summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/futex.c201
-rw-r--r--kernel/locking/lockdep.c4
-rw-r--r--kernel/locking/mutex-debug.c7
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/rcu/rcu.h5
-rw-r--r--kernel/rcu/srcu.c57
-rw-r--r--kernel/rcu/torture.c75
-rw-r--r--kernel/rcu/tree.c97
-rw-r--r--kernel/rcu/tree.h12
-rw-r--r--kernel/rcu/tree_plugin.h102
-rw-r--r--kernel/rcu/tree_trace.c3
-rw-r--r--kernel/rcu/update.c5
-rw-r--r--kernel/softirq.c49
14 files changed, 495 insertions, 126 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 5721f0e..dfa736c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1172,7 +1172,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
* do not allow it to share a thread group or signal handlers or
* parent with the forking task.
*/
- if (clone_flags & (CLONE_SIGHAND | CLONE_PARENT)) {
+ if (clone_flags & CLONE_SIGHAND) {
if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
(task_active_pid_ns(current) !=
current->nsproxy->pid_ns_for_children))
diff --git a/kernel/futex.c b/kernel/futex.c
index f6ff019..1ddc449 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -63,14 +63,101 @@
#include <linux/sched/rt.h>
#include <linux/hugetlb.h>
#include <linux/freezer.h>
+#include <linux/bootmem.h>
#include <asm/futex.h>
#include "locking/rtmutex_common.h"
-int __read_mostly futex_cmpxchg_enabled;
+/*
+ * Basic futex operation and ordering guarantees:
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
+ *
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
+ *
+ * CPU 0 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ * futex_wait(futex, val);
+ * uval = *futex;
+ * *futex = newval;
+ * sys_futex(WAKE, futex);
+ * futex_wake(futex);
+ * if (queue_empty())
+ * return;
+ * if (uval == val)
+ * lock(hash_bucket(futex));
+ * queue();
+ * unlock(hash_bucket(futex));
+ * schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ *
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ * futex_wait(futex, val);
+ *
+ * waiters++;
+ * mb(); (A) <-- paired with -.
+ * |
+ * lock(hash_bucket(futex)); |
+ * |
+ * uval = *futex; |
+ * | *futex = newval;
+ * | sys_futex(WAKE, futex);
+ * | futex_wake(futex);
+ * |
+ * `-------> mb(); (B)
+ * if (uval == val)
+ * queue();
+ * unlock(hash_bucket(futex));
+ * schedule(); if (waiters)
+ * lock(hash_bucket(futex));
+ * wake_waiters(futex);
+ * unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read -- this
+ * is guaranteed by the head counter in the hb spinlock; and where (B)
+ * orders the write to futex and the waiters read -- this is done by the
+ * barriers in get_futex_key_refs(), through either ihold or atomic_inc,
+ * depending on the futex type.
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ * X = Y = 0
+ *
+ * w[X]=1 w[Y]=1
+ * MB MB
+ * r[Y]=y r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
+ */
-#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
+int __read_mostly futex_cmpxchg_enabled;
/*
* Futex flags used to encode options to functions and preserve them across
@@ -149,9 +236,41 @@ static const struct futex_q futex_q_init = {
struct futex_hash_bucket {
spinlock_t lock;
struct plist_head chain;
-};
+} ____cacheline_aligned_in_smp;
-static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
+static unsigned long __read_mostly futex_hashsize;
+
+static struct futex_hash_bucket *futex_queues;
+
+static inline void futex_get_mm(union futex_key *key)
+{
+ atomic_inc(&key->private.mm->mm_count);
+ /*
+ * Ensure futex_get_mm() implies a full barrier such that
+ * get_futex_key() implies a full barrier. This is relied upon
+ * as full barrier (B), see the ordering comment above.
+ */
+ smp_mb__after_atomic_inc();
+}
+
+static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+ /*
+ * Tasks trying to enter the critical region are most likely
+ * potential waiters that will be added to the plist. Ensure
+ * that wakers won't miss to-be-slept tasks in the window between
+ * the wait call and the actual plist_add.
+ */
+ if (spin_is_locked(&hb->lock))
+ return true;
+ smp_rmb(); /* Make sure we check the lock state first */
+
+ return !plist_head_empty(&hb->chain);
+#else
+ return true;
+#endif
+}
/*
* We hash on the keys returned from get_futex_key (see below).
