Merge tag 'stable/for-linus-3.8-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull Xen fixes from Konrad Rzeszutek Wilk:
- CVE-2013-0190/XSA-40 (or stack corruption for 32-bit PV kernels)
- Fix racy vma access spotted by Al Viro
- Fix mmap batch ioctl potentially resulting in large O(n) page allcations.
- Fix vcpu online/offline BUG:scheduling while atomic..
- Fix unbound buffer scanning for more than 32 vCPUs.
- Fix grant table being incorrectly initialized
- Fix incorrect check in pciback
- Allow privcmd in backend domains.

Fix up whitespace conflict due to ugly merge resolution in Xen tree in
arch/arm/xen/enlighten.c

* tag 'stable/for-linus-3.8-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
xen: Fix stack corruption in xen_failsafe_callback for 32bit PVOPS guests.
Revert "xen/smp: Fix CPU online/offline bug triggering a BUG: scheduling while atomic."
xen/gntdev: remove erronous use of copy_to_user
xen/gntdev: correctly unmap unlinked maps in mmu notifier
xen/gntdev: fix unsafe vma access
xen/privcmd: Fix mmap batch ioctl.
Xen: properly bound buffer access when parsing cpu/*/availability
xen/grant-table: correctly initialize grant table version 1
x86/xen : Fix the wrong check in pciback
xen/privcmd: Relax access control in privcmd_ioctl_mmap

arch/x86/kernel/entry_32.S

···
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
-	addl $16,%esp
 	jmp iret_exc
 5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL

arch/x86/xen/smp.c

···
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
-	/*
-	 * Balance out the preempt calls - as we are running in cpu_idle
-	 * loop which has been called at bootup from cpu_bringup_and_idle.
-	 * The cpucpu_bringup_and_idle called cpu_bringup which made a
-	 * preempt_disable() So this preempt_enable will balance it out.
-	 */
-	preempt_enable();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */

drivers/xen/cpu_hotplug.c

···
 static int vcpu_online(unsigned int cpu)
 {
 	int err;
-	char dir[32], state[32];
+	char dir[16], state[16];
 
 	sprintf(dir, "cpu/%u", cpu);
-	err = xenbus_scanf(XBT_NIL, dir, "availability", "%s", state);
+	err = xenbus_scanf(XBT_NIL, dir, "availability", "%15s", state);
 	if (err != 1) {
 		if (!xen_initial_domain())
 			printk(KERN_ERR "XENBUS: Unable to read cpu state\n");

drivers/xen/gntdev.c

···
 static atomic_t pages_mapped = ATOMIC_INIT(0);
 
 static int use_ptemod;
+#define populate_freeable_maps use_ptemod
 
 struct gntdev_priv {
+	/* maps with visible offsets in the file descriptor */
 	struct list_head maps;
-	/* lock protects maps from concurrent changes */
+	/* maps that are not visible; will be freed on munmap.
+	 * Only populated if populate_freeable_maps == 1 */
+	struct list_head freeable_maps;
+	/* lock protects maps and freeable_maps */
 	spinlock_t lock;
 	struct mm_struct *mm;
 	struct mmu_notifier mn;
···
 	return NULL;
 }
 
-static void gntdev_put_map(struct grant_map *map)
+static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
 {
 	if (!map)
 		return;
···
 	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
 		notify_remote_via_evtchn(map->notify.event);
 		evtchn_put(map->notify.event);
+	}
+
+	if (populate_freeable_maps && priv) {
+		spin_lock(&priv->lock);
+		list_del(&map->next);
+		spin_unlock(&priv->lock);
 	}
 
 	if (map->pages && !use_ptemod)
···
 
 	if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
 		int pgno = (map->notify.addr >> PAGE_SHIFT);
-		if (pgno >= offset && pgno < offset + pages && use_ptemod) {
-			void __user *tmp = (void __user *)
-				map->vma->vm_start + map->notify.addr;
-			err = copy_to_user(tmp, &err, 1);
-			if (err)
-				return -EFAULT;
-			map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
-		} else if (pgno >= offset && pgno < offset + pages) {
-			uint8_t *tmp = kmap(map->pages[pgno]);
+		if (pgno >= offset && pgno < offset + pages) {
+			/* No need for kmap, pages are in lowmem */
+			uint8_t *tmp = pfn_to_kaddr(page_to_pfn(map->pages[pgno]));
 			tmp[map->notify.addr & (PAGE_SIZE-1)] = 0;
-			kunmap(map->pages[pgno]);
 			map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
 		}
 	}
···
 static void gntdev_vma_close(struct vm_area_struct *vma)
 {
 	struct grant_map *map = vma->vm_private_data;
+	struct file *file = vma->vm_file;
+	struct gntdev_priv *priv = file->private_data;
 
