/*
* Queued spinlock
*
* 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.
*
* (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
* (C) Copyright 2013-2014,2018 Red Hat, Inc.
* (C) Copyright 2015 Intel Corp.
* (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
*
* Authors: Waiman Long <longman@redhat.com>
* Peter Zijlstra <peterz@infradead.org>
*/
#ifndef _GEN_PV_LOCK_SLOWPATH
#include <linux/smp.h>
#include <linux/bug.h>
#include <linux/cpumask.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/mutex.h>
#include <linux/prefetch.h>
#include <asm/byteorder.h>
#include <asm/qspinlock.h>
/*
* Include queued spinlock statistics code
*/
#include "qspinlock_stat.h"
/*
* The basic principle of a queue-based spinlock can best be understood
* by studying a classic queue-based spinlock implementation called the
* MCS lock. The paper below provides a good description for this kind
* of lock.
*
* http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf
*
* This queued spinlock implementation is based on the MCS lock, however to make
* it fit the 4 bytes we assume spinlock_t to be, and preserve its existing
* API, we must modify it somehow.
*
* In particular; where the traditional MCS lock consists of a tail pointer
* (8 bytes) and needs the next pointer (another 8 bytes) of its own node to
* unlock the next pending (next->locked), we compress both these: {tail,
* next->locked} into a single u32 value.
*
* Since a spinlock disables recursion of its own context and there is a limit
* to the contexts that can nest; namely: task, softirq, hardirq, nmi. As there
* are at most 4 nesting levels, it can be encoded by a 2-bit number. Now
* we can encode the tail by combining the 2-bit nesting level with the cpu
* number. With one byte for the lock value and 3 bytes for the tail, only a
* 32-bit word is now needed. Even though we only need 1 bit for the lock,
* we extend it to a full byte to achieve better performance for architectures
* that support atomic byte write.
*
* We also change the first spinner to spin on the lock bit instead of its
* node; whereby avoiding the need to carry a node from lock to unlock, and
* preserving existing lock API. This also makes the unlock code simpler and
* faster.
*
* N.B. The current implementation only supports architectures that allow
* atomic operations on smaller 8-bit and 16-bit data types.
*
*/
#include "mcs_spinlock.h"
#ifdef CONFIG_PARAVIRT_SPINLOCKS
#define MAX_NODES 8
#else
#define MAX_NODES 4
#endif
/*
* The pending bit spinning loop count.
* This heuristic is used to limit the number of lockword accesses
* made by atomic_cond_read_relaxed when waiting for the lock to
* transition out of the "== _Q_PENDING_VAL" state. We don't spin
* indefinitely because there's no guarantee that we'll make forward
* progress.
*/
#ifndef _Q_PENDING_LOOPS
#define _Q_PENDING_LOOPS 1
#endif
/*
* Per-CPU queue node structures; we can never have more than 4 nested
* contexts: task, softirq, hardirq, nmi.
*
* Exactly fits one 64-byte cacheline on a 64-bit architecture.
*
* PV doubles the storage and uses the second cacheline for PV state.
*/
static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]);
/*
* We must be able to distinguish between no-tail and the tail at 0:0,
* therefore increment the cpu number by one.
*/
static inline __pure u32 encode_tail(int cpu, int idx)
{
u32 tail;
#ifdef CONFIG_DEBUG_SPINLOCK
BUG_ON(idx > 3);
#endif
tail = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
return tail;
}
static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
{
int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
int idx = (tail & _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
return per_cpu_ptr(&mcs_nodes[idx], cpu);
}
#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
#if _Q_PENDING_BITS == 8
/**
* clear_pending - clear the pending bit.
* @lock: Pointer to queued spinlock structure
*
* *,1,* -> *,0,*
*/
static __always_inline void clear_pending(struct qspinlock *lock)
{
WRITE_ONCE(lock->pending, 0);
}
/**
* clear_pending_set_locked - take ownership and clear the pending bit.
* @lock: Pointer to queued spinlock structure
*
* *,1,0 -> *,0,1
*
* Lock stealing is not allowed if this function is used.
*/
static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
{
WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
}
/*
* xchg_tail - Put in the new queue tail code word & retrieve previous one
* @lock : Pointer to queued spinlock structure
* @tail : The new queue tail code word
* Return: The previous queue tail code word
*
* xchg(lock, tail), which heads an address dependency
*
* p,*,* -> n,*,* ; prev = xchg(lock, node)
*/
static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
{
/*
* We can use relaxed semantics since the caller ensures that the
* MCS node is properly initialized before updating the tail.
*/
return (u32)xchg_relaxed(&lock->tail,
tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
}
#else /* _Q_PENDING_BITS == 8 */
/**
* clear_pending - clear the pending bit.
