5 files changed, 232 insertions, 36 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 038e2592664e..1e004d057468 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -27,6 +27,9 @@ config IRQ_WORK
         bool
         depends on HAVE_IRQ_WORK
 
+config BUILDTIME_EXTABLE_SORT
+        bool
+
 menu "General setup"
 
 config EXPERIMENTAL
@@ -387,6 +390,7 @@ config AUDIT_LOGINUID_IMMUTABLE
           but may not be backwards compatible with older init systems.
 
 source "kernel/irq/Kconfig"
+source "kernel/time/Kconfig"
 
 menu "RCU Subsystem"
 
@@ -458,6 +462,33 @@ config RCU_FANOUT
           Select a specific number if testing RCU itself.
           Take the default if unsure.
 
+config RCU_FANOUT_LEAF
+        int "Tree-based hierarchical RCU leaf-level fanout value"
+        range 2 RCU_FANOUT if 64BIT
+        range 2 RCU_FANOUT if !64BIT
+        depends on TREE_RCU || TREE_PREEMPT_RCU
+        default 16
+        help
+          This option controls the leaf-level fanout of hierarchical
+          implementations of RCU, and allows trading off cache misses
+          against lock contention.  Systems that synchronize their
+          scheduling-clock interrupts for energy-efficiency reasons will
+          want the default because the smaller leaf-level fanout keeps
+          lock contention levels acceptably low.  Very large systems
+          (hundreds or thousands of CPUs) will instead want to set this
+          value to the maximum value possible in order to reduce the
+          number of cache misses incurred during RCU's grace-period
+          initialization.  These systems tend to run CPU-bound, and thus
+          are not helped by synchronized interrupts, and thus tend to
+          skew them, which reduces lock contention enough that large
+          leaf-level fanouts work well.
+
+          Select a specific number if testing RCU itself.
+
+          Select the maximum permissible value for large systems.
+
+          Take the default if unsure.
+
 config RCU_FANOUT_EXACT
         bool "Disable tree-based hierarchical RCU auto-balancing"
         depends on TREE_RCU || TREE_PREEMPT_RCU
@@ -515,10 +546,25 @@ config RCU_BOOST_PRIO
         depends on RCU_BOOST
         default 1
         help
-          This option specifies the real-time priority to which preempted
-          RCU readers are to be boosted.  If you are working with CPU-bound
-          real-time applications, you should specify a priority higher then
-          the highest-priority CPU-bound application.
+          This option specifies the real-time priority to which long-term
+          preempted RCU readers are to be boosted.  If you are working
+          with a real-time application that has one or more CPU-bound
+          threads running at a real-time priority level, you should set
+          RCU_BOOST_PRIO to a priority higher then the highest-priority
+          real-time CPU-bound thread.  The default RCU_BOOST_PRIO value
+          of 1 is appropriate in the common case, which is real-time
+          applications that do not have any CPU-bound threads.
+
+          Some real-time applications might not have a single real-time
+          thread that saturates a given CPU, but instead might have
+          multiple real-time threads that, taken together, fully utilize
+          that CPU.  In this case, you should set RCU_BOOST_PRIO to
+          a priority higher than the lowest-priority thread that is
+          conspiring to prevent the CPU from running any non-real-time
+          tasks.  For example, if one thread at priority 10 and another
+          thread at priority 5 are between themselves fully consuming
+          the CPU time on a given CPU, then RCU_BOOST_PRIO should be
+          set to priority 6 or higher.
 
           Specify the real-time priority, or take the default if unsure.
 
@@ -828,7 +874,10 @@ config IPC_NS
 config USER_NS
         bool "User namespace (EXPERIMENTAL)"
         depends on EXPERIMENTAL
-        default y
+        depends on UIDGID_CONVERTED
+        select UIDGID_STRICT_TYPE_CHECKS
+
+        default n
         help
           This allows containers, i.e. vservers, to use user namespaces
           to provide different user info for different servers.
@@ -852,6 +901,131 @@ config NET_NS
 
