Merge tag 'for-linus-4.9-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from David Vrabel:
 "xen features and fixes for 4.9:

   - switch to new CPU hotplug mechanism

   - support driver_override in pciback

   - require vector callback for HVM guests (the alternate mechanism via
     the platform device has been broken for ages)"

* tag 'for-linus-4.9-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/x86: Update topology map for PV VCPUs
  xen/x86: Initialize per_cpu(xen_vcpu, 0) a little earlier
  xen/pciback: support driver_override
  xen/pciback: avoid multiple entries in slot list
  xen/pciback: simplify pcistub device handling
  xen: Remove event channel notification through Xen PCI platform device
  xen/events: Convert to hotplug state machine
  xen/x86: Convert to hotplug state machine
  x86/xen: add missing \n at end of printk warning message
  xen/grant-table: Use kmalloc_array() in arch_gnttab_valloc()
  xen: Make VPMU init message look less scary
  xen: rename xen_pmu_init() in sys-hypervisor.c
  hotplug: Prevent alloc/free of irq descriptors during cpu up/down (again)
  xen/x86: Move irq allocation from Xen smp_op.cpu_up()

9 files changed, 97 insertions, 92 deletions

diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index e6911caf5bbf..608a79d5a466 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -20,15 +20,4 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 /* No need for a barrier -- XCHG is a barrier on x86. */
 #define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
 
-extern int xen_have_vector_callback;
-
-/*
- * Events delivered via platform PCI interrupts are always
- * routed to vcpu 0 and hence cannot be rebound.
- */
-static inline bool xen_support_evtchn_rebind(void)
-{
-	return (!xen_hvm_domain() || xen_have_vector_callback);
-}
-
 #endif /* _ASM_X86_XEN_EVENTS_H */
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 3a483cb5ac81..bedfab98077a 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -456,7 +456,7 @@ void __init xen_msi_init(void)
 
 int __init pci_xen_hvm_init(void)
 {
-	if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
+	if (!xen_feature(XENFEAT_hvm_pirqs))
 		return 0;
 
 #ifdef CONFIG_ACPI
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f1d2182e071f..c0fdd57da7aa 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -137,8 +137,10 @@ struct shared_info xen_dummy_shared_info;
 void *xen_initial_gdt;
 
 RESERVE_BRK(shared_info_page_brk, PAGE_SIZE);
-__read_mostly int xen_have_vector_callback;
-EXPORT_SYMBOL_GPL(xen_have_vector_callback);
+
+static int xen_cpu_up_prepare(unsigned int cpu);
+static int xen_cpu_up_online(unsigned int cpu);
+static int xen_cpu_dead(unsigned int cpu);
 
 /*
  * Point at some empty memory to start with. We map the real shared_info
@@ -1519,10 +1521,7 @@ static void __init xen_pvh_early_guest_init(void)
 	if (!xen_feature(XENFEAT_auto_translated_physmap))
 		return;
 
-	if (!xen_feature(XENFEAT_hvm_callback_vector))
-		return;
-
-	xen_have_vector_callback = 1;
+	BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector));
 
 	xen_pvh_early_cpu_init(0, false);
 	xen_pvh_set_cr_flags(0);
@@ -1538,6 +1537,24 @@ static void __init xen_dom0_set_legacy_features(void)
 	x86_platform.legacy.rtc = 1;
 }
 
+static int xen_cpuhp_setup(void)
+{
+	int rc;
+
+	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
+				       "XEN_HVM_GUEST_PREPARE",
+				       xen_cpu_up_prepare, xen_cpu_dead);
+	if (rc >= 0) {
+		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					       "XEN_HVM_GUEST_ONLINE",
+					       xen_cpu_up_online, NULL);
+		if (rc < 0)
+			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
+	}
+
+	return rc >= 0 ? 0 : rc;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
@@ -1639,6 +1656,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	   possible map and a non-dummy shared_info. */
 	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
 
+	WARN_ON(xen_cpuhp_setup());
+
 	local_irq_disable();
 	early_boot_irqs_disabled = true;
 
@@ -1819,31 +1838,54 @@ static void __init init_hvm_pv_info(void)
 	xen_domain_type = XEN_HVM_DOMAIN;
 }
 
