Merge tag 'for-linus-5.16b-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - a series to speed up the boot of Xen PV guests

 - some cleanups in Xen related code

 - replacement of license texts with the appropriate SPDX headers and
   fixing of wrong SPDX headers in Xen header files

 - a small series making paravirtualized interrupt masking much simpler
   and at the same time removing complaints of objtool

 - a fix for Xen ballooning hogging workqueues for too long

 - enablement of the Xen pciback driver for Arm

 - some further small fixes/enhancements

* tag 'for-linus-5.16b-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (22 commits)
  xen/balloon: fix unused-variable warning
  xen/balloon: rename alloc/free_xenballooned_pages
  xen/balloon: add late_initcall_sync() for initial ballooning done
  x86/xen: remove 32-bit awareness from startup_xen
  xen: remove highmem remnants
  xen: allow pv-only hypercalls only with CONFIG_XEN_PV
  x86/xen: remove 32-bit pv leftovers
  xen-pciback: allow compiling on other archs than x86
  x86/xen: switch initial pvops IRQ functions to dummy ones
  x86/xen: remove xen_have_vcpu_info_placement flag
  x86/pvh: add prototype for xen_pvh_init()
  xen: Fix implicit type conversion
  xen: fix wrong SPDX headers of Xen related headers
  xen/pvcalls-back: Remove redundant 'flush_workqueue()' calls
  x86/xen: Remove redundant irq_enter/exit() invocations
  xen-pciback: Fix return in pm_ctrl_init()
  xen/x86: restrict PV Dom0 identity mapping
  xen/x86: there's no highmem anymore in PV mode
  xen/x86: adjust handling of the L3 user vsyscall special page table
  xen/x86: adjust xen_set_fixmap()
  ...

16 files changed, 206 insertions, 468 deletions

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index d9d6b0203ec4..fc1151e77569 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -577,7 +577,9 @@ void paravirt_leave_lazy_mmu(void);
 void paravirt_flush_lazy_mmu(void);
 
 void _paravirt_nop(void);
+void paravirt_BUG(void);
 u64 _paravirt_ident_64(u64);
+unsigned long paravirt_ret0(void);
 
 #define paravirt_nop	((void *)_paravirt_nop)
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 4a7ff8b0db20..0575f5863b7f 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -248,6 +248,7 @@ privcmd_call(unsigned int call,
 	return res;
 }
 
+#ifdef CONFIG_XEN_PV
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {
@@ -281,6 +282,107 @@ HYPERVISOR_callback_op(int cmd, void *arg)
 }
 
 static inline int
+HYPERVISOR_set_debugreg(int reg, unsigned long value)
+{
+	return _hypercall2(int, set_debugreg, reg, value);
+}
+
+static inline unsigned long
+HYPERVISOR_get_debugreg(int reg)
+{
+	return _hypercall1(unsigned long, get_debugreg, reg);
+}
+
+static inline int
+HYPERVISOR_update_descriptor(u64 ma, u64 desc)
+{
+	return _hypercall2(int, update_descriptor, ma, desc);
+}
+
+static inline int
+HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
+			     unsigned long flags)
+{
+	return _hypercall3(int, update_va_mapping, va, new_val.pte, flags);
+}
+
+static inline int
+HYPERVISOR_set_segment_base(int reg, unsigned long value)
+{
+	return _hypercall2(int, set_segment_base, reg, value);
+}
+
+static inline void
+MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
+{
+	mcl->op = __HYPERVISOR_fpu_taskswitch;
+	mcl->args[0] = set;
+
+	trace_xen_mc_entry(mcl, 1);
+}
+
+static inline void
+MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
+			pte_t new_val, unsigned long flags)
+{
+	mcl->op = __HYPERVISOR_update_va_mapping;
+	mcl->args[0] = va;
+	mcl->args[1] = new_val.pte;
+	mcl->args[2] = flags;
+
+	trace_xen_mc_entry(mcl, 3);
+}
+
+static inline void
+MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
+			struct desc_struct desc)
+{
+	mcl->op = __HYPERVISOR_update_descriptor;
+	mcl->args[0] = maddr;
+	mcl->args[1] = *(unsigned long *)&desc;
+
+	trace_xen_mc_entry(mcl, 2);
+}
+
+static inline void
+MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
+		 int count, int *success_count, domid_t domid)
+{
+	mcl->op = __HYPERVISOR_mmu_update;
+	mcl->args[0] = (unsigned long)req;
+	mcl->args[1] = count;
+	mcl->args[2] = (unsigned long)success_count;
+	mcl->args[3] = domid;
+
+	trace_xen_mc_entry(mcl, 4);
+}
+
+static inline void
+MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
+		int *success_count, domid_t domid)
+{
+	mcl->op = __HYPERVISOR_mmuext_op;
+	mcl->args[0] = (unsigned long)op;
+	mcl->args[1] = count;
+	mcl->args[2] = (unsigned long)success_count;
+	mcl->args[3] = domid;
+
+	trace_xen_mc_entry(mcl, 4);
+}
+
+static inline void
+MULTI_stack_switch(struct multicall_entry *mcl,
+		   unsigned long ss, unsigned long esp)
+{
+	mcl->op = __HYPERVISOR_stack_switch;
+	mcl->args[0] = ss;
+	mcl->args[1] = esp;
+
+	trace_xen_mc_entry(mcl, 2);
+}
+#endif
+
+static inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
 	return _hypercall2(int, sched_op, cmd, arg);
@@ -308,26 +410,6 @@ HYPERVISOR_platform_op(struct xen_platform_op *op)
 	return _hypercall1(int, platform_op, op);
 }
 
