcu_state fields as well as */
/* following. */
unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */
- unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
+ unsigned long gp_seq_needed; /* Track furthest future GP request. */
unsigned long completedqs; /* All QSes done for this node. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
@@ -163,7 +163,7 @@ union rcu_noqs {
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */
- unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */
+ unsigned long gp_seq_needed; /* Track furthest future GP request. */
union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */
bool core_needs_qs; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
@@ -328,6 +328,8 @@ struct rcu_state {
/* force_quiescent_state(). */
unsigned long gp_start; /* Time at which GP started, */
/* but in jiffies. */
+ unsigned long gp_end; /* Time last GP ended, again */
+ /* in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
unsigned long gp_req_activity; /* Time of last GP request */
@@ -398,17 +400,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
#define RCU_NAME rcu_name
#endif /* #else #ifdef CONFIG_TRACING */
-/*
- * RCU implementation internal declarations:
- */
-extern struct rcu_state rcu_sched_state;
-
-extern struct rcu_state rcu_bh_state;
-
-#ifdef CONFIG_PREEMPT_RCU
-extern struct rcu_state rcu_preempt_state;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-
int rcu_dynticks_snap(struct rcu_data *rdp);
#ifdef CONFIG_RCU_BOOST
@@ -466,6 +457,7 @@ static void __init rcu_spawn_nocb_kthreads(void);
static void __init rcu_organize_nocb_kthreads(void);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
static bool init_nocb_callback_list(struct rcu_data *rdp);
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp);
static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);
static void rcu_dynticks_task_enter(void);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 8d18c1014e2b..928fe5893a57 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -450,10 +450,12 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
}
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
preempt_disable();
- cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+ cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
/* If all offline, queue the work on an unbound CPU. */
- if (unlikely(cpu > rnp->grphi))
+ if (unlikely(cpu > rnp->grphi - rnp->grplo))
cpu = WORK_CPU_UNBOUND;
+ else
+ cpu += rnp->grplo;
queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
preempt_enable();
rnp->exp_need_flush = true;
@@ -690,8 +692,10 @@ static void sync_rcu_exp_handler(void *unused)
*/
if (t->rcu_read_lock_nesting > 0) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if (rnp->expmask & rdp->grpmask)
+ if (rnp->expmask & rdp->grpmask) {
rdp->deferred_qs = true;
+ WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
+ }
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 05915e536336..1b3dd2fc0cd6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -397,6 +397,11 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
return rnp->gp_tasks != NULL;
}
+/* Bias and limit values for ->rcu_read_lock_nesting. */
+#define RCU_NEST_BIAS INT_MAX
+#define RCU_NEST_NMAX (-INT_MAX / 2)
+#define RCU_NEST_PMAX (INT_MAX / 2)
+
/*
* Preemptible RCU implementation for rcu_read_lock().
* Just increment ->rcu_read_lock_nesting, shared state will be updated
@@ -405,6 +410,8 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
void __rcu_read_lock(void)
{
current->rcu_read_lock_nesting++;
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING))
+ WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX);
barrier(); /* critical section after entry code. */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -424,20 +431,18 @@ void __rcu_read_unlock(void)
--t->rcu_read_lock_nesting;
} else {
barrier(); /* critical section before exit code. */
- t->rcu_read_lock_nesting = INT_MIN;
+ t->rcu_read_lock_nesting = -RCU_NEST_BIAS;
barrier(); /* assign before ->rcu_read_unlock_special load */
if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
rcu_read_unlock_special(t);
barrier(); /* ->rcu_read_unlock_special load before assign */
t->rcu_read_lock_nesting = 0;
}
-#ifdef CONFIG_PROVE_LOCKING
- {
- int rrln = READ_ONCE(t->rcu_read_lock_nesting);
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+ int rrln = t->rcu_read_lock_nesting;
- WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+ WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
}
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -597,7 +602,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
*/
static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
{
- return (this_cpu_ptr(&rcu_data)->deferred_qs ||
+ return (__this_cpu_read(rcu_data.deferred_qs) ||
READ_ONCE(t->rcu_read_unlock_special.s)) &&
t->rcu_read_lock_nesting <= 0;
}
@@ -617,11 +622,11 @@ static void rcu_preempt_deferred_qs(struct task_struct *t)
if (!rcu_preempt_need_deferred_qs(t))
return;
if (couldrecurse)
- t->rcu_read_lock_nesting -= INT_MIN;
+ t->rcu_read_lock_nesting -= RCU_NEST_BIAS;
local_irq_save(flags);
rcu_preempt_deferred_qs_irqrestore(t, flags);
if (couldrecurse)
- t->rcu_read_lock_nesting += INT_MIN;
+ t->rcu_read_lock_nesting += RCU_NEST_BIAS;
}
/*
@@ -642,13 +647,21 @@ static void rcu_read_unlock_special(struct task_struct *t)
local_irq_save(flags);
irqs_were_disabled = irqs_disabled_flags(flags);
- if ((preempt_bh_were_disabled || irqs_were_disabled) &&
- t->rcu_read_unlock_special.b.blocked) {
+ if (preempt_bh_were_disabled || irqs_were_disabled) {
+ WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
/* Need to defer quiescent state until everything is enabled. */
- raise_softirq_irqoff(RCU_SOFTIRQ);
+ if (irqs_were_disabled) {
+ /* Enabling irqs does not reschedule, so... */
+ raise_softirq_irqoff(RCU_SOFTIRQ);
+ } else {
+ /* Enabling BH or preempt does reschedule, so... */
+ set_tsk_need_resched(current);
+ set_preempt_need_resched();
+ }
local_irq_restore(flags);
return;
}
+ WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
rcu_preempt_deferred_qs_irqrestore(t, flags);
}
@@ -1464,7 +1477,8 @@ static void __init rcu_spawn_boost_kthreads(void)
for_each_possible_cpu(cpu)
per_cpu(rcu_cpu_has_work, cpu) = 0;
- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
+ if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__))
+ return;
rcu_for_each_leaf_node(rnp)
(void)rcu_spawn_one_boost_kthread(rnp);
}
@@ -1997,7 +2011,7 @@ static bool rcu_nocb_cpu_needs_barrier(int cpu)
* (if a callback is in fact needed). This is associated with an
* atomic_inc() in the caller.
*/
- ret = atomic_long_read(&rdp->nocb_q_count);
+ ret = rcu_get_n_cbs_nocb_cpu(rdp);
#ifdef CONFIG_PROVE_RCU
rhp = READ_ONCE(rdp->nocb_head);
@@ -2052,7 +2066,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
TPS("WakeNotPoll"));
return;
}
- len = atomic_long_read(&rdp->nocb_q_count);
+ len = rcu_get_n_cbs_nocb_cpu(rdp);
if (old_rhpp == &rdp->nocb_head) {
if (!irqs_disabled_flags(flags)) {
/* ... if queue was empty ... */
@@ -2101,11 +2115,11 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
trace_rcu_kfree_callback(rcu_state.name, rhp,
(unsigned long)rhp->func,
-atomic_long_read(&rdp->nocb_q_count_lazy),
- -atomic_long_read(&rdp->nocb_q_count));
+ -rcu_get_n_cbs_nocb_cpu(rdp));
else
trace_rcu_callback(rcu_state.name, rhp,
-atomic_long_read(&rdp->nocb_q_count_lazy),
- -atomic_long_read(&rdp->nocb_q_count));
+ -rcu_get_n_cbs_nocb_cpu(rdp));
/*
* If called from an extended quiescent state with interrupts
@@ -2322,13 +2336,14 @@ static int rcu_nocb_kthread(void *arg)
tail = rdp->nocb_follower_tail;
rdp->nocb_follower_tail = &rdp->nocb_follower_head;
raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
- BUG_ON(!list);
+ if (WARN_ON_ONCE(!list))
+ continue;
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeNonEmpty"));
/* Each pass through the following loop invokes a callback. */
trace_rcu_batch_start(rcu_state.name,
atomic_long_read(&rdp->nocb_q_count_lazy),
- atomic_long_read(&rdp->nocb_q_count), -1);
+ rcu_get_n_cbs_nocb_cpu(rdp), -1);
c = cl = 0;
while (list) {
next = list->next;
@@ -2495,7 +2510,8 @@ static void rcu_spawn_one_nocb_kthread(int cpu)
/* Spawn the kthread for this CPU. */
t = kthread_run(rcu_nocb_kthread, rdp_spawn,
"rcuo%c/%d", rcu_state.abbr, cpu);
- BUG_ON(IS_ERR(t));
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo kthread, OOM is now expected behavior\n", __func__))
+ return;
WRITE_ONCE(rdp_spawn->nocb_kthread, t);
}
@@ -2587,6 +2603,26 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
return true;
}
+/*
+ * Bind the current task to the offloaded CPUs. If there are no offloaded
+ * CPUs, leave the task unbound. Splat if the bind attempt fails.
+ */
+void rcu_bind_current_to_nocb(void)
+{
+ if (cpumask_available(rcu_nocb_mask) && cpumask_weight(rcu_nocb_mask))
+ WARN_ON(sched_setaffinity(current->pid, rcu_nocb_mask));
+}
+EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb);
+
+/*
+ * Return the number of RCU callbacks still queued from the specified
+ * CPU, which must be a nocbs CPU.