@@ -161,7 +280,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
u32 hash = jhash2((u32*)&key->both.word,
(sizeof(key->both.word)+sizeof(key->both.ptr))/4,
key->both.offset);
- return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
+ return &futex_queues[hash & (futex_hashsize - 1)];
}
/*
@@ -187,10 +306,10 @@ static void get_futex_key_refs(union futex_key *key)
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
- ihold(key->shared.inode);
+ ihold(key->shared.inode); /* implies MB (B) */
break;
case FUT_OFF_MMSHARED:
- atomic_inc(&key->private.mm->mm_count);
+ futex_get_mm(key); /* implies MB (B) */
break;
}
}
@@ -264,7 +383,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
if (!fshared) {
key->private.mm = mm;
key->private.address = address;
- get_futex_key_refs(key);
+ get_futex_key_refs(key); /* implies MB (B) */
return 0;
}
@@ -371,7 +490,7 @@ again:
key->shared.pgoff = basepage_index(page);
}
- get_futex_key_refs(key);
+ get_futex_key_refs(key); /* implies MB (B) */
out:
unlock_page(page_head);
@@ -598,13 +717,10 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
{
struct futex_pi_state *pi_state = NULL;
struct futex_q *this, *next;
- struct plist_head *head;
struct task_struct *p;
pid_t pid = uval & FUTEX_TID_MASK;
- head = &hb->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (match_futex(&this->key, key)) {
/*
* Another waiter already exists - bump up
@@ -986,7 +1102,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
int ret;
@@ -998,10 +1113,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
goto out;
hb = hash_futex(&key);
+
+ /* Make sure we really have tasks to wakeup */
+ if (!hb_waiters_pending(hb))
+ goto out_put_key;
+
spin_lock(&hb->lock);
- head = &hb->chain;
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (match_futex (&this->key, &key)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1019,6 +1138,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
}
spin_unlock(&hb->lock);
+out_put_key:
put_futex_key(&key);
out:
return ret;
@@ -1034,7 +1154,6 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
struct futex_hash_bucket *hb1, *hb2;
- struct plist_head *head;
struct futex_q *this, *next;
int ret, op_ret;
@@ -1082,9 +1201,7 @@ retry_private:
goto retry;
}
- head = &hb1->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb1->chain, list) {
if (match_futex (&this->key, &key1)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1097,10 +1214,8 @@ retry_private:
}
if (op_ret > 0) {
- head = &hb2->chain;
-
op_ret = 0;
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb2->chain, list) {
if (match_futex (&this->key, &key2)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1270,7 +1385,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
int drop_count = 0, task_count = 0, ret;
struct futex_pi_state *pi_state = NULL;
struct futex_hash_bucket *hb1, *hb2;
- struct plist_head *head1;
struct futex_q *this, *next;
u32 curval2;
@@ -1393,8 +1507,7 @@ retry_private:
}
}
- head1 = &hb1->chain;
- plist_for_each_entry_safe(this, next, head1, list) {
+ plist_for_each_entry_safe(this, next, &hb1->chain, list) {
if (task_count - nr_wake >= nr_requeue)
break;
@@ -1489,12 +1602,12 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
hb = hash_futex(&q->key);
q->lock_ptr = &hb->lock;
- spin_lock(&hb->lock);
+ spin_lock(&hb->lock); /* implies MB (A) */
return hb;
}
static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+queue_unlock(struct futex_hash_bucket *hb)
__releases(&hb->lock)
{
spin_unlock(&hb->lock);
@@ -1867,7 +1980,7 @@ retry_private:
ret = get_futex_value_locked(&uval, uaddr);
if (ret) {
- queue_unlock(q, *hb);
+ queue_unlock(*hb);
ret = get_user(uval, uaddr);
if (ret)
@@ -1881,7 +1994,7 @@ retry_private:
}
if (uval != val) {
- queue_unlock(q, *hb);
+ queue_unlock(*hb);
ret = -EWOULDBLOCK;
}
@@ -2029,7 +2142,7 @@ retry_private:
* Task is exiting and we just wait for the
* exit to complete.