-static __always_inline int
-HYPERVISOR_set_debugreg(int reg, unsigned long value)
-{
-	return _hypercall2(int, set_debugreg, reg, value);
-}
-
-static __always_inline unsigned long
-HYPERVISOR_get_debugreg(int reg)
-{
-	return _hypercall1(unsigned long, get_debugreg, reg);
-}
-
-static inline int
-HYPERVISOR_update_descriptor(u64 ma, u64 desc)
-{
-	if (sizeof(u64) == sizeof(long))
-		return _hypercall2(int, update_descriptor, ma, desc);
-	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
-}
-
 static inline long
 HYPERVISOR_memory_op(unsigned int cmd, void *arg)
 {
@@ -341,18 +423,6 @@ HYPERVISOR_multicall(void *call_list, uint32_t nr_calls)
 }
 
 static inline int
-HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
-			     unsigned long flags)
-{
-	if (sizeof(new_val) == sizeof(long))
-		return _hypercall3(int, update_va_mapping, va,
-				   new_val.pte, flags);
-	else
-		return _hypercall4(int, update_va_mapping, va,
-				   new_val.pte, new_val.pte >> 32, flags);
-}
-
-static inline int
 HYPERVISOR_event_channel_op(int cmd, void *arg)
 {
 	return _hypercall2(int, event_channel_op, cmd, arg);
@@ -394,14 +464,6 @@ HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args)
 	return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args);
 }
 
-#ifdef CONFIG_X86_64
-static inline int
-HYPERVISOR_set_segment_base(int reg, unsigned long value)
-{
-	return _hypercall2(int, set_segment_base, reg, value);
-}
-#endif
-
 static inline int
 HYPERVISOR_suspend(unsigned long start_info_mfn)
 {
@@ -423,13 +485,6 @@ HYPERVISOR_hvm_op(int op, void *arg)
 }
 
 static inline int
-HYPERVISOR_tmem_op(
-	struct tmem_op *op)
-{
-	return _hypercall1(int, tmem_op, op);
-}
-
-static inline int
 HYPERVISOR_xenpmu_op(unsigned int op, void *arg)
 {
 	return _hypercall2(int, xenpmu_op, op, arg);
@@ -446,88 +501,4 @@ HYPERVISOR_dm_op(
 	return ret;
 }
 