+ */
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp)
+{
+ return atomic_long_read(&rdp->nocb_q_count);
+}
+
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
static bool rcu_nocb_cpu_needs_barrier(int cpu)
@@ -2647,6 +2683,11 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
return false;
}
+static unsigned long rcu_get_n_cbs_nocb_cpu(struct rcu_data *rdp)
+{
+ return 0;
+}
+
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
/*
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index f203b94f6b5b..1971869c4072 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -335,8 +335,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
/* Initialize and register callbacks for each crcu_array element. */
for (i = 0; i < n; i++) {
if (checktiny &&
- (crcu_array[i] == call_rcu ||
- crcu_array[i] == call_rcu_bh)) {
+ (crcu_array[i] == call_rcu)) {
might_sleep();
continue;
}
@@ -352,8 +351,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
/* Wait for all callbacks to be invoked. */
for (i = 0; i < n; i++) {
if (checktiny &&
- (crcu_array[i] == call_rcu ||
- crcu_array[i] == call_rcu_bh))
+ (crcu_array[i] == call_rcu))
continue;
for (j = 0; j < i; j++)
if (crcu_array[j] == crcu_array[i])
@@ -822,7 +820,8 @@ static int __init rcu_spawn_tasks_kthread(void)
struct task_struct *t;
t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
- BUG_ON(IS_ERR(t));
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__))
+ return 0;
smp_mb(); /* Ensure others see full kthread. */
WRITE_ONCE(rcu_tasks_kthread_ptr, t);
return 0;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6fedf3a98581..f66920173370 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -697,7 +697,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
/*
* SCHED_IDLE tasks get minimal weight:
*/
- if (idle_policy(p->policy)) {
+ if (task_has_idle_policy(p)) {
load->weight = scale_load(WEIGHT_IDLEPRIO);
load->inv_weight = WMULT_IDLEPRIO;
p->se.runnable_weight = load->weight;
@@ -2857,7 +2857,7 @@ unsigned long nr_running(void)
* preemption, thus the result might have a time-of-check-to-time-of-use
* race. The caller is responsible to use it correctly, for example:
*
- * - from a non-preemptable section (of course)
+ * - from a non-preemptible section (of course)
*
* - from a thread that is bound to a single CPU
*
@@ -4191,7 +4191,7 @@ recheck:
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
*/
- if (idle_policy(p->policy) && !idle_policy(policy)) {
+ if (task_has_idle_policy(p) && !idle_policy(policy)) {
if (!can_nice(p, task_nice(p)))
return -EPERM;
}
@@ -5783,7 +5783,7 @@ int sched_cpu_deactivate(unsigned int cpu)
*
* Do sync before park smpboot threads to take care the rcu boost case.
*/
- synchronize_rcu_mult(call_rcu, call_rcu_sched);
+ synchronize_rcu();
#ifdef CONFIG_SCHED_SMT
/*
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 5e54cbcae673..22bd8980f32f 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Scheduler code and data structures related to cpufreq.
*
* Copyright (C) 2016, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include "sched.h"
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3fffad3bc8a8..033ec7c45f13 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -1,18 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* CPUFreq governor based on scheduler-provided CPU utilization data.
*
* Copyright (C) 2016, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include "sched.h"
+#include <linux/sched/cpufreq.h>
#include <trace/events/power.h>
struct sugov_tunables {
@@ -167,7 +165,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
unsigned int freq = arch_scale_freq_invariant() ?
policy->cpuinfo.max_freq : policy->cur;
- freq = (freq + (freq >> 2)) * util / max;
+ freq = map_util_freq(util, freq, max);
if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
return sg_policy->next_freq;
@@ -197,15 +195,13 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
* based on the task model parameters and gives the minimal utilization
* required to meet deadlines.
*/
-static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+ unsigned long max, enum schedutil_type type)
{
- struct rq *rq = cpu_rq(sg_cpu->cpu);
- unsigned long util, irq, max;
-
- sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
- sg_cpu->bw_dl = cpu_bw_dl(rq);
+ unsigned long dl_util, util, irq;
+ struct rq *rq = cpu_rq(cpu);
- if (rt_rq_is_runnable(&rq->rt))
+ if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
return max;
/*
@@ -223,22 +219,31 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
* utilization (PELT windows are synchronized) we can directly add them
* to obtain the CPU's actual utilization.
*/
- util = cpu_util_cfs(rq);
+ util = util_cfs;
util += cpu_util_rt(rq);
+ dl_util = cpu_util_dl(rq);
+
/*
- * We do not make cpu_util_dl() a permanent part of this sum because we
- * want to use cpu_bw_dl() later on, but we need to check if the
- * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
- * f_max when there is no idle time.
+ * For frequency selection we do not make cpu_util_dl() a permanent part
+ * of this sum because we want to use cpu_bw_dl() later on, but we need
+ * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
+ * that we select f_max when there is no idle time.
*
* NOTE: numerical errors or stop class might cause us to not quite hit
* saturation when we should -- something for later.
*/
- if ((util + cpu_util_dl(rq)) >= max)
+ if (util + dl_util >= max)
return max;
/*
+ * OTOH, for energy computation we need the estimated running time, so
+ * include util_dl and ignore dl_bw.
+ */
+ if (type == ENERGY_UTIL)
+ util += dl_util;
+
+ /*
* There is still idle time; further improve the number by using the
* irq metric. Because IRQ/steal time is hidden from the task clock we
* need to scale the task numbers:
@@ -260,7 +265,22 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
* bw_dl as requested freq. However, cpufreq is not yet ready for such
* an interface. So, we only do the latter for now.
*/
- return min(max, util + sg_cpu->bw_dl);
+ if (type == FREQUENCY_UTIL)
+ util += cpu_bw_dl(rq);
+
+ return min(max, util);
+}
+
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+{
+ struct rq *rq = cpu_rq(sg_cpu->cpu);
+ unsigned long util = cpu_util_cfs(rq);
+ unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+
+ sg_cpu->max = max;
+ sg_cpu->bw_dl = cpu_bw_dl(rq);
+
+ return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL);
}
/**
@@ -601,7 +621,7 @@ static struct kobj_type sugov_tunables_ktype = {
/********************** cpufreq governor interface *********************/
-static struct cpufreq_governor schedutil_gov;
+struct cpufreq_governor schedutil_gov;
static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
{
@@ -860,7 +880,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
sg_policy->need_freq_update = true;
}
-static struct cpufreq_governor schedutil_gov = {
+struct cpufreq_governor schedutil_gov = {
.name = "schedutil",
.owner = THIS_MODULE,
.dynamic_switching = true,
@@ -883,3 +903,36 @@ static int __init sugov_register(void)
return cpufreq_register_governor(&schedutil_gov);
}
fs_initcall(sugov_register);
+
+#ifdef CONFIG_ENERGY_MODEL
+extern bool sched_energy_update;
+extern struct mutex sched_energy_mutex;
+
+static void rebuild_sd_workfn(struct work_struct *work)
+{
+ mutex_lock(&sched_energy_mutex);
+ sched_energy_update = true;
+ rebuild_sched_domains();
+ sched_energy_update = false;
+ mutex_unlock(&sched_energy_mutex);
+}
+static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
+
+/*
+ * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
+ * on governor changes to make sure the scheduler knows about it.
+ */
+void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+ struct cpufreq_governor *old_gov)
+{
+ if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) {
+ /*
+ * When called from the cpufreq_register_driver() path, the
+ * cpu_hotplug_lock is already held, so use a work item to
+ * avoid nested locking in rebuild_sched_domains().
+ */
+ schedule_work(&rebuild_sd_work);
+ }
+
+}
+#endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 0796f938c4f0..ba4a143bdcf3 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -525,7 +525,7 @@ void account_idle_ticks(unsigned long ticks)
/*
* Perform (stime * rtime) / total, but avoid multiplication overflow by
- * loosing precision when the numbers are big.
+ * losing precision when the numbers are big.
*/
static u64 scale_stime(u64 stime, u64 rtime, u64 total)
{
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 91e4202b0634..fb8b7b5d745d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -727,7 +727,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
* refill the runtime and set the deadline a period in the future,
* because keeping the current (absolute) deadline of the task would
* result in breaking guarantees promised to other tasks (refer to
- * Documentation/scheduler/sched-deadline.txt for more informations).
+ * Documentation/scheduler/sched-deadline.txt for more information).
*
* This function returns true if:
*
@@ -1695,6 +1695,14 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
}
#endif
+static inline void set_next_task(struct rq *rq, struct task_struct *p)
+{
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* You can't push away the running task */
+ dequeue_pushable_dl_task(rq, p);
+}
+
static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
struct dl_rq *dl_rq)
{
@@ -1750,10 +1758,8 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
BUG_ON(!dl_se);
p = dl_task_of(dl_se);
- p->se.exec_start = rq_clock_task(rq);
- /* Running task will never be pushed. */
- dequeue_pushable_dl_task(rq, p);
+ set_next_task(rq, p);
if (hrtick_enabled(rq))
start_hrtick_dl(rq, p);
@@ -1808,12 +1814,7 @@ static void task_fork_dl(struct task_struct *p)
static void set_curr_task_dl(struct rq *rq)
{
- struct task_struct *p = rq->curr;
-
- p->se.exec_start = rq_clock_task(rq);
-
- /* You can't push away the running task */
- dequeue_pushable_dl_task(rq, p);
+ set_next_task(rq, rq->curr);
}
#ifdef CONFIG_SMP
@@ -2041,10 +2042,8 @@ static int push_dl_task(struct rq *rq)
return 0;
retry:
- if (unlikely(next_task == rq->curr)) {
- WARN_ON(1);
+ if (WARN_ON(next_task == rq->curr))
return 0;
- }
/*
* If next_task preempts rq->curr, and rq->curr
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 6383aa6a60ca..02bd5f969b21 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -974,7 +974,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
#endif
P(policy);
P(prio);
- if (p->policy == SCHED_DEADLINE) {
+ if (task_has_dl_policy(p)) {
P(dl.runtime);
P(dl.deadline);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ac855b2f4774..d1907506318a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -38,7 +38,7 @@
* (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
*/
unsigned int sysctl_sched_latency = 6000000ULL;
-unsigned int normalized_sysctl_sched_latency = 6000000ULL;
+static unsigned int normalized_sysctl_sched_latency = 6000000ULL;
/*
* The initial- and re-scaling of tunables is configurable
@@ -58,8 +58,8 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_L
*
* (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
-unsigned int sysctl_sched_min_granularity = 750000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
+unsigned int sysctl_sched_min_granularity = 750000ULL;
+static unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
/*
* This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
@@ -81,8 +81,8 @@ unsigned int sysctl_sched_child_runs_first __read_mostly;
*
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
-unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
-unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
+static unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
@@ -94,6 +94,14 @@ int __weak arch_asym_cpu_priority(int cpu)
{
return -cpu;
}
+
+/*
+ * The margin used when comparing utilization with CPU capacity:
+ * util * margin < capacity * 1024
+ *
+ * (default: ~20%)
+ */
+static unsigned int capacity_margin = 1280;
#endif
#ifdef CONFIG_CFS_BANDWIDTH
@@ -110,14 +118,6 @@ int __weak arch_asym_cpu_priority(int cpu)
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
#endif
-/*
- * The margin used when comparing utilization with CPU capacity:
- * util * margin < capacity * 1024
- *
- * (default: ~20%)
- */
-unsigned int capacity_margin = 1280;
-
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
@@ -703,9 +703,9 @@ void init_entity_runnable_average(struct sched_entity *se)
memset(sa, 0, sizeof(*sa));
/*
- * Tasks are intialized with full load to be seen as heavy tasks until
+ * Tasks are initialized with full load to be seen as heavy tasks until
* they get a chance to stabilize to their real load level.