 endif # NAMESPACES
 
+config UIDGID_CONVERTED
+        # True if all of the selected software conmponents are known
+        # to have uid_t and gid_t converted to kuid_t and kgid_t
+        # where appropriate and are otherwise safe to use with
+        # the user namespace.
+        bool
+        default y
+
+        # List of kernel pieces that need user namespace work
+        # Features
+        depends on SYSVIPC = n
+        depends on IMA = n
+        depends on EVM = n
+        depends on KEYS = n
+        depends on AUDIT = n
+        depends on AUDITSYSCALL = n
+        depends on TASKSTATS = n
+        depends on TRACING = n
+        depends on FS_POSIX_ACL = n
+        depends on QUOTA = n
+        depends on QUOTACTL = n
+        depends on DEBUG_CREDENTIALS = n
+        depends on BSD_PROCESS_ACCT = n
+        depends on DRM = n
+        depends on PROC_EVENTS = n
+
+        # Networking
+        depends on NET = n
+        depends on NET_9P = n
+        depends on IPX = n
+        depends on PHONET = n
+        depends on NET_CLS_FLOW = n
+        depends on NETFILTER_XT_MATCH_OWNER = n
+        depends on NETFILTER_XT_MATCH_RECENT = n
+        depends on NETFILTER_XT_TARGET_LOG = n
+        depends on NETFILTER_NETLINK_LOG = n
+        depends on INET = n
+        depends on IPV6 = n
+        depends on IP_SCTP = n
+        depends on AF_RXRPC = n
+        depends on LLC2 = n
+        depends on NET_KEY = n
+        depends on INET_DIAG = n
+        depends on DNS_RESOLVER = n
+        depends on AX25 = n
+        depends on ATALK = n
+
+        # Filesystems
+        depends on USB_DEVICEFS = n
+        depends on USB_GADGETFS = n
+        depends on USB_FUNCTIONFS = n
+        depends on DEVTMPFS = n
+        depends on XENFS = n
+
+        depends on 9P_FS = n
+        depends on ADFS_FS = n
+        depends on AFFS_FS = n
+        depends on AFS_FS = n
+        depends on AUTOFS4_FS = n
+        depends on BEFS_FS = n
+        depends on BFS_FS = n
+        depends on BTRFS_FS = n
+        depends on CEPH_FS = n
+        depends on CIFS = n
+        depends on CODA_FS = n
+        depends on CONFIGFS_FS = n
+        depends on CRAMFS = n
+        depends on DEBUG_FS = n
+        depends on ECRYPT_FS = n
+        depends on EFS_FS = n
+        depends on EXOFS_FS = n
+        depends on FAT_FS = n
+        depends on FUSE_FS = n
+        depends on GFS2_FS = n
+        depends on HFS_FS = n
+        depends on HFSPLUS_FS = n
+        depends on HPFS_FS = n
+        depends on HUGETLBFS = n
+        depends on ISO9660_FS = n
+        depends on JFFS2_FS = n
+        depends on JFS_FS = n
+        depends on LOGFS = n
+        depends on MINIX_FS = n
+        depends on NCP_FS = n
+        depends on NFSD = n
+        depends on NFS_FS = n
+        depends on NILFS2_FS = n
+        depends on NTFS_FS = n
+        depends on OCFS2_FS = n
+        depends on OMFS_FS = n
+        depends on QNX4FS_FS = n
+        depends on QNX6FS_FS = n
+        depends on REISERFS_FS = n
+        depends on SQUASHFS = n
+        depends on SYSV_FS = n
+        depends on UBIFS_FS = n
+        depends on UDF_FS = n
+        depends on UFS_FS = n
+        depends on VXFS_FS = n
+        depends on XFS_FS = n
+
+        depends on !UML || HOSTFS = n
+
+        # The rare drivers that won't build
+        depends on AIRO = n
+        depends on AIRO_CS = n
+        depends on TUN = n
+        depends on INFINIBAND_QIB = n
+        depends on BLK_DEV_LOOP = n
+        depends on ANDROID_BINDER_IPC = n
+
+        # Security modules
+        depends on SECURITY_TOMOYO = n
+        depends on SECURITY_APPARMOR = n
+
+config UIDGID_STRICT_TYPE_CHECKS
+        bool "Require conversions between uid/gids and their internal representation"
+        depends on UIDGID_CONVERTED
+        default n
+        help
+         While the nececessary conversions are being added to all subsystems this option allows
+         the code to continue to build for unconverted subsystems.
+
+         Say Y here if you want the strict type checking enabled
+
 config SCHED_AUTOGROUP
         bool "Automatic process group scheduling"
         select EVENTFD
@@ -1156,7 +1330,7 @@ menu "Kernel Performance Events And Counters"
 
 config PERF_EVENTS
         bool "Kernel performance events and counters"
-        default y if (PROFILING || PERF_COUNTERS)
+        default y if PROFILING
         depends on HAVE_PERF_EVENTS
         select ANON_INODES
         select IRQ_WORK
@@ -1183,18 +1357,6 @@ config PERF_EVENTS
 
           Say Y if unsure.
 
