Merge tag 'for-linus-4.18-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:
 "This contains the following fixes/cleanups:

   - the removal of a BUG_ON() which wasn't necessary and which could
     trigger now due to a recent change

   - a correction of a long standing bug happening very rarely in Xen
     dom0 when a hypercall buffer from user land was not accessible by
     the hypervisor for very short periods of time due to e.g. page
     migration or compaction

   - usage of EXPORT_SYMBOL_GPL() instead of EXPORT_SYMBOL() in a
     Xen-related driver (no breakage possible as using those symbols
     without others already exported via EXPORT-SYMBOL_GPL() wouldn't
     make any sense)

   - a simplification for Xen PVH or Xen ARM guests

   - some additional error handling for callers of xenbus_printf()"

* tag 'for-linus-4.18-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: Remove unnecessary BUG_ON from __unbind_from_irq()
  xen: add new hypercall buffer mapping device
  xen/scsiback: add error handling for xenbus_printf
  scsi: xen-scsifront: add error handling for xenbus_printf
  xen/grant-table: Export gnttab_{alloc|free}_pages as GPL
  xen: add error handling for xenbus_printf
  xen: share start flags between PV and PVH

14 files changed, 297 insertions, 22 deletions

diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 8073625371f5..07060e5b5864 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -59,6 +59,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
 static __read_mostly unsigned int xen_events_irq;
 
+uint32_t xen_start_flags;
+EXPORT_SYMBOL(xen_start_flags);
+
 int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       xen_pfn_t *gfn, int nr,
@@ -293,9 +296,7 @@ void __init xen_early_init(void)
 	xen_setup_features();
 
 	if (xen_feature(XENFEAT_dom0))
-		xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
-	else
-		xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
+		xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
 
 	if (!console_set_on_cmdline && !xen_initial_domain())
 		add_preferred_console("hvc", 0, NULL);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c9081c6671f0..3b5318505c69 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -65,6 +65,13 @@ __read_mostly int xen_have_vector_callback;
 EXPORT_SYMBOL_GPL(xen_have_vector_callback);
 
 /*
+ * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
+ * before clearing the bss.
+ */
+uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
+EXPORT_SYMBOL(xen_start_flags);
+
+/*
  * Point at some empty memory to start with. We map the real shared_info
  * page as soon as fixmap is up and running.
  */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 357969a3697c..8d4e2e1ae60b 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1203,6 +1203,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		return;
 
 	xen_domain_type = XEN_PV_DOMAIN;
+	xen_start_flags = xen_start_info->flags;
 
 	xen_setup_features();
 
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index aa1c6a6831a9..c85d1a88f476 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -97,6 +97,7 @@ void __init xen_prepare_pvh(void)
 	}
 
 	xen_pvh = 1;
+	xen_start_flags = pvh_start_info.flags;
 
 	msr = cpuid_ebx(xen_cpuid_base() + 2);
 	pfn = __pa(hypercall_page);
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index 36f59a1be7e9..61389bdc7926 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -654,10 +654,17 @@ static int scsifront_dev_reset_handler(struct scsi_cmnd *sc)
 static int scsifront_sdev_configure(struct scsi_device *sdev)
 {
 	struct vscsifrnt_info *info = shost_priv(sdev->host);
+	int err;
 
-	if (info && current == info->curr)
-		xenbus_printf(XBT_NIL, info->dev->nodename,
+	if (info && current == info->curr) {
+		err = xenbus_printf(XBT_NIL, info->dev->nodename,
 			      info->dev_state_path, "%d", XenbusStateConnected);
+		if (err) {
+			xenbus_dev_error(info->dev, err,
+				"%s: writing dev_state_path", __func__);
+			return err;
+		}
+	}
 
 	return 0;
 }
@@ -665,10 +672,15 @@ static int scsifront_sdev_configure(struct scsi_device *sdev)
 static void scsifront_sdev_destroy(struct scsi_device *sdev)
 {
 	struct vscsifrnt_info *info = shost_priv(sdev->host);
+	int err;
 