- * Group entities are intialized with zero load to reflect the fact that
+ * Group entities are initialized with zero load to reflect the fact that
* nothing has been attached to the task group yet.
*/
if (entity_is_task(se))
@@ -2734,6 +2734,17 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
WRITE_ONCE(*ptr, res); \
} while (0)
+/*
+ * Remove and clamp on negative, from a local variable.
+ *
+ * A variant of sub_positive(), which does not use explicit load-store
+ * and is thus optimized for local variable updates.
+ */
+#define lsub_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ *ptr -= min_t(typeof(*ptr), *ptr, _val); \
+} while (0)
+
#ifdef CONFIG_SMP
static inline void
enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -3604,7 +3615,7 @@ static inline unsigned long _task_util_est(struct task_struct *p)
{
struct util_est ue = READ_ONCE(p->se.avg.util_est);
- return max(ue.ewma, ue.enqueued);
+ return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
}
static inline unsigned long task_util_est(struct task_struct *p)
@@ -3622,7 +3633,7 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
/* Update root cfs_rq's estimated utilization */
enqueued = cfs_rq->avg.util_est.enqueued;
- enqueued += (_task_util_est(p) | UTIL_AVG_UNCHANGED);
+ enqueued += _task_util_est(p);
WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
}
@@ -3650,8 +3661,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
/* Update root cfs_rq's estimated utilization */
ue.enqueued = cfs_rq->avg.util_est.enqueued;
- ue.enqueued -= min_t(unsigned int, ue.enqueued,
- (_task_util_est(p) | UTIL_AVG_UNCHANGED));
+ ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
/*
@@ -3966,8 +3976,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
/*
* When dequeuing a sched_entity, we must:
* - Update loads to have both entity and cfs_rq synced with now.
- * - Substract its load from the cfs_rq->runnable_avg.
- * - Substract its previous weight from cfs_rq->load.weight.
+ * - Subtract its load from the cfs_rq->runnable_avg.
+ * - Subtract its previous weight from cfs_rq->load.weight.
* - For group entity, update its weight to reflect the new share
* of its group cfs_rq.
*/
@@ -4640,7 +4650,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
cfs_b->distribute_running = 0;
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
- cfs_b->runtime -= min(runtime, cfs_b->runtime);
+ lsub_positive(&cfs_b->runtime, runtime);
}
/*
@@ -4774,7 +4784,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
raw_spin_lock(&cfs_b->lock);
if (expires == cfs_b->runtime_expires)
- cfs_b->runtime -= min(runtime, cfs_b->runtime);
+ lsub_positive(&cfs_b->runtime, runtime);
cfs_b->distribute_running = 0;
raw_spin_unlock(&cfs_b->lock);
}
@@ -5072,6 +5082,24 @@ static inline void hrtick_update(struct rq *rq)
}
#endif
+#ifdef CONFIG_SMP
+static inline unsigned long cpu_util(int cpu);
+static unsigned long capacity_of(int cpu);
+
+static inline bool cpu_overutilized(int cpu)
+{
+ return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
+}
+
+static inline void update_overutilized_status(struct rq *rq)
+{
+ if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+ WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
+}
+#else
+static inline void update_overutilized_status(struct rq *rq) { }
+#endif
+
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
@@ -5129,8 +5157,26 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
update_cfs_group(se);
}
- if (!se)
+ if (!se) {
add_nr_running(rq, 1);
+ /*
+ * Since new tasks are assigned an initial util_avg equal to
+ * half of the spare capacity of their CPU, tiny tasks have the
+ * ability to cross the overutilized threshold, which will
+ * result in the load balancer ruining all the task placement
+ * done by EAS. As a way to mitigate that effect, do not account
+ * for the first enqueue operation of new tasks during the
+ * overutilized flag detection.
+ *
+ * A better way of solving this problem would be to wait for
+ * the PELT signals of tasks to converge before taking them
+ * into account, but that is not straightforward to implement,
+ * and the following generally works well enough in practice.
+ */
+ if (flags & ENQUEUE_WAKEUP)
+ update_overutilized_status(rq);
+
+ }
hrtick_update(rq);
}
@@ -6241,7 +6287,7 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
util = READ_ONCE(cfs_rq->avg.util_avg);
/* Discount task's util from CPU's util */
- util -= min_t(unsigned int, util, task_util(p));
+ lsub_positive(&util, task_util(p));
/*
* Covered cases:
@@ -6290,10 +6336,9 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
* properly fix the execl regression and it helps in further
* reducing the chances for the above race.
*/
- if (unlikely(task_on_rq_queued(p) || current == p)) {
- estimated -= min_t(unsigned int, estimated,
- (_task_util_est(p) | UTIL_AVG_UNCHANGED));
- }
+ if (unlikely(task_on_rq_queued(p) || current == p))
+ lsub_positive(&estimated, _task_util_est(p));
+
util = max(util, estimated);
}
@@ -6333,6 +6378,213 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
}
/*
+ * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued)
+ * to @dst_cpu.
+ */
+static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
+{
+ struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs;
+ unsigned long util_est, util = READ_ONCE(cfs_rq->avg.util_avg);
+
+ /*
+ * If @p migrates from @cpu to another, remove its contribution. Or,
+ * if @p migrates from another CPU to @cpu, add its contribution. In
+ * the other cases, @cpu is not impacted by the migration, so the
+ * util_avg should already be correct.
+ */
+ if (task_cpu(p) == cpu && dst_cpu != cpu)
+ sub_positive(&util, task_util(p));
+ else if (task_cpu(p) != cpu && dst_cpu == cpu)
+ util += task_util(p);
+
+ if (sched_feat(UTIL_EST)) {
+ util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+ /*
+ * During wake-up, the task isn't enqueued yet and doesn't
+ * appear in the cfs_rq->avg.util_est.enqueued of any rq,
+ * so just add it (if needed) to "simulate" what will be
+ * cpu_util() after the task has been enqueued.
+ */
+ if (dst_cpu == cpu)
+ util_est += _task_util_est(p);
+
+ util = max(util, util_est);
+ }
+
+ return min(util, capacity_orig_of(cpu));
+}
+
+/*
+ * compute_energy(): Estimates the energy that would be consumed if @p was
+ * migrated to @dst_cpu. compute_energy() predicts what will be the utilization
+ * landscape of the * CPUs after the task migration, and uses the Energy Model
+ * to compute what would be the energy if we decided to actually migrate that
+ * task.
+ */
+static long
+compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
+{
+ long util, max_util, sum_util, energy = 0;
+ int cpu;
+
+ for (; pd; pd = pd->next) {
+ max_util = sum_util = 0;
+ /*
+ * The capacity state of CPUs of the current rd can be driven by
+ * CPUs of another rd if they belong to the same performance
+ * domain. So, account for the utilization of these CPUs too
+ * by masking pd with cpu_online_mask instead of the rd span.
+ *
+ * If an entire performance domain is outside of the current rd,
+ * it will not appear in its pd list and will not be accounted
+ * by compute_energy().
+ */
+ for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) {
+ util = cpu_util_next(cpu, p, dst_cpu);
+ util = schedutil_energy_util(cpu, util);
+ max_util = max(util, max_util);
+ sum_util += util;
+ }
+
+ energy += em_pd_energy(pd->em_pd, max_util, sum_util);
+ }
+
+ return energy;
+}
+
+/*
+ * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the
+ * waking task. find_energy_efficient_cpu() looks for the CPU with maximum
+ * spare capacity in each performance domain and uses it as a potential
+ * candidate to execute the task. Then, it uses the Energy Model to figure
+ * out which of the CPU candidates is the most energy-efficient.
+ *
+ * The rationale for this heuristic is as follows. In a performance domain,
+ * all the most energy efficient CPU candidates (according to the Energy
+ * Model) are those for which we'll request a low frequency. When there are
+ * several CPUs for which the frequency request will be the same, we don't
+ * have enough data to break the tie between them, because the Energy Model
+ * only includes active power costs. With this model, if we assume that
+ * frequency requests follow utilization (e.g. using schedutil), the CPU with
+ * the maximum spare capacity in a performance domain is guaranteed to be among
+ * the best candidates of the performance domain.
