Contributors: 15
Author Tokens Token Proportion Commits Commit Proportion
Peter Zijlstra 290 51.79% 1 4.55%
Jason Low 130 23.21% 3 13.64%
Tim Chen 30 5.36% 1 4.55%
Pan Xinhui 29 5.18% 1 4.55%
Davidlohr Bueso A 21 3.75% 3 13.64%
Waiman Long 20 3.57% 2 9.09%
David Laight 18 3.21% 2 9.09%
Ingo Molnar 5 0.89% 2 9.09%
Qian Cai 4 0.71% 1 4.55%
Prateek Sood 4 0.71% 1 4.55%
Will Deacon 2 0.36% 1 4.55%
Clark Williams 2 0.36% 1 4.55%
Uros Bizjak 2 0.36% 1 4.55%
Christian Bornträger 2 0.36% 1 4.55%
Greg Kroah-Hartman 1 0.18% 1 4.55%
Total 560 22 
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234
// SPDX-License-Identifier: GPL-2.0
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/osq_lock.h>

/*
 * An MCS like lock especially tailored for optimistic spinning for sleeping
 * lock implementations (mutex, rwsem, etc).
 *
 * Using a single mcs node per CPU is safe because sleeping locks should not be
 * called from interrupt context and we have preemption disabled while
 * spinning.
 */

struct optimistic_spin_node {
	struct optimistic_spin_node *next, *prev;
	int locked; /* 1 if lock acquired */
	int cpu; /* encoded CPU # + 1 value */
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);

/*
 * We use the value 0 to represent "no CPU", thus the encoded value
 * will be the CPU number incremented by 1.
 */
static inline int encode_cpu(int cpu_nr)
{
	return cpu_nr + 1;
}

static inline int node_cpu(struct optimistic_spin_node *node)
{
	return node->cpu - 1;
}

static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
{
	int cpu_nr = encoded_cpu_val - 1;

	return per_cpu_ptr(&osq_node, cpu_nr);
}

/*
 * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
 * Can return NULL in case we were the last queued and we updated @lock instead.
 *
 * If osq_lock() is being cancelled there must be a previous node
 * and 'old_cpu' is its CPU #.
 * For osq_unlock() there is never a previous node and old_cpu is
 * set to OSQ_UNLOCKED_VAL.
 */
static inline struct optimistic_spin_node *
osq_wait_next(struct optimistic_spin_queue *lock,
	      struct optimistic_spin_node *node,
	      int old_cpu)
{
	int curr = encode_cpu(smp_processor_id());

	for (;;) {
		if (atomic_read(&lock->tail) == curr &&
		    atomic_cmpxchg_acquire(&lock->tail, curr, old_cpu) == curr) {
			/*
			 * We were the last queued, we moved @lock back. @prev
			 * will now observe @lock and will complete its
			 * unlock()/unqueue().
			 */
			return NULL;
		}

		/*
		 * We must xchg() the @node->next value, because if we were to
		 * leave it in, a concurrent unlock()/unqueue() from
		 * @node->next might complete Step-A and think its @prev is
		 * still valid.
		 *
		 * If the concurrent unlock()/unqueue() wins the race, we'll
		 * wait for either @lock to point to us, through its Step-B, or
		 * wait for a new @node->next from its Step-C.
		 */
		if (node->next) {
			struct optimistic_spin_node *next;

			next = xchg(&node->next, NULL);
			if (next)
				return next;
		}

		cpu_relax();
	}
}

bool osq_lock(struct optimistic_spin_queue *lock)
{
	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
	struct optimistic_spin_node *prev, *next;
	int curr = encode_cpu(smp_processor_id());
	int old;

	node->locked = 0;
	node->next = NULL;
	node->cpu = curr;

	/*
	 * We need both ACQUIRE (pairs with corresponding RELEASE in
	 * unlock() uncontended, or fastpath) and RELEASE (to publish
	 * the node fields we just initialised) semantics when updating
	 * the lock tail.
	 */
	old = atomic_xchg(&lock->tail, curr);
	if (old == OSQ_UNLOCKED_VAL)
		return true;

	prev = decode_cpu(old);
	node->prev = prev;

	/*
	 * osq_lock()			unqueue
	 *
	 * node->prev = prev		osq_wait_next()
	 * WMB				MB
	 * prev->next = node		next->prev = prev // unqueue-C
	 *
	 * Here 'node->prev' and 'next->prev' are the same variable and we need
	 * to ensure these stores happen in-order to avoid corrupting the list.
	 */
	smp_wmb();

	WRITE_ONCE(prev->next, node);

	/*
	 * Normally @prev is untouchable after the above store; because at that
	 * moment unlock can proceed and wipe the node element from stack.
	 *
	 * However, since our nodes are static per-cpu storage, we're
	 * guaranteed their existence -- this allows us to apply
	 * cmpxchg in an attempt to undo our queueing.
	 */

	/*
	 * Wait to acquire the lock or cancellation. Note that need_resched()
	 * will come with an IPI, which will wake smp_cond_load_relaxed() if it
	 * is implemented with a monitor-wait. vcpu_is_preempted() relies on
	 * polling, be careful.
	 */
	if (smp_cond_load_relaxed(&node->locked, VAL || need_resched() ||
				  vcpu_is_preempted(node_cpu(node->prev))))
		return true;

	/* unqueue */
	/*
	 * Step - A  -- stabilize @prev
	 *
	 * Undo our @prev->next assignment; this will make @prev's
	 * unlock()/unqueue() wait for a next pointer since @lock points to us
	 * (or later).
	 */

	for (;;) {
		/*
		 * cpu_relax() below implies a compiler barrier which would
		 * prevent this comparison being optimized away.
		 */
		if (data_race(prev->next) == node &&
		    cmpxchg(&prev->next, node, NULL) == node)
			break;

		/*
		 * We can only fail the cmpxchg() racing against an unlock(),
		 * in which case we should observe @node->locked becoming
		 * true.
		 */
		if (smp_load_acquire(&node->locked))
			return true;

		cpu_relax();

		/*
		 * Or we race against a concurrent unqueue()'s step-B, in which
		 * case its step-C will write us a new @node->prev pointer.
		 */
		prev = READ_ONCE(node->prev);
	}

	/*
	 * Step - B -- stabilize @next
	 *
	 * Similar to unlock(), wait for @node->next or move @lock from @node
	 * back to @prev.
	 */

	next = osq_wait_next(lock, node, prev->cpu);
	if (!next)
		return false;

	/*
	 * Step - C -- unlink
	 *
	 * @prev is stable because its still waiting for a new @prev->next
	 * pointer, @next is stable because our @node->next pointer is NULL and
	 * it will wait in Step-A.
	 */

	WRITE_ONCE(next->prev, prev);
	WRITE_ONCE(prev->next, next);

	return false;
}

void osq_unlock(struct optimistic_spin_queue *lock)
{
	struct optimistic_spin_node *node, *next;
	int curr = encode_cpu(smp_processor_id());

	/*
	 * Fast path for the uncontended case.
	 */
	if (atomic_try_cmpxchg_release(&lock->tail, &curr, OSQ_UNLOCKED_VAL))
		return;

	/*
	 * Second most likely case.
	 */
	node = this_cpu_ptr(&osq_node);
	next = xchg(&node->next, NULL);
	if (next) {
		WRITE_ONCE(next->locked, 1);
		return;
	}

	next = osq_wait_next(lock, node, OSQ_UNLOCKED_VAL);
	if (next)
		WRITE_ONCE(next->locked, 1);
}