-static inline void
-MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
-{
-	mcl->op = __HYPERVISOR_fpu_taskswitch;
-	mcl->args[0] = set;
-
-	trace_xen_mc_entry(mcl, 1);
-}
-
-static inline void
-MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
-			pte_t new_val, unsigned long flags)
-{
-	mcl->op = __HYPERVISOR_update_va_mapping;
-	mcl->args[0] = va;
-	if (sizeof(new_val) == sizeof(long)) {
-		mcl->args[1] = new_val.pte;
-		mcl->args[2] = flags;
-	} else {
-		mcl->args[1] = new_val.pte;
-		mcl->args[2] = new_val.pte >> 32;
-		mcl->args[3] = flags;
-	}
-
-	trace_xen_mc_entry(mcl, sizeof(new_val) == sizeof(long) ? 3 : 4);
-}
-
-static inline void
-MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
-			struct desc_struct desc)
-{
-	mcl->op = __HYPERVISOR_update_descriptor;
-	if (sizeof(maddr) == sizeof(long)) {
-		mcl->args[0] = maddr;
-		mcl->args[1] = *(unsigned long *)&desc;
-	} else {
-		u32 *p = (u32 *)&desc;
-
-		mcl->args[0] = maddr;
-		mcl->args[1] = maddr >> 32;
-		mcl->args[2] = *p++;
-		mcl->args[3] = *p;
-	}
-
-	trace_xen_mc_entry(mcl, sizeof(maddr) == sizeof(long) ? 2 : 4);
-}
-
-static inline void
-MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
-		 int count, int *success_count, domid_t domid)
-{
-	mcl->op = __HYPERVISOR_mmu_update;
-	mcl->args[0] = (unsigned long)req;
-	mcl->args[1] = count;
-	mcl->args[2] = (unsigned long)success_count;
-	mcl->args[3] = domid;
-
-	trace_xen_mc_entry(mcl, 4);
-}
-
-static inline void
-MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
-		int *success_count, domid_t domid)
-{
-	mcl->op = __HYPERVISOR_mmuext_op;
-	mcl->args[0] = (unsigned long)op;
-	mcl->args[1] = count;
-	mcl->args[2] = (unsigned long)success_count;
-	mcl->args[3] = domid;
-
-	trace_xen_mc_entry(mcl, 4);
-}
-
-static inline void
-MULTI_stack_switch(struct multicall_entry *mcl,
-		   unsigned long ss, unsigned long esp)
-{
-	mcl->op = __HYPERVISOR_stack_switch;
-	mcl->args[0] = ss;
-	mcl->args[1] = esp;
-
-	trace_xen_mc_entry(mcl, 2);
-}
-
 #endif /* _ASM_X86_XEN_HYPERCALL_H */
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index ff4b52e37e60..4957f59deb40 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -62,4 +62,8 @@ void xen_arch_register_cpu(int num);
 void xen_arch_unregister_cpu(int num);
 #endif
 
+#ifdef CONFIG_PVH
+void __init xen_pvh_init(struct boot_params *boot_params);
+#endif
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index 4557f7cb0fa6..9015b888edd6 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -22,25 +22,6 @@ static inline int __init pci_xen_initial_domain(void)
 	return -1;
 }
 #endif
-#ifdef CONFIG_XEN_DOM0
-int xen_find_device_domain_owner(struct pci_dev *dev);
-int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
-int xen_unregister_device_domain_owner(struct pci_dev *dev);
-#else
-static inline int xen_find_device_domain_owner(struct pci_dev *dev)
-{
-	return -1;
-}
-static inline int xen_register_device_domain_owner(struct pci_dev *dev,
-						   uint16_t domain)
-{
-	return -1;
-}
-static inline int xen_unregister_device_domain_owner(struct pci_dev *dev)
-{
-	return -1;
-}
-#endif
 
 #if defined(CONFIG_PCI_MSI)
 #if defined(CONFIG_PCI_XEN)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index ebc45360ffd4..7157c2df3bc2 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -46,6 +46,17 @@ asm (".pushsection .entry.text, \"ax\"\n"
      ".type _paravirt_nop, @function\n\t"
      ".popsection");
 
+/* stub always returning 0. */
+asm (".pushsection .entry.text, \"ax\"\n"
+     ".global paravirt_ret0\n"
+     "paravirt_ret0:\n\t"
+     "xor %" _ASM_AX ", %" _ASM_AX ";\n\t"
+     "ret\n\t"
+     ".size paravirt_ret0, . - paravirt_ret0\n\t"
+     ".type paravirt_ret0, @function\n\t"
+     ".popsection");
+
+
 void __init default_banner(void)
 {
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
@@ -53,7 +64,7 @@ void __init default_banner(void)
 }
 
 /* Undefined instruction for dealing with missing ops pointers. */
-static void paravirt_BUG(void)
+noinstr void paravirt_BUG(void)
 {
 	BUG();
 }
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 5debe4ac6f81..12da00558631 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -23,6 +23,7 @@
 
 #include <xen/features.h>
 #include <xen/events.h>
+#include <xen/pci.h>
 #include <asm/xen/pci.h>
 #include <asm/xen/cpuid.h>
 #include <asm/apic.h>
@@ -585,78 +586,3 @@ int __init pci_xen_initial_domain(void)
 }
 #endif
 