-	if (info && current == info->curr)
-		xenbus_printf(XBT_NIL, info->dev->nodename,
+	if (info && current == info->curr) {
+		err = xenbus_printf(XBT_NIL, info->dev->nodename,
 			      info->dev_state_path, "%d", XenbusStateClosed);
+		if (err)
+			xenbus_dev_error(info->dev, err,
+				"%s: writing dev_state_path", __func__);
+	}
 }
 
 static struct scsi_host_template scsifront_sht = {
@@ -1003,9 +1015,12 @@ static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op)
 
 			if (scsi_add_device(info->host, chn, tgt, lun)) {
 				dev_err(&dev->dev, "scsi_add_device\n");
-				xenbus_printf(XBT_NIL, dev->nodename,
+				err = xenbus_printf(XBT_NIL, dev->nodename,
 					      info->dev_state_path,
 					      "%d", XenbusStateClosed);
+				if (err)
+					xenbus_dev_error(dev, err,
+						"%s: writing dev_state_path", __func__);
 			}
 			break;
 		case VSCSIFRONT_OP_DEL_LUN:
@@ -1019,10 +1034,14 @@ static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op)
 			}
 			break;
 		case VSCSIFRONT_OP_READD_LUN:
-			if (device_state == XenbusStateConnected)
-				xenbus_printf(XBT_NIL, dev->nodename,
+			if (device_state == XenbusStateConnected) {
+				err = xenbus_printf(XBT_NIL, dev->nodename,
 					      info->dev_state_path,
 					      "%d", XenbusStateConnected);
+				if (err)
+					xenbus_dev_error(dev, err,
+						"%s: writing dev_state_path", __func__);
+			}
 			break;
 		default:
 			break;
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 451e833f5931..48b154276179 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -41,4 +41,4 @@ obj-$(CONFIG_XEN_PVCALLS_FRONTEND)	+= pvcalls-front.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o
-xen-privcmd-y				:= privcmd.o
+xen-privcmd-y				:= privcmd.o privcmd-buf.o
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 762378f1811c..08e4af04d6f2 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -628,8 +628,6 @@ static void __unbind_from_irq(unsigned int irq)
 		xen_irq_info_cleanup(info);
 	}
 
-	BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
-
 	xen_free_irq(irq);
 }
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 2473b0a9e6e4..ba9f3eec2bd0 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -799,7 +799,7 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 
 	return 0;
 }
-EXPORT_SYMBOL(gnttab_alloc_pages);
+EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
 
 /**
  * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
@@ -820,7 +820,7 @@ void gnttab_free_pages(int nr_pages, struct page **pages)
 	}
 	free_xenballooned_pages(nr_pages, pages);
 }
-EXPORT_SYMBOL(gnttab_free_pages);
+EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
 /* Handling of paged out grant targets (GNTST_eagain) */
 #define MAX_DELAY 256
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 8835065029d3..c93d8ef8df34 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -289,8 +289,15 @@ static void sysrq_handler(struct xenbus_watch *watch, const char *path,
 		return;
 	}
 
-	if (sysrq_key != '\0')
-		xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+	if (sysrq_key != '\0') {
+		err = xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
+		if (err) {
+			pr_err("%s: Error %d writing sysrq in control/sysrq\n",
+			       __func__, err);
+			xenbus_transaction_end(xbt, 1);
+			return;
+		}
+	}
 
 	err = xenbus_transaction_end(xbt, 0);
 	if (err == -EAGAIN)
@@ -342,7 +349,12 @@ static int setup_shutdown_watcher(void)
 			continue;
 		snprintf(node, FEATURE_PATH_SIZE, "feature-%s",
 			 shutdown_handlers[idx].command);
-		xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+		err = xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+		if (err) {
+			pr_err("%s: Error %d writing %s\n", __func__,
+				err, node);
+			return err;
+		}
 	}
 