*/
- queue_unlock(&q, hb);
+ queue_unlock(hb);
put_futex_key(&q.key);
cond_resched();
goto retry;
@@ -2081,7 +2194,7 @@ retry_private:
goto out_put_key;
out_unlock_put_key:
- queue_unlock(&q, hb);
+ queue_unlock(hb);
out_put_key:
put_futex_key(&q.key);
@@ -2091,7 +2204,7 @@ out:
return ret != -EINTR ? ret : -ERESTARTNOINTR;
uaddr_faulted:
- queue_unlock(&q, hb);
+ queue_unlock(hb);
ret = fault_in_user_writeable(uaddr);
if (ret)
@@ -2113,7 +2226,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
u32 uval, vpid = task_pid_vnr(current);
int ret;
@@ -2153,9 +2265,7 @@ retry:
* Ok, other tasks may need to be woken up - check waiters
* and do the wakeup if necessary:
*/
- head = &hb->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (!match_futex (&this->key, &key))
continue;
ret = wake_futex_pi(uaddr, uval, this);
@@ -2734,8 +2844,21 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
static int __init futex_init(void)
{
u32 curval;
- int i;
+ unsigned int futex_shift;
+ unsigned long i;
+
+#if CONFIG_BASE_SMALL
+ futex_hashsize = 16;
+#else
+ futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
+ futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
+ futex_hashsize, 0,
+ futex_hashsize < 256 ? HASH_SMALL : 0,
+ &futex_shift, NULL,
+ futex_hashsize, futex_hashsize);
+ futex_hashsize = 1UL << futex_shift;
/*
* This will fail and we want it. Some arch implementations do
* runtime detection of the futex_atomic_cmpxchg_inatomic()
@@ -2749,7 +2872,7 @@ static int __init futex_init(void)
if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
futex_cmpxchg_enabled = 1;
- for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
+ for (i = 0; i < futex_hashsize; i++) {
plist_head_init(&futex_queues[i].chain);
spin_lock_init(&futex_queues[i].lock);
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 576ba75..eb8a547 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
/*
* Is this the address of a static object:
*/
+#ifdef __KERNEL__
static int static_obj(void *obj)
{
unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
*/
return is_module_address(addr) || is_module_percpu_address(addr);
}
+#endif
/*
* To make lock name printouts unique, we calculate a unique
@@ -4115,6 +4117,7 @@ void debug_check_no_locks_held(void)
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
+#ifdef __KERNEL__
void debug_show_all_locks(void)
{
struct task_struct *g, *p;
@@ -4172,6 +4175,7 @@ retry:
read_unlock(&tasklist_lock);
}
EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
/*
* Careful: only use this function if you are sure that
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443f..faf6f5b 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -75,7 +75,12 @@ void debug_mutex_unlock(struct mutex *lock)
return;
DEBUG_LOCKS_WARN_ON(lock->magic != lock);
- DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
+ if (!lock->owner)
+ DEBUG_LOCKS_WARN_ON(!lock->owner);
+ else
+ DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
mutex_clear_owner(lock);
}
diff --git a/kernel/panic.c b/kernel/panic.c
index c00b4ce..6d63003 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,7 +33,7 @@ static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
-int panic_timeout;
+int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7859a0a..79c3877 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -96,19 +96,22 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-extern void kfree(const void *);
+void kfree(const void *);
static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
{
unsigned long offset = (unsigned long)head->func;
+ rcu_lock_acquire(&rcu_callback_map);
if (__is_kfree_rcu_offset(offset)) {
RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
kfree((void *)head - offset);
+ rcu_lock_release(&rcu_callback_map);
return 1;
} else {
RCU_TRACE(trace_rcu_invoke_callback(rn, head));
head->func(head);
+ rcu_lock_release(&rcu_callback_map);
return 0;
}
}
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 01d5ccb..3318d82 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -363,6 +363,29 @@ static void srcu_flip(struct srcu_struct *sp)
/*
* Enqueue an SRCU callback on the specified srcu_struct structure,
* initiating grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section. On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu(). It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * 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 *head,
void (*func)(struct rcu_head *head))
@@ -459,7 +482,30 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
* Note that it is illegal to call synchronize_srcu() from the corresponding
* SRCU read-side critical section; doing so will result in deadlock.
* However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu(). In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU read-side critical section. Note that these
+ * guarantees include CPUs that are offline, idle, or executing in user mode,
+ * as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_srcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_srcu(). This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
*/
void synchronize_srcu(struct srcu_struct *sp)
{
@@ -476,12 +522,8 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
* Wait for an SRCU grace period to elapse, but be more aggressive about
* spinning rather than blocking when waiting.
*
- * Note that it is also illegal to call synchronize_srcu_expedited()
- * from the corresponding SRCU read-side critical section;
- * doing so will result in deadlock. However, it is perfectly legal
- * to call synchronize_srcu_expedited() on one srcu_struct from some
- * other srcu_struct's read-side critical section, as long as
- * the resulting graph of srcu_structs is acyclic.
+ * 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)
{
@@ -491,6 +533,7 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
/**
* srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
*/
void srcu_barrier(struct srcu_struct *sp)
{
diff --git a/kernel/rcu/torture.c b/kernel/rcu/torture.c
index 3929cd4..732f8ae 100644
--- a/kernel/rcu/torture.c
+++ b/kernel/rcu/torture.c
@@ -139,8 +139,6 @@ MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
#define VERBOSE_PRINTK_ERRSTRING(s) \
do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
-static char printk_buf[4096];
-
static int nrealreaders;
static struct task_struct *writer_task;
static struct task_struct **fakewriter_tasks;
@@ -376,7 +374,7 @@ struct rcu_torture_ops {
void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
void (*cb_barrier)(void);
void (*fqs)(void);
- int (*stats)(char *page);
+ void (*stats)(char *page);
int irq_capable;
int can_boost;
const char *name;
@@ -578,21 +576,19 @@ static void srcu_torture_barrier(void)
srcu_barrier(&srcu_ctl);
}
-static int srcu_torture_stats(char *page)
+static void srcu_torture_stats(char *page)
{
- int cnt = 0;
int cpu;
int idx = srcu_ctl.completed & 0x1;
- cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
+ page += sprintf(page, "%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
- cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
+ page += sprintf(page, " %d(%lu,%lu)", cpu,
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
}
- cnt += sprintf(&page[cnt], "\n");
- return cnt;
+ sprintf(page, "\n");
}
static void srcu_torture_synchronize_expedited(void)
@@ -1052,10 +1048,9 @@ rcu_torture_reader(void *arg)
/*
* Create an RCU-torture statistics message in the specified buffer.