+ *
+ * In practice, it could be preferable from an energy standpoint to pack
+ * small tasks on a CPU in order to let other CPUs go in deeper idle states,
+ * but that could also hurt our chances to go cluster idle, and we have no
+ * ways to tell with the current Energy Model if this is actually a good
+ * idea or not. So, find_energy_efficient_cpu() basically favors
+ * cluster-packing, and spreading inside a cluster. That should at least be
+ * a good thing for latency, and this is consistent with the idea that most
+ * of the energy savings of EAS come from the asymmetry of the system, and
+ * not so much from breaking the tie between identical CPUs. That's also the
+ * reason why EAS is enabled in the topology code only for systems where
+ * SD_ASYM_CPUCAPACITY is set.
+ *
+ * NOTE: Forkees are not accepted in the energy-aware wake-up path because
+ * they don't have any useful utilization data yet and it's not possible to
+ * forecast their impact on energy consumption. Consequently, they will be
+ * placed by find_idlest_cpu() on the least loaded CPU, which might turn out
+ * to be energy-inefficient in some use-cases. The alternative would be to
+ * bias new tasks towards specific types of CPUs first, or to try to infer
+ * their util_avg from the parent task, but those heuristics could hurt
+ * other use-cases too. So, until someone finds a better way to solve this,
+ * let's keep things simple by re-using the existing slow path.
+ */
+
+static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
+{
+ unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX;
+ struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+ int cpu, best_energy_cpu = prev_cpu;
+ struct perf_domain *head, *pd;
+ unsigned long cpu_cap, util;
+ struct sched_domain *sd;
+
+ rcu_read_lock();
+ pd = rcu_dereference(rd->pd);
+ if (!pd || READ_ONCE(rd->overutilized))
+ goto fail;
+ head = pd;
+
+ /*
+ * Energy-aware wake-up happens on the lowest sched_domain starting
+ * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu.
+ */
+ sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity));
+ while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+ sd = sd->parent;
+ if (!sd)
+ goto fail;
+
+ sync_entity_load_avg(&p->se);
+ if (!task_util_est(p))
+ goto unlock;
+
+ for (; pd; pd = pd->next) {
+ unsigned long cur_energy, spare_cap, max_spare_cap = 0;
+ int max_spare_cap_cpu = -1;
+
+ for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
+ if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ continue;
+
+ /* Skip CPUs that will be overutilized. */
+ util = cpu_util_next(cpu, p, cpu);
+ cpu_cap = capacity_of(cpu);
+ if (cpu_cap * 1024 < util * capacity_margin)
+ continue;
+
+ /* Always use prev_cpu as a candidate. */
+ if (cpu == prev_cpu) {
+ prev_energy = compute_energy(p, prev_cpu, head);
+ best_energy = min(best_energy, prev_energy);
+ continue;
+ }
+
+ /*
+ * Find the CPU with the maximum spare capacity in
+ * the performance domain
+ */
+ spare_cap = cpu_cap - util;
+ if (spare_cap > max_spare_cap) {
+ max_spare_cap = spare_cap;
+ max_spare_cap_cpu = cpu;
+ }
+ }
+
+ /* Evaluate the energy impact of using this CPU. */
+ if (max_spare_cap_cpu >= 0) {
+ cur_energy = compute_energy(p, max_spare_cap_cpu, head);
+ if (cur_energy < best_energy) {
+ best_energy = cur_energy;
+ best_energy_cpu = max_spare_cap_cpu;
+ }
+ }
+ }
+unlock:
+ rcu_read_unlock();
+
+ /*
+ * Pick the best CPU if prev_cpu cannot be used, or if it saves at
+ * least 6% of the energy used by prev_cpu.
+ */
+ if (prev_energy == ULONG_MAX)
+ return best_energy_cpu;
+
+ if ((prev_energy - best_energy) > (prev_energy >> 4))
+ return best_energy_cpu;
+
+ return prev_cpu;
+
+fail:
+ rcu_read_unlock();
+
+ return -1;
+}
+
+/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
* SD_BALANCE_FORK, or SD_BALANCE_EXEC.
@@ -6355,8 +6607,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
if (sd_flag & SD_BALANCE_WAKE) {
record_wakee(p);
- want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
- && cpumask_test_cpu(cpu, &p->cpus_allowed);
+
+ if (static_branch_unlikely(&sched_energy_present)) {
+ new_cpu = find_energy_efficient_cpu(p, prev_cpu);
+ if (new_cpu >= 0)
+ return new_cpu;
+ new_cpu = prev_cpu;
+ }
+
+ want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
+ cpumask_test_cpu(cpu, &p->cpus_allowed);
}
rcu_read_lock();
@@ -6520,7 +6780,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
static void set_last_buddy(struct sched_entity *se)
{
- if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+ if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
return;
for_each_sched_entity(se) {
@@ -6532,7 +6792,7 @@ static void set_last_buddy(struct sched_entity *se)
static void set_next_buddy(struct sched_entity *se)
{
- if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+ if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
return;
for_each_sched_entity(se) {
@@ -6590,8 +6850,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
return;
/* Idle tasks are by definition preempted by non-idle tasks. */
- if (unlikely(curr->policy == SCHED_IDLE) &&
- likely(p->policy != SCHED_IDLE))
+ if (unlikely(task_has_idle_policy(curr)) &&
+ likely(!task_has_idle_policy(p)))
goto preempt;
/*
@@ -7012,7 +7272,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
if (p->sched_class != &fair_sched_class)
return 0;
- if (unlikely(p->policy == SCHED_IDLE))
+ if (unlikely(task_has_idle_policy(p)))
return 0;
/*
@@ -7896,16 +8156,16 @@ static bool update_nohz_stats(struct rq *rq, bool force)
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
* @env: The load balancing environment.
* @group: sched_group whose statistics are to be updated.
- * @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @local_group: Does group contain this_cpu.
* @sgs: variable to hold the statistics for this group.
- * @overload: Indicate pullable load (e.g. >1 runnable task).
+ * @sg_status: Holds flag indicating the status of the sched_group
*/
static inline void update_sg_lb_stats(struct lb_env *env,
- struct sched_group *group, int load_idx,
- int local_group, struct sg_lb_stats *sgs,
- bool *overload)
+ struct sched_group *group,
+ struct sg_lb_stats *sgs,
+ int *sg_status)
{
+ int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
+ int load_idx = get_sd_load_idx(env->sd, env->idle);
unsigned long load;
int i, nr_running;
@@ -7929,7 +8189,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
nr_running = rq->nr_running;
if (nr_running > 1)
- *overload = true;
+ *sg_status |= SG_OVERLOAD;
+
+ if (cpu_overutilized(i))
+ *sg_status |= SG_OVERUTILIZED;
#ifdef CONFIG_NUMA_BALANCING
sgs->nr_numa_running += rq->nr_numa_running;
@@ -7945,7 +8208,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
sgs->group_misfit_task_load < rq->misfit_task_load) {
sgs->group_misfit_task_load = rq->misfit_task_load;
- *overload = 1;
+ *sg_status |= SG_OVERLOAD;
}
}
@@ -8090,17 +8353,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats *local = &sds->local_stat;
struct sg_lb_stats tmp_sgs;
- int load_idx;
- bool overload = false;
bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
+ int sg_status = 0;
#ifdef CONFIG_NO_HZ_COMMON
if (env->idle == CPU_NEWLY_IDLE && READ_ONCE(nohz.has_blocked))
env->flags |= LBF_NOHZ_STATS;
#endif
- load_idx = get_sd_load_idx(env->sd, env->idle);
-
do {
struct sg_lb_stats *sgs = &tmp_sgs;
int local_group;
@@ -8115,8 +8375,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
update_group_capacity(env->sd, env->dst_cpu);
}
- update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
- &overload);
+ update_sg_lb_stats(env, sg, sgs, &sg_status);
if (local_group)
goto next_group;
@@ -8165,9 +8424,15 @@ next_group:
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
if (!env->sd->parent) {
+ struct root_domain *rd = env->dst_rq->rd;
+
/* update overload indicator if we are at root domain */
- if (READ_ONCE(env->dst_rq->rd->overload) != overload)
- WRITE_ONCE(env->dst_rq->rd->overload, overload);
+ WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD);
+
+ /* Update over-utilization (tipping point, U >= 0) indicator */
+ WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
+ } else if (sg_status & SG_OVERUTILIZED) {
+ WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED);
}
}
@@ -8394,6 +8659,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* this level.
*/
update_sd_lb_stats(env, &sds);
+
+ if (static_branch_unlikely(&sched_energy_present)) {
+ struct root_domain *rd = env->dst_rq->rd;
+
+ if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized))
+ goto out_balanced;
+ }
+
local = &sds.local_stat;
busiest = &sds.busiest_stat;
@@ -8910,13 +9183,22 @@ out_all_pinned:
sd->nr_balance_failed = 0;
out_one_pinned:
+ ld_moved = 0;
+
+ /*
+ * idle_balance() disregards balance intervals, so we could repeatedly
+ * reach this code, which would lead to balance_interval skyrocketting
+ * in a short amount of time. Skip the balance_interval increase logic
+ * to avoid that.
+ */
+ if (env.idle == CPU_NEWLY_IDLE)
+ goto out;
+
/* tune up the balancing interval */
- if (((env.flags & LBF_ALL_PINNED) &&
- sd->balance_interval < MAX_PINNED_INTERVAL) ||
- (sd->balance_interval < sd->max_interval))
+ if ((env.flags & LBF_ALL_PINNED &&
+ sd->balance_interval < MAX_PINNED_INTERVAL) ||
+ sd->balance_interval < sd->max_interval)
sd->balance_interval *= 2;
-
- ld_moved = 0;
out:
return ld_moved;
}
@@ -9281,7 +9563,7 @@ static void nohz_balancer_kick(struct rq *rq)
}
}
- sd = rcu_dereference(per_cpu(sd_asym, cpu));
+ sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
if (sd) {
for_each_cpu(i, sched_domain_span(sd)) {
if (i == cpu ||
@@ -9533,9 +9815,7 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
return false;
}
- /*
- * barrier, pairs with nohz_balance_enter_idle(), ensures ...
