Merge tag 'for-linus-5.3a-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:
 "Fixes and features:

   - A series to introduce a common command line parameter for disabling
     paravirtual extensions when running as a guest in virtualized
     environment

   - A fix for int3 handling in Xen pv guests

   - Removal of the Xen-specific tmem driver as support of tmem in Xen
     has been dropped (and it was experimental only)

   - A security fix for running as Xen dom0 (XSA-300)

   - A fix for IRQ handling when offlining cpus in Xen guests

   - Some small cleanups"

* tag 'for-linus-5.3a-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: let alloc_xenballooned_pages() fail if not enough memory free
  xen/pv: Fix a boot up hang revealed by int3 self test
  x86/xen: Add "nopv" support for HVM guest
  x86/paravirt: Remove const mark from x86_hyper_xen_hvm variable
  xen: Map "xen_nopv" parameter to "nopv" and mark it obsolete
  x86: Add "nopv" parameter to disable PV extensions
  x86/xen: Mark xen_hvm_need_lapic() and xen_x2apic_para_available() as __init
  xen: remove tmem driver
  Revert "x86/paravirt: Set up the virt_spin_lock_key after static keys get initialized"
  xen/events: fix binding user event channels to cpus

Documentation/admin-guide/kernel-parameters.txt

@@ -4698,27 +4698,6 @@
 			Force threading of all interrupt handlers except those
 			marked explicitly IRQF_NO_THREAD.
 
-	tmem		[KNL,XEN]
-			Enable the Transcendent memory driver if built-in.
-
-	tmem.cleancache=0|1 [KNL, XEN]
-			Default is on (1). Disable the usage of the cleancache
-			API to send anonymous pages to the hypervisor.
-
-	tmem.frontswap=0|1 [KNL, XEN]
-			Default is on (1). Disable the usage of the frontswap
-			API to send swap pages to the hypervisor. If disabled
-			the selfballooning and selfshrinking are force disabled.
-
-	tmem.selfballooning=0|1 [KNL, XEN]
-			Default is on (1). Disable the driving of swap pages
-			to the hypervisor.
-
-	tmem.selfshrinking=0|1 [KNL, XEN]
-			Default is on (1). Partial swapoff that immediately
-			transfers pages from Xen hypervisor back to the
-			kernel based on different criteria.
-
 	topology=	[S390]
 			Format: {off | on}
 			Specify if the kernel should make use of the cpu
@@ -5288,6 +5267,8 @@
 	xen_nopv	[X86]
 			Disables the PV optimizations forcing the HVM guest to
 			run as generic HVM guest with no PV drivers.
+			This option is obsoleted by the "nopv" option, which
+			has equivalent effect for XEN platform.
 
 	xen_scrub_pages=	[XEN]
 			Boolean option to control scrubbing pages before giving them back
@@ -5302,6 +5283,11 @@
 			improve timer resolution at the expense of processing
 			more timer interrupts.
 
+	nopv=		[X86,XEN,KVM,HYPER_V,VMWARE]
+			Disables the PV optimizations forcing the guest to run
+			as generic guest with no PV drivers. Currently support
+			XEN HVM, KVM, HYPER_V and VMWARE guest.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

arch/x86/entry/entry_64.S

@@ -1176,7 +1176,6 @@ idtentry stack_segment		do_stack_segment	has_error_code=1
 #ifdef CONFIG_XEN_PV
 idtentry xennmi			do_nmi			has_error_code=0
 idtentry xendebug		do_debug		has_error_code=0
-idtentry xenint3		do_int3			has_error_code=0
 #endif
 
 idtentry general_protection	do_general_protection	has_error_code=1

arch/x86/include/asm/hypervisor.h

@@ -53,8 +53,20 @@ struct hypervisor_x86 {
 
 	/* runtime callbacks */
 	struct x86_hyper_runtime runtime;
+
+	/* ignore nopv parameter */
+	bool ignore_nopv;
 };
 
