Merge branch 'x86-paravirt-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 paravirt updates from Ingo Molnar:
 "Two main changes:

   - Remove no longer used parts of the paravirt infrastructure and put
     large quantities of paravirt ops under a new config option
     PARAVIRT_XXL=y, which is selected by XEN_PV only. (Joergen Gross)

   - Enable PV spinlocks on Hyperv (Yi Sun)"

* 'x86-paravirt-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/hyperv: Enable PV qspinlock for Hyper-V
  x86/hyperv: Add GUEST_IDLE_MSR support
  x86/paravirt: Clean up native_patch()
  x86/paravirt: Prevent redefinition of SAVE_FLAGS macro
  x86/xen: Make xen_reservation_lock static
  x86/paravirt: Remove unneeded mmu related paravirt ops bits
  x86/paravirt: Move the Xen-only pv_mmu_ops under the PARAVIRT_XXL umbrella
  x86/paravirt: Move the pv_irq_ops under the PARAVIRT_XXL umbrella
  x86/paravirt: Move the Xen-only pv_cpu_ops under the PARAVIRT_XXL umbrella
  x86/paravirt: Move items in pv_info under PARAVIRT_XXL umbrella
  x86/paravirt: Introduce new config option PARAVIRT_XXL
  x86/paravirt: Remove unused paravirt bits
  x86/paravirt: Use a single ops structure
  x86/paravirt: Remove clobbers from struct paravirt_patch_site
  x86/paravirt: Remove clobbers parameter from paravirt patch functions
  x86/paravirt: Make paravirt_patch_call() and paravirt_patch_jmp() static
  x86/xen: Add SPDX identifier in arch/x86/xen files
  x86/xen: Link platform-pci-unplug.o only if CONFIG_XEN_PVHVM
  x86/xen: Move pv specific parts of arch/x86/xen/mmu.c to mmu_pv.c
  x86/xen: Move pv irq related functions under CONFIG_XEN_PV umbrella

3 files changed, 94 insertions, 2 deletions

diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index b21ee65c41018..1c11f9420a820 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 0000000000000..a861b0456b1a7
--- /dev/null
+++ b/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);
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index ef5f29f913d7b..e65d7fe6489f3 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -231,6 +231,6 @@ void hyperv_setup_mmu_ops(void)
 		return;
 
 	pr_info("Using hypercall for remote TLB flush\n");
-	pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
-	pv_mmu_ops.tlb_remove_table = tlb_remove_table;
+	pv_ops.mmu.flush_tlb_others = hyperv_flush_tlb_others;
+	pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 }