-#ifdef CONFIG_XEN_DOM0
-
-struct xen_device_domain_owner {
-	domid_t domain;
-	struct pci_dev *dev;
-	struct list_head list;
-};
-
-static DEFINE_SPINLOCK(dev_domain_list_spinlock);
-static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list);
-
-static struct xen_device_domain_owner *find_device(struct pci_dev *dev)
-{
-	struct xen_device_domain_owner *owner;
-
-	list_for_each_entry(owner, &dev_domain_list, list) {
-		if (owner->dev == dev)
-			return owner;
-	}
-	return NULL;
-}
-
-int xen_find_device_domain_owner(struct pci_dev *dev)
-{
-	struct xen_device_domain_owner *owner;
-	int domain = -ENODEV;
-
-	spin_lock(&dev_domain_list_spinlock);
-	owner = find_device(dev);
-	if (owner)
-		domain = owner->domain;
-	spin_unlock(&dev_domain_list_spinlock);
-	return domain;
-}
-EXPORT_SYMBOL_GPL(xen_find_device_domain_owner);
-
-int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain)
-{
-	struct xen_device_domain_owner *owner;
-
-	owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL);
-	if (!owner)
-		return -ENODEV;
-
-	spin_lock(&dev_domain_list_spinlock);
-	if (find_device(dev)) {
-		spin_unlock(&dev_domain_list_spinlock);
-		kfree(owner);
-		return -EEXIST;
-	}
-	owner->domain = domain;
-	owner->dev = dev;
-	list_add_tail(&owner->list, &dev_domain_list);
-	spin_unlock(&dev_domain_list_spinlock);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xen_register_device_domain_owner);
-
-int xen_unregister_device_domain_owner(struct pci_dev *dev)
-{
-	struct xen_device_domain_owner *owner;
-
-	spin_lock(&dev_domain_list_spinlock);
-	owner = find_device(dev);
-	if (!owner) {
-		spin_unlock(&dev_domain_list_spinlock);
-		return -ENODEV;
-	}
-	list_del(&owner->list);
-	spin_unlock(&dev_domain_list_spinlock);
-	kfree(owner);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
-#endif /* CONFIG_XEN_DOM0 */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 95d970359e17..30c6e986a6cd 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -31,25 +31,10 @@ EXPORT_SYMBOL_GPL(hypercall_page);
  * Pointer to the xen_vcpu_info structure or
  * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
  * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
- * but if the hypervisor supports VCPUOP_register_vcpu_info then it can point
- * to xen_vcpu_info. The pointer is used in __xen_evtchn_do_upcall to
- * acknowledge pending events.
- * Also more subtly it is used by the patched version of irq enable/disable
- * e.g. xen_irq_enable_direct and xen_iret in PV mode.
- *
- * The desire to be able to do those mask/unmask operations as a single
- * instruction by using the per-cpu offset held in %gs is the real reason
- * vcpu info is in a per-cpu pointer and the original reason for this
- * hypercall.
- *
+ * but during boot it is switched to point to xen_vcpu_info.
+ * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events.
  */
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
-
-/*
- * Per CPU pages used if hypervisor supports VCPUOP_register_vcpu_info
- * hypercall. This can be used both in PV and PVHVM mode. The structure
- * overrides the default per_cpu(xen_vcpu, cpu) value.
- */
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 
 /* Linux <-> Xen vCPU id mapping */
@@ -84,21 +69,6 @@ EXPORT_SYMBOL(xen_start_flags);
  */
 struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;
 
-/*
- * Flag to determine whether vcpu info placement is available on all
- * VCPUs.  We assume it is to start with, and then set it to zero on
- * the first failure.  This is because it can succeed on some VCPUs
- * and not others, since it can involve hypervisor memory allocation,
- * or because the guest failed to guarantee all the appropriate
- * constraints on all VCPUs (ie buffer can't cross a page boundary).
- *
- * Note that any particular CPU may be using a placed vcpu structure,
- * but we can only optimise if the all are.
- *
- * 0: not available, 1: available
- */
-int xen_have_vcpu_info_placement = 1;
-
 static int xen_cpu_up_online(unsigned int cpu)
 {
 	xen_init_lock_cpu(cpu);
@@ -124,10 +94,8 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int),
 	return rc >= 0 ? 0 : rc;
 }
 