+extern const struct hypervisor_x86 x86_hyper_vmware;
+extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
+extern const struct hypervisor_x86 x86_hyper_xen_pv;
+extern const struct hypervisor_x86 x86_hyper_kvm;
+extern const struct hypervisor_x86 x86_hyper_jailhouse;
+extern const struct hypervisor_x86 x86_hyper_acrn;
+extern struct hypervisor_x86 x86_hyper_xen_hvm;
+
+extern bool nopv;
 extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
 static inline bool hypervisor_is_type(enum x86_hypervisor_type type)

arch/x86/include/asm/traps.h

@@ -40,7 +40,7 @@ asmlinkage void simd_coprocessor_error(void);
 asmlinkage void xen_divide_error(void);
 asmlinkage void xen_xennmi(void);
 asmlinkage void xen_xendebug(void);
-asmlinkage void xen_xenint3(void);
+asmlinkage void xen_int3(void);
 asmlinkage void xen_overflow(void);
 asmlinkage void xen_bounds(void);
 asmlinkage void xen_invalid_op(void);

arch/x86/include/asm/x86_init.h

@@ -301,6 +301,8 @@ extern struct x86_apic_ops x86_apic_ops;
 extern void x86_early_init_platform_quirks(void);
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
+extern bool bool_x86_init_noop(void);
+extern void x86_op_int_noop(int cpu);
 extern bool x86_pnpbios_disabled(void);
 
 #endif

arch/x86/include/asm/xen/hypervisor.h

@@ -44,14 +44,14 @@ static inline uint32_t xen_cpuid_base(void)
 }
 
 #ifdef CONFIG_XEN
-extern bool xen_hvm_need_lapic(void);
+extern bool __init xen_hvm_need_lapic(void);
 
-static inline bool xen_x2apic_para_available(void)
+static inline bool __init xen_x2apic_para_available(void)
 {
 	return xen_hvm_need_lapic();
 }
 #else
-static inline bool xen_x2apic_para_available(void)
+static inline bool __init xen_x2apic_para_available(void)
 {
 	return (xen_cpuid_base() != 0);
 }

arch/x86/kernel/cpu/hypervisor.c

@@ -26,14 +26,6 @@
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 
-extern const struct hypervisor_x86 x86_hyper_vmware;
-extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
-extern const struct hypervisor_x86 x86_hyper_xen_pv;
-extern const struct hypervisor_x86 x86_hyper_xen_hvm;
-extern const struct hypervisor_x86 x86_hyper_kvm;
-extern const struct hypervisor_x86 x86_hyper_jailhouse;
-extern const struct hypervisor_x86 x86_hyper_acrn;
-
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
 #ifdef CONFIG_XEN_PV
@@ -58,6 +50,14 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
 enum x86_hypervisor_type x86_hyper_type;
 EXPORT_SYMBOL(x86_hyper_type);
 
+bool __initdata nopv;
+static __init int parse_nopv(char *arg)
+{
+	nopv = true;
+	return 0;
+}
+early_param("nopv", parse_nopv);
+
 static inline const struct hypervisor_x86 * __init
 detect_hypervisor_vendor(void)
 {
@@ -65,6 +65,9 @@ detect_hypervisor_vendor(void)
 	uint32_t pri, max_pri = 0;
 
 	for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) {
+		if (unlikely(nopv) && !(*p)->ignore_nopv)
+			continue;
+
 		pri = (*p)->detect();
 		if (pri > max_pri) {
 			max_pri = pri;

arch/x86/kernel/jailhouse.c

@@ -217,4 +217,5 @@ const struct hypervisor_x86 x86_hyper_jailhouse __refconst = {
 	.detect			= jailhouse_detect,
 	.init.init_platform	= jailhouse_init_platform,
 	.init.x2apic_available	= jailhouse_x2apic_available,
+	.ignore_nopv		= true,
 };

arch/x86/kernel/smpboot.c

@@ -1368,8 +1368,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
 
-	native_pv_lock_init();
-
 	uv_system_init();
 
 	set_mtrr_aps_delayed_init();
@@ -1399,6 +1397,7 @@ void __init native_smp_prepare_boot_cpu(void)
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
 	cpu_set_state_online(me);
+	native_pv_lock_init();
 }
 
 void __init calculate_max_logical_packages(void)

arch/x86/kernel/x86_init.c

@@ -29,8 +29,8 @@ void x86_init_noop(void) { }
 void __init x86_init_uint_noop(unsigned int unused) { }
 static int __init iommu_init_noop(void) { return 0; }
 static void iommu_shutdown_noop(void) { }
-static bool __init bool_x86_init_noop(void) { return false; }
-static void x86_op_int_noop(int cpu) { }
+bool __init bool_x86_init_noop(void) { return false; }
+void x86_op_int_noop(int cpu) { }
 
 /*
  * The platform setup functions are preset with the default functions

arch/x86/xen/enlighten_hvm.c

@@ -210,18 +210,18 @@ static void __init xen_hvm_guest_init(void)
 #endif
 }
 
-static bool xen_nopv;
 static __init int xen_parse_nopv(char *arg)
 {
-       xen_nopv = true;
+	pr_notice("\"xen_nopv\" is deprecated, please use \"nopv\" instead\n");
+
+	if (xen_cpuid_base())
+		nopv = true;
 	return 0;
 }
 early_param("xen_nopv", xen_parse_nopv);
 
