Merge tag 'for-linus-5.1a-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

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

   - remove fallback code for very old Xen hypervisors

   - three patches for fixing Xen dom0 boot regressions

   - an old patch for Xen PCI passthrough which was never applied for
     unknown reasons

   - some more minor fixes and cleanup patches"

* tag 'for-linus-5.1a-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: fix dom0 boot on huge systems
  xen, cpu_hotplug: Prevent an out of bounds access
  xen: remove pre-xen3 fallback handlers
  xen/ACPI: Switch to bitmap_zalloc()
  x86/xen: dont add memory above max allowed allocation
  x86: respect memory size limiting via mem= parameter
  xen/gntdev: Check and release imported dma-bufs on close
  xen/gntdev: Do not destroy context while dma-bufs are in use
  xen/pciback: Don't disable PCI_COMMAND on PCI device reset.
  xen-scsiback: mark expected switch fall-through
  xen: mark expected switch fall-through

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

@@ -332,15 +332,11 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
 		return _hypercall4(int, update_va_mapping, va,
 				   new_val.pte, new_val.pte >> 32, flags);
 }
-extern int __must_check xen_event_channel_op_compat(int, void *);
 
 static inline int
 HYPERVISOR_event_channel_op(int cmd, void *arg)
 {
-	int rc = _hypercall2(int, event_channel_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS))
-		rc = xen_event_channel_op_compat(cmd, arg);
-	return rc;
+	return _hypercall2(int, event_channel_op, cmd, arg);
 }
 
 static inline int
@@ -355,15 +351,10 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
 	return _hypercall3(int, console_io, cmd, count, str);
 }
 
-extern int __must_check xen_physdev_op_compat(int, void *);
-
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
-	int rc = _hypercall2(int, physdev_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS))
-		rc = xen_physdev_op_compat(cmd, arg);
-	return rc;
+	return _hypercall2(int, physdev_op, cmd, arg);
 }
 
 static inline int

arch/x86/kernel/e820.c

@@ -14,6 +14,7 @@
 #include <linux/acpi.h>
 #include <linux/firmware-map.h>
 #include <linux/sort.h>
+#include <linux/memory_hotplug.h>
 
 #include <asm/e820/api.h>
 #include <asm/setup.h>
@@ -878,6 +879,10 @@ static int __init parse_memopt(char *p)
 
 	e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	max_mem_size = mem_size;
+#endif
+
 	return 0;
 }
 early_param("mem", parse_memopt);

arch/x86/xen/mmu_pv.c

@@ -2114,10 +2114,10 @@ void __init xen_relocate_p2m(void)
 				pt = early_memremap(pt_phys, PAGE_SIZE);
 				clear_page(pt);
 				for (idx_pte = 0;
-						idx_pte < min(n_pte, PTRS_PER_PTE);
-						idx_pte++) {
-					set_pte(pt + idx_pte,
-							pfn_pte(p2m_pfn, PAGE_KERNEL));
+				     idx_pte < min(n_pte, PTRS_PER_PTE);
+				     idx_pte++) {
+					pt[idx_pte] = pfn_pte(p2m_pfn,
+							      PAGE_KERNEL);
 					p2m_pfn++;
 				}
 				n_pte -= PTRS_PER_PTE;
@@ -2125,8 +2125,7 @@ void __init xen_relocate_p2m(void)
 				make_lowmem_page_readonly(__va(pt_phys));
 				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
 						PFN_DOWN(pt_phys));
-				set_pmd(pmd + idx_pt,
-						__pmd(_PAGE_TABLE | pt_phys));
+				pmd[idx_pt] = __pmd(_PAGE_TABLE | pt_phys);
 				pt_phys += PAGE_SIZE;
 			}
 			n_pt -= PTRS_PER_PMD;
@@ -2134,7 +2133,7 @@ void __init xen_relocate_p2m(void)
 			make_lowmem_page_readonly(__va(pmd_phys));
 			pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
 					PFN_DOWN(pmd_phys));
-			set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+			pud[idx_pmd] = __pud(_PAGE_TABLE | pmd_phys);
 			pmd_phys += PAGE_SIZE;
 		}
 		n_pmd -= PTRS_PER_PUD;

