[RFC PATCH V3 0/4] RISC-V: Add PARAVIRT_SPINLOCKS support

[RFC PATCH V3 0/4] RISC-V: Add PARAVIRT_SPINLOCKS support

[guoren]

From: "Guo Ren (Alibaba DAMO Academy)" <guoren@kernel.org>

Paravirtualized spinlocks allow a unfair qspinlock to replace the
ticket-lock or native fair qspinlock implementation with something
virtualization-friendly, for example, halt the virtual CPU rather
than spinning.

You could observe the paravirt qspinlock internal work situation with
/sys/kernel/debug/tracing/trace:

ls /sys/kernel/debug/tracing/events/paravirt/
 enable   filter   pv_kick  pv_wait

echo 1 > /sys/kernel/debug/tracing/events/paravirt/enable
cat /sys/kernel/debug/tracing/trace
 entries-in-buffer/entries-written: 33927/33927   #P:12

                                _-----=> irqs-off/BH-disabled
                               / _----=> need-resched
                              | / _---=> hardirq/softirq
                              || / _--=> preempt-depth
                              ||| / _-=> migrate-disable
                              |||| /     delay
           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
              | |         |   |||||     |         |
             sh-100     [001] d..2.    28.312294: pv_wait: cpu 1 out of wfi
         <idle>-0       [000] d.h4.    28.322030: pv_kick: cpu 0 kick target cpu 1
             sh-100     [001] d..2.    30.982631: pv_wait: cpu 1 out of wfi
         <idle>-0       [000] d.h4.    30.993289: pv_kick: cpu 0 kick target cpu 1
             sh-100     [002] d..2.    44.987573: pv_wait: cpu 2 out of wfi
         <idle>-0       [000] d.h4.    44.989000: pv_kick: cpu 0 kick target cpu 2
         <idle>-0       [003] d.s3.    51.593978: pv_kick: cpu 3 kick target cpu 4
      rcu_sched-15      [004] d..2.    51.595192: pv_wait: cpu 4 out of wfi
lock_torture_wr-115     [004] ...2.    52.656482: pv_kick: cpu 4 kick target cpu 2
lock_torture_wr-113     [002] d..2.    52.659146: pv_wait: cpu 2 out of wfi
lock_torture_wr-114     [008] d..2.    52.659507: pv_wait: cpu 8 out of wfi
lock_torture_wr-114     [008] d..2.    52.663503: pv_wait: cpu 8 out of wfi
lock_torture_wr-113     [002] ...2.    52.666128: pv_kick: cpu 2 kick target cpu 8
lock_torture_wr-114     [008] d..2.    52.667261: pv_wait: cpu 8 out of wfi
lock_torture_wr-114     [009] .n.2.    53.141515: pv_kick: cpu 9 kick target cpu 11
lock_torture_wr-113     [002] d..2.    53.143339: pv_wait: cpu 2 out of wfi
lock_torture_wr-116     [007] d..2.    53.143412: pv_wait: cpu 7 out of wfi
lock_torture_wr-118     [000] d..2.    53.143457: pv_wait: cpu 0 out of wfi
lock_torture_wr-115     [008] d..2.    53.143481: pv_wait: cpu 8 out of wfi
lock_torture_wr-117     [011] d..2.    53.143522: pv_wait: cpu 11 out of wfi
lock_torture_wr-117     [011] ...2.    53.143987: pv_kick: cpu 11 kick target cpu 8
lock_torture_wr-115     [008] ...2.    53.144269: pv_kick: cpu 8 kick target cpu 7

This series is split from [1]. The newest discussion is at [2].

[1]: https://lore.kernel.org/linux-riscv/20231225125847.2778638-1-guoren@kernel.org/
[2]: https://lists.riscv.org/g/tech-prs/message/1211

Changelog:
v3:
 - Rebase on linux-6.18-rc7.
 - Simplify nopvspin usage.

v2:
https://lore.kernel.org/linux-riscv/20241227011011.2331381-1-guoren@kernel.org/
 - Add RFC tag.
 - Using new SBI_EXT_PVLOCK ID.
 - Add virt_spin_lock support.
 - Add nopvspin support.

v1:
https://lore.kernel.org/linux-riscv/20241222033917.1754495-1-guoren@kernel.org/