* @lock: Pointer to queued spinlock structure
*
* *,1,* -> *,0,*
*/
static __always_inline void clear_pending(struct qspinlock *lock)
{
atomic_andnot(_Q_PENDING_VAL, &lock->val);
}
/**
* clear_pending_set_locked - take ownership and clear the pending bit.
* @lock: Pointer to queued spinlock structure
*
* *,1,0 -> *,0,1
*/
static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
{
atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
}
/**
* xchg_tail - Put in the new queue tail code word & retrieve previous one
* @lock : Pointer to queued spinlock structure
* @tail : The new queue tail code word
* Return: The previous queue tail code word
*
* xchg(lock, tail)
*
* p,*,* -> n,*,* ; prev = xchg(lock, node)
*/
static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
{
u32 old, new, val = atomic_read(&lock->val);
for (;;) {
new = (val & _Q_LOCKED_PENDING_MASK) | tail;
/*
* We can use relaxed semantics since the caller ensures that
* the MCS node is properly initialized before updating the
* tail.
*/
old = atomic_cmpxchg_relaxed(&lock->val, val, new);
if (old == val)
break;
val = old;
}
return old;
}
#endif /* _Q_PENDING_BITS == 8 */
/**
* queued_fetch_set_pending_acquire - fetch the whole lock value and set pending
* @lock : Pointer to queued spinlock structure
* Return: The previous lock value
*
* *,*,* -> *,1,*
*/
#ifndef queued_fetch_set_pending_acquire
static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
{
return atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
}
#endif
/**
* set_locked - Set the lock bit and own the lock
* @lock: Pointer to queued spinlock structure
*
* *,*,0 -> *,0,1
*/
static __always_inline void set_locked(struct qspinlock *lock)
{
WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
}
/*
* Generate the native code for queued_spin_unlock_slowpath(); provide NOPs for
* all the PV callbacks.
*/
static __always_inline void __pv_init_node(struct mcs_spinlock *node) { }
static __always_inline void __pv_wait_node(struct mcs_spinlock *node,
struct mcs_spinlock *prev) { }
static __always_inline void __pv_kick_node(struct qspinlock *lock,
struct mcs_spinlock *node) { }
static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
struct mcs_spinlock *node)
{ return 0; }
#define pv_enabled() false
#define pv_init_node __pv_init_node
#define pv_wait_node __pv_wait_node
#define pv_kick_node __pv_kick_node
#define pv_wait_head_or_lock __pv_wait_head_or_lock
#ifdef CONFIG_PARAVIRT_SPINLOCKS
#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
#endif
#endif /* _GEN_PV_LOCK_SLOWPATH */
/**
* queued_spin_lock_slowpath - acquire the queued spinlock
* @lock: Pointer to queued spinlock structure
* @val: Current value of the queued spinlock 32-bit word
*
* (queue tail, pending bit, lock value)
*
* fast : slow : unlock
* : :
* uncontended (0,0,0) -:--> (0,0,1) ------------------------------:--> (*,*,0)
* : | ^--------.------. / :
* : v \ \ | :
* pending : (0,1,1) +--> (0,1,0) \ | :
* : | ^--' | | :
* : v | | :
* uncontended : (n,x,y) +--> (n,0,0) --' | :
* queue : | ^--' | :
* : v | :
* contended : (*,x,y) +--> (*,0,0) ---> (*,0,1) -' :
* queue : ^--' :
*/
void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
{
struct mcs_spinlock *prev, *next, *node;
u32 old, tail;
int idx;
BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
if (pv_enabled())
goto pv_queue;
if (virt_spin_lock(lock))
return;
/*
* Wait for in-progress pending->locked hand-overs with a bounded
* number of spins so that we guarantee forward progress.
*
* 0,1,0 -> 0,0,1
*/
if (val == _Q_PENDING_VAL) {
int cnt = _Q_PENDING_LOOPS;
val = atomic_cond_read_relaxed(&lock->val,
(VAL != _Q_PENDING_VAL) || !cnt--);
}
/*
* If we observe any contention; queue.
*/
if (val & ~_Q_LOCKED_MASK)
goto queue;
/*
* trylock || pending
*
* 0,0,0 -> 0,0,1 ; trylock
* 0,0,1 -> 0,1,1 ; pending
*/
val = queued_fetch_set_pending_acquire(lock);
/*
* If we observe any contention; undo and queue.
*/
if (unlikely(val & ~_Q_LOCKED_MASK)) {
if (!(val & _Q_PENDING_MASK))
clear_pending(lock);
goto queue;
}
/*
* We're pending, wait for the owner to go away.
*
* 0,1,1 -> 0,1,0
*
* this wait loop must be a load-acquire such that we match the
* store-release that clears the locked bit and create lock
* sequentiality; this is because not all
* clear_pending_set_locked() implementations imply full
* barriers.