-static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action,
-			      void *hcpu)
+static int xen_cpu_up_prepare(unsigned int cpu)
 {
-	int cpu = (long)hcpu;
-	switch (action) {
-	case CPU_UP_PREPARE:
+	int rc;
+
+	if (xen_hvm_domain()) {
+		/*
+		 * This can happen if CPU was offlined earlier and
+		 * offlining timed out in common_cpu_die().
+		 */
+		if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) {
+			xen_smp_intr_free(cpu);
+			xen_uninit_lock_cpu(cpu);
+		}
+
 		if (cpu_acpi_id(cpu) != U32_MAX)
 			per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
 		else
 			per_cpu(xen_vcpu_id, cpu) = cpu;
 		xen_vcpu_setup(cpu);
-		if (xen_have_vector_callback) {
-			if (xen_feature(XENFEAT_hvm_safe_pvclock))
-				xen_setup_timer(cpu);
-		}
-		break;
-	default:
-		break;
 	}
-	return NOTIFY_OK;
+
+	if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock))
+		xen_setup_timer(cpu);
+
+	rc = xen_smp_intr_init(cpu);
+	if (rc) {
+		WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n",
+		     cpu, rc);
+		return rc;
+	}
+	return 0;
 }
 
-static struct notifier_block xen_hvm_cpu_notifier = {
-	.notifier_call	= xen_hvm_cpu_notify,
-};
+static int xen_cpu_dead(unsigned int cpu)
+{
+	xen_smp_intr_free(cpu);
+
+	if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock))
+		xen_teardown_timer(cpu);
+
+	return 0;
+}
+
+static int xen_cpu_up_online(unsigned int cpu)
+{
+	xen_init_lock_cpu(cpu);
+	return 0;
+}
 
 #ifdef CONFIG_KEXEC_CORE
 static void xen_hvm_shutdown(void)
@@ -1871,10 +1913,10 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_panic_handler_init();
 
-	if (xen_feature(XENFEAT_hvm_callback_vector))
-		xen_have_vector_callback = 1;
+	BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector));
+
 	xen_hvm_smp_init();
-	register_cpu_notifier(&xen_hvm_cpu_notifier);
+	WARN_ON(xen_cpuhp_setup());
 	xen_unplug_emulated_devices();
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
@@ -1910,7 +1952,7 @@ bool xen_hvm_need_lapic(void)
 		return false;
 	if (!xen_hvm_domain())
 		return false;
-	if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback)
+	if (xen_feature(XENFEAT_hvm_pirqs))
 		return false;
 	return true;
 }
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index de4144c24f1c..809b6c812654 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -89,7 +89,7 @@ void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 
 static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
 {
-	area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL);
+	area->ptes = kmalloc_array(nr_frames, sizeof(*area->ptes), GFP_KERNEL);
 	if (area->ptes == NULL)
 		return -ENOMEM;
 
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index d37a0c7f82cb..90d1b83cf35f 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -61,7 +61,7 @@ static int check_platform_magic(void)
 		}
 		break;
 	default:
-		printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version");
+		printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version\n");
 		return XEN_PLATFORM_ERR_PROTOCOL;
 	}
 
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 32bdc2c90297..b9fc52556bcc 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -547,8 +547,11 @@ void xen_pmu_init(int cpu)
 	return;
 
 fail:
-	pr_info_once("Could not initialize VPMU for cpu %d, error %d\n",
-		cpu, err);
+	if (err == -EOPNOTSUPP || err == -ENOSYS)
+		pr_info_once("VPMU disabled by hypervisor.\n");
+	else
+		pr_info_once("Could not initialize VPMU for cpu %d, error %d\n",
+			cpu, err);
 	free_pages((unsigned long)xenpmu_data, 0);
 }
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 0b4d04c8ab4d..9fa27ceeecfd 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -87,6 +87,12 @@ static void cpu_bringup(void)
 	cpu_data(cpu).x86_max_cores = 1;
 	set_cpu_sibling_map(cpu);
 
