x86/paravirt: Trace contended_release on unlock

On PARAVIRT_SPINLOCKS=y kernels queued_spin_unlock() is dispatched
through a static_call(). Those PARAVIRT_SPINLOCKS=y kernels are quite
popular. Gating contended_release behind a static branch would leave a
NOP on the unlock hot path even, when the tracepoint is disabled.

Since the static_call() is already present, swap its target to a traced
unlock, when the tracepoint is enabled instead. When contended_release
tracepoint is disabled the target is the plain unlock (an inline store
on native x86_64), so the unlock path is unchanged and the tracepoint is
truly zero-cost.

Provide two traced variants, native_queued_spin_unlock_traced() and
pv_queued_spin_unlock_traced(), so each tail-calls its own base unlock
directly rather than recursing through the now-traced static_call().

Teach pv_is_native_spin_unlock() that the traced native variant still
counts as native.

Only PARAVIRT_SPINLOCKS=y is affected. PARAVIRT_SPINLOCKS=n keeps the
generic static-branch path.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juergen Gross <jgross@suse.com>
Link: https://patch.msgid.link/17fa67f9fa4cf93f1150725e89f5f916e41a9b6f.1785778551.git.d@ilvokhin.com

2 files changed, 53 insertions, 2 deletions

diff --git a/arch/x86/include/asm/paravirt-spinlock.h b/arch/x86/include/asm/paravirt-spinlock.h
index ff735830de4a..302bc2ba3a75 100644
--- a/arch/x86/include/asm/paravirt-spinlock.h
+++ b/arch/x86/include/asm/paravirt-spinlock.h
@@ -99,6 +99,8 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 
 void __init native_pv_lock_init(void);
 __visible void __native_queued_spin_unlock(struct qspinlock *lock);
+__visible void native_queued_spin_unlock_traced(struct qspinlock *lock);
+__visible void pv_queued_spin_unlock_traced(struct qspinlock *lock);
 bool pv_is_native_spin_unlock(void);
 __visible bool __native_vcpu_is_preempted(long cpu);
 bool pv_is_native_vcpu_is_preempted(void);
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index ddc19dc28ba1..ca12b3655307 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -7,6 +7,7 @@
 #include <linux/spinlock.h>
 #include <linux/export.h>
 #include <linux/jump_label.h>
+#include <trace/events/lock.h>
 
 DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key);
 
@@ -30,10 +31,58 @@ EXPORT_STATIC_CALL_TRAMP(queued_spin_lock_slowpath);
 DEFINE_STATIC_CALL(queued_spin_unlock, __raw_callee_save___native_queued_spin_unlock);
 EXPORT_STATIC_CALL_TRAMP(queued_spin_unlock);
 
+/*
+ * Traced unlock variants, swapped in via static_call while the
+ * contended_release tracepoint is enabled. Two of them, so each tail calls its
+ * own base directly.
+ */
+__visible void native_queued_spin_unlock_traced(struct qspinlock *lock)
+{
+	if (queued_spin_is_contended(lock))
+		trace_call__contended_release(lock);
+	native_queued_spin_unlock(lock);
+}
+PV_CALLEE_SAVE_REGS_THUNK(native_queued_spin_unlock_traced);
+
+__visible void pv_queued_spin_unlock_traced(struct qspinlock *lock)
+{
+	if (queued_spin_is_contended(lock))
+		trace_call__contended_release(lock);
+	__raw_callee_save___pv_queued_spin_unlock(lock);
+}
+PV_CALLEE_SAVE_REGS_THUNK(pv_queued_spin_unlock_traced);
+
 bool pv_is_native_spin_unlock(void)
 {
-	return static_call_query(queued_spin_unlock) ==
-		__raw_callee_save___native_queued_spin_unlock;
+	void *unlock = static_call_query(queued_spin_unlock);
+
+	return unlock == __raw_callee_save___native_queued_spin_unlock ||
+	       unlock == __raw_callee_save_native_queued_spin_unlock_traced;
+}
+
+int arch_contended_release_trace_reg(void)
+{
+	void *cur = static_call_query(queued_spin_unlock);
+
+	if (cur == __raw_callee_save___native_queued_spin_unlock)
+		static_call_update(queued_spin_unlock,
+				   __raw_callee_save_native_queued_spin_unlock_traced);
+	else if (cur == __raw_callee_save___pv_queued_spin_unlock)
+		static_call_update(queued_spin_unlock,
+				   __raw_callee_save_pv_queued_spin_unlock_traced);
+	return 0;
+}
+
+void arch_contended_release_trace_unreg(void)
+{
+	void *cur = static_call_query(queued_spin_unlock);
+
+	if (cur == __raw_callee_save_native_queued_spin_unlock_traced)
+		static_call_update(queued_spin_unlock,
+				   __raw_callee_save___native_queued_spin_unlock);
+	else if (cur == __raw_callee_save_pv_queued_spin_unlock_traced)
+		static_call_update(queued_spin_unlock,
+				   __raw_callee_save___pv_queued_spin_unlock);
 }
 
 __visible bool __native_vcpu_is_preempted(long cpu)