Guo Ren (Alibaba DAMO Academy) (4):
  RISC-V: paravirt: Add pvqspinlock KVM backend
  RISC-V: paravirt: Add pvqspinlock frontend
  RISC-V: paravirt: pvqspinlock: Add trace point for pv_kick/wait
  RISC-V: paravirt: Support nopvspin to disable PARAVIRT_SPINLOCKS

 .../admin-guide/kernel-parameters.txt         |  2 +-
 arch/riscv/Kconfig                            | 12 +++
 arch/riscv/include/asm/Kbuild                 |  1 -
 arch/riscv/include/asm/kvm_vcpu_sbi.h         |  1 +
 arch/riscv/include/asm/qspinlock.h            | 59 +++++++++++++
 arch/riscv/include/asm/qspinlock_paravirt.h   | 28 +++++++
 arch/riscv/include/asm/sbi.h                  |  5 ++
 arch/riscv/include/uapi/asm/kvm.h             |  1 +
 arch/riscv/kernel/Makefile                    |  2 +
 arch/riscv/kernel/qspinlock_paravirt.c        | 84 +++++++++++++++++++
 arch/riscv/kernel/setup.c                     |  5 ++
 .../kernel/trace_events_filter_paravirt.h     | 60 +++++++++++++
 arch/riscv/kvm/Makefile                       |  1 +
 arch/riscv/kvm/vcpu_sbi.c                     |  4 +
 arch/riscv/kvm/vcpu_sbi_pvlock.c              | 57 +++++++++++++
 15 files changed, 320 insertions(+), 2 deletions(-)
 create mode 100644 arch/riscv/include/asm/qspinlock.h
 create mode 100644 arch/riscv/include/asm/qspinlock_paravirt.h
 create mode 100644 arch/riscv/kernel/qspinlock_paravirt.c
 create mode 100644 arch/riscv/kernel/trace_events_filter_paravirt.h
 create mode 100644 arch/riscv/kvm/vcpu_sbi_pvlock.c

-- 
2.40.1

[RFC PATCH V3 1/4] RISC-V: paravirt: Add pvqspinlock KVM backend

[guoren]

From: "Guo Ren (Alibaba DAMO Academy)" <guoren@kernel.org>

Add the files functions needed to support the SBI PVLOCK (paravirt
qspinlock kick_cpu) extension. Implement kvm_sbi_ext_pvlock_kick_-
cpu(), and we only need to call the kvm_vcpu_kick() and bring
target_vcpu from the halt state.

Reviewed-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Guo Ren (Alibaba DAMO Academy) <guoren@kernel.org>
---
 arch/riscv/include/asm/kvm_vcpu_sbi.h |  1 +
 arch/riscv/include/asm/sbi.h          |  5 +++
 arch/riscv/include/uapi/asm/kvm.h     |  1 +
 arch/riscv/kvm/Makefile               |  1 +
 arch/riscv/kvm/vcpu_sbi.c             |  4 ++
 arch/riscv/kvm/vcpu_sbi_pvlock.c      | 57 +++++++++++++++++++++++++++
 6 files changed, 69 insertions(+)
 create mode 100644 arch/riscv/kvm/vcpu_sbi_pvlock.c

diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index 3497489e04db..d0df83ecd9fd 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -107,6 +107,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_fwft;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pvlock;
 
 #ifdef CONFIG_RISCV_PMU_SBI
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu;
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index ccc77a89b1e2..dd0734e1ebb6 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -37,6 +37,7 @@ enum sbi_ext_id {
 	SBI_EXT_NACL = 0x4E41434C,
 	SBI_EXT_FWFT = 0x46574654,
 	SBI_EXT_MPXY = 0x4D505859,
+	SBI_EXT_PVLOCK = 0x50564C4B,
 
 	/* Experimentals extensions must lie within this range */
 	SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -505,6 +506,10 @@ enum sbi_mpxy_rpmi_attribute_id {
 #define SBI_MPXY_CHAN_CAP_SEND_WITHOUT_RESP	BIT(4)
 #define SBI_MPXY_CHAN_CAP_GET_NOTIFICATIONS	BIT(5)
 