+	/*
+	 * identify_cpu() may have set logical_pkg_id to -1 due
+	 * to incorrect phys_proc_id. Let's re-comupte it.
+	 */
+	topology_update_package_map(apic->cpu_present_to_apicid(cpu), cpu);
+
 	xen_setup_cpu_clockevents();
 
 	notify_cpu_starting(cpu);
@@ -115,7 +121,7 @@ asmlinkage __visible void cpu_bringup_and_idle(int cpu)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
-static void xen_smp_intr_free(unsigned int cpu)
+void xen_smp_intr_free(unsigned int cpu)
 {
 	if (per_cpu(xen_resched_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL);
@@ -159,7 +165,7 @@ static void xen_smp_intr_free(unsigned int cpu)
 		per_cpu(xen_pmu_irq, cpu).name = NULL;
 	}
 };
-static int xen_smp_intr_init(unsigned int cpu)
+int xen_smp_intr_init(unsigned int cpu)
 {
 	int rc;
 	char *resched_name, *callfunc_name, *debug_name, *pmu_name;
@@ -475,8 +481,6 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 	common_cpu_up(cpu, idle);
 
 	xen_setup_runstate_info(cpu);
-	xen_setup_timer(cpu);
-	xen_init_lock_cpu(cpu);
 
 	/*
 	 * PV VCPUs are always successfully taken down (see 'while' loop
@@ -495,10 +499,6 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	xen_pmu_init(cpu);
 
-	rc = xen_smp_intr_init(cpu);
-	if (rc)
-		return rc;
-
 	rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL);
 	BUG_ON(rc);
 
@@ -769,47 +769,10 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	xen_init_lock_cpu(0);
 }
 
-static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
-{
-	int rc;
-
-	/*
-	 * This can happen if CPU was offlined earlier and
-	 * offlining timed out in common_cpu_die().
-	 */
-	if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) {
-		xen_smp_intr_free(cpu);
-		xen_uninit_lock_cpu(cpu);
-	}
-
-	/*
-	 * xen_smp_intr_init() needs to run before native_cpu_up()
-	 * so that IPI vectors are set up on the booting CPU before
-	 * it is marked online in native_cpu_up().
-	*/
-	rc = xen_smp_intr_init(cpu);
-	WARN_ON(rc);
-	if (!rc)
-		rc =  native_cpu_up(cpu, tidle);
-
-	/*
-	 * We must initialize the slowpath CPU kicker _after_ the native
-	 * path has executed. If we initialized it before none of the
-	 * unlocker IPI kicks would reach the booting CPU as the booting
-	 * CPU had not set itself 'online' in cpu_online_mask. That mask
-	 * is checked when IPIs are sent (on HVM at least).
-	 */
-	xen_init_lock_cpu(cpu);
-	return rc;
-}
-
 void __init xen_hvm_smp_init(void)
 {
-	if (!xen_have_vector_callback)
-		return;
 	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
-	smp_ops.cpu_up = xen_hvm_cpu_up;
 	smp_ops.cpu_die = xen_cpu_die;
 	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
 	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index 963d62a35c82..c5c16dc4f694 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -1,5 +1,6 @@
 #ifndef _XEN_SMP_H
 
+#ifdef CONFIG_SMP
 extern void xen_send_IPI_mask(const struct cpumask *mask,
 			      int vector);
 extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
@@ -8,6 +9,18 @@ extern void xen_send_IPI_allbutself(int vector);
 extern void xen_send_IPI_all(int vector);
 extern void xen_send_IPI_self(int vector);
 
+extern int xen_smp_intr_init(unsigned int cpu);
+extern void xen_smp_intr_free(unsigned int cpu);
+
+#else /* CONFIG_SMP */
+
+static inline int xen_smp_intr_init(unsigned int cpu)
+{
+	return 0;
+}
+static inline void xen_smp_intr_free(unsigned int cpu) {}
+#endif /* CONFIG_SMP */
+
 #ifdef CONFIG_XEN_PVH
 extern void xen_pvh_early_cpu_init(int cpu, bool entry);
 #else
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 67356d29d74d..33d8f6a7829d 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -432,11 +432,6 @@ static void xen_hvm_setup_cpu_clockevents(void)
 
 void __init xen_hvm_init_time_ops(void)
 {
-	/* vector callback is needed otherwise we cannot receive interrupts
-	 * on cpu > 0 and at this point we don't know how many cpus are
-	 * available */
-	if (!xen_have_vector_callback)
-		return;
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
 		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
 				"disable pv timer\n");