*/
-static int
+static void
rcu_torture_printk(char *page)
{
- int cnt = 0;
int cpu;
int i;
long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
@@ -1071,8 +1066,8 @@ rcu_torture_printk(char *page)
if (pipesummary[i] != 0)
break;
}
- cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt],
+ page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page,
"rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
rcu_torture_current,
rcu_torture_current_version,
@@ -1080,53 +1075,52 @@ rcu_torture_printk(char *page)
atomic_read(&n_rcu_torture_alloc),
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free));
- cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ",
+ page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
atomic_read(&n_rcu_torture_mberror),
n_rcu_torture_boost_ktrerror,
n_rcu_torture_boost_rterror);
- cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ",
+ page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
n_rcu_torture_timers);
- cnt += sprintf(&page[cnt],
+ page += sprintf(page,
"onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
n_online_successes, n_online_attempts,
n_offline_successes, n_offline_attempts,
min_online, max_online,
min_offline, max_offline,
sum_online, sum_offline, HZ);
- cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
+ page += sprintf(page, "barrier: %ld/%ld:%ld",
n_barrier_successes,
n_barrier_attempts,
n_rcu_torture_barrier_error);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
if (atomic_read(&n_rcu_torture_mberror) != 0 ||
n_rcu_torture_barrier_error != 0 ||
n_rcu_torture_boost_ktrerror != 0 ||
n_rcu_torture_boost_rterror != 0 ||
n_rcu_torture_boost_failure != 0 ||
i > 1) {
- cnt += sprintf(&page[cnt], "!!! ");
+ page += sprintf(page, "!!! ");
atomic_inc(&n_rcu_torture_error);
WARN_ON_ONCE(1);
}
- cnt += sprintf(&page[cnt], "Reader Pipe: ");
+ page += sprintf(page, "Reader Pipe: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
- cnt += sprintf(&page[cnt], " %ld", pipesummary[i]);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt], "Reader Batch: ");
+ page += sprintf(page, " %ld", pipesummary[i]);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "Reader Batch: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
- cnt += sprintf(&page[cnt], " %ld", batchsummary[i]);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt], "Free-Block Circulation: ");
+ page += sprintf(page, " %ld", batchsummary[i]);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "Free-Block Circulation: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
- cnt += sprintf(&page[cnt], " %d",
+ page += sprintf(page, " %d",
atomic_read(&rcu_torture_wcount[i]));
}
- cnt += sprintf(&page[cnt], "\n");
+ page += sprintf(page, "\n");
if (cur_ops->stats)
- cnt += cur_ops->stats(&page[cnt]);
- return cnt;
+ cur_ops->stats(page);
}
/*
@@ -1140,10 +1134,17 @@ rcu_torture_printk(char *page)
static void
rcu_torture_stats_print(void)
{
- int cnt;
+ int size = nr_cpu_ids * 200 + 8192;
+ char *buf;
- cnt = rcu_torture_printk(printk_buf);
- pr_alert("%s", printk_buf);
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf) {
+ pr_err("rcu-torture: Out of memory, need: %d", size);
+ return;
+ }
+ rcu_torture_printk(buf);
+ pr_alert("%s", buf);
+ kfree(buf);
}
/*
@@ -1578,6 +1579,7 @@ static int rcu_torture_barrier_cbs(void *arg)
{
long myid = (long)arg;
bool lastphase = 0;
+ bool newphase;
struct rcu_head rcu;
init_rcu_head_on_stack(&rcu);
@@ -1585,10 +1587,11 @@ static int rcu_torture_barrier_cbs(void *arg)
set_user_nice(current, 19);
do {
wait_event(barrier_cbs_wq[myid],
- barrier_phase != lastphase ||
+ (newphase =
+ ACCESS_ONCE(barrier_phase)) != lastphase ||
kthread_should_stop() ||
fullstop != FULLSTOP_DONTSTOP);
- lastphase = barrier_phase;
+ lastphase = newphase;
smp_mb(); /* ensure barrier_phase load before ->call(). */
if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
break;
@@ -1625,7 +1628,7 @@ static int rcu_torture_barrier(void *arg)
if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
break;
n_barrier_attempts++;
- cur_ops->cb_barrier();
+ cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
n_rcu_torture_barrier_error++;
WARN_ON_ONCE(1);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd08198..b3d116c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -369,6 +369,9 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
bool user)
{
+ struct rcu_state *rsp;
+ struct rcu_data *rdp;
+
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
@@ -380,6 +383,10 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
}
+ for_each_rcu_flavor(rsp) {
+ rdp = this_cpu_ptr(rsp->rda);
+ do_nocb_deferred_wakeup(rdp);
+ }
rcu_prepare_for_idle(smp_processor_id());
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
smp_mb__before_atomic_inc(); /* See above. */
@@ -411,11 +418,12 @@ static void rcu_eqs_enter(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
