9 files changed, 584 insertions, 19 deletions

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index b0cf80bf4169..347f17edad77 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -338,30 +338,29 @@ static void unmask_evtchn(int port)
 
 static int find_unbound_irq(void)
 {
-	int irq;
-	struct irq_desc *desc;
+	struct irq_data *data;
+	int irq, res;
 
 	for (irq = 0; irq < nr_irqs; irq++) {
-		desc = irq_to_desc(irq);
+		data = irq_get_irq_data(irq);
 		/* only 0->15 have init'd desc; handle irq > 16 */
-		if (desc == NULL)
+		if (!data)
 			break;
-		if (desc->chip == &no_irq_chip)
+		if (data->chip == &no_irq_chip)
 			break;
-		if (desc->chip != &xen_dynamic_chip)
+		if (data->chip != &xen_dynamic_chip)
 			continue;
 		if (irq_info[irq].type == IRQT_UNBOUND)
-			break;
+			return irq;
 	}
 
 	if (irq == nr_irqs)
 		panic("No available IRQ to bind to: increase nr_irqs!\n");
 
-	desc = irq_to_desc_alloc_node(irq, 0);
-	if (WARN_ON(desc == NULL))
-		return -1;
+	res = irq_alloc_desc_at(irq, 0);
 
-	dynamic_irq_init_keep_chip_data(irq);
+	if (WARN_ON(res != irq))
+		return -1;
 
 	return irq;
 }
@@ -495,7 +494,7 @@ static void unbind_from_irq(unsigned int irq)
 	if (irq_info[irq].type != IRQT_UNBOUND) {
 		irq_info[irq] = mk_unbound_info();
 
-		dynamic_irq_cleanup(irq);
+		irq_free_desc(irq);
 	}
 
 	spin_unlock(&irq_mapping_update_lock);
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 66e185cfe92f..fec6ba3c08a8 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -467,6 +467,7 @@ static const struct file_operations evtchn_fops = {
 	.fasync  = evtchn_fasync,
 	.open    = evtchn_open,
 	.release = evtchn_release,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice evtchn_miscdev = {
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index d409495876f1..132939f36020 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -64,9 +64,11 @@
 
 
 int xen_store_evtchn;
-EXPORT_SYMBOL(xen_store_evtchn);
+EXPORT_SYMBOL_GPL(xen_store_evtchn);
 
 struct xenstore_domain_interface *xen_store_interface;
+EXPORT_SYMBOL_GPL(xen_store_interface);
+
 static unsigned long xen_store_mfn;
 
 static BLOCKING_NOTIFIER_HEAD(xenstore_chain);
diff --git a/drivers/xen/xenfs/Makefile b/drivers/xen/xenfs/Makefile
index 25275c3bbdff..4fde9440fe1f 100644
--- a/drivers/xen/xenfs/Makefile
+++ b/drivers/xen/xenfs/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_XENFS) += xenfs.o
 
