Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
  virtio: remove virtio-pci root device
  LGUEST_GUEST: fix unmet direct dependencies (VIRTUALIZATION && VIRTIO)
  lguest: compile fixes
  lguest: Use this_cpu_ops
  lguest: document --rng in example Launcher
  lguest: example launcher to use guard pages, drop PROT_EXEC, fix limit logic
  lguest: --username and --chroot options

Documentation/lguest/lguest.c

@@ -39,6 +39,9 @@
 #include <limits.h>
 #include <stddef.h>
 #include <signal.h>
+#include <pwd.h>
+#include <grp.h>
+
 #include <linux/virtio_config.h>
 #include <linux/virtio_net.h>
 #include <linux/virtio_blk.h>
@@ -298,20 +301,27 @@ static void *map_zeroed_pages(unsigned int num)
 
 	/*
 	 * We use a private mapping (ie. if we write to the page, it will be
-	 * copied).
+	 * copied). We allocate an extra two pages PROT_NONE to act as guard
+	 * pages against read/write attempts that exceed allocated space.
 	 */
-	addr = mmap(NULL, getpagesize() * num,
+	addr = mmap(NULL, getpagesize() * (num+2),
-		    PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
+		    PROT_NONE, MAP_PRIVATE, fd, 0);
+
 	if (addr == MAP_FAILED)
 		err(1, "Mmapping %u pages of /dev/zero", num);
 
+	if (mprotect(addr + getpagesize(), getpagesize() * num,
+		     PROT_READ|PROT_WRITE) == -1)
+		err(1, "mprotect rw %u pages failed", num);
+
 	/*
 	 * One neat mmap feature is that you can close the fd, and it
 	 * stays mapped.
 	 */
 	close(fd);
 
-	return addr;
+	/* Return address after PROT_NONE page */
+	return addr + getpagesize();
 }
 
 /* Get some more pages for a device. */
@@ -343,7 +353,7 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
 	 * done to it.  This allows us to share untouched memory between
 	 * Guests.
 	 */
-	if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC,
+	if (mmap(addr, len, PROT_READ|PROT_WRITE,
 		 MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED)
 		return;
 
@@ -573,10 +583,10 @@ static void *_check_pointer(unsigned long addr, unsigned int size,
 			    unsigned int line)
 {
 	/*
-	 * We have to separately check addr and addr+size, because size could
+	 * Check if the requested address and size exceeds the allocated memory,
-	 * be huge and addr + size might wrap around.
+	 * or addr + size wraps around.
 	 */
-	if (addr >= guest_limit || addr + size >= guest_limit)
+	if ((addr + size) > guest_limit || (addr + size) < addr)
 		errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr);
 	/*
 	 * We return a pointer for the caller's convenience, now we know it's
@@ -1872,6 +1882,8 @@ static struct option opts[] = {
 	{ "block", 1, NULL, 'b' },
 	{ "rng", 0, NULL, 'r' },
 	{ "initrd", 1, NULL, 'i' },
+	{ "username", 1, NULL, 'u' },
+	{ "chroot", 1, NULL, 'c' },
 	{ NULL },
 };
 static void usage(void)
@@ -1894,6 +1906,12 @@ int main(int argc, char *argv[])
 	/* If they specify an initrd file to load. */
 	const char *initrd_name = NULL;
 
+	/* Password structure for initgroups/setres[gu]id */
+	struct passwd *user_details = NULL;
+
+	/* Directory to chroot to */
+	char *chroot_path = NULL;
+
 	/* Save the args: we "reboot" by execing ourselves again. */
 	main_args = argv;
 
@@ -1950,6 +1968,14 @@ int main(int argc, char *argv[])
 		case 'i':
 			initrd_name = optarg;
 			break;
+		case 'u':
+			user_details = getpwnam(optarg);
+			if (!user_details)
+				err(1, "getpwnam failed, incorrect username?");
+			break;
+		case 'c':
+			chroot_path = optarg;
+			break;
 		default:
 			warnx("Unknown argument %s", argv[optind]);
 			usage();
@@ -2021,6 +2047,37 @@ int main(int argc, char *argv[])
 	/* If we exit via err(), this kills all the threads, restores tty. */
 	atexit(cleanup_devices);
 
+	/* If requested, chroot to a directory */
+	if (chroot_path) {
+		if (chroot(chroot_path) != 0)
+			err(1, "chroot(\"%s\") failed", chroot_path);
+
+		if (chdir("/") != 0)
+			err(1, "chdir(\"/\") failed");
+
+		verbose("chroot done\n");
+	}
+
+	/* If requested, drop privileges */
+	if (user_details) {
+		uid_t u;
+		gid_t g;
+
+		u = user_details->pw_uid;
+		g = user_details->pw_gid;
+
+		if (initgroups(user_details->pw_name, g) != 0)
+			err(1, "initgroups failed");
+
+		if (setresgid(g, g, g) != 0)
+			err(1, "setresgid failed");
+
+		if (setresuid(u, u, u) != 0)
+			err(1, "setresuid failed");
+
+		verbose("Dropping privileges completed\n");
+	}
+
 	/* Finally, run the Guest.  This doesn't return. */
 	run_guest();
 }

Documentation/lguest/lguest.txt

@@ -117,6 +117,11 @@ Running Lguest:
     
   for general information on how to get bridging to work.
 