- if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+ if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
- else
+ rcu_eqs_enter_common(rdtp, oldval, user);
+ } else {
rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
- rcu_eqs_enter_common(rdtp, oldval, user);
+ }
}
/**
@@ -533,11 +541,12 @@ static void rcu_eqs_exit(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(oldval < 0);
- if (oldval & DYNTICK_TASK_NEST_MASK)
+ if (oldval & DYNTICK_TASK_NEST_MASK) {
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
- else
+ } else {
rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
- rcu_eqs_exit_common(rdtp, oldval, user);
+ rcu_eqs_exit_common(rdtp, oldval, user);
+ }
}
/**
@@ -716,7 +725,7 @@ bool rcu_lockdep_current_cpu_online(void)
bool ret;
if (in_nmi())
- return 1;
+ return true;
preempt_disable();
rdp = this_cpu_ptr(&rcu_sched_data);
rnp = rdp->mynode;
@@ -755,6 +764,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
}
/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
+/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
* idle state since the last call to dyntick_save_progress_counter()
@@ -812,16 +827,34 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
*/
rcu_kick_nohz_cpu(rdp->cpu);
+ /*
+ * Alternatively, the CPU might be running in the kernel
+ * for an extended period of time without a quiescent state.
+ * Attempt to force the CPU through the scheduler to gain the
+ * needed quiescent state, but only if the grace period has gone
+ * on for an uncommonly long time. If there are many stuck CPUs,
+ * we will beat on the first one until it gets unstuck, then move
+ * to the next. Only do this for the primary flavor of RCU.
+ */
+ if (rdp->rsp == rcu_state &&
+ ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+ rdp->rsp->jiffies_resched += 5;
+ resched_cpu(rdp->cpu);
+ }
+
return 0;
}
static void record_gp_stall_check_time(struct rcu_state *rsp)
{
unsigned long j = ACCESS_ONCE(jiffies);
+ unsigned long j1;
rsp->gp_start = j;
smp_wmb(); /* Record start time before stall time. */
- rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
+ j1 = rcu_jiffies_till_stall_check();
+ rsp->jiffies_stall = j + j1;
+ rsp->jiffies_resched = j + j1 / 2;
}
/*
@@ -1133,8 +1166,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
* hold it, acquire the root rcu_node structure's lock in order to
* start one (if needed).
*/
- if (rnp != rnp_root)
+ if (rnp != rnp_root) {
raw_spin_lock(&rnp_root->lock);
+ smp_mb__after_unlock_lock();
+ }
/*
* Get a new grace-period number. If there really is no grace
@@ -1354,6 +1389,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
local_irq_restore(flags);
return;
}
+ smp_mb__after_unlock_lock();
__note_gp_changes(rsp, rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
@@ -1368,6 +1404,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
rcu_bind_gp_kthread();
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
if (rsp->gp_flags == 0) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq(&rnp->lock);
@@ -1409,6 +1446,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rdp = this_cpu_ptr(rsp->rda);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
@@ -1463,6 +1501,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
/* Clear flag to prevent immediate re-entry. */
if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
raw_spin_unlock_irq(&rnp->lock);
}
@@ -1480,6 +1519,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
struct rcu_node *rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
gp_duration = jiffies - rsp->gp_start;
if (gp_duration > rsp->gp_max)
rsp->gp_max = gp_duration;
@@ -1505,16 +1545,19 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
ACCESS_ONCE(rnp->completed) = rsp->gpnum;
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
__note_gp_changes(rsp, rnp, rdp);
+ /* smp_mb() provided by prior unlock-lock pair. */
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched();
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rcu_nocb_gp_set(rnp, nocb);
rsp->completed = rsp->gpnum; /* Declare grace period done. */
@@ -1553,6 +1596,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
wait_event_interruptible(rsp->gp_wq,
ACCESS_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
+ /* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
cond_resched();
@@ -1582,6 +1626,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
(!ACCESS_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp)),
j);
+ /* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
if (!ACCESS_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
@@ -1749,6 +1794,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
WARN_ON_ONCE(rnp_c->qsmask);
}
@@ -1778,6 +1824,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
rnp->completed == rnp->gpnum) {
@@ -1901,13 +1948,13 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
* Adopt the RCU callbacks from the specified rcu_state structure's
* orphanage. The caller must hold the ->orphan_lock.