 	pr_debug("gntdev_vma_close %p\n", vma);
-	map->vma = NULL;
+	if (use_ptemod) {
+		/* It is possible that an mmu notifier could be running
+		 * concurrently, so take priv->lock to ensure that the vma won't
+		 * vanishing during the unmap_grant_pages call, since we will
+		 * spin here until that completes. Such a concurrent call will
+		 * not do any unmapping, since that has been done prior to
+		 * closing the vma, but it may still iterate the unmap_ops list.
+		 */
+		spin_lock(&priv->lock);
+		map->vma = NULL;
+		spin_unlock(&priv->lock);
+	}
 	vma->vm_private_data = NULL;
-	gntdev_put_map(map);
+	gntdev_put_map(priv, map);
 }
 
 static struct vm_operations_struct gntdev_vmops = {
···
 
 /* ------------------------------------------------------------------ */
 
+static void unmap_if_in_range(struct grant_map *map,
+			      unsigned long start, unsigned long end)
+{
+	unsigned long mstart, mend;
+	int err;
+
+	if (!map->vma)
+		return;
+	if (map->vma->vm_start >= end)
+		return;
+	if (map->vma->vm_end <= start)
+		return;
+	mstart = max(start, map->vma->vm_start);
+	mend   = min(end,   map->vma->vm_end);
+	pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
+			map->index, map->count,
+			map->vma->vm_start, map->vma->vm_end,
+			start, end, mstart, mend);
+	err = unmap_grant_pages(map,
+				(mstart - map->vma->vm_start) >> PAGE_SHIFT,
+				(mend - mstart) >> PAGE_SHIFT);
+	WARN_ON(err);
+}
+
 static void mn_invl_range_start(struct mmu_notifier *mn,
 				struct mm_struct *mm,
 				unsigned long start, unsigned long end)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
 	struct grant_map *map;
-	unsigned long mstart, mend;
-	int err;
 
 	spin_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
-		if (!map->vma)
-			continue;
-		if (map->vma->vm_start >= end)
-			continue;
-		if (map->vma->vm_end <= start)
-			continue;
-		mstart = max(start, map->vma->vm_start);
-		mend   = min(end,   map->vma->vm_end);
-		pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
-				map->index, map->count,
-				map->vma->vm_start, map->vma->vm_end,
-				start, end, mstart, mend);
-		err = unmap_grant_pages(map,
-					(mstart - map->vma->vm_start) >> PAGE_SHIFT,
-					(mend - mstart) >> PAGE_SHIFT);
-		WARN_ON(err);
+		unmap_if_in_range(map, start, end);
+	}
+	list_for_each_entry(map, &priv->freeable_maps, next) {
+		unmap_if_in_range(map, start, end);
 	}
 	spin_unlock(&priv->lock);
 }
···
 
 	spin_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
+		if (!map->vma)
+			continue;
+		pr_debug("map %d+%d (%lx %lx)\n",
+				map->index, map->count,
+				map->vma->vm_start, map->vma->vm_end);
+		err = unmap_grant_pages(map, /* offset */ 0, map->count);
+		WARN_ON(err);
+	}
+	list_for_each_entry(map, &priv->freeable_maps, next) {
 		if (!map->vma)
 			continue;
 		pr_debug("map %d+%d (%lx %lx)\n",
···
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&priv->maps);
+	INIT_LIST_HEAD(&priv->freeable_maps);
 	spin_lock_init(&priv->lock);
 
 	if (use_ptemod) {
···
 	while (!list_empty(&priv->maps)) {
 		map = list_entry(priv->maps.next, struct grant_map, next);
 		list_del(&map->next);
-		gntdev_put_map(map);
+		gntdev_put_map(NULL /* already removed */, map);
 	}
+	WARN_ON(!list_empty(&priv->freeable_maps));
 