+enum sbi_ext_pvlock_fid {
+	SBI_EXT_PVLOCK_KICK_CPU = 0,
+};
+
 /* SBI spec version fields */
 #define SBI_SPEC_VERSION_DEFAULT	0x1
 #define SBI_SPEC_VERSION_MAJOR_SHIFT	24
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 759a4852c09a..9d447995de84 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -211,6 +211,7 @@ enum KVM_RISCV_SBI_EXT_ID {
 	KVM_RISCV_SBI_EXT_STA,
 	KVM_RISCV_SBI_EXT_SUSP,
 	KVM_RISCV_SBI_EXT_FWFT,
+	KVM_RISCV_SBI_EXT_PVLOCK,
 	KVM_RISCV_SBI_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile
index 07197395750e..40ddb7c06ffe 100644
--- a/arch/riscv/kvm/Makefile
+++ b/arch/riscv/kvm/Makefile
@@ -35,6 +35,7 @@ kvm-y += vcpu_sbi_sta.o
 kvm-y += vcpu_sbi_system.o
 kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
 kvm-y += vcpu_switch.o
+kvm-y += vcpu_sbi_pvlock.o
 kvm-y += vcpu_timer.o
 kvm-y += vcpu_vector.o
 kvm-y += vm.o
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index 1b13623380e1..dd74f789f44c 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -90,6 +90,10 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = {
 		.ext_idx = KVM_RISCV_SBI_EXT_VENDOR,
 		.ext_ptr = &vcpu_sbi_ext_vendor,
 	},
+	{
+		.ext_idx = KVM_RISCV_SBI_EXT_PVLOCK,
+		.ext_ptr = &vcpu_sbi_ext_pvlock,
+	},
 };
 
 static const struct kvm_riscv_sbi_extension_entry *
diff --git a/arch/riscv/kvm/vcpu_sbi_pvlock.c b/arch/riscv/kvm/vcpu_sbi_pvlock.c
new file mode 100644
index 000000000000..aeb48c3fca50
--- /dev/null
+++ b/arch/riscv/kvm/vcpu_sbi_pvlock.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c), 2025 Alibaba Damo Academy
+ *
+ * Authors:
+ *     Guo Ren <guoren@kernel.org>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <asm/sbi.h>
+#include <asm/kvm_vcpu_sbi.h>
+
+static int kvm_sbi_ext_pvlock_kick_cpu(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu *target;
+
+	target = kvm_get_vcpu_by_id(kvm, cp->a0);
+	if (!target)
+		return SBI_ERR_INVALID_PARAM;
+
+	kvm_vcpu_kick(target);
+
+	if (READ_ONCE(target->ready))
+		kvm_vcpu_yield_to(target);
+
+	return SBI_SUCCESS;
+}
+
+static int kvm_sbi_ext_pvlock_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
+				      struct kvm_vcpu_sbi_return *retdata)
+{
+	int ret = 0;
+	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
+	unsigned long funcid = cp->a6;
+
+	switch (funcid) {
+	case SBI_EXT_PVLOCK_KICK_CPU:
+		ret = kvm_sbi_ext_pvlock_kick_cpu(vcpu);
+		break;
+	default:
+		ret = SBI_ERR_NOT_SUPPORTED;
+	}
+
+	retdata->err_val = ret;
+
+	return 0;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pvlock = {
+	.extid_start = SBI_EXT_PVLOCK,
+	.extid_end = SBI_EXT_PVLOCK,
+	.handler = kvm_sbi_ext_pvlock_handler,
+};
-- 
2.40.1

[RFC PATCH V3 2/4] RISC-V: paravirt: Add pvqspinlock frontend

[guoren]

From: "Guo Ren (Alibaba DAMO Academy)" <guoren@kernel.org>

Add an unfair qspinlock virtualization-friendly frontend, by halting the
virtual CPU rather than spinning.

Using static_call to switch between:
  native_queued_spin_lock_slowpath()    __pv_queued_spin_lock_slowpath()
  native_queued_spin_unlock()           __pv_queued_spin_unlock()

Add the pv_wait & pv_kick implementations.

Reviewed-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Guo Ren (Alibaba DAMO Academy) <guoren@kernel.org>
---
 arch/riscv/Kconfig                          | 12 ++++
 arch/riscv/include/asm/Kbuild               |  1 -
 arch/riscv/include/asm/qspinlock.h          | 35 +++++++++++
 arch/riscv/include/asm/qspinlock_paravirt.h | 28 +++++++++
 arch/riscv/kernel/Makefile                  |  2 +
 arch/riscv/kernel/qspinlock_paravirt.c      | 69 +++++++++++++++++++++
 arch/riscv/kernel/setup.c                   |  5 ++
 7 files changed, 151 insertions(+), 1 deletion(-)
 create mode 100644 arch/riscv/include/asm/qspinlock.h
 create mode 100644 arch/riscv/include/asm/qspinlock_paravirt.h
 create mode 100644 arch/riscv/kernel/qspinlock_paravirt.c

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index fadec20b87a8..7d29370e6318 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -1111,6 +1111,18 @@ config PARAVIRT_TIME_ACCOUNTING
 
 	  If in doubt, say N here.
 