+- Random number generation. Using the --rng option will provide a
+  /dev/hwrng in the guest that will read from the host's /dev/random.
+  Use this option in conjunction with rng-tools (see ../hw_random.txt)
+  to provide entropy to the guest kernel's /dev/random.
+
 There is a helpful mailing list at http://ozlabs.org/mailman/listinfo/lguest
 
 Good luck!

arch/x86/lguest/Kconfig

@@ -2,6 +2,7 @@ config LGUEST_GUEST
 	bool "Lguest guest support"
 	select PARAVIRT
 	depends on X86_32
+	select VIRTUALIZATION
 	select VIRTIO
 	select VIRTIO_RING
 	select VIRTIO_CONSOLE

arch/x86/lguest/boot.c

@@ -824,7 +824,7 @@ static void __init lguest_init_IRQ(void)
 
 	for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
 		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
-		__get_cpu_var(vector_irq)[i] = i - FIRST_EXTERNAL_VECTOR;
+		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
 		if (i != SYSCALL_VECTOR)
 			set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
 	}

drivers/lguest/page_tables.c

@@ -1137,7 +1137,7 @@ void free_guest_pagetable(struct lguest *lg)
  */
 void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages)
 {
-	pte_t *switcher_pte_page = __get_cpu_var(switcher_pte_pages);
+	pte_t *switcher_pte_page = __this_cpu_read(switcher_pte_pages);
 	pte_t regs_pte;
 
 #ifdef CONFIG_X86_PAE

drivers/lguest/x86/core.c

@@ -90,8 +90,8 @@ static void copy_in_guest_info(struct lg_cpu *cpu, struct lguest_pages *pages)
 	 * meanwhile).  If that's not the case, we pretend everything in the
 	 * Guest has changed.
 	 */
-	if (__get_cpu_var(lg_last_cpu) != cpu || cpu->last_pages != pages) {
+	if (__this_cpu_read(lg_last_cpu) != cpu || cpu->last_pages != pages) {
-		__get_cpu_var(lg_last_cpu) = cpu;
+		__this_cpu_write(lg_last_cpu, cpu);
 		cpu->last_pages = pages;
 		cpu->changed = CHANGED_ALL;
 	}

drivers/virtio/virtio_pci.c

@@ -96,11 +96,6 @@ static struct pci_device_id virtio_pci_id_table[] = {
 
 MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
 
-/* A PCI device has it's own struct device and so does a virtio device so
- * we create a place for the virtio devices to show up in sysfs.  I think it
- * would make more sense for virtio to not insist on having it's own device. */
-static struct device *virtio_pci_root;
-
 /* Convert a generic virtio device to our structure */
 static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
 {
@@ -629,7 +624,7 @@ static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
 	if (vp_dev == NULL)
 		return -ENOMEM;
 
-	vp_dev->vdev.dev.parent = virtio_pci_root;
+	vp_dev->vdev.dev.parent = &pci_dev->dev;
 	vp_dev->vdev.dev.release = virtio_pci_release_dev;
 	vp_dev->vdev.config = &virtio_pci_config_ops;
 	vp_dev->pci_dev = pci_dev;
@@ -717,17 +712,7 @@ static struct pci_driver virtio_pci_driver = {
 
 static int __init virtio_pci_init(void)
 {
-	int err;
+	return pci_register_driver(&virtio_pci_driver);
-
-	virtio_pci_root = root_device_register("virtio-pci");
-	if (IS_ERR(virtio_pci_root))
-		return PTR_ERR(virtio_pci_root);
-
-	err = pci_register_driver(&virtio_pci_driver);
-	if (err)
-		root_device_unregister(virtio_pci_root);
-
-	return err;
 }
 
 module_init(virtio_pci_init);
@@ -735,7 +720,6 @@ module_init(virtio_pci_init);
 static void __exit virtio_pci_exit(void)
 {
 	pci_unregister_driver(&virtio_pci_driver);
-	root_device_unregister(virtio_pci_root);
 }
 
 module_exit(virtio_pci_exit);