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
···
 
 	if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
 		pr_debug("can't map: over limit\n");
-		gntdev_put_map(map);
+		gntdev_put_map(NULL, map);
 		return err;
 	}
 
 	if (copy_from_user(map->grants, &u->refs,
 			   sizeof(map->grants[0]) * op.count) != 0) {
-		gntdev_put_map(map);
-		return err;
+		gntdev_put_map(NULL, map);
+		return -EFAULT;
 	}
 
 	spin_lock(&priv->lock);
···
 	map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
 	if (map) {
 		list_del(&map->next);
+		if (populate_freeable_maps)
+			list_add_tail(&map->next, &priv->freeable_maps);
 		err = 0;
 	}
 	spin_unlock(&priv->lock);
 	if (map)
-		gntdev_put_map(map);
+		gntdev_put_map(priv, map);
 	return err;
 }
 
···
 	struct ioctl_gntdev_get_offset_for_vaddr op;
 	struct vm_area_struct *vma;
 	struct grant_map *map;
+	int rv = -EINVAL;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
 		return -EFAULT;
 	pr_debug("priv %p, offset for vaddr %lx\n", priv, (unsigned long)op.vaddr);
 
+	down_read(&current->mm->mmap_sem);
 	vma = find_vma(current->mm, op.vaddr);
 	if (!vma || vma->vm_ops != &gntdev_vmops)
-		return -EINVAL;
+		goto out_unlock;
 
 	map = vma->vm_private_data;
 	if (!map)
-		return -EINVAL;
+		goto out_unlock;
 
 	op.offset = map->index << PAGE_SHIFT;
 	op.count = map->count;
+	rv = 0;
 
-	if (copy_to_user(u, &op, sizeof(op)) != 0)
+ out_unlock:
+	up_read(&current->mm->mmap_sem);
+
+	if (rv == 0 && copy_to_user(u, &op, sizeof(op)) != 0)
 		return -EFAULT;
-	return 0;
+	return rv;
 }
 
 static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
···
 out_put_map:
 	if (use_ptemod)
 		map->vma = NULL;
-	gntdev_put_map(map);
+	gntdev_put_map(priv, map);
 	return err;
 }
 

drivers/xen/grant-table.c

···
 /* External tools reserve first few grant table entries. */
 #define NR_RESERVED_ENTRIES 8
 #define GNTTAB_LIST_END 0xffffffff
-#define GREFS_PER_GRANT_FRAME \
-(grant_table_version == 1 ?                      \
-(PAGE_SIZE / sizeof(struct grant_entry_v1)) :   \
-(PAGE_SIZE / sizeof(union grant_entry_v2)))
 
 static grant_ref_t **gnttab_list;
 static unsigned int nr_grant_frames;
···
 static grant_status_t *grstatus;
 
 static int grant_table_version;
+static int grefs_per_grant_frame;
 
 static struct gnttab_free_callback *gnttab_free_callback_list;
 
···
 	unsigned int new_nr_grant_frames, extra_entries, i;
 	unsigned int nr_glist_frames, new_nr_glist_frames;
 
-	new_nr_grant_frames = nr_grant_frames + more_frames;
-	extra_entries       = more_frames * GREFS_PER_GRANT_FRAME;
+	BUG_ON(grefs_per_grant_frame == 0);
 
-	nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
+	new_nr_grant_frames = nr_grant_frames + more_frames;
+	extra_entries       = more_frames * grefs_per_grant_frame;
+
+	nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
 	new_nr_glist_frames =
-		(new_nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
+		(new_nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
 	for (i = nr_glist_frames; i < new_nr_glist_frames; i++) {
 		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC);
 		if (!gnttab_list[i])
···
 	}
 
 
-	for (i = GREFS_PER_GRANT_FRAME * nr_grant_frames;
-	     i < GREFS_PER_GRANT_FRAME * new_nr_grant_frames - 1; i++)
+	for (i = grefs_per_grant_frame * nr_grant_frames;
+	     i < grefs_per_grant_frame * new_nr_grant_frames - 1; i++)
 		gnttab_entry(i) = i + 1;
 
 	gnttab_entry(i) = gnttab_free_head;
-	gnttab_free_head = GREFS_PER_GRANT_FRAME * nr_grant_frames;
+	gnttab_free_head = grefs_per_grant_frame * nr_grant_frames;
 	gnttab_free_count += extra_entries;
 