arch/x86/xen/setup.c

@@ -12,6 +12,7 @@
 #include <linux/memblock.h>
 #include <linux/cpuidle.h>
 #include <linux/cpufreq.h>
+#include <linux/memory_hotplug.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -589,6 +590,14 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start,
 	if (type == E820_TYPE_RAM) {
 		start = PAGE_ALIGN(start);
 		end &= ~((phys_addr_t)PAGE_SIZE - 1);
+#ifdef CONFIG_MEMORY_HOTPLUG
+		/*
+		 * Don't allow adding memory not in E820 map while booting the
+		 * system. Once the balloon driver is up it will remove that
+		 * restriction again.
+		 */
+		max_mem_size = end;
+#endif
 	}
 
 	e820__range_add(start, end - start, type);
@@ -748,6 +757,10 @@ char * __init xen_memory_setup(void)
 	memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries);
 	set_xen_guest_handle(memmap.buffer, xen_e820_table.entries);
 
+#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_XEN_BALLOON)
+	xen_saved_max_mem_size = max_mem_size;
+#endif
+
 	op = xen_initial_domain() ?
 		XENMEM_machine_memory_map :
 		XENMEM_memory_map;

drivers/xen/Makefile

 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
-obj-$(CONFIG_X86)			+= fallback.o
 obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o time.o
 obj-y	+= mem-reservation.o
 obj-y	+= events/

drivers/xen/cpu_hotplug.c

@@ -54,7 +54,7 @@ static int vcpu_online(unsigned int cpu)
 }
 static void vcpu_hotplug(unsigned int cpu)
 {
-	if (!cpu_possible(cpu))
+	if (cpu >= nr_cpu_ids || !cpu_possible(cpu))
 		return;
 
 	switch (vcpu_online(cpu)) {

drivers/xen/fallback.c

-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/bug.h>
-#include <linux/export.h>
-#include <asm/hypervisor.h>
-#include <asm/xen/hypercall.h>
-
-int xen_event_channel_op_compat(int cmd, void *arg)
-{
-	struct evtchn_op op;
-	int rc;
-
-	op.cmd = cmd;
-	memcpy(&op.u, arg, sizeof(op.u));
-	rc = _hypercall1(int, event_channel_op_compat, &op);
-
-	switch (cmd) {
-	case EVTCHNOP_close:
-	case EVTCHNOP_send:
-	case EVTCHNOP_bind_vcpu:
-	case EVTCHNOP_unmask:
-		/* no output */
-		break;
-
-#define COPY_BACK(eop) \
-	case EVTCHNOP_##eop: \
-		memcpy(arg, &op.u.eop, sizeof(op.u.eop)); \
-		break
-
-	COPY_BACK(bind_interdomain);
-	COPY_BACK(bind_virq);
-	COPY_BACK(bind_pirq);
-	COPY_BACK(status);
-	COPY_BACK(alloc_unbound);
-	COPY_BACK(bind_ipi);
-#undef COPY_BACK
-
-	default:
-		WARN_ON(rc != -ENOSYS);
-		break;
-	}
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(xen_event_channel_op_compat);
-
-int xen_physdev_op_compat(int cmd, void *arg)
-{
-	struct physdev_op op;
-	int rc;
-
-	op.cmd = cmd;
-	memcpy(&op.u, arg, sizeof(op.u));
-	rc = _hypercall1(int, physdev_op_compat, &op);
-
-	switch (cmd) {
-	case PHYSDEVOP_IRQ_UNMASK_NOTIFY:
-	case PHYSDEVOP_set_iopl:
-	case PHYSDEVOP_set_iobitmap:
-	case PHYSDEVOP_apic_write:
-		/* no output */
-		break;
-
-#define COPY_BACK(pop, fld) \
-	case PHYSDEVOP_##pop: \
-		memcpy(arg, &op.u.fld, sizeof(op.u.fld)); \
-		break
-
-	COPY_BACK(irq_status_query, irq_status_query);
-	COPY_BACK(apic_read, apic_op);
-	COPY_BACK(ASSIGN_VECTOR, irq_op);
-#undef COPY_BACK
-
-	default:
-		WARN_ON(rc != -ENOSYS);
-		break;
-	}
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(xen_physdev_op_compat);

drivers/xen/gntdev-dmabuf.c

@@ -80,6 +80,12 @@ struct gntdev_dmabuf_priv {
 	struct list_head imp_list;
 	/* This is the lock which protects dma_buf_xxx lists. */
 	struct mutex lock;
+	/*
+	 * We reference this file while exporting dma-bufs, so
+	 * the grant device context is not destroyed while there are
+	 * external users alive.
+	 */
+	struct file *filp;
 };
 