+config PARAVIRT_SPINLOCKS
+	bool "Paravirtualization layer for spinlocks"
+	depends on QUEUED_SPINLOCKS
+	default y
+	help
+	  Paravirtualized spinlocks allow a unfair qspinlock to replace the
+	  test-set kvm-guest virt spinlock implementation with something
+	  virtualization-friendly, for example, halt the virtual CPU rather
+	  than spinning.
+
+	  If you are unsure how to answer this question, answer Y.
+
 config RELOCATABLE
 	bool "Build a relocatable kernel"
 	depends on !XIP_KERNEL
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index bd5fc9403295..1258bd239b49 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -13,6 +13,5 @@ generic-y += spinlock_types.h
 generic-y += ticket_spinlock.h
 generic-y += qrwlock.h
 generic-y += qrwlock_types.h
-generic-y += qspinlock.h
 generic-y += user.h
 generic-y += vmlinux.lds.h
diff --git a/arch/riscv/include/asm/qspinlock.h b/arch/riscv/include/asm/qspinlock.h
new file mode 100644
index 000000000000..b39f23415ec1
--- /dev/null
+++ b/arch/riscv/include/asm/qspinlock.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c), 2025 Alibaba Damo Academy
+ * Authors:
+ *	Guo Ren <guoren@kernel.org>
+ */
+
+#ifndef _ASM_RISCV_QSPINLOCK_H
+#define _ASM_RISCV_QSPINLOCK_H
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#include <asm/qspinlock_paravirt.h>
+
+/* How long a lock should spin before we consider blocking */
+#define SPIN_THRESHOLD		(1 << 15)
+
+void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+void __pv_init_lock_hash(void);
+void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+
+static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	static_call(pv_queued_spin_lock_slowpath)(lock, val);
+}
+
+#define queued_spin_unlock	queued_spin_unlock
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	static_call(pv_queued_spin_unlock)(lock);
+}
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_RISCV_QSPINLOCK_H */
diff --git a/arch/riscv/include/asm/qspinlock_paravirt.h b/arch/riscv/include/asm/qspinlock_paravirt.h
new file mode 100644
index 000000000000..ded8c5a399bb
--- /dev/null
+++ b/arch/riscv/include/asm/qspinlock_paravirt.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c), 2025 Alibaba Damo Academy
+ * Authors:
+ *	Guo Ren <guoren@kernel.org>
+ */
+
+#ifndef _ASM_RISCV_QSPINLOCK_PARAVIRT_H
+#define _ASM_RISCV_QSPINLOCK_PARAVIRT_H
+
+void pv_wait(u8 *ptr, u8 val);
+void pv_kick(int cpu);
+
+void dummy_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+void dummy_queued_spin_unlock(struct qspinlock *lock);
+
+DECLARE_STATIC_CALL(pv_queued_spin_lock_slowpath, dummy_queued_spin_lock_slowpath);
+DECLARE_STATIC_CALL(pv_queued_spin_unlock, dummy_queued_spin_unlock);
+
+bool __init pv_qspinlock_init(void);
+
+void __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked);
+
+bool pv_is_native_spin_unlock(void);
+
+void __pv_queued_spin_unlock(struct qspinlock *lock);
+
+#endif /* _ASM_RISCV_QSPINLOCK_PARAVIRT_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index f60fce69b725..6ea874bcd447 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -125,3 +125,5 @@ obj-$(CONFIG_ACPI)		+= acpi.o
 obj-$(CONFIG_ACPI_NUMA)	+= acpi_numa.o
 
 obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o
+
+obj-$(CONFIG_PARAVIRT_SPINLOCKS) += qspinlock_paravirt.o
diff --git a/arch/riscv/kernel/qspinlock_paravirt.c b/arch/riscv/kernel/qspinlock_paravirt.c
new file mode 100644
index 000000000000..299dddaa14b8
--- /dev/null
+++ b/arch/riscv/kernel/qspinlock_paravirt.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c), 2025 Alibaba Damo Academy
+ * Authors:
+ *	Guo Ren <guoren@kernel.org>
+ */
+
+#include <linux/static_call.h>
+#include <asm/qspinlock_paravirt.h>
+#include <asm/sbi.h>
+
+void pv_kick(int cpu)
+{
+	sbi_ecall(SBI_EXT_PVLOCK, SBI_EXT_PVLOCK_KICK_CPU,
+		  cpuid_to_hartid_map(cpu), 0, 0, 0, 0, 0);
+	return;
+}
+
+void pv_wait(u8 *ptr, u8 val)
+{
+	unsigned long flags;
+
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+	if (READ_ONCE(*ptr) != val)
+		goto out;
+
+	wait_for_interrupt();
+out:
+	local_irq_restore(flags);
+}
+
+static void native_queued_spin_unlock(struct qspinlock *lock)
+{
+	smp_store_release(&lock->locked, 0);
+}
+
+DEFINE_STATIC_CALL(pv_queued_spin_lock_slowpath, native_queued_spin_lock_slowpath);
+EXPORT_STATIC_CALL(pv_queued_spin_lock_slowpath);
+
+DEFINE_STATIC_CALL(pv_queued_spin_unlock, native_queued_spin_unlock);
+EXPORT_STATIC_CALL(pv_queued_spin_unlock);
+
+bool __init pv_qspinlock_init(void)
+{
+	if (num_possible_cpus() == 1)
+		return false;
+
+	if (!sbi_probe_extension(SBI_EXT_PVLOCK))
+		return false;
+
+	pr_info("PV qspinlocks enabled\n");
+	__pv_init_lock_hash();
+
+	static_call_update(pv_queued_spin_lock_slowpath, __pv_queued_spin_lock_slowpath);
+	static_call_update(pv_queued_spin_unlock, __pv_queued_spin_unlock);
+
+	return true;
+}
+
+bool pv_is_native_spin_unlock(void)
+{
+	if (static_call_query(pv_queued_spin_unlock) == native_queued_spin_unlock)
+		return true;
+	else
+		return false;
+}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index b5bc5fc65cea..0df27501e28d 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -288,6 +288,11 @@ static void __init riscv_spinlock_init(void)
 		return;
 	}
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+	if (pv_qspinlock_init())
+		return;
+#endif
+
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&
 	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&
 	    IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZACAS) &&
-- 
2.40.1

[RFC PATCH V3 3/4] RISC-V: paravirt: pvqspinlock: Add trace point for pv_kick/wait

[guoren]

From: "Guo Ren (Alibaba DAMO Academy)" <guoren@kernel.org>

Add trace point for pv_kick&wait, here is the output:

ls /sys/kernel/debug/tracing/events/paravirt/
 enable   filter   pv_kick  pv_wait

cat /sys/kernel/debug/tracing/trace
 entries-in-buffer/entries-written: 33927/33927   #P:12

                                _-----=> irqs-off/BH-disabled
                               / _----=> need-resched
                              | / _---=> hardirq/softirq
                              || / _--=> preempt-depth
                              ||| / _-=> migrate-disable
                              |||| /     delay
           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
              | |         |   |||||     |         |
             sh-100     [001] d..2.    28.312294: pv_wait: cpu 1 out of wfi
         <idle>-0       [000] d.h4.    28.322030: pv_kick: cpu 0 kick target cpu 1
             sh-100     [001] d..2.    30.982631: pv_wait: cpu 1 out of wfi
         <idle>-0       [000] d.h4.    30.993289: pv_kick: cpu 0 kick target cpu 1
             sh-100     [002] d..2.    44.987573: pv_wait: cpu 2 out of wfi
         <idle>-0       [000] d.h4.    44.989000: pv_kick: cpu 0 kick target cpu 2
         <idle>-0       [003] d.s3.    51.593978: pv_kick: cpu 3 kick target cpu 4
      rcu_sched-15      [004] d..2.    51.595192: pv_wait: cpu 4 out of wfi
lock_torture_wr-115     [004] ...2.    52.656482: pv_kick: cpu 4 kick target cpu 2
lock_torture_wr-113     [002] d..2.    52.659146: pv_wait: cpu 2 out of wfi
lock_torture_wr-114     [008] d..2.    52.659507: pv_wait: cpu 8 out of wfi
lock_torture_wr-114     [008] d..2.    52.663503: pv_wait: cpu 8 out of wfi
lock_torture_wr-113     [002] ...2.    52.666128: pv_kick: cpu 2 kick target cpu 8
lock_torture_wr-114     [008] d..2.    52.667261: pv_wait: cpu 8 out of wfi
lock_torture_wr-114     [009] .n.2.    53.141515: pv_kick: cpu 9 kick target cpu 11
lock_torture_wr-113     [002] d..2.    53.143339: pv_wait: cpu 2 out of wfi
lock_torture_wr-116     [007] d..2.    53.143412: pv_wait: cpu 7 out of wfi
lock_torture_wr-118     [000] d..2.    53.143457: pv_wait: cpu 0 out of wfi
lock_torture_wr-115     [008] d..2.    53.143481: pv_wait: cpu 8 out of wfi
lock_torture_wr-117     [011] d..2.    53.143522: pv_wait: cpu 11 out of wfi
lock_torture_wr-117     [011] ...2.    53.143987: pv_kick: cpu 11 kick target cpu 8
lock_torture_wr-115     [008] ...2.    53.144269: pv_kick: cpu 8 kick target cpu 7