 	nr_grant_frames = new_nr_grant_frames;
···
 
 static unsigned nr_status_frames(unsigned nr_grant_frames)
 {
-	return (nr_grant_frames * GREFS_PER_GRANT_FRAME + SPP - 1) / SPP;
+	BUG_ON(grefs_per_grant_frame == 0);
+	return (nr_grant_frames * grefs_per_grant_frame + SPP - 1) / SPP;
 }
 
 static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes)
···
 	rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1);
 	if (rc == 0 && gsv.version == 2) {
 		grant_table_version = 2;
+		grefs_per_grant_frame = PAGE_SIZE / sizeof(union grant_entry_v2);
 		gnttab_interface = &gnttab_v2_ops;
 	} else if (grant_table_version == 2) {
 		/*
···
 		panic("we need grant tables version 2, but only version 1 is available");
 	} else {
 		grant_table_version = 1;
+		grefs_per_grant_frame = PAGE_SIZE / sizeof(struct grant_entry_v1);
 		gnttab_interface = &gnttab_v1_ops;
 	}
 	printk(KERN_INFO "Grant tables using version %d layout.\n",
 		grant_table_version);
 }
 
-int gnttab_resume(void)
+static int gnttab_setup(void)
 {
 	unsigned int max_nr_gframes;
 
-	gnttab_request_version();
 	max_nr_gframes = gnttab_max_grant_frames();
 	if (max_nr_gframes < nr_grant_frames)
 		return -ENOSYS;
···
 	return 0;
 }
 
+int gnttab_resume(void)
+{
+	gnttab_request_version();
+	return gnttab_setup();
+}
+
 int gnttab_suspend(void)
 {
 	gnttab_interface->unmap_frames();
···
 	int rc;
 	unsigned int cur, extra;
 
+	BUG_ON(grefs_per_grant_frame == 0);
 	cur = nr_grant_frames;
-	extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) /
-		 GREFS_PER_GRANT_FRAME);
+	extra = ((req_entries + (grefs_per_grant_frame-1)) /
+		 grefs_per_grant_frame);
 	if (cur + extra > gnttab_max_grant_frames())
 		return -ENOSPC;
 
···
 	unsigned int nr_init_grefs;
 	int ret;
 
+	gnttab_request_version();
 	nr_grant_frames = 1;
 	boot_max_nr_grant_frames = __max_nr_grant_frames();
 
 	/* Determine the maximum number of frames required for the
 	 * grant reference free list on the current hypervisor.
 	 */
+	BUG_ON(grefs_per_grant_frame == 0);
 	max_nr_glist_frames = (boot_max_nr_grant_frames *
-			       GREFS_PER_GRANT_FRAME / RPP);
+			       grefs_per_grant_frame / RPP);
 
 	gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *),
 			      GFP_KERNEL);
 	if (gnttab_list == NULL)
 		return -ENOMEM;
 
-	nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
+	nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
 	for (i = 0; i < nr_glist_frames; i++) {
 		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
 		if (gnttab_list[i] == NULL) {
···
 		}
 	}
 
-	if (gnttab_resume() < 0) {
+	if (gnttab_setup() < 0) {
 		ret = -ENODEV;
 		goto ini_nomem;
 	}
 
-	nr_init_grefs = nr_grant_frames * GREFS_PER_GRANT_FRAME;
+	nr_init_grefs = nr_grant_frames * grefs_per_grant_frame;
 
 	for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
 		gnttab_entry(i) = i + 1;

drivers/xen/privcmd.c

···
 	LIST_HEAD(pagelist);
 	struct mmap_mfn_state state;
 
-	if (!xen_initial_domain())
-		return -EPERM;
-
 	/* We only support privcmd_ioctl_mmap_batch for auto translated. */
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return -ENOSYS;
···
 	 *      -ENOENT if at least 1 -ENOENT has happened.
 	 */
 	int global_error;
-	/* An array for individual errors */
-	int *err;
+	int version;
 
 	/* User-space mfn array to store errors in the second pass for V1. */
 	xen_pfn_t __user *user_mfn;
+	/* User-space int array to store errors in the second pass for V2. */
+	int __user *user_err;
 };
 
 /* auto translated dom0 note: if domU being created is PV, then mfn is
···
 					 &cur_page);
 