-xenfs-objs = super.o xenbus.o
\ No newline at end of file
+xenfs-y			  = super.o xenbus.o privcmd.o
+xenfs-$(CONFIG_XEN_DOM0) += xenstored.o
diff --git a/drivers/xen/xenfs/privcmd.c b/drivers/xen/xenfs/privcmd.c
new file mode 100644
index 000000000000..f80be7f6eb95
--- /dev/null
+++ b/drivers/xen/xenfs/privcmd.c
@@ -0,0 +1,404 @@
+/******************************************************************************
+ * privcmd.c
+ *
+ * Interface to privileged domain-0 commands.
+ *
+ * Copyright (c) 2002-2004, K A Fraser, B Dragovic
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/uaccess.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xen.h>
+#include <xen/privcmd.h>
+#include <xen/interface/xen.h>
+#include <xen/features.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+
+#ifndef HAVE_ARCH_PRIVCMD_MMAP
+static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma);
+#endif
+
+static long privcmd_ioctl_hypercall(void __user *udata)
+{
+	struct privcmd_hypercall hypercall;
+	long ret;
+
+	if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
+		return -EFAULT;
+
+	ret = privcmd_call(hypercall.op,
+			   hypercall.arg[0], hypercall.arg[1],
+			   hypercall.arg[2], hypercall.arg[3],
+			   hypercall.arg[4]);
+
+	return ret;
+}
+
+static void free_page_list(struct list_head *pages)
+{
+	struct page *p, *n;
+
+	list_for_each_entry_safe(p, n, pages, lru)
+		__free_page(p);
+
+	INIT_LIST_HEAD(pages);
+}
+
+/*
+ * Given an array of items in userspace, return a list of pages
+ * containing the data.  If copying fails, either because of memory
+ * allocation failure or a problem reading user memory, return an
+ * error code; its up to the caller to dispose of any partial list.
+ */
+static int gather_array(struct list_head *pagelist,
+			unsigned nelem, size_t size,
+			void __user *data)
+{
+	unsigned pageidx;
+	void *pagedata;
+	int ret;
+
+	if (size > PAGE_SIZE)
+		return 0;
+
+	pageidx = PAGE_SIZE;
+	pagedata = NULL;	/* quiet, gcc */
+	while (nelem--) {
+		if (pageidx > PAGE_SIZE-size) {
+			struct page *page = alloc_page(GFP_KERNEL);
+
+			ret = -ENOMEM;
+			if (page == NULL)
+				goto fail;
+
+			pagedata = page_address(page);
+
+			list_add_tail(&page->lru, pagelist);
+			pageidx = 0;
+		}
+
+		ret = -EFAULT;
+		if (copy_from_user(pagedata + pageidx, data, size))
+			goto fail;
+
+		data += size;
+		pageidx += size;
+	}
+
+	ret = 0;
+
+fail:
+	return ret;
+}
+
+/*
+ * Call function "fn" on each element of the array fragmented
+ * over a list of pages.
+ */
+static int traverse_pages(unsigned nelem, size_t size,
+			  struct list_head *pos,
+			  int (*fn)(void *data, void *state),
+			  void *state)
+{
+	void *pagedata;
+	unsigned pageidx;
+	int ret = 0;
+
+	BUG_ON(size > PAGE_SIZE);
+
+	pageidx = PAGE_SIZE;
+	pagedata = NULL;	/* hush, gcc */
+
+	while (nelem--) {
+		if (pageidx > PAGE_SIZE-size) {
+			struct page *page;
+			pos = pos->next;
+			page = list_entry(pos, struct page, lru);
+			pagedata = page_address(page);
+			pageidx = 0;
+		}
+
+		ret = (*fn)(pagedata + pageidx, state);
+		if (ret)
+			break;
+		pageidx += size;
+	}
+
+	return ret;
+}
+
+struct mmap_mfn_state {
+	unsigned long va;
+	struct vm_area_struct *vma;
+	domid_t domain;
+};
+
+static int mmap_mfn_range(void *data, void *state)
+{
+	struct privcmd_mmap_entry *msg = data;
+	struct mmap_mfn_state *st = state;
+	struct vm_area_struct *vma = st->vma;
+	int rc;
+
+	/* Do not allow range to wrap the address space. */
+	if ((msg->npages > (LONG_MAX >> PAGE_SHIFT)) ||
+	    ((unsigned long)(msg->npages << PAGE_SHIFT) >= -st->va))
+		return -EINVAL;
+
+	/* Range chunks must be contiguous in va space. */
+	if ((msg->va != st->va) ||
+	    ((msg->va+(msg->npages<<PAGE_SHIFT)) > vma->vm_end))
+		return -EINVAL;
+
+	rc = xen_remap_domain_mfn_range(vma,
+					msg->va & PAGE_MASK,
+					msg->mfn, msg->npages,
+					vma->vm_page_prot,
+					st->domain);
+	if (rc < 0)
+		return rc;
+
+	st->va += msg->npages << PAGE_SHIFT;
+
+	return 0;
+}
+
+static long privcmd_ioctl_mmap(void __user *udata)
+{
+	struct privcmd_mmap mmapcmd;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc;
+	LIST_HEAD(pagelist);
+	struct mmap_mfn_state state;
+
+	if (!xen_initial_domain())
+		return -EPERM;
+
+	if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd)))
+		return -EFAULT;
+
+	rc = gather_array(&pagelist,
+			  mmapcmd.num, sizeof(struct privcmd_mmap_entry),
+			  mmapcmd.entry);