Reviewed-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Guo Ren (Alibaba DAMO Academy) <guoren@kernel.org>
---
 arch/riscv/kernel/qspinlock_paravirt.c        |  7 +++
 .../kernel/trace_events_filter_paravirt.h     | 60 +++++++++++++++++++
 2 files changed, 67 insertions(+)
 create mode 100644 arch/riscv/kernel/trace_events_filter_paravirt.h

diff --git a/arch/riscv/kernel/qspinlock_paravirt.c b/arch/riscv/kernel/qspinlock_paravirt.c
index 299dddaa14b8..cae991139abe 100644
--- a/arch/riscv/kernel/qspinlock_paravirt.c
+++ b/arch/riscv/kernel/qspinlock_paravirt.c
@@ -9,8 +9,13 @@
 #include <asm/qspinlock_paravirt.h>
 #include <asm/sbi.h>
 
+#define CREATE_TRACE_POINTS
+#include "trace_events_filter_paravirt.h"
+
 void pv_kick(int cpu)
 {
+	trace_pv_kick(smp_processor_id(), cpu);
+
 	sbi_ecall(SBI_EXT_PVLOCK, SBI_EXT_PVLOCK_KICK_CPU,
 		  cpuid_to_hartid_map(cpu), 0, 0, 0, 0, 0);
 	return;
@@ -28,6 +33,8 @@ void pv_wait(u8 *ptr, u8 val)
 		goto out;
 
 	wait_for_interrupt();
+
+	trace_pv_wait(smp_processor_id());
 out:
 	local_irq_restore(flags);
 }
diff --git a/arch/riscv/kernel/trace_events_filter_paravirt.h b/arch/riscv/kernel/trace_events_filter_paravirt.h
new file mode 100644
index 000000000000..db5e702a1f12
--- /dev/null
+++ b/arch/riscv/kernel/trace_events_filter_paravirt.h
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c), 2025 Alibaba Damo Academy
+ * Authors:
+ *	Guo Ren <guoren@kernel.org>
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM paravirt
+
+#if !defined(_TRACE_PARAVIRT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PARAVIRT_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(pv_kick,
+	TP_PROTO(int cpu, int target),
+	TP_ARGS(cpu, target),
+
+	TP_STRUCT__entry(
+		__field(int, cpu)
+		__field(int, target)
+	),
+
+	TP_fast_assign(
+		__entry->cpu = cpu;
+		__entry->target = target;
+	),
+
+	TP_printk("cpu %d pv_kick target cpu %d",
+		__entry->cpu,
+		__entry->target
+	)
+);
+
+TRACE_EVENT(pv_wait,
+	TP_PROTO(int cpu),
+	TP_ARGS(cpu),
+
+	TP_STRUCT__entry(
+		__field(int, cpu)
+	),
+
+	TP_fast_assign(
+		__entry->cpu = cpu;
+	),
+
+	TP_printk("cpu %d out of wfi",
+		__entry->cpu
+	)
+);
+
+#endif /* _TRACE_PARAVIRT_H || TRACE_HEADER_MULTI_READ */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH ../../../arch/riscv/kernel/
+#define TRACE_INCLUDE_FILE trace_events_filter_paravirt
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
2.40.1

[RFC PATCH V3 4/4] RISC-V: paravirt: Support nopvspin to disable PARAVIRT_SPINLOCKS

[guoren]

From: "Guo Ren (Alibaba DAMO Academy)" <guoren@kernel.org>

The VM guests should fall back to a Test-and-Set spinlock when
PARAVIRT_SPINLOCKS disabled, because fair locks have horrible lock
'holder' preemption issues. The virt_spin_lock_key would shortcut for
the queued_spin_lock_- slowpath() function that allow virt_spin_lock
to hijack it. ref: 43b3f02899f7 ("locking/qspinlock/x86: Fix
performance regression under unaccelerated VMs").