-bool xen_hvm_need_lapic(void)
+bool __init xen_hvm_need_lapic(void)
 {
-	if (xen_nopv)
-		return false;
 	if (xen_pv_domain())
 		return false;
 	if (!xen_hvm_domain())
@@ -230,15 +230,6 @@ bool xen_hvm_need_lapic(void)
 		return false;
 	return true;
 }
-EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
-
-static uint32_t __init xen_platform_hvm(void)
-{
-	if (xen_pv_domain() || xen_nopv)
-		return 0;
-
-	return xen_cpuid_base();
-}
 
 static __init void xen_hvm_guest_late_init(void)
 {
@@ -251,6 +242,9 @@ static __init void xen_hvm_guest_late_init(void)
 	/* PVH detected. */
 	xen_pvh = true;
 
+	if (nopv)
+		panic("\"nopv\" and \"xen_nopv\" parameters are unsupported in PVH guest.");
+
 	/* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */
 	if (!nr_ioapics && acpi_irq_model == ACPI_IRQ_MODEL_PIC)
 		acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
@@ -260,7 +254,38 @@ static __init void xen_hvm_guest_late_init(void)
 #endif
 }
 
-const __initconst struct hypervisor_x86 x86_hyper_xen_hvm = {
+static uint32_t __init xen_platform_hvm(void)
+{
+	uint32_t xen_domain = xen_cpuid_base();
+	struct x86_hyper_init *h = &x86_hyper_xen_hvm.init;
+
+	if (xen_pv_domain())
+		return 0;
+
+	if (xen_pvh_domain() && nopv) {
+		/* Guest booting via the Xen-PVH boot entry goes here */
+		pr_info("\"nopv\" parameter is ignored in PVH guest\n");
+		nopv = false;
+	} else if (nopv && xen_domain) {
+		/*
+		 * Guest booting via normal boot entry (like via grub2) goes
+		 * here.
+		 *
+		 * Use interface functions for bare hardware if nopv,
+		 * xen_hvm_guest_late_init is an exception as we need to
+		 * detect PVH and panic there.
+		 */
+		h->init_platform = x86_init_noop;
+		h->x2apic_available = bool_x86_init_noop;
+		h->init_mem_mapping = x86_init_noop;
+		h->init_after_bootmem = x86_init_noop;
+		h->guest_late_init = xen_hvm_guest_late_init;
+		x86_hyper_xen_hvm.runtime.pin_vcpu = x86_op_int_noop;
+	}
+	return xen_domain;
+}
+
+struct hypervisor_x86 x86_hyper_xen_hvm __initdata = {
 	.name                   = "Xen HVM",
 	.detect                 = xen_platform_hvm,
 	.type			= X86_HYPER_XEN_HVM,
@@ -269,4 +294,5 @@ const __initconst struct hypervisor_x86 x86_hyper_xen_hvm = {
 	.init.init_mem_mapping	= xen_hvm_init_mem_mapping,
 	.init.guest_late_init	= xen_hvm_guest_late_init,
 	.runtime.pin_vcpu       = xen_pin_vcpu,
+	.ignore_nopv            = true,
 };

arch/x86/xen/enlighten_pv.c

@@ -596,12 +596,12 @@ struct trap_array_entry {
 
 static struct trap_array_entry trap_array[] = {
 	{ debug,                       xen_xendebug,                    true },
-	{ int3,                        xen_xenint3,                     true },
 	{ double_fault,                xen_double_fault,                true },
 #ifdef CONFIG_X86_MCE
 	{ machine_check,               xen_machine_check,               true },
 #endif
 	{ nmi,                         xen_xennmi,                      true },
+	{ int3,                        xen_int3,                        false },
 	{ overflow,                    xen_overflow,                    false },
 #ifdef CONFIG_IA32_EMULATION
 	{ entry_INT80_compat,          xen_entry_INT80_compat,          false },
@@ -1463,4 +1463,5 @@ const __initconst struct hypervisor_x86 x86_hyper_xen_pv = {
 	.detect                 = xen_platform_pv,
 	.type			= X86_HYPER_XEN_PV,
 	.runtime.pin_vcpu       = xen_pin_vcpu,
+	.ignore_nopv		= true,
 };

arch/x86/xen/spinlock.c

@@ -68,11 +68,8 @@ void xen_init_lock_cpu(int cpu)
 	int irq;
 	char *name;
 