 	return 0;
diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c
new file mode 100644
index 000000000000..df1ed37c3269
--- /dev/null
+++ b/drivers/xen/privcmd-buf.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+
+/******************************************************************************
+ * privcmd-buf.c
+ *
+ * Mmap of hypercall buffers.
+ *
+ * Copyright (c) 2018 Juergen Gross
+ */
+
+#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include "privcmd.h"
+
+MODULE_LICENSE("GPL");
+
+static unsigned int limit = 64;
+module_param(limit, uint, 0644);
+MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by "
+			"the privcmd-buf device per open file");
+
+struct privcmd_buf_private {
+	struct mutex lock;
+	struct list_head list;
+	unsigned int allocated;
+};
+
+struct privcmd_buf_vma_private {
+	struct privcmd_buf_private *file_priv;
+	struct list_head list;
+	unsigned int users;
+	unsigned int n_pages;
+	struct page *pages[];
+};
+
+static int privcmd_buf_open(struct inode *ino, struct file *file)
+{
+	struct privcmd_buf_private *file_priv;
+
+	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
+	if (!file_priv)
+		return -ENOMEM;
+
+	mutex_init(&file_priv->lock);
+	INIT_LIST_HEAD(&file_priv->list);
+
+	file->private_data = file_priv;
+
+	return 0;
+}
+
+static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv)
+{
+	unsigned int i;
+
+	vma_priv->file_priv->allocated -= vma_priv->n_pages;
+
+	list_del(&vma_priv->list);
+
+	for (i = 0; i < vma_priv->n_pages; i++)
+		if (vma_priv->pages[i])
+			__free_page(vma_priv->pages[i]);
+
+	kfree(vma_priv);
+}
+
+static int privcmd_buf_release(struct inode *ino, struct file *file)
+{
+	struct privcmd_buf_private *file_priv = file->private_data;
+	struct privcmd_buf_vma_private *vma_priv;
+
+	mutex_lock(&file_priv->lock);
+
+	while (!list_empty(&file_priv->list)) {
+		vma_priv = list_first_entry(&file_priv->list,
+					    struct privcmd_buf_vma_private,
+					    list);
+		privcmd_buf_vmapriv_free(vma_priv);
+	}
+
+	mutex_unlock(&file_priv->lock);
+
+	kfree(file_priv);
+
+	return 0;
+}
+
+static void privcmd_buf_vma_open(struct vm_area_struct *vma)
+{
+	struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data;
+
+	if (!vma_priv)
+		return;
+
+	mutex_lock(&vma_priv->file_priv->lock);
+	vma_priv->users++;
+	mutex_unlock(&vma_priv->file_priv->lock);
+}
+
+static void privcmd_buf_vma_close(struct vm_area_struct *vma)
+{
+	struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data;
+	struct privcmd_buf_private *file_priv;
+
+	if (!vma_priv)
+		return;
+
+	file_priv = vma_priv->file_priv;
+
+	mutex_lock(&file_priv->lock);
+
+	vma_priv->users--;
+	if (!vma_priv->users)
+		privcmd_buf_vmapriv_free(vma_priv);
+
+	mutex_unlock(&file_priv->lock);
+}
+
+static vm_fault_t privcmd_buf_vma_fault(struct vm_fault *vmf)
+{
+	pr_debug("fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
+		 vmf->vma, vmf->vma->vm_start, vmf->vma->vm_end,
+		 vmf->pgoff, (void *)vmf->address);
+
+	return VM_FAULT_SIGBUS;
+}
+
+static const struct vm_operations_struct privcmd_buf_vm_ops = {
+	.open = privcmd_buf_vma_open,
+	.close = privcmd_buf_vma_close,
+	.fault = privcmd_buf_vma_fault,
+};
+
+static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct privcmd_buf_private *file_priv = file->private_data;
+	struct privcmd_buf_vma_private *vma_priv;
+	unsigned long count = vma_pages(vma);
+	unsigned int i;
+	int ret = 0;
+
+	if (!(vma->vm_flags & VM_SHARED) || count > limit ||
+	    file_priv->allocated + count > limit)
+		return -EINVAL;
+
+	vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *),
+			   GFP_KERNEL);
+	if (!vma_priv)
+		return -ENOMEM;
+
+	vma_priv->n_pages = count;
+	count = 0;
+	for (i = 0; i < vma_priv->n_pages; i++) {
+		vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!vma_priv->pages[i])
+			break;
+		count++;
+	}
+
+	mutex_lock(&file_priv->lock);
+
+	file_priv->allocated += count;
+
+	vma_priv->file_priv = file_priv;
+	vma_priv->users = 1;
+
+	vma->vm_flags |= VM_IO | VM_DONTEXPAND;
+	vma->vm_ops = &privcmd_buf_vm_ops;
+	vma->vm_private_data = vma_priv;
+
+	list_add(&vma_priv->list, &file_priv->list);
+
+	if (vma_priv->n_pages != count)
+		ret = -ENOMEM;
+	else
+		for (i = 0; i < vma_priv->n_pages; i++) {
+			ret = vm_insert_page(vma, vma->vm_start + i * PAGE_SIZE,
+					     vma_priv->pages[i]);
+			if (ret)
+				break;
+		}
+
+	if (ret)
+		privcmd_buf_vmapriv_free(vma_priv);
+
+	mutex_unlock(&file_priv->lock);
+
+	return ret;
+}
+
+const struct file_operations xen_privcmdbuf_fops = {
+	.owner = THIS_MODULE,
+	.open = privcmd_buf_open,
+	.release = privcmd_buf_release,
+	.mmap = privcmd_buf_mmap,
+};
+EXPORT_SYMBOL_GPL(xen_privcmdbuf_fops);
+
+struct miscdevice xen_privcmdbuf_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "xen/hypercall",
+	.fops = &xen_privcmdbuf_fops,
+};
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 8ae0349d9f0a..7e6e682104dc 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1007,12 +1007,21 @@ static int __init privcmd_init(void)
 		pr_err("Could not register Xen privcmd device\n");
 		return err;
 	}
+
+	err = misc_register(&xen_privcmdbuf_dev);
+	if (err != 0) {
+		pr_err("Could not register Xen hypercall-buf device\n");
+		misc_deregister(&privcmd_dev);
+		return err;
+	}
+
 	return 0;
 }
 