Add a static key controlling whether virt_spin_lock() should be
called or not. Add nopvspin support as x86.

Signed-off-by: Guo Ren (Alibaba DAMO Academy) <guoren@kernel.org>
---
 .../admin-guide/kernel-parameters.txt         |  2 +-
 arch/riscv/include/asm/qspinlock.h            | 24 +++++++++++++++++++
 arch/riscv/kernel/qspinlock_paravirt.c        |  8 +++++++
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6c42061ca20e..9e895e9ca655 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4393,7 +4393,7 @@
 			as generic guest with no PV drivers. Currently support
 			XEN HVM, KVM, HYPER_V and VMWARE guest.
 
-	nopvspin	[X86,XEN,KVM,EARLY]
+	nopvspin	[X86,RISCV,XEN,KVM,EARLY]
 			Disables the qspinlock slow path using PV optimizations
 			which allow the hypervisor to 'idle' the guest on lock
 			contention.
diff --git a/arch/riscv/include/asm/qspinlock.h b/arch/riscv/include/asm/qspinlock.h
index b39f23415ec1..70ad7679fce0 100644
--- a/arch/riscv/include/asm/qspinlock.h
+++ b/arch/riscv/include/asm/qspinlock.h
@@ -14,6 +14,8 @@
 /* How long a lock should spin before we consider blocking */
 #define SPIN_THRESHOLD		(1 << 15)
 
+extern bool nopvspin;
+
 void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
 void __pv_init_lock_hash(void);
 void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
@@ -31,5 +33,27 @@ static inline void queued_spin_unlock(struct qspinlock *lock)
 #endif /* CONFIG_PARAVIRT_SPINLOCKS */
 
 #include <asm-generic/qspinlock.h>
+#include <asm/jump_label.h>
+
+/*
+ * The KVM guests fall back to a Test-and-Set spinlock, because fair locks
+ * have horrible lock 'holder' preemption issues. The test_and_set_spinlock_key
+ * would shortcut for the queued_spin_lock_slowpath() function that allow
+ * virt_spin_lock to hijack it.
+ */
+DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key);
+
+#define virt_spin_lock rv_virt_spin_lock
+static inline bool rv_virt_spin_lock(struct qspinlock *lock)
+{
+	if (!static_branch_likely(&virt_spin_lock_key))
+		return false;
+
+	do {
+		smp_cond_load_relaxed((s32 *)&lock->val, VAL == 0);
+	} while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
+
+	return true;
+}
 
 #endif /* _ASM_RISCV_QSPINLOCK_H */
diff --git a/arch/riscv/kernel/qspinlock_paravirt.c b/arch/riscv/kernel/qspinlock_paravirt.c
index cae991139abe..b89f13d0d6e8 100644
--- a/arch/riscv/kernel/qspinlock_paravirt.c
+++ b/arch/riscv/kernel/qspinlock_paravirt.c
@@ -50,6 +50,8 @@ EXPORT_STATIC_CALL(pv_queued_spin_lock_slowpath);
 DEFINE_STATIC_CALL(pv_queued_spin_unlock, native_queued_spin_unlock);
 EXPORT_STATIC_CALL(pv_queued_spin_unlock);
 
+DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key);
+
 bool __init pv_qspinlock_init(void)
 {
 	if (num_possible_cpus() == 1)
@@ -58,6 +60,12 @@ bool __init pv_qspinlock_init(void)
 	if (!sbi_probe_extension(SBI_EXT_PVLOCK))
 		return false;
 
+	if (nopvspin) {
+		static_branch_enable(&virt_spin_lock_key);
+		pr_info("virt_spin_lock enabled by nopvspin\n");
+		return true;
+	}
+
 	pr_info("PV qspinlocks enabled\n");
 	__pv_init_lock_hash();
 
-- 
2.40.1