 	/* Store error code for second pass. */
-	*(st->err++) = ret;
+	if (st->version == 1) {
+		if (ret < 0) {
+			/*
+			 * V1 encodes the error codes in the 32bit top nibble of the
+			 * mfn (with its known limitations vis-a-vis 64 bit callers).
+			 */
+			*mfnp |= (ret == -ENOENT) ?
+						PRIVCMD_MMAPBATCH_PAGED_ERROR :
+						PRIVCMD_MMAPBATCH_MFN_ERROR;
+		}
+	} else { /* st->version == 2 */
+		*((int *) mfnp) = ret;
+	}
 
 	/* And see if it affects the global_error. */
 	if (ret < 0) {
···
 	return 0;
 }
 
-static int mmap_return_errors_v1(void *data, void *state)
+static int mmap_return_errors(void *data, void *state)
 {
-	xen_pfn_t *mfnp = data;
 	struct mmap_batch_state *st = state;
-	int err = *(st->err++);
 
-	/*
-	 * V1 encodes the error codes in the 32bit top nibble of the
-	 * mfn (with its known limitations vis-a-vis 64 bit callers).
-	 */
-	*mfnp |= (err == -ENOENT) ?
-				PRIVCMD_MMAPBATCH_PAGED_ERROR :
-				PRIVCMD_MMAPBATCH_MFN_ERROR;
-	return __put_user(*mfnp, st->user_mfn++);
+	if (st->version == 1) {
+		xen_pfn_t mfnp = *((xen_pfn_t *) data);
+		if (mfnp & PRIVCMD_MMAPBATCH_MFN_ERROR)
+			return __put_user(mfnp, st->user_mfn++);
+		else
+			st->user_mfn++;
+	} else { /* st->version == 2 */
+		int err = *((int *) data);
+		if (err)
+			return __put_user(err, st->user_err++);
+		else
+			st->user_err++;
+	}
+
+	return 0;
 }
 
 /* Allocate pfns that are then mapped with gmfns from foreign domid. Update
···
 	struct vm_area_struct *vma;
 	unsigned long nr_pages;
 	LIST_HEAD(pagelist);
-	int *err_array = NULL;
 	struct mmap_batch_state state;
-
-	if (!xen_initial_domain())
-		return -EPERM;
 
 	switch (version) {
 	case 1:
···
 		goto out;
 	}
 
-	err_array = kcalloc(m.num, sizeof(int), GFP_KERNEL);
-	if (err_array == NULL) {
-		ret = -ENOMEM;
-		goto out;
+	if (version == 2) {
+		/* Zero error array now to only copy back actual errors. */
+		if (clear_user(m.err, sizeof(int) * m.num)) {
+			ret = -EFAULT;
+			goto out;
+		}
 	}
 
 	down_write(&mm->mmap_sem);
···
 	state.va            = m.addr;
 	state.index         = 0;
 	state.global_error  = 0;
-	state.err           = err_array;
+	state.version       = version;
 
 	/* mmap_batch_fn guarantees ret == 0 */
 	BUG_ON(traverse_pages(m.num, sizeof(xen_pfn_t),
···
 
 	up_write(&mm->mmap_sem);
 
-	if (version == 1) {
-		if (state.global_error) {
-			/* Write back errors in second pass. */
-			state.user_mfn = (xen_pfn_t *)m.arr;
-			state.err      = err_array;
-			ret = traverse_pages(m.num, sizeof(xen_pfn_t),
-					     &pagelist, mmap_return_errors_v1, &state);
-		} else
-			ret = 0;
-
-	} else if (version == 2) {
-		ret = __copy_to_user(m.err, err_array, m.num * sizeof(int));
-		if (ret)
-			ret = -EFAULT;
-	}
+	if (state.global_error) {
+		/* Write back errors in second pass. */
+		state.user_mfn = (xen_pfn_t *)m.arr;
+		state.user_err = m.err;
+		ret = traverse_pages(m.num, sizeof(xen_pfn_t),
+							 &pagelist, mmap_return_errors, &state);
+	} else
+		ret = 0;
 
 	/* If we have not had any EFAULT-like global errors then set the global
 	 * error to -ENOENT if necessary. */
···
 		ret = -ENOENT;
 
 out:
-	kfree(err_array);
 	free_page_list(&pagelist);
 
 	return ret;

drivers/xen/xen-pciback/pciback.h

···
 static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
 					     struct pci_dev *dev)
 {
-	if (xen_pcibk_backend && xen_pcibk_backend->free)
+	if (xen_pcibk_backend && xen_pcibk_backend->release)
 		return xen_pcibk_backend->release(pdev, dev);
 }