- */
+ /* could be _relaxed() */
flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu));
if (!(flags & NOHZ_KICK_MASK))
return false;
@@ -9785,6 +10065,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
task_tick_numa(rq, curr);
update_misfit_status(curr, rq);
+ update_overutilized_status(task_rq(curr));
}
/*
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index e6802181900f..81faddba9e20 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -8,14 +8,14 @@
*/
#include "sched.h"
-DEFINE_STATIC_KEY_FALSE(housekeeping_overriden);
-EXPORT_SYMBOL_GPL(housekeeping_overriden);
+DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
+EXPORT_SYMBOL_GPL(housekeeping_overridden);
static cpumask_var_t housekeeping_mask;
static unsigned int housekeeping_flags;
int housekeeping_any_cpu(enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return cpumask_any_and(housekeeping_mask, cpu_online_mask);
return smp_processor_id();
@@ -24,7 +24,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return housekeeping_mask;
return cpu_possible_mask;
@@ -33,7 +33,7 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask);
void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
set_cpus_allowed_ptr(t, housekeeping_mask);
}
@@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(housekeeping_affine);
bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
{
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
if (housekeeping_flags & flags)
return cpumask_test_cpu(cpu, housekeeping_mask);
return true;
@@ -53,7 +53,7 @@ void __init housekeeping_init(void)
if (!housekeeping_flags)
return;
- static_branch_enable(&housekeeping_overriden);
+ static_branch_enable(&housekeeping_overridden);
if (housekeeping_flags & HK_FLAG_TICK)
sched_tick_offload_init();
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 76e0eaf4654e..3cd8a3a795d2 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -210,7 +210,7 @@ static int membarrier_register_global_expedited(void)
* future scheduler executions will observe the new
* thread flag state for this mm.
*/
- synchronize_sched();
+ synchronize_rcu();
}
atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY,
&mm->membarrier_state);
@@ -246,7 +246,7 @@ static int membarrier_register_private_expedited(int flags)
* Ensure all future scheduler executions will observe the
* new thread flag state for this process.
*/
- synchronize_sched();
+ synchronize_rcu();
}
atomic_or(state, &mm->membarrier_state);
@@ -298,7 +298,7 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
if (tick_nohz_full_enabled())
return -EINVAL;
if (num_online_cpus() > 1)
- synchronize_sched();
+ synchronize_rcu();
return 0;
case MEMBARRIER_CMD_GLOBAL_EXPEDITED:
return membarrier_global_expedited();
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a21ea6021929..e4f398ad9e73 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1498,6 +1498,14 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
#endif
}
+static inline void set_next_task(struct rq *rq, struct task_struct *p)
+{
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* The running task is never eligible for pushing */
+ dequeue_pushable_task(rq, p);
+}
+
static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
struct rt_rq *rt_rq)
{
@@ -1518,7 +1526,6 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
struct sched_rt_entity *rt_se;
- struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
do {
@@ -1527,10 +1534,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
rt_rq = group_rt_rq(rt_se);
} while (rt_rq);
- p = rt_task_of(rt_se);
- p->se.exec_start = rq_clock_task(rq);
-
- return p;
+ return rt_task_of(rt_se);
}
static struct task_struct *
@@ -1573,8 +1577,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
p = _pick_next_task_rt(rq);
- /* The running task is never eligible for pushing */
- dequeue_pushable_task(rq, p);
+ set_next_task(rq, p);
rt_queue_push_tasks(rq);
@@ -1810,10 +1813,8 @@ static int push_rt_task(struct rq *rq)
return 0;
retry:
- if (unlikely(next_task == rq->curr)) {
- WARN_ON(1);
+ if (WARN_ON(next_task == rq->curr))
return 0;
- }
/*
* It's possible that the next_task slipped in of
@@ -2355,12 +2356,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
static void set_curr_task_rt(struct rq *rq)
{
- struct task_struct *p = rq->curr;
-
- p->se.exec_start = rq_clock_task(rq);
-
- /* The running task is never eligible for pushing */
- dequeue_pushable_task(rq, p);
+ set_next_task(rq, rq->curr);
}
static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4e524ab589c9..0ba08924e017 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -45,6 +45,7 @@
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/delayacct.h>
+#include <linux/energy_model.h>
#include <linux/init_task.h>
#include <linux/kprobes.h>
#include <linux/kthread.h>
@@ -177,6 +178,11 @@ static inline bool valid_policy(int policy)
rt_policy(policy) || dl_policy(policy);
}
+static inline int task_has_idle_policy(struct task_struct *p)
+{
+ return idle_policy(p->policy);
+}
+
static inline int task_has_rt_policy(struct task_struct *p)
{
return rt_policy(p->policy);
@@ -632,7 +638,7 @@ struct dl_rq {
/*
* Deadline values of the currently executing and the
* earliest ready task on this rq. Caching these facilitates
- * the decision wether or not a ready but not running task
+ * the decision whether or not a ready but not running task
* should migrate somewhere else.
*/
struct {
@@ -704,6 +710,16 @@ static inline bool sched_asym_prefer(int a, int b)
return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b);
}
+struct perf_domain {
+ struct em_perf_domain *em_pd;
+ struct perf_domain *next;
+ struct rcu_head rcu;
+};
+
+/* Scheduling group status flags */
+#define SG_OVERLOAD 0x1 /* More than one runnable task on a CPU. */
+#define SG_OVERUTILIZED 0x2 /* One or more CPUs are over-utilized. */
+
/*
* We add the notion of a root-domain which will be used to define per-domain
* variables. Each exclusive cpuset essentially defines an island domain by
@@ -726,6 +742,9 @@ struct root_domain {
*/
int overload;
+ /* Indicate one or more cpus over-utilized (tipping point) */
+ int overutilized;
+
/*
* The bit corresponding to a CPU gets set here if such CPU has more
* than one runnable -deadline task (as it is below for RT tasks).
@@ -756,6 +775,12 @@ struct root_domain {
struct cpupri cpupri;
unsigned long max_cpu_capacity;
+
+ /*
+ * NULL-terminated list of performance domains intersecting with the
+ * CPUs of the rd. Protected by RCU.
+ */
+ struct perf_domain *pd;
};
extern struct root_domain def_root_domain;
@@ -1285,7 +1310,8 @@ DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
extern struct static_key_false sched_asym_cpucapacity;
struct sched_group_capacity {
@@ -1429,7 +1455,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
#ifdef CONFIG_SMP
/*
* After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
- * successfuly executed on another CPU. We must ensure that updates of
+ * successfully executed on another CPU. We must ensure that updates of
* per-task data have been completed by this moment.
*/
smp_wmb();
@@ -1794,12 +1820,12 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
rq->nr_running = prev_nr + count;
- if (prev_nr < 2 && rq->nr_running >= 2) {
#ifdef CONFIG_SMP
+ if (prev_nr < 2 && rq->nr_running >= 2) {
if (!READ_ONCE(rq->rd->overload))
WRITE_ONCE(rq->rd->overload, 1);
-#endif
}
+#endif
sched_update_tick_dependency(rq);
}
@@ -1855,27 +1881,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
#endif
#ifdef CONFIG_SMP
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
- return sd->smt_gain / sd->span_weight;
-
- return SCHED_CAPACITY_SCALE;
-}
-#endif
-#else
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
-{
- return SCHED_CAPACITY_SCALE;
-}
-#endif
-#endif
-
-#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -2207,6 +2212,31 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+/**
+ * enum schedutil_type - CPU utilization type
+ * @FREQUENCY_UTIL: Utilization used to select frequency
+ * @ENERGY_UTIL: Utilization used during energy calculation
+ *
+ * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
+ * need to be aggregated differently depending on the usage made of them. This
+ * enum is used within schedutil_freq_util() to differentiate the types of
+ * utilization expected by the callers, and adjust the aggregation accordingly.
+ */
+enum schedutil_type {
+ FREQUENCY_UTIL,
+ ENERGY_UTIL,
+};
+
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+ unsigned long max, enum schedutil_type type);
+
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+ unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+
+ return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL);
+}
+
static inline unsigned long cpu_bw_dl(struct rq *rq)
{
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -2233,6 +2263,11 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
{
return READ_ONCE(rq->avg_rt.util_avg);
}
+#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+ return cfs;
+}
#endif
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
@@ -2262,3 +2297,13 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned
return util;
}
#endif
+
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+#define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus)))
+#else
+#define perf_domain_span(pd) NULL
+#endif
+
+#ifdef CONFIG_SMP
+extern struct static_key_false sched_energy_present;
+#endif
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8d7f15ba5916..3f35ba1d8fde 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -201,6 +201,199 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
return 1;
}
+DEFINE_STATIC_KEY_FALSE(sched_energy_present);
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+DEFINE_MUTEX(sched_energy_mutex);
+bool sched_energy_update;
+
+static void free_pd(struct perf_domain *pd)
+{
+ struct perf_domain *tmp;
+
+ while (pd) {
+ tmp = pd->next;
+ kfree(pd);
+ pd = tmp;
+ }
+}
+
+static struct perf_domain *find_pd(struct perf_domain *pd, int cpu)
+{
+ while (pd) {
+ if (cpumask_test_cpu(cpu, perf_domain_span(pd)))
+ return pd;
+ pd = pd->next;
+ }
+
+ return NULL;
+}
+
+static struct perf_domain *pd_init(int cpu)
+{
+ struct em_perf_domain *obj = em_cpu_get(cpu);
+ struct perf_domain *pd;
+
+ if (!obj) {
+ if (sched_debug())
+ pr_info("%s: no EM found for CPU%d\n", __func__, cpu);
+ return NULL;
+ }
+
+ pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+ if (!pd)
+ return NULL;
+ pd->em_pd = obj;
+
+ return pd;
+}
+
+static void perf_domain_debug(const struct cpumask *cpu_map,
+ struct perf_domain *pd)
+{
+ if (!sched_debug() || !pd)
+ return;
+
+ printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
+
+ while (pd) {
+ printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+ cpumask_first(perf_domain_span(pd)),
+ cpumask_pr_args(perf_domain_span(pd)),
+ em_pd_nr_cap_states(pd->em_pd));
+ pd = pd->next;
+ }
+
+ printk(KERN_CONT "\n");
+}
+
+static void destroy_perf_domain_rcu(struct rcu_head *rp)
+{
+ struct perf_domain *pd;
+
+ pd = container_of(rp, struct perf_domain, rcu);
+ free_pd(pd);
+}
+
+static void sched_energy_set(bool has_eas)
+{
+ if (!has_eas && static_branch_unlikely(&sched_energy_present)) {
+ if (sched_debug())
+ pr_info("%s: stopping EAS\n", __func__);
+ static_branch_disable_cpuslocked(&sched_energy_present);
+ } else if (has_eas && !static_branch_unlikely(&sched_energy_present)) {
+ if (sched_debug())
+ pr_info("%s: starting EAS\n", __func__);
+ static_branch_enable_cpuslocked(&sched_energy_present);
+ }
+}
+
+/*
+ * EAS can be used on a root domain if it meets all the following conditions:
+ * 1. an Energy Model (EM) is available;
+ * 2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
+ * 3. the EM complexity is low enough to keep scheduling overheads low;
+ * 4. schedutil is driving the frequency of all CPUs of the rd;
+ *
+ * The complexity of the Energy Model is defined as:
+ *
+ * C = nr_pd * (nr_cpus + nr_cs)
+ *
+ * with parameters defined as:
+ * - nr_pd: the number of performance domains
+ * - nr_cpus: the number of CPUs
+ * - nr_cs: the sum of the number of capacity states of all performance
+ * domains (for example, on a system with 2 performance domains,
+ * with 10 capacity states each, nr_cs = 2 * 10 = 20).