 static void __exit privcmd_exit(void)
 {
 	misc_deregister(&privcmd_dev);
+	misc_deregister(&xen_privcmdbuf_dev);
 }
 
 module_init(privcmd_init);
diff --git a/drivers/xen/privcmd.h b/drivers/xen/privcmd.h
index 14facaeed36f..0dd9f8f67ee3 100644
--- a/drivers/xen/privcmd.h
+++ b/drivers/xen/privcmd.h
@@ -1,3 +1,6 @@
 #include <linux/fs.h>
 
 extern const struct file_operations xen_privcmd_fops;
+extern const struct file_operations xen_privcmdbuf_fops;
+
+extern struct miscdevice xen_privcmdbuf_dev;
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 7bc88fd43cfc..e2f3e8b0fba9 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1012,6 +1012,7 @@ static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state,
 {
 	struct v2p_entry *entry;
 	unsigned long flags;
+	int err;
 
 	if (try) {
 		spin_lock_irqsave(&info->v2p_lock, flags);
@@ -1027,8 +1028,11 @@ static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state,
 			scsiback_del_translation_entry(info, vir);
 		}
 	} else if (!try) {
-		xenbus_printf(XBT_NIL, info->dev->nodename, state,
+		err = xenbus_printf(XBT_NIL, info->dev->nodename, state,
 			      "%d", XenbusStateClosed);
+		if (err)
+			xenbus_dev_error(info->dev, err,
+				"%s: writing %s", __func__, state);
 	}
 }
 
@@ -1067,8 +1071,11 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op,
 	snprintf(str, sizeof(str), "vscsi-devs/%s/p-dev", ent);
 	val = xenbus_read(XBT_NIL, dev->nodename, str, NULL);
 	if (IS_ERR(val)) {
-		xenbus_printf(XBT_NIL, dev->nodename, state,
+		err = xenbus_printf(XBT_NIL, dev->nodename, state,
 			      "%d", XenbusStateClosed);
+		if (err)
+			xenbus_dev_error(info->dev, err,
+				"%s: writing %s", __func__, state);
 		return;
 	}
 	strlcpy(phy, val, VSCSI_NAMELEN);
@@ -1079,8 +1086,11 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op,
 	err = xenbus_scanf(XBT_NIL, dev->nodename, str, "%u:%u:%u:%u",
 			   &vir.hst, &vir.chn, &vir.tgt, &vir.lun);
 	if (XENBUS_EXIST_ERR(err)) {
-		xenbus_printf(XBT_NIL, dev->nodename, state,
+		err = xenbus_printf(XBT_NIL, dev->nodename, state,
 			      "%d", XenbusStateClosed);
+		if (err)
+			xenbus_dev_error(info->dev, err,
+				"%s: writing %s", __func__, state);
 		return;
 	}
 
diff --git a/include/xen/xen.h b/include/xen/xen.h
index 9d4340c907d1..1e1d9bd0bd37 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -25,12 +25,16 @@ extern bool xen_pvh;
 #define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
 #define xen_pvh_domain()	(xen_pvh)
 
+#include <linux/types.h>
+
+extern uint32_t xen_start_flags;
+
 #ifdef CONFIG_XEN_DOM0
 #include <xen/interface/xen.h>
 #include <asm/xen/hypervisor.h>
 
 #define xen_initial_domain()	(xen_domain() && \
-				 xen_start_info && xen_start_info->flags & SIF_INITDOMAIN)
+				 (xen_start_flags & SIF_INITDOMAIN))
 #else  /* !CONFIG_XEN_DOM0 */
 #define xen_initial_domain()	(0)
 #endif	/* CONFIG_XEN_DOM0 */