-config PERF_COUNTERS
-        bool "Kernel performance counters (old config option)"
-        depends on HAVE_PERF_EVENTS
-        help
-          This config has been obsoleted by the PERF_EVENTS
-          config option - please see that one for details.
-
-          It has no effect on the kernel whether you enable
-          it or not, it is a compatibility placeholder.
-
-          Say N if unsure.
-
 config DEBUG_PERF_USE_VMALLOC
         default n
         bool "Debug: use vmalloc to back perf mmap() buffers"
diff --git a/init/Makefile b/init/Makefile
index 0bf677aa0872..7bc47ee31c36 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -10,6 +10,10 @@ obj-$(CONFIG_BLK_DEV_INITRD)   += initramfs.o
 endif
 obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o
 
+ifneq ($(CONFIG_ARCH_INIT_TASK),y)
+obj-y                          += init_task.o
+endif
+
 mounts-y                        := do_mounts.o
 mounts-$(CONFIG_BLK_DEV_RAM)    += do_mounts_rd.o
 mounts-$(CONFIG_BLK_DEV_INITRD) += do_mounts_initrd.o
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 0e93f92a0345..42b0707c3481 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -472,7 +472,7 @@ void __init change_floppy(char *fmt, ...)
 void __init mount_root(void)
 {
 #ifdef CONFIG_ROOT_NFS
-        if (MAJOR(ROOT_DEV) == UNNAMED_MAJOR) {
+        if (ROOT_DEV == Root_NFS) {
                 if (mount_nfs_root())
                         return;
 
diff --git a/init/init_task.c b/init/init_task.c
new file mode 100644
index 000000000000..8b2f3996b035
--- /dev/null
+++ b/init/init_task.c
@@ -0,0 +1,24 @@
+#include <linux/init_task.h>
+#include <linux/export.h>
+#include <linux/mqueue.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+
+static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
+static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
+
+/* Initial task structure */
+struct task_struct init_task = INIT_TASK(init_task);
+EXPORT_SYMBOL(init_task);
+
+/*
+ * Initial thread structure. Alignment of this is handled by a special
+ * linker map entry.
+ */
+union thread_union init_thread_union __init_task_data =
+        { INIT_THREAD_INFO(init_task) };
diff --git a/init/main.c b/init/main.c
index 44b2433334c7..1ca6b32c4828 100644
--- a/init/main.c
+++ b/init/main.c
@@ -226,7 +226,7 @@ static int __init loglevel(char *str)
 early_param("loglevel", loglevel);
 
 /* Change NUL term back to "=", to make "param" the whole string. */
-static int __init repair_env_string(char *param, char *val)
+static int __init repair_env_string(char *param, char *val, const char *unused)
 {
         if (val) {
                 /* param=val or param="val"? */
@@ -246,9 +246,9 @@ static int __init repair_env_string(char *param, char *val)
  * Unknown boot options get handed to init, unless they look like
  * unused parameters (modprobe will find them in /proc/cmdline).
  */
-static int __init unknown_bootoption(char *param, char *val)
+static int __init unknown_bootoption(char *param, char *val, const char *unused)
 {
-        repair_env_string(param, val);
+        repair_env_string(param, val, unused);
 
         /* Handle obsolete-style parameters */
         if (obsolete_checksetup(param))
@@ -385,7 +385,7 @@ static noinline void __init_refok rest_init(void)
 }
 
 /* Check for early params. */
-static int __init do_early_param(char *param, char *val)
+static int __init do_early_param(char *param, char *val, const char *unused)
 {
         const struct obs_kernel_param *p;
 
@@ -560,9 +560,6 @@ asmlinkage void __init start_kernel(void)
         early_boot_irqs_disabled = false;
         local_irq_enable();
 
-        /* Interrupts are enabled now so all GFP allocations are safe. */
-        gfp_allowed_mask = __GFP_BITS_MASK;
-
         kmem_cache_init_late();
 
         /*
@@ -728,14 +725,14 @@ static initcall_t *initcall_levels[] __initdata = {
 };
 
 static char *initcall_level_names[] __initdata = {
-        "early parameters",
-        "core parameters",
-        "postcore parameters",
-        "arch parameters",
-        "subsys parameters",
-        "fs parameters",
-        "device parameters",
-        "late parameters",
+        "early",
+        "core",
+        "postcore",
+        "arch",
+        "subsys",
+        "fs",
+        "device",
+        "late",
 };
 
 static void __init do_initcall_level(int level)
@@ -748,7 +745,7 @@ static void __init do_initcall_level(int level)
                    static_command_line, __start___param,
                    __stop___param - __start___param,
                    level, level,
-                   repair_env_string);
+                   &repair_env_string);
 
         for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
                 do_one_initcall(*fn);
@@ -758,8 +755,13 @@ static void __init do_initcalls(void)
 {
         int level;
 
-        for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++)
+        for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) {
+                pr_info("initlevel:%d=%s, %d registered initcalls\n",
+                        level, initcall_level_names[level],
+                        (int) (initcall_levels[level+1]
+                                - initcall_levels[level]));
                 do_initcall_level(level);
+        }
 }
 
 /*
@@ -842,6 +844,10 @@ static int __init kernel_init(void * unused)
          * Wait until kthreadd is all set-up.
          */
         wait_for_completion(&kthreadd_done);
+
+        /* Now the scheduler is fully set up and can do blocking allocations */
+        gfp_allowed_mask = __GFP_BITS_MASK;
+
         /*
          * init can allocate pages on any node
          */