+ *
+ * It is generally not a good idea to use such a model in the wake-up path on
+ * very complex platforms because of the associated scheduling overheads. The
+ * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
+ * with per-CPU DVFS and less than 8 capacity states each, for example.
+ */
+#define EM_MAX_COMPLEXITY 2048
+
+extern struct cpufreq_governor schedutil_gov;
+static bool build_perf_domains(const struct cpumask *cpu_map)
+{
+ int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
+ struct perf_domain *pd = NULL, *tmp;
+ int cpu = cpumask_first(cpu_map);
+ struct root_domain *rd = cpu_rq(cpu)->rd;
+ struct cpufreq_policy *policy;
+ struct cpufreq_governor *gov;
+
+ /* EAS is enabled for asymmetric CPU capacity topologies. */
+ if (!per_cpu(sd_asym_cpucapacity, cpu)) {
+ if (sched_debug()) {
+ pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n",
+ cpumask_pr_args(cpu_map));
+ }
+ goto free;
+ }
+
+ for_each_cpu(i, cpu_map) {
+ /* Skip already covered CPUs. */
+ if (find_pd(pd, i))
+ continue;
+
+ /* Do not attempt EAS if schedutil is not being used. */
+ policy = cpufreq_cpu_get(i);
+ if (!policy)
+ goto free;
+ gov = policy->governor;
+ cpufreq_cpu_put(policy);
+ if (gov != &schedutil_gov) {
+ if (rd->pd)
+ pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n",
+ cpumask_pr_args(cpu_map));
+ goto free;
+ }
+
+ /* Create the new pd and add it to the local list. */
+ tmp = pd_init(i);
+ if (!tmp)
+ goto free;
+ tmp->next = pd;
+ pd = tmp;
+
+ /*
+ * Count performance domains and capacity states for the
+ * complexity check.
+ */
+ nr_pd++;
+ nr_cs += em_pd_nr_cap_states(pd->em_pd);
+ }
+
+ /* Bail out if the Energy Model complexity is too high. */
+ if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+ WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
+ cpumask_pr_args(cpu_map));
+ goto free;
+ }
+
+ perf_domain_debug(cpu_map, pd);
+
+ /* Attach the new list of performance domains to the root domain. */
+ tmp = rd->pd;
+ rcu_assign_pointer(rd->pd, pd);
+ if (tmp)
+ call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+
+ return !!pd;
+
+free:
+ free_pd(pd);
+ tmp = rd->pd;
+ rcu_assign_pointer(rd->pd, NULL);
+ if (tmp)
+ call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+
+ return false;
+}
+#else
+static void free_pd(struct perf_domain *pd) { }
+#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/
+
static void free_rootdomain(struct rcu_head *rcu)
{
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
@@ -211,6 +404,7 @@ static void free_rootdomain(struct rcu_head *rcu)
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
+ free_pd(rd->pd);
kfree(rd);
}
@@ -397,7 +591,8 @@ DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
static void update_top_cache_domain(int cpu)
@@ -423,7 +618,10 @@ static void update_top_cache_domain(int cpu)
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
- rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+ rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd);
+
+ sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY);
+ rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd);
}
/*
@@ -1133,7 +1331,6 @@ sd_init(struct sched_domain_topology_level *tl,
.last_balance = jiffies,
.balance_interval = sd_weight,
- .smt_gain = 0,
.max_newidle_lb_cost = 0,
.next_decay_max_lb_cost = jiffies,
.child = child,
@@ -1164,7 +1361,6 @@ sd_init(struct sched_domain_topology_level *tl,
if (sd->flags & SD_SHARE_CPUCAPACITY) {
sd->imbalance_pct = 110;
- sd->smt_gain = 1178; /* ~15% */
} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
sd->imbalance_pct = 117;
@@ -1934,6 +2130,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
+ bool __maybe_unused has_eas = false;
int i, j, n;
int new_topology;
@@ -1961,8 +2158,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
/* Destroy deleted domains: */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_cur[i], doms_new[j])
- && dattrs_equal(dattr_cur, i, dattr_new, j))
+ if (cpumask_equal(doms_cur[i], doms_new[j]) &&
+ dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
/* No match - a current sched domain not in new doms_new[] */
@@ -1982,8 +2179,8 @@ match1:
/* Build new domains: */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(doms_new[i], doms_cur[j])
- && dattrs_equal(dattr_new, i, dattr_cur, j))
+ if (cpumask_equal(doms_new[i], doms_cur[j]) &&
+ dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
/* No match - add a new doms_new */
@@ -1992,6 +2189,24 @@ match2:
;
}
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+ /* Build perf. domains: */
+ for (i = 0; i < ndoms_new; i++) {
+ for (j = 0; j < n && !sched_energy_update; j++) {
+ if (cpumask_equal(doms_new[i], doms_cur[j]) &&
+ cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) {
+ has_eas = true;
+ goto match3;
+ }
+ }
+ /* No match - add perf. domains for a new rd */
+ has_eas |= build_perf_domains(doms_new[i]);
+match3:
+ ;
+ }
+ sched_energy_set(has_eas);
+#endif
+
/* Remember the new sched domains: */
if (doms_cur != &fallback_doms)
free_sched_domains(doms_cur, ndoms_cur);
diff --git a/kernel/sys.c b/kernel/sys.c
index 123bd73046ec..64b5a230f38d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -121,6 +121,9 @@
#ifndef SVE_GET_VL
# define SVE_GET_VL() (-EINVAL)
#endif
+#ifndef PAC_RESET_KEYS
+# define PAC_RESET_KEYS(a, b) (-EINVAL)
+#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
@@ -2476,6 +2479,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
break;
+ case PR_PAC_RESET_KEYS:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = PAC_RESET_KEYS(me, arg2);
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index fa5de5e8de61..2c97e8c2d29f 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Alarmtimer interface
*
@@ -10,10 +11,6 @@
* Copyright (C) 2010 IBM Corperation
*
* Author: John Stultz <john.stultz@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/time.h>
#include <linux/hrtimer.h>
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 8c0e4092f661..5e77662dd2d9 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/clockevents.c
- *
* This file contains functions which manage clock event devices.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/clockchips.h>
@@ -39,10 +35,8 @@ static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
u64 clc = (u64) latch << evt->shift;
u64 rnd;
- if (unlikely(!evt->mult)) {
+ if (WARN_ON(!evt->mult))
evt->mult = 1;
- WARN_ON(1);
- }
rnd = (u64) evt->mult - 1;
/*
@@ -164,10 +158,8 @@ void clockevents_switch_state(struct clock_event_device *dev,
* on it, so fix it up and emit a warning:
*/
if (clockevent_state_oneshot(dev)) {
- if (unlikely(!dev->mult)) {
+ if (WARN_ON(!dev->mult))
dev->mult = 1;
- WARN_ON(1);
- }
}
}
}
@@ -315,10 +307,8 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
int64_t delta;
int rc;
- if (unlikely(expires < 0)) {
- WARN_ON_ONCE(1);
+ if (WARN_ON_ONCE(expires < 0))
return -ETIME;
- }
dev->next_event = expires;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index ffe081623aec..3bcc19ceb073 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -1,26 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * linux/kernel/time/clocksource.c
- *
* This file contains the functions which manage clocksource drivers.
*
* Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * TODO WishList:
- * o Allow clocksource drivers to be unregistered
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 9cdd74bd2d27..f5cfa1b73d6f 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1,34 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/hrtimer.c
- *
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
*
* High-resolution kernel timers
*
- * In contrast to the low-resolution timeout API implemented in
- * kernel/timer.c, hrtimers provide finer resolution and accuracy
- * depending on system configuration and capabilities.
- *
- * These timers are currently used for:
- * - itimers
- * - POSIX timers
- * - nanosleep
- * - precise in-kernel timing
+ * In contrast to the low-resolution timeout API, aka timer wheel,
+ * hrtimers provide finer resolution and accuracy depending on system
+ * configuration and capabilities.