 /* DMA buffer export support. */
@@ -311,6 +317,7 @@ static void dmabuf_exp_release(struct kref *kref)
 
 	dmabuf_exp_wait_obj_signal(gntdev_dmabuf->priv, gntdev_dmabuf);
 	list_del(&gntdev_dmabuf->next);
+	fput(gntdev_dmabuf->priv->filp);
 	kfree(gntdev_dmabuf);
 }
 
@@ -423,6 +430,7 @@ static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
 	mutex_lock(&args->dmabuf_priv->lock);
 	list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list);
 	mutex_unlock(&args->dmabuf_priv->lock);
+	get_file(gntdev_dmabuf->priv->filp);
 	return 0;
 
 fail:
@@ -737,6 +745,14 @@ static int dmabuf_imp_release(struct gntdev_dmabuf_priv *priv, u32 fd)
 	return 0;
 }
 
+static void dmabuf_imp_release_all(struct gntdev_dmabuf_priv *priv)
+{
+	struct gntdev_dmabuf *q, *gntdev_dmabuf;
+
+	list_for_each_entry_safe(gntdev_dmabuf, q, &priv->imp_list, next)
+		dmabuf_imp_release(priv, gntdev_dmabuf->fd);
+}
+
 /* DMA buffer IOCTL support. */
 
 long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
@@ -834,7 +850,7 @@ long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
 	return dmabuf_imp_release(priv->dmabuf_priv, op.fd);
 }
 
-struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void)
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(struct file *filp)
 {
 	struct gntdev_dmabuf_priv *priv;
 
@@ -847,10 +863,13 @@ struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void)
 	INIT_LIST_HEAD(&priv->exp_wait_list);
 	INIT_LIST_HEAD(&priv->imp_list);
 
+	priv->filp = filp;
+
 	return priv;
 }
 
 void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv)
 {
+	dmabuf_imp_release_all(priv);
 	kfree(priv);
 }

drivers/xen/gntdev-dmabuf.h

@@ -14,7 +14,7 @@
 struct gntdev_dmabuf_priv;
 struct gntdev_priv;
 
-struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void);
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(struct file *filp);
 
 void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv);
 

drivers/xen/gntdev.c

@@ -600,7 +600,7 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	mutex_init(&priv->lock);
 
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
-	priv->dmabuf_priv = gntdev_dmabuf_init();
+	priv->dmabuf_priv = gntdev_dmabuf_init(flip);
 	if (IS_ERR(priv->dmabuf_priv)) {
 		ret = PTR_ERR(priv->dmabuf_priv);
 		kfree(priv);

drivers/xen/xen-acpi-processor.c

@@ -410,21 +410,21 @@ static int check_acpi_ids(struct acpi_processor *pr_backup)
 	/* All online CPUs have been processed at this stage. Now verify
 	 * whether in fact "online CPUs" == physical CPUs.
 	 */
-	acpi_id_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
+	acpi_id_present = bitmap_zalloc(nr_acpi_bits, GFP_KERNEL);
 	if (!acpi_id_present)
 		return -ENOMEM;
 
-	acpi_id_cst_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
+	acpi_id_cst_present = bitmap_zalloc(nr_acpi_bits, GFP_KERNEL);
 	if (!acpi_id_cst_present) {
-		kfree(acpi_id_present);
+		bitmap_free(acpi_id_present);
 		return -ENOMEM;
 	}
 
 	acpi_psd = kcalloc(nr_acpi_bits, sizeof(struct acpi_psd_package),
 			   GFP_KERNEL);
 	if (!acpi_psd) {
-		kfree(acpi_id_present);
-		kfree(acpi_id_cst_present);
+		bitmap_free(acpi_id_present);
+		bitmap_free(acpi_id_cst_present);
 		return -ENOMEM;
 	}
 
