[PATCH v4 2/2] locking/pvqspinlock, hv: Enable PV qspinlock for Hyper-V

[Yi Sun]

Follow PV spinlock mechanism to implement the callback functions
to allow the CPU idling and kicking operations on Hyper-V.

Cc: "K. Y. Srinivasan" <kys@xxxxxxxxxxxxx>
Cc: Haiyang Zhang <haiyangz@xxxxxxxxxxxxx>
Cc: Stephen Hemminger <sthemmin@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Michael Kelley (EOSG) <Michael.H.Kelley@xxxxxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Signed-off-by: Yi Sun <yi.y.sun@xxxxxxxxxxxxxxx>
---
v3->v4:
    - To avoid possible hang issue (if hv_qlock_wait can be
      interrupted, kick may happen before reading HV_X64_MSR_GUEST_IDLE
      so that hang happens), disable interrupt before READ_ONCE, then
      restore it after reading HV_X64_MSR_GUEST_IDLE.
      (suggested by Juergen Gross)
---
 Documentation/admin-guide/kernel-parameters.txt |  5 ++
 arch/x86/hyperv/Makefile                        |  4 ++
 arch/x86/hyperv/hv_spinlock.c                   | 85 +++++++++++++++++++++++++
 arch/x86/include/asm/mshyperv.h                 |  1 +
 arch/x86/kernel/cpu/mshyperv.c                  | 14 ++++
 5 files changed, 109 insertions(+)
 create mode 100644 arch/x86/hyperv/hv_spinlock.c

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 92eb1f4..0fc8448 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1385,6 +1385,11 @@
 	hvc_iucv_allow=	[S390]	Comma-separated list of z/VM user IDs.
 				If specified, z/VM IUCV HVC accepts connections
 				from listed z/VM user IDs only.
+
+	hv_nopvspin	[X86,HYPER_V]
+			Disables the ticketlock slowpath using HYPER-V PV
+			optimizations.
+
 	keep_bootcon	[KNL]
 			Do not unregister boot console at start. This is only
 			useful for debugging when something happens in the window
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index b21ee65..1c11f94 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1,2 +1,6 @@
 obj-y			:= hv_init.o mmu.o nested.o
 obj-$(CONFIG_X86_64)	+= hv_apic.o
+
+ifdef CONFIG_X86_64
+obj-$(CONFIG_PARAVIRT_SPINLOCKS)	+= hv_spinlock.o
+endif
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
new file mode 100644
index 0000000..b628343
--- /dev/null
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V specific spinlock code.
+ *
+ * Copyright (C) 2018, Intel, Inc.
+ *
+ * Author : Yi Sun <yi.y.sun@xxxxxxxxx>
+ */
+
+#define pr_fmt(fmt) "Hyper-V: " fmt
+
+#include <linux/spinlock.h>
+
+#include <asm/mshyperv.h>
+#include <asm/hyperv-tlfs.h>
+#include <asm/paravirt.h>
+#include <asm/qspinlock.h>
+#include <asm/apic.h>
+
+static bool __initdata hv_pvspin = true;
+
+static void hv_qlock_kick(int cpu)
+{
+	apic->send_IPI(cpu, X86_PLATFORM_IPI_VECTOR);
+}
+
+static void hv_qlock_wait(u8 *byte, u8 val)
+{
+	unsigned long msr_val;
+	unsigned long flags;
+
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+
+	if (READ_ONCE(*byte) != val)
+		goto out;
+
+	/*
+	 * Read HV_X64_MSR_GUEST_IDLE MSR can trigger the guest's
+	 * transition to the idle power state which can be exited
+	 * by an IPI even if IF flag is disabled.
+	 */
+	rdmsrl(HV_X64_MSR_GUEST_IDLE, msr_val);
+
+out:
+	local_irq_restore(flags);
+}
+
+/*
+ * Hyper-V does not support this so far.
+ */
+bool hv_vcpu_is_preempted(int vcpu)
+{
+	return false;
+}
+PV_CALLEE_SAVE_REGS_THUNK(hv_vcpu_is_preempted);
+
+void __init hv_init_spinlocks(void)
+{
+	if (!hv_pvspin ||
+	    !apic ||
+	    !(ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) ||
+	    !(ms_hyperv.features & HV_X64_MSR_GUEST_IDLE_AVAILABLE)) {
+		pr_info("PV spinlocks disabled\n");
+		return;
+	}
+	pr_info("PV spinlocks enabled\n");
+
+	__pv_init_lock_hash();
+	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+	pv_lock_ops.wait = hv_qlock_wait;
+	pv_lock_ops.kick = hv_qlock_kick;
+	pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(hv_vcpu_is_preempted);
+}
+
+static __init int hv_parse_nopvspin(char *arg)
+{
+	hv_pvspin = false;
+	return 0;
+}
+early_param("hv_nopvspin", hv_parse_nopvspin);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f377044..759cfd2 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -351,6 +351,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 
 #ifdef CONFIG_X86_64
 void hv_apic_init(void);
+void __init hv_init_spinlocks(void);
 #else
 static inline void hv_apic_init(void) {}
 #endif
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index ad12733..a5cc219 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -199,6 +199,16 @@ static unsigned long hv_get_tsc_khz(void)
 	return freq / 1000;
 }
 
+#if defined(CONFIG_SMP) && IS_ENABLED(CONFIG_HYPERV)
+static void __init hv_smp_prepare_boot_cpu(void)
+{
+	native_smp_prepare_boot_cpu();
+#if defined(CONFIG_X86_64) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+	hv_init_spinlocks();
+#endif
+}
+#endif
+
 static void __init ms_hyperv_init_platform(void)
 {
 	int hv_host_info_eax;
@@ -303,6 +313,10 @@ static void __init ms_hyperv_init_platform(void)
 	if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)
 		alloc_intr_gate(HYPERV_STIMER0_VECTOR,
 				hv_stimer0_callback_vector);
+
+#if defined(CONFIG_SMP)
+	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
+#endif
 #endif
 }
 
-- 
1.9.1