*
* Started by: Thomas Gleixner and Ingo Molnar
*
* Credits:
- * based on kernel/timer.c
+ * Based on the original timer wheel code
*
* Help, testing, suggestions, bugfixes, improvements were
* provided by:
*
* George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
* et. al.
- *
- * For licencing details see kernel-base/COPYING
*/
#include <linux/cpu.h>
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 9a65713c8309..02068b2d5862 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/itimer.c
- *
* Copyright (C) 1992 Darren Senn
*/
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 497719127bf9..dc1b6f1929f9 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -1,25 +1,9 @@
-/***********************************************************************
-* linux/kernel/time/jiffies.c
-*
-* This file contains the jiffies based clocksource.
-*
-* Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
-*
-* This program is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation; either version 2 of the License, or
-* (at your option) any later version.
-*
-* This program is distributed in the hope that it will be useful,
-* but WITHOUT ANY WARRANTY; without even the implied warranty of
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-* GNU General Public License for more details.
-*
-* You should have received a copy of the GNU General Public License
-* along with this program; if not, write to the Free Software
-* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-*
-************************************************************************/
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * This file contains the jiffies based clocksource.
+ *
+ * Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
+ */
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/module.h>
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index c5e0cba3b39c..bc3a3c37ec9c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -17,7 +17,6 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/rtc.h>
-#include <linux/math64.h>
#include "ntp_internal.h"
#include "timekeeping_internal.h"
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index fe56c4e06c51..425bbfce6819 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * posix-clock.c - support for dynamic clock devices
+ * Support for dynamic clock devices
*
* Copyright (C) 2010 OMICRON electronics GmbH
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/device.h>
#include <linux/export.h>
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 989ccf028bde..a51895486e5e 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Dummy stubs used when CONFIG_POSIX_TIMERS=n
*
* Created by: Nicolas Pitre, July 2016
* Copyright: (C) 2016 Linaro Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/linkage.h>
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 31f49ae80f43..0e84bb72a3da 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1,34 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * linux/kernel/posix-timers.c
- *
- *
* 2002-10-15 Posix Clocks & timers
* by George Anzinger george@mvista.com
- *
* Copyright (C) 2002 2003 by MontaVista Software.
*
* 2004-06-01 Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug.
* Copyright (C) 2004 Boris Hu
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or (at
- * your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
-
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * MontaVista Software | 1237 East Arques Avenue | Sunnyvale | CA 94085 | USA
- */
-
-/* These are all the functions necessary to implement
- * POSIX clocks & timers
+ * These are all the functions necessary to implement POSIX clocks & timers
*/
#include <linux/mm.h>
#include <linux/interrupt.h>
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index cbc72c2c1fca..094b82ca95e5 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * sched_clock.c: Generic sched_clock() support, to extend low level
- * hardware time counters to full 64-bit ns values.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Generic sched_clock() support, to extend low level hardware time
+ * counters to full 64-bit ns values.
*/
#include <linux/clocksource.h>
#include <linux/init.h>
diff --git a/kernel/time/test_udelay.c b/kernel/time/test_udelay.c
index b0928ab3270f..77c63005dc4e 100644
--- a/kernel/time/test_udelay.c
+++ b/kernel/time/test_udelay.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* udelay() test kernel module
*
@@ -7,15 +8,6 @@
* Specifying usecs of 0 or negative values will run multiples tests.
*
* Copyright (C) 2014 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#include <linux/debugfs.h>
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index a59641fb88b6..5be6154e2fd2 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -1,8 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-broadcast-hrtimer.c
- * This file emulates a local clock event device
- * via a pseudo clock device.
+ * Emulate a local clock event device via a pseudo clock device.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index be0aac2b4300..803fa67aace9 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-broadcast.c
- *
* This file contains functions which emulate a local clock-event
* device via a broadcast event source.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 14de3727b18e..529143b4c8d2 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-common.c
- *
* This file contains the base functions to manage periodic tick
* related events.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 6fe615d57ebb..f9745d47425a 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-oneshot.c
- *
* This file contains functions which manage high resolution tick
* related events.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
- *
- * This code is licenced under the GPL version 2. For details see
- * kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 69e673b88474..6fa52cd6df0b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/tick-sched.c
- *
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
@@ -8,8 +7,6 @@
* No idle tick implementation for low and high resolution timers
*
* Started by: Thomas Gleixner and Ingo Molnar
- *
- * Distribute under GPLv2.
*/
#include <linux/cpu.h>
#include <linux/err.h>
diff --git a/kernel/time/time.c b/kernel/time/time.c
index ad204cf6d001..5aa0a156e331 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -1,14 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time.c
- *
* Copyright (C) 1991, 1992 Linus Torvalds
*
- * This file contains the interface functions for the various
- * time related system calls: time, stime, gettimeofday, settimeofday,
- * adjtime
- */
-/*
- * Modification history kernel/time.c
+ * This file contains the interface functions for the various time related
+ * system calls: time, stime, gettimeofday, settimeofday, adjtime
+ *
+ * Modification history:
*
* 1993-09-02 Philip Gladstone
* Created file with time related functions from sched/core.c and adjtimex()
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
index f83bbb81600b..7ed0e0fb5831 100644
--- a/kernel/time/timeconst.bc
+++ b/kernel/time/timeconst.bc
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
scale=0
define gcd(a,b) {
diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c
index 7142580ad94f..589e0a552129 100644
--- a/kernel/time/timeconv.c
+++ b/kernel/time/timeconv.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: LGPL-2.0+
/*
* Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
* This file is part of the GNU C Library.
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
index 8afd78932bdf..85b98e727306 100644
--- a/kernel/time/timecounter.c
+++ b/kernel/time/timecounter.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
- * linux/kernel/time/timecounter.c
- *
- * based on code that migrated away from
- * linux/kernel/time/clocksource.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
+ * Based on clocksource code. See commit 74d23cc704d1
*/
-
#include <linux/export.h>
#include <linux/timecounter.h>
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2d110c948805..c801e25875a3 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/time/timekeeping.c
- *
- * Kernel timekeeping code and accessor functions
- *
- * This code was moved from linux/kernel/timer.c.
- * Please see that file for copyright and history logs.
- *
+ * Kernel timekeeping code and accessor functions. Based on code from
+ * timer.c, moved in commit 8524070b7982.
*/
-
#include <linux/timekeeper_internal.h>
#include <linux/module.h>
#include <linux/interrupt.h>
@@ -50,7 +45,9 @@ enum timekeeping_adv_mode {
static struct {
seqcount_t seq;
struct timekeeper timekeeper;
-} tk_core ____cacheline_aligned;
+} tk_core ____cacheline_aligned = {
+ .seq = SEQCNT_ZERO(tk_core.seq),
+};
static DEFINE_RAW_SPINLOCK(timekeeper_lock);
static struct timekeeper shadow_timekeeper;
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 238e4be60229..86489950d690 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -1,17 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* debugfs file to track time spent in suspend
*
* Copyright (c) 2011, Google, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
*/
#include <linux/debugfs.h>
@@ -28,7 +19,7 @@
static unsigned int sleep_time_bin[NUM_BINS] = {0};
-static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
+static int tk_debug_sleep_time_show(struct seq_file *s, void *data)
{
unsigned int bin;
seq_puts(s, " time (secs) count\n");
@@ -42,18 +33,7 @@ static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
}
return 0;
}
-
-static int tk_debug_sleep_time_open(struct inode *inode, struct file *file)
-{
- return single_open(file, tk_debug_show_sleep_time, NULL);
-}
-
-static const struct file_operations tk_debug_sleep_time_fops = {
- .open = tk_debug_sleep_time_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(tk_debug_sleep_time);
static int __init tk_debug_sleep_time_init(void)
{
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index fa49cd753dea..444156debfa0 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/timer.c
- *
* Kernel internal timers
*
* Copyright (C) 1991, 1992 Linus Torvalds
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index d647dabdac97..98ba50dcb1b2 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * kernel/time/timer_list.c
- *
* List pending timers
*
* Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#include <linux/proc_fs.h>
diff --git a/kernel/torture.c b/kernel/torture.c
index 17d91f5fba2a..bbf6d473e50c 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -194,11 +194,23 @@ torture_onoff(void *arg)
int cpu;
int maxcpu = -1;
DEFINE_TORTURE_RANDOM(rand);
+ int ret;
VERBOSE_TOROUT_STRING("torture_onoff task started");
for_each_online_cpu(cpu)
maxcpu = cpu;
WARN_ON(maxcpu < 0);
+ if (!IS_MODULE(CONFIG_TORTURE_TEST))
+ for_each_possible_cpu(cpu) {
+ if (cpu_online(cpu))
+ continue;
+ ret = cpu_up(cpu);
+ if (ret && verbose) {
+ pr_alert("%s" TORTURE_FLAG
+ "%s: Initial online %d: errno %d\n",
+ __func__, torture_type, cpu, ret);
+ }
+ }
if (maxcpu == 0) {
VERBOSE_TOROUT_STRING("Only one CPU, so CPU-hotplug testing is disabled");
@@ -233,16 +245,15 @@ stop:
*/
int torture_onoff_init(long ooholdoff, long oointerval)
{
- int ret = 0;
-
#ifdef CONFIG_HOTPLUG_CPU
onoff_holdoff = ooholdoff;
onoff_interval = oointerval;
if (onoff_interval <= 0)
return 0;
- ret = torture_create_kthread(torture_onoff, NULL, onoff_task);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
- return ret;
+ return torture_create_kthread(torture_onoff, NULL, onoff_task);
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+ return 0;
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
}
EXPORT_SYMBOL_GPL(torture_onoff_init);
@@ -513,15 +524,13 @@ static int torture_shutdown(void *arg)
*/
int torture_shutdown_init(int ssecs, void (*cleanup)(void))
{
- int ret = 0;
-
torture_shutdown_hook = cleanup;
if (ssecs > 0) {
shutdown_time = ktime_add(ktime_get(), ktime_set(ssecs, 0));
- ret = torture_create_kthread(torture_shutdown, NULL,
+ return torture_create_kthread(torture_shutdown, NULL,
shutdown_task);
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL_GPL(torture_shutdown_init);
@@ -620,13 +629,10 @@ static int torture_stutter(void *arg)
/*
* Initialize and kick off the torture_stutter kthread.