-	if (!xen_pvspin) {
-		if (cpu == 0)
-			static_branch_disable(&virt_spin_lock_key);
+	if (!xen_pvspin)
 		return;
-	}
 
 	WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
 	     cpu, per_cpu(lock_kicker_irq, cpu));
@@ -124,6 +121,7 @@ void __init xen_init_spinlocks(void)
 
 	if (!xen_pvspin) {
 		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
+		static_branch_disable(&virt_spin_lock_key);
 		return;
 	}
 	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");

arch/x86/xen/xen-asm_64.S

@@ -32,7 +32,6 @@ xen_pv_trap divide_error
 xen_pv_trap debug
 xen_pv_trap xendebug
 xen_pv_trap int3
-xen_pv_trap xenint3
 xen_pv_trap xennmi
 xen_pv_trap overflow
 xen_pv_trap bounds

drivers/xen/Kconfig

@@ -10,21 +10,6 @@ config XEN_BALLOON
 	  the system to expand the domain's memory allocation, or alternatively
 	  return unneeded memory to the system.
 
-config XEN_SELFBALLOONING
-	bool "Dynamically self-balloon kernel memory to target"
-	depends on XEN && XEN_BALLOON && CLEANCACHE && SWAP && XEN_TMEM
-	help
-	  Self-ballooning dynamically balloons available kernel memory driven
-	  by the current usage of anonymous memory ("committed AS") and
-	  controlled by various sysfs-settable parameters.  Configuring
-	  FRONTSWAP is highly recommended; if it is not configured, self-
-	  ballooning is disabled by default. If FRONTSWAP is configured,
-	  frontswap-selfshrinking is enabled by default but can be disabled
-	  with the 'tmem.selfshrink=0' kernel boot parameter; and self-ballooning
-	  is enabled by default but can be disabled with the 'tmem.selfballooning=0'
-	  kernel boot parameter.  Note that systems without a sufficiently
-	  large swap device should not enable self-ballooning.
-
 config XEN_BALLOON_MEMORY_HOTPLUG
 	bool "Memory hotplug support for Xen balloon driver"
 	depends on XEN_BALLOON && MEMORY_HOTPLUG
@@ -191,14 +176,6 @@ config SWIOTLB_XEN
 	def_bool y
 	select SWIOTLB
 
-config XEN_TMEM
-	tristate
-	depends on !ARM && !ARM64
-	default m if (CLEANCACHE || FRONTSWAP)
-	help
-	  Shim to interface in-kernel Transcendent Memory hooks
-	  (e.g. cleancache and frontswap) to Xen tmem hypercalls.
-
 config XEN_PCIDEV_BACKEND
 	tristate "Xen PCI-device backend driver"
 	depends on PCI && X86 && XEN

drivers/xen/Makefile

@@ -17,14 +17,12 @@ dom0-$(CONFIG_X86) += pcpu.o
 obj-$(CONFIG_XEN_DOM0)			+= $(dom0-y)
 obj-$(CONFIG_BLOCK)			+= biomerge.o
 obj-$(CONFIG_XEN_BALLOON)		+= xen-balloon.o
-obj-$(CONFIG_XEN_SELFBALLOONING)	+= xen-selfballoon.o
 obj-$(CONFIG_XEN_DEV_EVTCHN)		+= xen-evtchn.o
 obj-$(CONFIG_XEN_GNTDEV)		+= xen-gntdev.o
 obj-$(CONFIG_XEN_GRANT_DEV_ALLOC)	+= xen-gntalloc.o
 obj-$(CONFIG_XENFS)			+= xenfs/
 obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
 obj-$(CONFIG_XEN_PVHVM)			+= platform-pci.o
-obj-$(CONFIG_XEN_TMEM)			+= tmem.o
 obj-$(CONFIG_SWIOTLB_XEN)		+= swiotlb-xen.o
 obj-$(CONFIG_XEN_MCE_LOG)		+= mcelog.o
 obj-$(CONFIG_XEN_PCIDEV_BACKEND)	+= xen-pciback/

drivers/xen/balloon.c

@@ -535,8 +535,15 @@ static void balloon_process(struct work_struct *work)
 				state = reserve_additional_memory();
 		}
 
-		if (credit < 0)
-			state = decrease_reservation(-credit, GFP_BALLOON);
+		if (credit < 0) {
+			long n_pages;
+
+			n_pages = min(-credit, si_mem_available());
+			state = decrease_reservation(n_pages, GFP_BALLOON);
+			if (state == BP_DONE && n_pages != -credit &&
+			    n_pages < totalreserve_pages)
+				state = BP_EAGAIN;
+		}
 
 		state = update_schedule(state);
 