-static int xen_vcpu_setup_restore(int cpu)
+static void xen_vcpu_setup_restore(int cpu)
 {
-	int rc = 0;
-
 	/* Any per_cpu(xen_vcpu) is stale, so reset it */
 	xen_vcpu_info_reset(cpu);
 
@@ -136,11 +104,8 @@ static int xen_vcpu_setup_restore(int cpu)
 	 * be handled by hotplug.
 	 */
 	if (xen_pv_domain() ||
-	    (xen_hvm_domain() && cpu_online(cpu))) {
-		rc = xen_vcpu_setup(cpu);
-	}
-
-	return rc;
+	    (xen_hvm_domain() && cpu_online(cpu)))
+		xen_vcpu_setup(cpu);
 }
 
 /*
@@ -150,7 +115,7 @@ static int xen_vcpu_setup_restore(int cpu)
  */
 void xen_vcpu_restore(void)
 {
-	int cpu, rc;
+	int cpu;
 
 	for_each_possible_cpu(cpu) {
 		bool other_cpu = (cpu != smp_processor_id());
@@ -170,20 +135,9 @@ void xen_vcpu_restore(void)
 		if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock))
 			xen_setup_runstate_info(cpu);
 
-		rc = xen_vcpu_setup_restore(cpu);
-		if (rc)
-			pr_emerg_once("vcpu restore failed for cpu=%d err=%d. "
-					"System will hang.\n", cpu, rc);
-		/*
-		 * In case xen_vcpu_setup_restore() fails, do not bring up the
-		 * VCPU. This helps us avoid the resulting OOPS when the VCPU
-		 * accesses pvclock_vcpu_time via xen_vcpu (which is NULL.)
-		 * Note that this does not improve the situation much -- now the
-		 * VM hangs instead of OOPSing -- with the VCPUs that did not
-		 * fail, spinning in stop_machine(), waiting for the failed
-		 * VCPUs to come up.
-		 */
-		if (other_cpu && is_up && (rc == 0) &&
+		xen_vcpu_setup_restore(cpu);
+
+		if (other_cpu && is_up &&
 		    HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
 			BUG();
 	}
@@ -200,7 +154,7 @@ void xen_vcpu_info_reset(int cpu)
 	}
 }
 
-int xen_vcpu_setup(int cpu)
+void xen_vcpu_setup(int cpu)
 {
 	struct vcpu_register_vcpu_info info;
 	int err;
@@ -221,44 +175,26 @@ int xen_vcpu_setup(int cpu)
 	 */
 	if (xen_hvm_domain()) {
 		if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
-			return 0;
+			return;
 	}
 
-	if (xen_have_vcpu_info_placement) {
-		vcpup = &per_cpu(xen_vcpu_info, cpu);
-		info.mfn = arbitrary_virt_to_mfn(vcpup);
-		info.offset = offset_in_page(vcpup);
-
-		/*
-		 * Check to see if the hypervisor will put the vcpu_info
-		 * structure where we want it, which allows direct access via
-		 * a percpu-variable.
-		 * N.B. This hypercall can _only_ be called once per CPU.
-		 * Subsequent calls will error out with -EINVAL. This is due to
-		 * the fact that hypervisor has no unregister variant and this
-		 * hypercall does not allow to over-write info.mfn and
-		 * info.offset.
-		 */
-		err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info,
-					 xen_vcpu_nr(cpu), &info);
-
-		if (err) {
-			pr_warn_once("register_vcpu_info failed: cpu=%d err=%d\n",
-				     cpu, err);
-			xen_have_vcpu_info_placement = 0;
-		} else {
-			/*
-			 * This cpu is using the registered vcpu info, even if
-			 * later ones fail to.
-			 */
-			per_cpu(xen_vcpu, cpu) = vcpup;
-		}
-	}
+	vcpup = &per_cpu(xen_vcpu_info, cpu);
+	info.mfn = arbitrary_virt_to_mfn(vcpup);
+	info.offset = offset_in_page(vcpup);
 
-	if (!xen_have_vcpu_info_placement)
-		xen_vcpu_info_reset(cpu);
+	/*
+	 * N.B. This hypercall can _only_ be called once per CPU.
+	 * Subsequent calls will error out with -EINVAL. This is due to
+	 * the fact that hypervisor has no unregister variant and this
+	 * hypercall does not allow to over-write info.mfn and
+	 * info.offset.
+	 */
+	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
+				 &info);
+	if (err)
+		panic("register_vcpu_info failed: cpu=%d err=%d\n", cpu, err);
 