*/
-int torture_stutter_init(int s)
+int torture_stutter_init(const int s)
{
- int ret;
-
stutter = s;
- ret = torture_create_kthread(torture_stutter, NULL, stutter_task);
- return ret;
+ return torture_create_kthread(torture_stutter, NULL, stutter_task);
}
EXPORT_SYMBOL_GPL(torture_stutter_init);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e23eb9fc77aa..f0ff24173a0b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -173,7 +173,7 @@ static void ftrace_sync(struct work_struct *work)
{
/*
* This function is just a stub to implement a hard force
- * of synchronize_sched(). This requires synchronizing
+ * of synchronize_rcu(). This requires synchronizing
* tasks even in userspace and idle.
*
* Yes, function tracing is rude.
@@ -934,7 +934,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
ftrace_profile_enabled = 0;
/*
* unregister_ftrace_profiler calls stop_machine
- * so this acts like an synchronize_sched.
+ * so this acts like an synchronize_rcu.
*/
unregister_ftrace_profiler();
}
@@ -1086,7 +1086,7 @@ struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr)
/*
* Some of the ops may be dynamically allocated,
- * they are freed after a synchronize_sched().
+ * they are freed after a synchronize_rcu().
*/
preempt_disable_notrace();
@@ -1286,7 +1286,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
{
if (!hash || hash == EMPTY_HASH)
return;
- call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
+ call_rcu(&hash->rcu, __free_ftrace_hash_rcu);
}
void ftrace_free_filter(struct ftrace_ops *ops)
@@ -1501,7 +1501,7 @@ static bool hash_contains_ip(unsigned long ip,
* the ip is not in the ops->notrace_hash.
*
* This needs to be called with preemption disabled as
- * the hashes are freed with call_rcu_sched().
+ * the hashes are freed with call_rcu().
*/
static int
ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
@@ -4496,7 +4496,7 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
if (ftrace_enabled && !ftrace_hash_empty(hash))
ftrace_run_modify_code(&probe->ops, FTRACE_UPDATE_CALLS,
&old_hash_ops);
- synchronize_sched();
+ synchronize_rcu();
hlist_for_each_entry_safe(entry, tmp, &hhd, hlist) {
hlist_del(&entry->hlist);
@@ -5314,7 +5314,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
mutex_unlock(&graph_lock);
/* Wait till all users are no longer using the old hash */
- synchronize_sched();
+ synchronize_rcu();
free_ftrace_hash(old_hash);
}
@@ -5708,7 +5708,7 @@ void ftrace_release_mod(struct module *mod)
list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) {
if (mod_map->mod == mod) {
list_del_rcu(&mod_map->list);
- call_rcu_sched(&mod_map->rcu, ftrace_free_mod_map);
+ call_rcu(&mod_map->rcu, ftrace_free_mod_map);
break;
}
}
@@ -5928,7 +5928,7 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
struct ftrace_mod_map *mod_map;
const char *ret = NULL;
- /* mod_map is freed via call_rcu_sched() */
+ /* mod_map is freed via call_rcu() */
preempt_disable();
list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
ret = ftrace_func_address_lookup(mod_map, addr, size, off, sym);
@@ -6263,7 +6263,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
/*
* Some of the ops may be dynamically allocated,
- * they must be freed after a synchronize_sched().
+ * they must be freed after a synchronize_rcu().
*/
preempt_disable_notrace();
@@ -6434,7 +6434,7 @@ static void clear_ftrace_pids(struct trace_array *tr)
rcu_assign_pointer(tr->function_pids, NULL);
/* Wait till all users are no longer using pid filtering */
- synchronize_sched();
+ synchronize_rcu();
trace_free_pid_list(pid_list);
}
@@ -6581,7 +6581,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf,
rcu_assign_pointer(tr->function_pids, pid_list);
if (filtered_pids) {
- synchronize_sched();
+ synchronize_rcu();
trace_free_pid_list(filtered_pids);
} else if (pid_list) {
/* Register a probe to set whether to ignore the tracing of a task */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 65bd4616220d..4f3247a53259 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1834,7 +1834,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
* There could have been a race between checking
* record_disable and incrementing it.
*/
- synchronize_sched();
+ synchronize_rcu();
for_each_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
rb_check_pages(cpu_buffer);
@@ -3151,7 +3151,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
* This prevents all writes to the buffer. Any attempt to write
* to the buffer after this will fail and return NULL.
*
- * The caller should call synchronize_sched() after this.
+ * The caller should call synchronize_rcu() after this.
*/
void ring_buffer_record_disable(struct ring_buffer *buffer)
{
@@ -3253,7 +3253,7 @@ bool ring_buffer_record_is_set_on(struct ring_buffer *buffer)
* This prevents all writes to the buffer. Any attempt to write
* to the buffer after this will fail and return NULL.
*
- * The caller should call synchronize_sched() after this.
+ * The caller should call synchronize_rcu() after this.
*/
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
{
@@ -4191,7 +4191,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
void
ring_buffer_read_prepare_sync(void)
{
- synchronize_sched();
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
@@ -4363,7 +4363,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
atomic_inc(&cpu_buffer->record_disabled);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -4496,7 +4496,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
goto out;
/*
- * We can't do a synchronize_sched here because this
+ * We can't do a synchronize_rcu here because this
* function can be called in atomic context.
* Normally this will be called from the same CPU as cpu.
* If not it's up to the caller to protect this.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ff1c4b20cd0a..51612b4a603f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1681,7 +1681,7 @@ void tracing_reset(struct trace_buffer *buf, int cpu)
ring_buffer_record_disable(buffer);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
ring_buffer_reset_cpu(buffer, cpu);
ring_buffer_record_enable(buffer);
@@ -1698,7 +1698,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf)
ring_buffer_record_disable(buffer);
/* Make sure all commits have finished */
- synchronize_sched();
+ synchronize_rcu();
buf->time_start = buffer_ftrace_now(buf, buf->cpu);
@@ -2250,7 +2250,7 @@ void trace_buffered_event_disable(void)
preempt_enable();
/* Wait for all current users to finish */
- synchronize_sched();
+ synchronize_rcu();
for_each_tracing_cpu(cpu) {
free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
@@ -5398,7 +5398,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
if (tr->current_trace->reset)
tr->current_trace->reset(tr);
- /* Current trace needs to be nop_trace before synchronize_sched */
+ /* Current trace needs to be nop_trace before synchronize_rcu */
tr->current_trace = &nop_trace;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5412,7 +5412,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
* The update_max_tr is called from interrupts disabled
* so a synchronized_sched() is sufficient.
*/
- synchronize_sched();
+ synchronize_rcu();
free_snapshot(tr);
}
#endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 5574e862de8d..27821480105e 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1616,7 +1616,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
/*
* The calls can still be using the old filters.
- * Do a synchronize_sched() and to ensure all calls are
+ * Do a synchronize_rcu() and to ensure all calls are
* done with them before we free them.
*/
tracepoint_synchronize_unregister();
@@ -1848,7 +1848,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir,
if (filter) {
/*
* No event actually uses the system filter
- * we can free it without synchronize_sched().
+ * we can free it without synchronize_rcu().
*/
__free_filter(system->filter);
system->filter = filter;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index fec67188c4d2..adc153ab51c0 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -333,7 +333,7 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
* event_call related objects, which will be accessed in
* the kprobe_trace_func/kretprobe_trace_func.
*/
- synchronize_sched();
+ synchronize_rcu();
kfree(link); /* Ignored if link == NULL */
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index a3be42304485..46f2ab1e08a9 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -92,7 +92,7 @@ static __init int release_early_probes(void)
while (early_probes) {
tmp = early_probes;
early_probes = tmp->next;
- call_rcu_sched(tmp, rcu_free_old_probes);
+ call_rcu(tmp, rcu_free_old_probes);
}
return 0;
@@ -123,7 +123,7 @@ static inline void release_probes(struct tracepoint_func *old)
* cover both cases. So let us chain the SRCU and sched RCU
* callbacks to wait for both grace periods.
*/
- call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
+ call_rcu(&tp_probes->rcu, rcu_free_old_probes);
}
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0280deac392e..392be4b252f6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3396,7 +3396,7 @@ static void put_unbound_pool(struct worker_pool *pool)
del_timer_sync(&pool->mayday_timer);
/* sched-RCU protected to allow dereferences from get_work_pool() */
- call_rcu_sched(&pool->rcu, rcu_free_pool);
+ call_rcu(&pool->rcu, rcu_free_pool);
}
/**
@@ -3503,14 +3503,14 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
put_unbound_pool(pool);
mutex_unlock(&wq_pool_mutex);
- call_rcu_sched(&pwq->rcu, rcu_free_pwq);
+ call_rcu(&pwq->rcu, rcu_free_pwq);
/*
* If we're the last pwq going away, @wq is already dead and no one
* is gonna access it anymore. Schedule RCU free.
*/
if (is_last)
- call_rcu_sched(&wq->rcu, rcu_free_wq);
+ call_rcu(&wq->rcu, rcu_free_wq);
}
/**
@@ -4195,7 +4195,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
* The base ref is never dropped on per-cpu pwqs. Directly
* schedule RCU free.
*/
- call_rcu_sched(&wq->rcu, rcu_free_wq);
+ call_rcu(&wq->rcu, rcu_free_wq);
} else {
/*
* We're the sole accessor of @wq at this point. Directly