*/
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
{
int i;
struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
- if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+ if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
return;
/* Do the accounting first. */
@@ -1986,12 +2033,13 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
- rcu_adopt_orphan_cbs(rsp);
+ rcu_adopt_orphan_cbs(rsp, flags);
/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
mask = rdp->grpmask; /* rnp->grplo is constant. */
do {
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rnp->qsmaskinit &= ~mask;
if (rnp->qsmaskinit != 0) {
if (rnp != rdp->mynode)
@@ -2202,6 +2250,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
cond_resched();
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (!rcu_gp_in_progress(rsp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
@@ -2231,6 +2280,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
rnp = rcu_get_root(rsp);
if (rnp->qsmask == 0) {
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
}
}
@@ -2263,6 +2313,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
/* Reached the root of the rcu_node tree, acquire lock. */
raw_spin_lock_irqsave(&rnp_old->lock, flags);
+ smp_mb__after_unlock_lock();
raw_spin_unlock(&rnp_old->fqslock);
if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
rsp->n_force_qs_lh++;
@@ -2303,6 +2354,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
/* If there are callbacks ready, invoke them. */
if (cpu_has_callbacks_ready_to_invoke(rdp))
invoke_rcu_callbacks(rsp, rdp);
+
+ /* Do any needed deferred wakeups of rcuo kthreads. */
+ do_nocb_deferred_wakeup(rdp);
}
/*
@@ -2378,6 +2432,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
struct rcu_node *rnp_root = rcu_get_root(rsp);
raw_spin_lock(&rnp_root->lock);
+ smp_mb__after_unlock_lock();
rcu_start_gp(rsp);
raw_spin_unlock(&rnp_root->lock);
} else {
@@ -2437,7 +2492,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
if (cpu != -1)
rdp = per_cpu_ptr(rsp->rda, cpu);
- offline = !__call_rcu_nocb(rdp, head, lazy);
+ offline = !__call_rcu_nocb(rdp, head, lazy, flags);
WARN_ON_ONCE(offline);
/* _call_rcu() is illegal on offline CPU; leak the callback. */
local_irq_restore(flags);
@@ -2757,6 +2812,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
/* Check for CPU stalls, if enabled. */
check_cpu_stall(rsp, rdp);
+ /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
+ if (rcu_nohz_full_cpu(rsp))
+ return 0;
+
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rcu_scheduler_fully_active &&
rdp->qs_pending && !rdp->passed_quiesce) {
@@ -2790,6 +2849,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
return 1;
}
+ /* Does this CPU need a deferred NOCB wakeup? */
+ if (rcu_nocb_need_deferred_wakeup(rdp)) {
+ rdp->n_rp_nocb_defer_wakeup++;
+ return 1;
+ }
+
/* nothing to do */
rdp->n_rp_need_nothing++;
return 0;
@@ -3214,9 +3279,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
- for (i = rcu_num_lvls - 1; i > 0; i--)
+ rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+ for (i = rcu_num_lvls - 2; i >= 0; i--)
rsp->levelspread[i] = CONFIG_RCU_FANOUT;
- rsp->levelspread[0] = rcu_fanout_leaf;
}
#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
static void __init rcu_init_levelspread(struct rcu_state *rsp)
@@ -3346,6 +3411,8 @@ static void __init rcu_init_geometry(void)
if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
+ pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
+ rcu_fanout_leaf, nr_cpu_ids);
/*
* Compute number of nodes that can be handled an rcu_node tree
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 52be957..8c19873 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -317,6 +317,7 @@ struct rcu_data {
unsigned long n_rp_cpu_needs_gp;
unsigned long n_rp_gp_completed;
unsigned long n_rp_gp_started;
+ unsigned long n_rp_nocb_defer_wakeup;
unsigned long n_rp_need_nothing;
/* 6) _rcu_barrier() and OOM callbacks. */
@@ -335,6 +336,7 @@ struct rcu_data {
int nocb_p_count_lazy; /* (approximate). */
wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */
struct task_struct *nocb_kthread;
+ bool nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/* 8) RCU CPU stall data. */
@@ -453,6 +455,8 @@ struct rcu_state {
/* but in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
+ unsigned long jiffies_resched; /* Time at which to resched */
+ /* a reluctant CPU. */
unsigned long gp_max; /* Maximum GP duration in */
/* jiffies. */
const char *name; /* Name of structure. */
@@ -548,9 +552,12 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
static void rcu_init_one_nocb(struct rcu_node *rnp);
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy);
+ bool lazy, unsigned long flags);
static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp);
+ struct rcu_data *rdp,
+ unsigned long flags);
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
static void rcu_kick_nohz_cpu(int cpu);
@@ -564,6 +571,7 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
unsigned long maxj);
static void rcu_bind_gp_kthread(void);
static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
#endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 08a7652..6e2ef4b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -204,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
t->rcu_blocked_node = rnp;
@@ -312,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
}
@@ -361,10 +363,14 @@ void rcu_read_unlock_special(struct task_struct *t)
special = t->rcu_read_unlock_special;
if (special & RCU_READ_UNLOCK_NEED_QS) {
rcu_preempt_qs(smp_processor_id());
+ if (!t->rcu_read_unlock_special) {
+ local_irq_restore(flags);
+ return;
+ }
}
- /* Hardware IRQ handlers cannot block. */
- if (in_irq() || in_serving_softirq()) {
+ /* Hardware IRQ handlers cannot block, complain if they get here. */
+ if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
local_irq_restore(flags);
return;
}
@@ -381,6 +387,7 @@ void rcu_read_unlock_special(struct task_struct *t)
for (;;) {
rnp = t->rcu_blocked_node;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
if (rnp == t->rcu_blocked_node)
break;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -605,6 +612,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
while (!list_empty(lp)) {
t = list_entry(lp->next, typeof(*t), rcu_node_entry);
raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
list_del(&t->rcu_node_entry);
t->rcu_blocked_node = rnp_root;
list_add(&t->rcu_node_entry, lp_root);
@@ -629,6 +637,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
* in this case.