*/
if (val & _Q_LOCKED_MASK)
atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_MASK));
/*
* take ownership and clear the pending bit.
*
* 0,1,0 -> 0,0,1
*/
clear_pending_set_locked(lock);
qstat_inc(qstat_lock_pending, true);
return;
/*
* End of pending bit optimistic spinning and beginning of MCS
* queuing.
*/
queue:
qstat_inc(qstat_lock_slowpath, true);
pv_queue:
node = this_cpu_ptr(&mcs_nodes[0]);
idx = node->count++;
tail = encode_tail(smp_processor_id(), idx);
node += idx;
/*
* Ensure that we increment the head node->count before initialising
* the actual node. If the compiler is kind enough to reorder these
* stores, then an IRQ could overwrite our assignments.
*/
barrier();
node->locked = 0;
node->next = NULL;
pv_init_node(node);
/*
* We touched a (possibly) cold cacheline in the per-cpu queue node;
* attempt the trylock once more in the hope someone let go while we
* weren't watching.
*/
if (queued_spin_trylock(lock))
goto release;
/*
* Ensure that the initialisation of @node is complete before we
* publish the updated tail via xchg_tail() and potentially link
* @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
*/
smp_wmb();
/*
* Publish the updated tail.
* We have already touched the queueing cacheline; don't bother with
* pending stuff.
*
* p,*,* -> n,*,*
*/
old = xchg_tail(lock, tail);
next = NULL;
/*
* if there was a previous node; link it and wait until reaching the
* head of the waitqueue.
*/
if (old & _Q_TAIL_MASK) {
prev = decode_tail(old);
/* Link @node into the waitqueue. */
WRITE_ONCE(prev->next, node);
pv_wait_node(node, prev);
arch_mcs_spin_lock_contended(&node->locked);
/*
* While waiting for the MCS lock, the next pointer may have
* been set by another lock waiter. We optimistically load
* the next pointer & prefetch the cacheline for writing
* to reduce latency in the upcoming MCS unlock operation.
*/
next = READ_ONCE(node->next);
if (next)
prefetchw(next);
}
/*
* we're at the head of the waitqueue, wait for the owner & pending to
* go away.
*
* *,x,y -> *,0,0
*
* this wait loop must use a load-acquire such that we match the
* store-release that clears the locked bit and create lock
* sequentiality; this is because the set_locked() function below
* does not imply a full barrier.
*
* The PV pv_wait_head_or_lock function, if active, will acquire
* the lock and return a non-zero value. So we have to skip the
* atomic_cond_read_acquire() call. As the next PV queue head hasn't
* been designated yet, there is no way for the locked value to become
* _Q_SLOW_VAL. So both the set_locked() and the
* atomic_cmpxchg_relaxed() calls will be safe.
*
* If PV isn't active, 0 will be returned instead.
*
*/
if ((val = pv_wait_head_or_lock(lock, node)))
goto locked;
val = atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK));
locked:
/*
* claim the lock:
*
* n,0,0 -> 0,0,1 : lock, uncontended
* *,*,0 -> *,*,1 : lock, contended
*
* If the queue head is the only one in the queue (lock value == tail)
* and nobody is pending, clear the tail code and grab the lock.
* Otherwise, we only need to grab the lock.
*/
/*
* In the PV case we might already have _Q_LOCKED_VAL set.
*
* The atomic_cond_read_acquire() call above has provided the
* necessary acquire semantics required for locking.
*/
if (((val & _Q_TAIL_MASK) == tail) &&
atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
goto release; /* No contention */
/* Either somebody is queued behind us or _Q_PENDING_VAL is set */
set_locked(lock);
/*
* contended path; wait for next if not observed yet, release.
*/
if (!next)
next = smp_cond_load_relaxed(&node->next, (VAL));
arch_mcs_spin_unlock_contended(&next->locked);
pv_kick_node(lock, next);
release:
/*
* release the node
*/
__this_cpu_dec(mcs_nodes[0].count);
}
EXPORT_SYMBOL(queued_spin_lock_slowpath);
/*
* Generate the paravirt code for queued_spin_unlock_slowpath().
*/
#if !defined(_GEN_PV_LOCK_SLOWPATH) && defined(CONFIG_PARAVIRT_SPINLOCKS)
#define _GEN_PV_LOCK_SLOWPATH
#undef pv_enabled
#define pv_enabled() true
#undef pv_init_node
#undef pv_wait_node
#undef pv_kick_node
#undef pv_wait_head_or_lock
#undef queued_spin_lock_slowpath
#define queued_spin_lock_slowpath __pv_queued_spin_lock_slowpath
#include "qspinlock_paravirt.h"
#include "qspinlock.c"
#endif