@@ -575,6 +582,9 @@ static int add_ballooned_pages(int nr_pages)
 		}
 	}
 
+	if (si_mem_available() < nr_pages)
+		return -ENOMEM;
+
 	st = decrease_reservation(nr_pages, GFP_USER);
 	if (st != BP_DONE)
 		return -ENOMEM;
@@ -707,7 +717,7 @@ static int __init balloon_init(void)
 	balloon_stats.schedule_delay = 1;
 	balloon_stats.max_schedule_delay = 32;
 	balloon_stats.retry_count = 1;
-	balloon_stats.max_retry_count = RETRY_UNLIMITED;
+	balloon_stats.max_retry_count = 4;
 
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
 	set_online_page_callback(&xen_online_page);

drivers/xen/events/events_base.c

@@ -1294,7 +1294,7 @@ void rebind_evtchn_irq(int evtchn, int irq)
 }
 
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
-int xen_rebind_evtchn_to_cpu(int evtchn, unsigned tcpu)
+static int xen_rebind_evtchn_to_cpu(int evtchn, unsigned int tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
 	int masked;
@@ -1328,7 +1328,6 @@ int xen_rebind_evtchn_to_cpu(int evtchn, unsigned tcpu)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xen_rebind_evtchn_to_cpu);
 
 static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 			    bool force)
@@ -1342,6 +1341,15 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 	return ret;
 }
 
+/* To be called with desc->lock held. */
+int xen_set_affinity_evtchn(struct irq_desc *desc, unsigned int tcpu)
+{
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+
+	return set_affinity_irq(d, cpumask_of(tcpu), false);
+}
+EXPORT_SYMBOL_GPL(xen_set_affinity_evtchn);
+
 static void enable_dynirq(struct irq_data *data)
 {
 	int evtchn = evtchn_from_irq(data->irq);

drivers/xen/evtchn.c

@@ -447,7 +447,7 @@ static void evtchn_bind_interdom_next_vcpu(int evtchn)
 	this_cpu_write(bind_last_selected_cpu, selected_cpu);
 
 	/* unmask expects irqs to be disabled */
-	xen_rebind_evtchn_to_cpu(evtchn, selected_cpu);
+	xen_set_affinity_evtchn(desc, selected_cpu);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 

drivers/xen/xen-balloon.c

@@ -129,8 +129,6 @@ void xen_balloon_init(void)
 {
 	register_balloon(&balloon_dev);
 
-	register_xen_selfballooning(&balloon_dev);
-
 	register_xenstore_notifier(&xenstore_notifier);
 }
 EXPORT_SYMBOL_GPL(xen_balloon_init);

include/xen/balloon.h

@@ -27,16 +27,6 @@ void balloon_set_new_target(unsigned long target);
 int alloc_xenballooned_pages(int nr_pages, struct page **pages);
 void free_xenballooned_pages(int nr_pages, struct page **pages);
 
-struct device;
-#ifdef CONFIG_XEN_SELFBALLOONING
-extern int register_xen_selfballooning(struct device *dev);
-#else
-static inline int register_xen_selfballooning(struct device *dev)
-{
-	return -ENOSYS;
-}
-#endif
-
 #ifdef CONFIG_XEN_BALLOON
 void xen_balloon_init(void);
 #else

include/xen/events.h

@@ -3,6 +3,7 @@
 #define _XEN_EVENTS_H
 
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #ifdef CONFIG_PCI_MSI
 #include <linux/msi.h>
 #endif
@@ -59,7 +60,7 @@ void evtchn_put(unsigned int evtchn);
 
 void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector);
 void rebind_evtchn_irq(int evtchn, int irq);
-int xen_rebind_evtchn_to_cpu(int evtchn, unsigned tcpu);
+int xen_set_affinity_evtchn(struct irq_desc *desc, unsigned int tcpu);
 
 static inline void notify_remote_via_evtchn(int port)
 {

include/xen/tmem.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_TMEM_H
-#define _XEN_TMEM_H
-
-#include <linux/types.h>
-
-#ifdef CONFIG_XEN_TMEM_MODULE
-#define tmem_enabled true
-#else
-/* defined in drivers/xen/tmem.c */
-extern bool tmem_enabled;
-#endif
-
-#ifdef CONFIG_XEN_SELFBALLOONING
-extern int xen_selfballoon_init(bool, bool);
-#endif
-
-#endif /* _XEN_TMEM_H */