*/
raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
if (rnp_root->boost_tasks != NULL &&
rnp_root->boost_tasks != rnp_root->gp_tasks &&
rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -772,6 +781,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
unsigned long mask;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
for (;;) {
if (!sync_rcu_preempt_exp_done(rnp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -779,14 +789,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
}
if (rnp->parent == NULL) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- if (wake)
+ if (wake) {
+ smp_mb(); /* EGP done before wake_up(). */
wake_up(&sync_rcu_preempt_exp_wq);
+ }
break;
}
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
rnp = rnp->parent;
raw_spin_lock(&rnp->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
rnp->expmask &= ~mask;
}
}
@@ -806,6 +819,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
int must_wait = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (list_empty(&rnp->blkd_tasks)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
} else {
@@ -886,6 +900,7 @@ void synchronize_rcu_expedited(void)
/* Initialize ->expmask for all non-leaf rcu_node structures. */
rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rnp->expmask = rnp->qsmaskinit;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
@@ -1191,6 +1206,7 @@ static int rcu_boost(struct rcu_node *rnp)
return 0; /* Nothing left to boost. */
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
/*
* Recheck under the lock: all tasks in need of boosting
@@ -1377,6 +1393,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
if (IS_ERR(t))
return PTR_ERR(t);
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rnp->boost_kthread_task = t;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
sp.sched_priority = RCU_BOOST_PRIO;
@@ -1769,6 +1786,7 @@ static void rcu_prepare_for_idle(int cpu)
continue;
rnp = rdp->mynode;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rcu_accelerate_cbs(rsp, rnp, rdp);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
@@ -1852,6 +1870,7 @@ static int rcu_oom_notify(struct notifier_block *self,
/* Wait for callbacks from earlier instance to complete. */
wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0);
+ smp_mb(); /* Ensure callback reuse happens after callback invocation. */
/*
* Prevent premature wakeup: ensure that all increments happen
@@ -2101,7 +2120,8 @@ bool rcu_is_nocb_cpu(int cpu)
static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
struct rcu_head *rhp,
struct rcu_head **rhtp,
- int rhcount, int rhcount_lazy)
+ int rhcount, int rhcount_lazy,
+ unsigned long flags)
{
int len;
struct rcu_head **old_rhpp;
@@ -2122,9 +2142,16 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
}
len = atomic_long_read(&rdp->nocb_q_count);
if (old_rhpp == &rdp->nocb_head) {
- wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+ if (!irqs_disabled_flags(flags)) {
+ wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WakeEmpty"));
+ } else {
+ rdp->nocb_defer_wakeup = true;
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WakeEmptyIsDeferred"));
+ }
rdp->qlen_last_fqs_check = 0;
- trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
} else if (len > rdp->qlen_last_fqs_check + qhimark) {
wake_up_process(t); /* ... or if many callbacks queued. */
rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2145,12 +2172,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
* "rcuo" kthread can find it.
*/
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy)
+ bool lazy, unsigned long flags)
{
if (!rcu_is_nocb_cpu(rdp->cpu))
return 0;
- __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+ __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
if (__is_kfree_rcu_offset((unsigned long)rhp->func))
trace_rcu_kfree_callback(rdp->rsp->name, rhp,
(unsigned long)rhp->func,
@@ -2168,7 +2195,8 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
* not a no-CBs CPU.