-	return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0);
+	per_cpu(xen_vcpu, cpu) = vcpup;
 }
 
 void __init xen_banner(void)
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index e68ea5f4ad1c..42300941ec29 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -163,9 +163,9 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
 		per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
 	else
 		per_cpu(xen_vcpu_id, cpu) = cpu;
-	rc = xen_vcpu_setup(cpu);
-	if (rc || !xen_have_vector_callback)
-		return rc;
+	xen_vcpu_setup(cpu);
+	if (!xen_have_vector_callback)
+		return 0;
 
 	if (xen_feature(XENFEAT_hvm_safe_pvclock))
 		xen_setup_timer(cpu);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 4f63117f09bb..5004feb16783 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -27,7 +27,6 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/page-flags.h>
-#include <linux/highmem.h>
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/edd.h>
@@ -993,31 +992,13 @@ void __init xen_setup_vcpu_info_placement(void)
 	for_each_possible_cpu(cpu) {
 		/* Set up direct vCPU id mapping for PV guests. */
 		per_cpu(xen_vcpu_id, cpu) = cpu;
-
-		/*
-		 * xen_vcpu_setup(cpu) can fail  -- in which case it
-		 * falls back to the shared_info version for cpus
-		 * where xen_vcpu_nr(cpu) < MAX_VIRT_CPUS.
-		 *
-		 * xen_cpu_up_prepare_pv() handles the rest by failing
-		 * them in hotplug.
-		 */
-		(void) xen_vcpu_setup(cpu);
+		xen_vcpu_setup(cpu);
 	}
 
-	/*
-	 * xen_vcpu_setup managed to place the vcpu_info within the
-	 * percpu area for all cpus, so make use of it.
-	 */
-	if (xen_have_vcpu_info_placement) {
-		pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
-		pv_ops.irq.irq_disable =
-			__PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
-		pv_ops.irq.irq_enable =
-			__PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
-		pv_ops.mmu.read_cr2 =
-			__PV_IS_CALLEE_SAVE(xen_read_cr2_direct);
-	}
+	pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
+	pv_ops.irq.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
+	pv_ops.irq.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
+	pv_ops.mmu.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2_direct);
 }
 
 static const struct pv_info xen_info __initconst = {
@@ -1247,12 +1228,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
 	__default_kernel_pte_mask &= ~_PAGE_GLOBAL;
 
-	/*
-	 * Prevent page tables from being allocated in highmem, even
-	 * if CONFIG_HIGHPTE is enabled.
-	 */
-	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-
 	/* Get mfn list */
 	xen_build_dynamic_phys_to_machine();
 
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 4fe387e520af..06c3c2fb4b06 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -24,60 +24,6 @@ noinstr void xen_force_evtchn_callback(void)
 	(void)HYPERVISOR_xen_version(0, NULL);
 }
 
-asmlinkage __visible noinstr unsigned long xen_save_fl(void)
-{
-	struct vcpu_info *vcpu;
-	unsigned long flags;
-
-	vcpu = this_cpu_read(xen_vcpu);
-
-	/* flag has opposite sense of mask */
-	flags = !vcpu->evtchn_upcall_mask;
-
-	/* convert to IF type flag
-	   -0 -> 0x00000000
-	   -1 -> 0xffffffff
-	*/
-	return (-flags) & X86_EFLAGS_IF;
-}
-__PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl, ".noinstr.text");
-
-asmlinkage __visible noinstr void xen_irq_disable(void)
-{
-	/* There's a one instruction preempt window here.  We need to
-	   make sure we're don't switch CPUs between getting the vcpu
-	   pointer and updating the mask. */
-	preempt_disable();
-	this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1;
-	preempt_enable_no_resched();
-}
-__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable, ".noinstr.text");
-
-asmlinkage __visible noinstr void xen_irq_enable(void)
-{
-	struct vcpu_info *vcpu;
-
-	/*
-	 * We may be preempted as soon as vcpu->evtchn_upcall_mask is
-	 * cleared, so disable preemption to ensure we check for
-	 * events on the VCPU we are still running on.
-	 */
-	preempt_disable();
-
-	vcpu = this_cpu_read(xen_vcpu);
-	vcpu->evtchn_upcall_mask = 0;
-
-	/* Doesn't matter if we get preempted here, because any
-	   pending event will get dealt with anyway. */
-
-	barrier(); /* unmask then check (avoid races) */
-	if (unlikely(vcpu->evtchn_upcall_pending))
-		xen_force_evtchn_callback();
-
-	preempt_enable();
-}
-__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable, ".noinstr.text");
-
 static void xen_safe_halt(void)
 {
 	/* Blocking includes an implicit local_irq_enable(). */
@@ -96,10 +42,10 @@ static void xen_halt(void)
 