+
+	if (rc || list_empty(&pagelist))
+		goto out;
+
+	down_write(&mm->mmap_sem);
+
+	{
+		struct page *page = list_first_entry(&pagelist,
+						     struct page, lru);
+		struct privcmd_mmap_entry *msg = page_address(page);
+
+		vma = find_vma(mm, msg->va);
+		rc = -EINVAL;
+
+		if (!vma || (msg->va != vma->vm_start) ||
+		    !privcmd_enforce_singleshot_mapping(vma))
+			goto out_up;
+	}
+
+	state.va = vma->vm_start;
+	state.vma = vma;
+	state.domain = mmapcmd.dom;
+
+	rc = traverse_pages(mmapcmd.num, sizeof(struct privcmd_mmap_entry),
+			    &pagelist,
+			    mmap_mfn_range, &state);
+
+
+out_up:
+	up_write(&mm->mmap_sem);
+
+out:
+	free_page_list(&pagelist);
+
+	return rc;
+}
+
+struct mmap_batch_state {
+	domid_t domain;
+	unsigned long va;
+	struct vm_area_struct *vma;
+	int err;
+
+	xen_pfn_t __user *user;
+};
+
+static int mmap_batch_fn(void *data, void *state)
+{
+	xen_pfn_t *mfnp = data;
+	struct mmap_batch_state *st = state;
+
+	if (xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
+				       st->vma->vm_page_prot, st->domain) < 0) {
+		*mfnp |= 0xf0000000U;
+		st->err++;
+	}
+	st->va += PAGE_SIZE;
+
+	return 0;
+}
+
+static int mmap_return_errors(void *data, void *state)
+{
+	xen_pfn_t *mfnp = data;
+	struct mmap_batch_state *st = state;
+
+	put_user(*mfnp, st->user++);
+
+	return 0;
+}
+
+static struct vm_operations_struct privcmd_vm_ops;
+
+static long privcmd_ioctl_mmap_batch(void __user *udata)
+{
+	int ret;
+	struct privcmd_mmapbatch m;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long nr_pages;
+	LIST_HEAD(pagelist);
+	struct mmap_batch_state state;
+
+	if (!xen_initial_domain())
+		return -EPERM;
+
+	if (copy_from_user(&m, udata, sizeof(m)))
+		return -EFAULT;
+
+	nr_pages = m.num;
+	if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
+		return -EINVAL;
+
+	ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t),
+			   m.arr);
+
+	if (ret || list_empty(&pagelist))
+		goto out;
+
+	down_write(&mm->mmap_sem);
+
+	vma = find_vma(mm, m.addr);
+	ret = -EINVAL;
+	if (!vma ||
+	    vma->vm_ops != &privcmd_vm_ops ||
+	    (m.addr != vma->vm_start) ||
+	    ((m.addr + (nr_pages << PAGE_SHIFT)) != vma->vm_end) ||
+	    !privcmd_enforce_singleshot_mapping(vma)) {
+		up_write(&mm->mmap_sem);
+		goto out;
+	}
+
+	state.domain = m.dom;
+	state.vma = vma;
+	state.va = m.addr;
+	state.err = 0;
+
+	ret = traverse_pages(m.num, sizeof(xen_pfn_t),
+			     &pagelist, mmap_batch_fn, &state);
+
+	up_write(&mm->mmap_sem);
+
+	if (state.err > 0) {
+		ret = 0;
+
+		state.user = m.arr;
+		traverse_pages(m.num, sizeof(xen_pfn_t),
+			       &pagelist,
+			       mmap_return_errors, &state);
+	}
+
+out:
+	free_page_list(&pagelist);
+
+	return ret;
+}
+
+static long privcmd_ioctl(struct file *file,
+			  unsigned int cmd, unsigned long data)
+{
+	int ret = -ENOSYS;
+	void __user *udata = (void __user *) data;
+
+	switch (cmd) {
+	case IOCTL_PRIVCMD_HYPERCALL:
+		ret = privcmd_ioctl_hypercall(udata);
+		break;
+
+	case IOCTL_PRIVCMD_MMAP:
+		ret = privcmd_ioctl_mmap(udata);
+		break;
+
+	case IOCTL_PRIVCMD_MMAPBATCH:
+		ret = privcmd_ioctl_mmap_batch(udata);
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+#ifndef HAVE_ARCH_PRIVCMD_MMAP
+static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
+	       vma, vma->vm_start, vma->vm_end,
+	       vmf->pgoff, vmf->virtual_address);
+
+	return VM_FAULT_SIGBUS;
+}
+
+static struct vm_operations_struct privcmd_vm_ops = {
+	.fault = privcmd_fault
+};
+
+static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	/* Unsupported for auto-translate guests. */
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return -ENOSYS;
+
+	/* DONTCOPY is essential for Xen as copy_page_range is broken. */
+	vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY;
+	vma->vm_ops = &privcmd_vm_ops;
+	vma->vm_private_data = NULL;
+
+	return 0;
+}
+
+static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma)
+{
+	return (xchg(&vma->vm_private_data, (void *)1) == NULL);
+}
+#endif
+
+const struct file_operations privcmd_file_ops = {
+	.unlocked_ioctl = privcmd_ioctl,
+	.mmap = privcmd_mmap,
+};
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
index 78bfab0700ba..d6662b789b6b 100644
--- a/drivers/xen/xenfs/super.c
+++ b/drivers/xen/xenfs/super.c
@@ -12,6 +12,8 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/magic.h>
+#include <linux/mm.h>
+#include <linux/backing-dev.h>
 