*/
static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp)
+ struct rcu_data *rdp,
+ unsigned long flags)
{
long ql = rsp->qlen;
long qll = rsp->qlen_lazy;
@@ -2182,14 +2210,14 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
/* First, enqueue the donelist, if any. This preserves CB ordering. */
if (rsp->orphan_donelist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
- rsp->orphan_donetail, ql, qll);
+ rsp->orphan_donetail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_donelist = NULL;
rsp->orphan_donetail = &rsp->orphan_donelist;
}
if (rsp->orphan_nxtlist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
- rsp->orphan_nxttail, ql, qll);
+ rsp->orphan_nxttail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_nxtlist = NULL;
rsp->orphan_nxttail = &rsp->orphan_nxtlist;
@@ -2209,6 +2237,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
struct rcu_node *rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
c = rcu_start_future_gp(rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -2250,6 +2279,7 @@ static int rcu_nocb_kthread(void *arg)
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("Sleep"));
wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+ /* Memory barrier provide by xchg() below. */
} else if (firsttime) {
firsttime = 0;
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
@@ -2310,6 +2340,22 @@ static int rcu_nocb_kthread(void *arg)
return 0;
}
+/* Is a deferred wakeup of rcu_nocb_kthread() required? */
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+ return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+}
+
+/* Do a deferred wakeup of rcu_nocb_kthread(). */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+ if (!rcu_nocb_need_deferred_wakeup(rdp))
+ return;
+ ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
+ wake_up(&rdp->nocb_wq);
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+}
+
/* Initialize per-rcu_data variables for no-CBs CPUs. */
static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
{
@@ -2365,13 +2411,14 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
}
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy)
+ bool lazy, unsigned long flags)
{
return 0;
}
static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp)
+ struct rcu_data *rdp,
+ unsigned long flags)
{
return 0;
}
@@ -2380,6 +2427,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
{
}
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+ return false;
+}
+
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+}
+
static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
{
}
@@ -2829,3 +2885,23 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
}
#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+/*
+ * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
+ * grace-period kthread will do force_quiescent_state() processing?
+ * The idea is to avoid waking up RCU core processing on such a
+ * CPU unless the grace period has extended for too long.
+ *
+ * This code relies on the fact that all NO_HZ_FULL CPUs are also
+ * CONFIG_RCU_NOCB_CPUs.
+ */
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ if (tick_nohz_full_cpu(smp_processor_id()) &&
+ (!rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
+ return 1;
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
+ return 0;
+}
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 3596797..4def475 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -364,9 +364,10 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
rdp->n_rp_report_qs,
rdp->n_rp_cb_ready,
rdp->n_rp_cpu_needs_gp);
- seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
+ seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n",
rdp->n_rp_gp_completed,
rdp->n_rp_gp_started,
+ rdp->n_rp_nocb_defer_wakeup,
rdp->n_rp_need_nothing);
}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 6cb3dff..802365c 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -128,6 +128,11 @@ struct lockdep_map rcu_sched_lock_map =
STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
+static struct lock_class_key rcu_callback_key;
+struct lockdep_map rcu_callback_map =
+ STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
+EXPORT_SYMBOL_GPL(rcu_callback_map);
+
int notrace debug_lockdep_rcu_enabled(void)
{
return rcu_scheduler_active && debug_locks &&
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025cc..9a4500e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -211,14 +211,48 @@ EXPORT_SYMBOL(local_bh_enable_ip);
#define MAX_SOFTIRQ_TIME msecs_to_jiffies(2)
#define MAX_SOFTIRQ_RESTART 10
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+
+static inline bool lockdep_softirq_start(void)
+{
+ bool in_hardirq = false;
+
+ if (trace_hardirq_context(current)) {
+ in_hardirq = true;
+ trace_hardirq_exit();
+ }
+
+ lockdep_softirq_enter();
+
+ return in_hardirq;
+}
+
+static inline void lockdep_softirq_end(bool in_hardirq)
+{
+ lockdep_softirq_exit();
+
+ if (in_hardirq)
+ trace_hardirq_enter();
+}
+#else
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
+#endif
+
asmlinkage void __do_softirq(void)
{
- struct softirq_action *h;
- __u32 pending;
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
- int cpu;
unsigned long old_flags = current->flags;
int max_restart = MAX_SOFTIRQ_RESTART;
+ struct softirq_action *h;
+ bool in_hardirq;
+ __u32 pending;
+ int cpu;
/*
* Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -231,7 +265,7 @@ asmlinkage void __do_softirq(void)
account_irq_enter_time(current);
__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
- lockdep_softirq_enter();
+ in_hardirq = lockdep_softirq_start();
cpu = smp_processor_id();
restart:
@@ -278,16 +312,13 @@ restart:
wakeup_softirqd();
}
- lockdep_softirq_exit();
-
+ lockdep_softirq_end(in_hardirq);
account_irq_exit_time(current);
__local_bh_enable(SOFTIRQ_OFFSET);
WARN_ON_ONCE(in_interrupt());
tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
-
-
asmlinkage void do_softirq(void)
{
__u32 pending;
@@ -375,13 +406,13 @@ void irq_exit(void)
#endif
account_irq_exit_time(current);
- trace_hardirq_exit();
preempt_count_sub(HARDIRQ_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
tick_irq_exit();
rcu_irq_exit();
+ trace_hardirq_exit(); /* must be last! */
}
/*
OpenPOWER on IntegriCloud