@@ -533,14 +533,14 @@ static int __init xen_acpi_processor_init(void)
 		return -ENODEV;
 
 	nr_acpi_bits = get_max_acpi_id() + 1;
-	acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
+	acpi_ids_done = bitmap_zalloc(nr_acpi_bits, GFP_KERNEL);
 	if (!acpi_ids_done)
 		return -ENOMEM;
 
 	acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
 	if (!acpi_perf_data) {
 		pr_debug("Memory allocation error for acpi_perf_data\n");
-		kfree(acpi_ids_done);
+		bitmap_free(acpi_ids_done);
 		return -ENOMEM;
 	}
 	for_each_possible_cpu(i) {
@@ -584,7 +584,7 @@ static int __init xen_acpi_processor_init(void)
 err_out:
 	/* Freeing a NULL pointer is OK: alloc_percpu zeroes. */
 	free_acpi_perf_data();
-	kfree(acpi_ids_done);
+	bitmap_free(acpi_ids_done);
 	return rc;
 }
 static void __exit xen_acpi_processor_exit(void)
@@ -592,9 +592,9 @@ static void __exit xen_acpi_processor_exit(void)
 	int i;
 
 	unregister_syscore_ops(&xap_syscore_ops);
-	kfree(acpi_ids_done);
-	kfree(acpi_id_present);
-	kfree(acpi_id_cst_present);
+	bitmap_free(acpi_ids_done);
+	bitmap_free(acpi_id_present);
+	bitmap_free(acpi_id_cst_present);
 	kfree(acpi_psd);
 	for_each_possible_cpu(i)
 		acpi_processor_unregister_performance(i);

drivers/xen/xen-balloon.c

@@ -37,6 +37,7 @@
 #include <linux/mm_types.h>
 #include <linux/init.h>
 #include <linux/capability.h>
+#include <linux/memory_hotplug.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -50,6 +51,10 @@
 
 #define BALLOON_CLASS_NAME "xen_memory"
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+u64 xen_saved_max_mem_size = 0;
+#endif
+
 static struct device balloon_dev;
 
 static int register_balloon(struct device *dev);
@@ -63,6 +68,12 @@ static void watch_target(struct xenbus_watch *watch,
 	static bool watch_fired;
 	static long target_diff;
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/* The balloon driver will take care of adding memory now. */
+	if (xen_saved_max_mem_size)
+		max_mem_size = xen_saved_max_mem_size;
+#endif
+
 	err = xenbus_scanf(XBT_NIL, "memory", "target", "%llu", &new_target);
 	if (err != 1) {
 		/* This is ok (for domain0 at least) - so just return */

drivers/xen/xen-pciback/pciback_ops.c

@@ -127,8 +127,6 @@ void xen_pcibk_reset_device(struct pci_dev *dev)
 		if (pci_is_enabled(dev))
 			pci_disable_device(dev);
 
-		pci_write_config_word(dev, PCI_COMMAND, 0);
-
 		dev->is_busmaster = 0;
 	} else {
 		pci_read_config_word(dev, PCI_COMMAND, &cmd);

drivers/xen/xen-pciback/xenbus.c

@@ -544,7 +544,7 @@ static void xen_pcibk_frontend_changed(struct xenbus_device *xdev,
 		xenbus_switch_state(xdev, XenbusStateClosed);
 		if (xenbus_dev_is_online(xdev))
 			break;
-		/* fall through if not online */
+		/* fall through - if not online */
 	case XenbusStateUnknown:
 		dev_dbg(&xdev->dev, "frontend is gone! unregister device\n");
 		device_unregister(&xdev->dev);

drivers/xen/xen-scsiback.c

@@ -1184,7 +1184,7 @@ static void scsiback_frontend_changed(struct xenbus_device *dev,
 		xenbus_switch_state(dev, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
-		/* fall through if not online */
+		/* fall through - if not online */
 	case XenbusStateUnknown:
 		device_unregister(&dev->dev);
 		break;

include/linux/memory_hotplug.h

@@ -100,6 +100,8 @@ extern void __online_page_free(struct page *page);
 
 extern int try_online_node(int nid);
 
+extern u64 max_mem_size;
+
 extern bool memhp_auto_online;
 /* If movable_node boot option specified */
 extern bool movable_node_enabled;

include/xen/xen.h

@@ -46,4 +46,8 @@ struct bio_vec;
 bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 		const struct bio_vec *vec2);
 
+#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_XEN_BALLOON)
+extern u64 xen_saved_max_mem_size;
+#endif
+
 #endif	/* _XEN_XEN_H */

mm/memory_hotplug.c

@@ -96,10 +96,16 @@ void mem_hotplug_done(void)
 	cpus_read_unlock();
 }
 
+u64 max_mem_size = U64_MAX;
+
 /* add this memory to iomem resource */
 static struct resource *register_memory_resource(u64 start, u64 size)
 {
 	struct resource *res, *conflict;
+
+	if (start + size > max_mem_size)
+		return ERR_PTR(-E2BIG);
+
 	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
 	if (!res)
 		return ERR_PTR(-ENOMEM);