 #include <xen/xen.h>
 
@@ -22,6 +24,62 @@
 MODULE_DESCRIPTION("Xen filesystem");
 MODULE_LICENSE("GPL");
 
+static int xenfs_set_page_dirty(struct page *page)
+{
+	return !TestSetPageDirty(page);
+}
+
+static const struct address_space_operations xenfs_aops = {
+	.set_page_dirty = xenfs_set_page_dirty,
+};
+
+static struct backing_dev_info xenfs_backing_dev_info = {
+	.ra_pages	= 0,	/* No readahead */
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+};
+
+static struct inode *xenfs_make_inode(struct super_block *sb, int mode)
+{
+	struct inode *ret = new_inode(sb);
+
+	if (ret) {
+		ret->i_mode = mode;
+		ret->i_mapping->a_ops = &xenfs_aops;
+		ret->i_mapping->backing_dev_info = &xenfs_backing_dev_info;
+		ret->i_uid = ret->i_gid = 0;
+		ret->i_blocks = 0;
+		ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME;
+	}
+	return ret;
+}
+
+static struct dentry *xenfs_create_file(struct super_block *sb,
+					struct dentry *parent,
+					const char *name,
+					const struct file_operations *fops,
+					void *data,
+					int mode)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(parent, name);
+	if (!dentry)
+		return NULL;
+
+	inode = xenfs_make_inode(sb, S_IFREG | mode);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+
+	inode->i_fop = fops;
+	inode->i_private = data;
+
+	d_add(dentry, inode);
+	return dentry;
+}
+
 static ssize_t capabilities_read(struct file *file, char __user *buf,
 				 size_t size, loff_t *off)
 {
@@ -35,6 +93,7 @@ static ssize_t capabilities_read(struct file *file, char __user *buf,
 
 static const struct file_operations capabilities_file_ops = {
 	.read = capabilities_read,
+	.llseek = default_llseek,
 };
 
 static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
@@ -43,10 +102,23 @@ static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
 		[1] = {},
 		{ "xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR },
 		{ "capabilities", &capabilities_file_ops, S_IRUGO },
+		{ "privcmd", &privcmd_file_ops, S_IRUSR|S_IWUSR },
 		{""},
 	};
+	int rc;
 
