rqspinlock: Drop PV and virtualization support

Changes to rqspinlock in subsequent commits will be algorithmic
modifications, which won't remain in agreement with the implementations
of paravirt spin lock and virt_spin_lock support. These future changes
include measures for terminating waiting loops in slow path after a
certain point. While using a fair lock like qspinlock directly inside
virtual machines leads to suboptimal performance under certain
conditions, we cannot use the existing virtualization support before we
make it resilient as well.  Therefore, drop it for now.

Note that we need to drop qspinlock_stat.h, as it's only relevant in
case of CONFIG_PARAVIRT_SPINLOCKS=y, but we need to keep lock_events.h
in the includes, which was indirectly pulled in before.

Reviewed-by: Barret Rhoden <brho@google.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250316040541.108729-7-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: kkdwivedi

kernel/bpf/rqspinlock.c

@@ -11,8 +11,6 @@
  *          Peter Zijlstra <peterz@infradead.org>
  */
 
-#ifndef _GEN_PV_LOCK_SLOWPATH
-
 #include <linux/smp.h>
 #include <linux/bug.h>
 #include <linux/cpumask.h>
@@ -29,7 +27,7 @@
  * Include queued spinlock definitions and statistics code
  */
 #include "../locking/qspinlock.h"
-#include "../locking/qspinlock_stat.h"
+#include "../locking/lock_events.h"
 
 /*
  * The basic principle of a queue-based spinlock can best be understood
@@ -75,38 +73,9 @@
  * 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 qnode, rqnodes[_Q_MAX_NODES]);
 
-/*
- * Generate the native code for resilient_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 resilient_queued_spin_lock_slowpath	native_resilient_queued_spin_lock_slowpath
-#endif
-
-#endif /* _GEN_PV_LOCK_SLOWPATH */
-
 /**
  * resilient_queued_spin_lock_slowpath - acquire the queued spinlock
  * @lock: Pointer to queued spinlock structure
@@ -136,12 +105,6 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 
 	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.
@@ -212,7 +175,6 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 	 */
 queue:
 	lockevent_inc(lock_slowpath);
-pv_queue:
 	node = this_cpu_ptr(&rqnodes[0].mcs);
 	idx = node->count++;
 	tail = encode_tail(smp_processor_id(), idx);
@@ -251,7 +213,6 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 
 	node->locked = 0;
 	node->next = NULL;
-	pv_init_node(node);
 
 	/*
 	 * We touched a (possibly) cold cacheline in the per-cpu queue node;
@@ -288,7 +249,6 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 		/* Link @node into the waitqueue. */
 		WRITE_ONCE(prev->next, node);
 
-		pv_wait_node(node, prev);
 		arch_mcs_spin_lock_contended(&node->locked);
 
 		/*
@@ -312,23 +272,9 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 	 * 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:
 	 *
@@ -341,11 +287,6 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 	 */
 
 	/*
-	 * In the PV case we might already have _Q_LOCKED_VAL set, because
-	 * of lock stealing; therefore we must also allow:
-	 *
-	 * n,0,1 -> 0,0,1
-	 *
 	 * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the
 	 *       above wait condition, therefore any concurrent setting of
 	 *       PENDING will make the uncontended transition fail.
@@ -369,7 +310,6 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 		next = smp_cond_load_relaxed(&node->next, (VAL));
 
 	arch_mcs_spin_unlock_contended(&next->locked);
-	pv_kick_node(lock, next);
 
 release:
 	trace_contention_end(lock, 0);
@@ -380,32 +320,3 @@ void __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 	__this_cpu_dec(rqnodes[0].mcs.count);
 }
 EXPORT_SYMBOL_GPL(resilient_queued_spin_lock_slowpath);
-
-/*
- * Generate the paravirt code for resilient_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  resilient_queued_spin_lock_slowpath
-#define resilient_queued_spin_lock_slowpath	__pv_resilient_queued_spin_lock_slowpath
-
-#include "../locking/qspinlock_paravirt.h"
-#include "rqspinlock.c"
-
-bool nopvspin;
-static __init int parse_nopvspin(char *arg)
-{
-	nopvspin = true;
-	return 0;
-}
-early_param("nopvspin", parse_nopvspin);
-#endif