x86/hyperv: Enable PV qspinlock for Hyper-V

Implement the required wait and kick callbacks to support PV spinlocks in
Hyper-V guests.

[ tglx: Document the requirement for disabling interrupts in the wait()
  	callback. Remove goto and unnecessary includes. Add prototype
	for hv_vcpu_is_preempted(). Adapted to pending paravirt changes. ]

Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Michael Kelley (EOSG) <Michael.H.Kelley@microsoft.com>
Cc: chao.p.peng@intel.com
Cc: chao.gao@intel.com
Cc: isaku.yamahata@intel.com
Cc: tianyu.lan@microsoft.com
Link: https://lkml.kernel.org/r/1538987374-51217-3-git-send-email-yi.y.sun@linux.intel.com

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 paravirt spinlock optimizations
+				      which allow the hypervisor to 'idle' the
+				      guest on lock contention.
+
 	keep_bootcon	[KNL]
 			Do not unregister boot console at start. This is only
 			useful for debugging when something happens in the window

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

arch/x86/hyperv/hv_spinlock.c

@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V specific spinlock code.
+ *
+ * Copyright (C) 2018, Intel, Inc.
+ *
+ * Author : Yi Sun <yi.y.sun@intel.com>
+ */
+
+#define pr_fmt(fmt) "Hyper-V: " fmt
+
+#include <linux/spinlock.h>
+
+#include <asm/mshyperv.h>
+#include <asm/paravirt.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;
+
+	/*
+	 * Reading HV_X64_MSR_GUEST_IDLE MSR tells the hypervisor that the
+	 * vCPU can be put into 'idle' state. This 'idle' state is
+	 * terminated by an IPI, usually from hv_qlock_kick(), even if
+	 * interrupts are disabled on the vCPU.
+	 *
+	 * To prevent a race against the unlock path it is required to
+	 * disable interrupts before accessing the HV_X64_MSR_GUEST_IDLE
+	 * MSR. Otherwise, if the IPI from hv_qlock_kick() arrives between
+	 * the lock value check and the rdmsrl() then the vCPU might be put
+	 * into 'idle' state by the hypervisor and kept in that state for
+	 * an unspecified amount of time.
+	 */
+	local_irq_save(flags);
+	/*
+	 * Only issue the rdmsrl() when the lock state has not changed.
+	 */
+	if (READ_ONCE(*byte) == val)
+		rdmsrl(HV_X64_MSR_GUEST_IDLE, msr_val);
+	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_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+	pv_ops.lock.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+	pv_ops.lock.wait = hv_qlock_wait;
+	pv_ops.lock.kick = hv_qlock_kick;
+	pv_ops.lock.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);

arch/x86/include/asm/mshyperv.h

@@ -351,6 +351,8 @@ int hyperv_flush_guest_mapping(u64 as);
 
 #ifdef CONFIG_X86_64
 void hv_apic_init(void);
+void __init hv_init_spinlocks(void);
+bool hv_vcpu_is_preempted(int vcpu);
 #else
 static inline void hv_apic_init(void) {}
 #endif

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);
+
+# ifdef CONFIG_SMP
+	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
+# endif
 #endif
 }