-	return simple_fill_super(sb, XENFS_SUPER_MAGIC, xenfs_files);
+	rc = simple_fill_super(sb, XENFS_SUPER_MAGIC, xenfs_files);
+	if (rc < 0)
+		return rc;
+
+	if (xen_initial_domain()) {
+		xenfs_create_file(sb, sb->s_root, "xsd_kva",
+				  &xsd_kva_file_ops, NULL, S_IRUSR|S_IWUSR);
+		xenfs_create_file(sb, sb->s_root, "xsd_port",
+				  &xsd_port_file_ops, NULL, S_IRUSR|S_IWUSR);
+	}
+
+	return rc;
 }
 
 static int xenfs_get_sb(struct file_system_type *fs_type,
@@ -65,11 +137,25 @@ static struct file_system_type xenfs_type = {
 
 static int __init xenfs_init(void)
 {
-	if (xen_domain())
-		return register_filesystem(&xenfs_type);
+	int err;
+	if (!xen_domain()) {
+		printk(KERN_INFO "xenfs: not registering filesystem on non-xen platform\n");
+		return 0;
+	}
+
+	err = register_filesystem(&xenfs_type);
+	if (err) {
+		printk(KERN_ERR "xenfs: Unable to register filesystem!\n");
+		goto out;
+	}
+
+	err = bdi_init(&xenfs_backing_dev_info);
+	if (err)
+		unregister_filesystem(&xenfs_type);
+
+ out:
 
-	printk(KERN_INFO "XENFS: not registering filesystem on non-xen platform\n");
-	return 0;
+	return err;
 }
 
 static void __exit xenfs_exit(void)
diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c
index 3b39c3752e21..1c1236087f78 100644
--- a/drivers/xen/xenfs/xenbus.c
+++ b/drivers/xen/xenfs/xenbus.c
@@ -594,4 +594,5 @@ const struct file_operations xenbus_file_ops = {
 	.open = xenbus_file_open,
 	.release = xenbus_file_release,
 	.poll = xenbus_file_poll,
+	.llseek = no_llseek,
 };
diff --git a/drivers/xen/xenfs/xenfs.h b/drivers/xen/xenfs/xenfs.h
index 51f08b2d0bf1..b68aa6200003 100644
--- a/drivers/xen/xenfs/xenfs.h
+++ b/drivers/xen/xenfs/xenfs.h
@@ -2,5 +2,8 @@
 #define _XENFS_XENBUS_H
 
 extern const struct file_operations xenbus_file_ops;
+extern const struct file_operations privcmd_file_ops;
+extern const struct file_operations xsd_kva_file_ops;
+extern const struct file_operations xsd_port_file_ops;
 
 #endif	/* _XENFS_XENBUS_H */
diff --git a/drivers/xen/xenfs/xenstored.c b/drivers/xen/xenfs/xenstored.c
new file mode 100644
index 000000000000..fef20dbc6a5c
--- /dev/null
+++ b/drivers/xen/xenfs/xenstored.c
@@ -0,0 +1,68 @@
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+
+#include <xen/page.h>
+
+#include "xenfs.h"
+#include "../xenbus/xenbus_comms.h"
+
+static ssize_t xsd_read(struct file *file, char __user *buf,
+			    size_t size, loff_t *off)
+{
+	const char *str = (const char *)file->private_data;
+	return simple_read_from_buffer(buf, size, off, str, strlen(str));
+}
+
+static int xsd_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static int xsd_kva_open(struct inode *inode, struct file *file)
+{
+	file->private_data = (void *)kasprintf(GFP_KERNEL, "0x%p",
+					       xen_store_interface);
+	if (!file->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+static int xsd_kva_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	size_t size = vma->vm_end - vma->vm_start;
+
+	if ((size > PAGE_SIZE) || (vma->vm_pgoff != 0))
+		return -EINVAL;
+
+	if (remap_pfn_range(vma, vma->vm_start,
+			    virt_to_pfn(xen_store_interface),
+			    size, vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+const struct file_operations xsd_kva_file_ops = {
+	.open = xsd_kva_open,
+	.mmap = xsd_kva_mmap,
+	.read = xsd_read,
+	.release = xsd_release,
+};
+
+static int xsd_port_open(struct inode *inode, struct file *file)
+{
+	file->private_data = (void *)kasprintf(GFP_KERNEL, "%d",
+					       xen_store_evtchn);
+	if (!file->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+const struct file_operations xsd_port_file_ops = {
+	.open = xsd_port_open,
+	.read = xsd_read,
+	.release = xsd_release,
+};