 static const typeof(pv_ops) xen_irq_ops __initconst = {
 	.irq = {
-
-		.save_fl = PV_CALLEE_SAVE(xen_save_fl),
-		.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
-		.irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+		/* Initial interrupt flag handling only called while interrupts off. */
+		.save_fl = __PV_IS_CALLEE_SAVE(paravirt_ret0),
+		.irq_disable = __PV_IS_CALLEE_SAVE(paravirt_nop),
+		.irq_enable = __PV_IS_CALLEE_SAVE(paravirt_BUG),
 
 		.safe_halt = xen_safe_halt,
 		.halt = xen_halt,
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index cdbf4822f431..00354866921b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -41,7 +41,6 @@
  * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
  */
 #include <linux/sched/mm.h>
-#include <linux/highmem.h>
 #include <linux/debugfs.h>
 #include <linux/bug.h>
 #include <linux/vmalloc.h>
@@ -86,8 +85,10 @@
 #include "mmu.h"
 #include "debugfs.h"
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 /* l3 pud for userspace vsyscall mapping */
 static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
+#endif
 
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
@@ -241,9 +242,11 @@ static void xen_set_pmd(pmd_t *ptr, pmd_t val)
  * Associate a virtual page frame with a given physical page frame
  * and protection flags for that frame.
  */
-void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
+void __init set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
 {
-	set_pte_vaddr(vaddr, mfn_pte(mfn, flags));
+	if (HYPERVISOR_update_va_mapping(vaddr, mfn_pte(mfn, flags),
+					 UVMF_INVLPG))
+		BUG();
 }
 
 static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
@@ -789,7 +792,9 @@ static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
 static void __init xen_after_bootmem(void)
 {
 	static_branch_enable(&xen_struct_pages_ready);
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 	SetPagePinned(virt_to_page(level3_user_vsyscall));
+#endif
 	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
 }
 
@@ -1192,6 +1197,13 @@ static void __init xen_pagetable_p2m_setup(void)
 
 static void __init xen_pagetable_init(void)
 {
+	/*
+	 * The majority of further PTE writes is to pagetables already
+	 * announced as such to Xen. Hence it is more efficient to use
+	 * hypercalls for these updates.
+	 */
+	pv_ops.mmu.set_pte = __xen_set_pte;
+
 	paging_init();
 	xen_post_allocator_init();
 
@@ -1421,10 +1433,18 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
  *
  * Many of these PTE updates are done on unpinned and writable pages
  * and doing a hypercall for these is unnecessary and expensive.  At
- * this point it is not possible to tell if a page is pinned or not,
- * so always write the PTE directly and rely on Xen trapping and
+ * this point it is rarely possible to tell if a page is pinned, so
+ * mostly write the PTE directly and rely on Xen trapping and
  * emulating any updates as necessary.
  */
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
+{
+	if (unlikely(is_early_ioremap_ptep(ptep)))
+		__xen_set_pte(ptep, pte);
+	else
+		native_set_pte(ptep, pte);
+}
+
 __visible pte_t xen_make_pte_init(pteval_t pte)
 {
 	unsigned long pfn;
@@ -1446,11 +1466,6 @@ __visible pte_t xen_make_pte_init(pteval_t pte)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
 
-static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
-{
-	__xen_set_pte(ptep, pte);
-}
-
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
 static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
@@ -1750,7 +1765,6 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	set_page_prot(init_top_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
-	set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
 	set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
@@ -1767,6 +1781,13 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Unpin Xen-provided one */
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+	/* Pin user vsyscall L3 */
+	set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
+			  PFN_DOWN(__pa_symbol(level3_user_vsyscall)));
+#endif
+
 	/*
 	 * At this stage there can be no user pgd, and no page structure to
 	 * attach it to, so make sure we just set kernel pgd.
@@ -1999,6 +2020,7 @@ static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
 static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 {
 	pte_t pte;
+	unsigned long vaddr;
 
 	phys >>= PAGE_SHIFT;
 
@@ -2039,15 +2061,15 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 		break;
 	}
 
-	__native_set_fixmap(idx, pte);
+	vaddr = __fix_to_virt(idx);
+	if (HYPERVISOR_update_va_mapping(vaddr, pte, UVMF_INVLPG))
+		BUG();
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
-	if (idx == VSYSCALL_PAGE) {
-		unsigned long vaddr = __fix_to_virt(idx);
+	if (idx == VSYSCALL_PAGE)
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
-	}
 #endif
 }
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f387fc7e5250..af216feb63d9 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -306,10 +306,6 @@ static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn)
 		BUG();
 	}
 
-	/* Update kernel mapping, but not for highmem. */
-	if (pfn >= PFN_UP(__pa(high_memory - 1)))
-		return;
-
 	if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT),
 					 mfn_pte(mfn, PAGE_KERNEL), 0)) {
 		WARN(1, "Failed to update kernel mapping for mfn=%ld pfn=%ld\n",
@@ -429,13 +425,13 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 	}
 
 	/*
-	 * If the PFNs are currently mapped, the VA mapping also needs
-	 * to be updated to be 1:1.
+	 * If the PFNs are currently mapped, their VA mappings need to be
+	 * zapped.
 	 */
 	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
 		(void)HYPERVISOR_update_va_mapping(
 			(unsigned long)__va(pfn << PAGE_SHIFT),
-			mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+			native_make_pte(0), 0);
 
 	return remap_pfn;
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index c1b2f764b29a..c3e1f9a7d43a 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -121,34 +121,10 @@ int xen_smp_intr_init(unsigned int cpu)
 
 void __init xen_smp_cpus_done(unsigned int max_cpus)
 {
-	int cpu, rc, count = 0;
-
 	if (xen_hvm_domain())
 		native_smp_cpus_done(max_cpus);
 	else
 		calculate_max_logical_packages();
-
-	if (xen_have_vcpu_info_placement)
-		return;
-
-	for_each_online_cpu(cpu) {
-		if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS)
-			continue;
-
-		rc = remove_cpu(cpu);
-
-		if (rc == 0) {
-			/*
-			 * Reset vcpu_info so this cpu cannot be onlined again.
-			 */
-			xen_vcpu_info_reset(cpu);
-			count++;
-		} else {
-			pr_warn("%s: failed to bring CPU %d down, error %d\n",
-				__func__, cpu, rc);
-		}
-	}
-	WARN(count, "%s: brought %d CPUs offline\n", __func__, count);
 }
 
 void xen_smp_send_reschedule(int cpu)
@@ -268,20 +244,16 @@ void xen_send_IPI_allbutself(int vector)
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
 {
-	irq_enter();
 	generic_smp_call_function_interrupt();
 	inc_irq_stat(irq_call_count);
-	irq_exit();
 
 	return IRQ_HANDLED;
 }
 
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
 {
-	irq_enter();
 	generic_smp_call_function_single_interrupt();
 	inc_irq_stat(irq_call_count);
-	irq_exit();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 7ed56c6075b0..9e55bcbfcd33 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -458,10 +458,8 @@ static void xen_pv_stop_other_cpus(int wait)
 
 static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
 {
-	irq_enter();
 	irq_work_run();
 	inc_irq_stat(apic_irq_work_irqs);
-	irq_exit();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 9e27b86a0c31..6a64496edefb 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -45,13 +45,13 @@ SYM_CODE_START(startup_xen)
 
 	/* Clear .bss */
 	xor %eax,%eax
-	mov $__bss_start, %_ASM_DI
-	mov $__bss_stop, %_ASM_CX
-	sub %_ASM_DI, %_ASM_CX
-	shr $__ASM_SEL(2, 3), %_ASM_CX
-	rep __ASM_SIZE(stos)
+	mov $__bss_start, %rdi
+	mov $__bss_stop, %rcx
+	sub %rdi, %rcx
+	shr $3, %rcx
+	rep stosq
 
-	mov %_ASM_SI, xen_start_info
+	mov %rsi, xen_start_info
 	mov initial_stack(%rip), %rsp
 
 	/* Set up %gs.
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 8bc8b72a205d..fd0fec6e92f4 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -76,9 +76,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
 bool xen_vcpu_stolen(int vcpu);
 
-extern int xen_have_vcpu_info_placement;
-
-int xen_vcpu_setup(int cpu);
+void xen_vcpu_setup(int cpu);
 void xen_vcpu_info_reset(int cpu);
 void xen_setup_vcpu_info_placement(void);