Merge branch 'next' into for-linus

Merge first round of changes for 3.13 merge window.

4 files changed, 158 insertions, 53 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 9d3a7887a6d..3ecd8a1178f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -53,6 +53,20 @@ config CROSS_COMPILE
 	  need to set this unless you want the configured kernel build
 	  directory to select the cross-compiler automatically.
 
+config COMPILE_TEST
+	bool "Compile also drivers which will not load"
+	default n
+	help
+	  Some drivers can be compiled on a different platform than they are
+	  intended to be run on. Despite they cannot be loaded there (or even
+	  when they load they cannot be used due to missing HW support),
+	  developers still, opposing to distributors, might want to build such
+	  drivers to compile-test them.
+
+	  If you are a developer and want to build everything available, say Y
+	  here. If you are a user/distributor, say N here to exclude useless
+	  drivers to be distributed.
+
 config LOCALVERSION
 	string "Local version - append to kernel release"
 	help
@@ -98,10 +112,13 @@ config HAVE_KERNEL_XZ
 config HAVE_KERNEL_LZO
 	bool
 
+config HAVE_KERNEL_LZ4
+	bool
+
 choice
 	prompt "Kernel compression mode"
 	default KERNEL_GZIP
-	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO
+	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
 	help
 	  The linux kernel is a kind of self-extracting executable.
 	  Several compression algorithms are available, which differ
@@ -168,6 +185,18 @@ config KERNEL_LZO
 	  size is about 10% bigger than gzip; however its speed
 	  (both compression and decompression) is the fastest.
 
+config KERNEL_LZ4
+	bool "LZ4"
+	depends on HAVE_KERNEL_LZ4
+	help
+	  LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
+	  A preliminary version of LZ4 de/compression tool is available at
+	  <https://code.google.com/p/lz4/>.
+
+	  Its compression ratio is worse than LZO. The size of the kernel
+	  is about 8% bigger than LZO. But the decompression speed is
+	  faster than LZO.
+
 endchoice
 
 config DEFAULT_HOSTNAME
@@ -431,6 +460,7 @@ choice
 config TREE_RCU
 	bool "Tree-based hierarchical RCU"
 	depends on !PREEMPT && SMP
+	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -440,6 +470,7 @@ config TREE_RCU
 config TREE_PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
 	depends on PREEMPT
+	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -458,18 +489,10 @@ config TINY_RCU
 	  is not required.  This option greatly reduces the
 	  memory footprint of RCU.
 
-config TINY_PREEMPT_RCU
-	bool "Preemptible UP-only small-memory-footprint RCU"
-	depends on PREEMPT && !SMP
-	help
-	  This option selects the RCU implementation that is designed
-	  for real-time UP systems.  This option greatly reduces the
-	  memory footprint of RCU.
-
 endchoice
 
 config PREEMPT_RCU
-	def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU )
+	def_bool TREE_PREEMPT_RCU
 	help
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
@@ -505,13 +528,29 @@ config RCU_USER_QS
 config CONTEXT_TRACKING_FORCE
 	bool "Force context tracking"
 	depends on CONTEXT_TRACKING
-	default CONTEXT_TRACKING
+	default y if !NO_HZ_FULL
 	help
-	  Probe on user/kernel boundaries by default in order to
-	  test the features that rely on it such as userspace RCU extended
-	  quiescent states.
-	  This test is there for debugging until we have a real user like the
-	  full dynticks mode.
+	  The major pre-requirement for full dynticks to work is to
+	  support the context tracking subsystem. But there are also
+	  other dependencies to provide in order to make the full
+	  dynticks working.
+
+	  This option stands for testing when an arch implements the
+	  context tracking backend but doesn't yet fullfill all the
+	  requirements to make the full dynticks feature working.
+	  Without the full dynticks, there is no way to test the support
+	  for context tracking and the subsystems that rely on it: RCU
+	  userspace extended quiescent state and tickless cputime
+	  accounting. This option copes with the absence of the full
+	  dynticks subsystem by forcing the context tracking on all
+	  CPUs in the system.
+
+	  Say Y only if you're working on the developpement of an
+	  architecture backend for the context tracking.
+
+	  Say N otherwise, this option brings an overhead that you
+	  don't want in production.
+
 
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
@@ -655,7 +694,7 @@ config RCU_BOOST_DELAY
 	  Accept the default if unsure.
 
 config RCU_NOCB_CPU
-	bool "Offload RCU callback processing from boot-selected CPUs (EXPERIMENTAL"
+	bool "Offload RCU callback processing from boot-selected CPUs"
 	depends on TREE_RCU || TREE_PREEMPT_RCU
 	default n
 	help
@@ -681,9 +720,10 @@ choice
 	prompt "Build-forced no-CBs CPUs"
 	default RCU_NOCB_CPU_NONE
 	help
-	  This option allows no-CBs CPUs to be specified at build time.
-	  Additional no-CBs CPUs may be specified by the rcu_nocbs=
-	  boot parameter.
+	  This option allows no-CBs CPUs (whose RCU callbacks are invoked
+	  from kthreads rather than from softirq context) to be specified
+	  at build time.  Additional no-CBs CPUs may be specified by
+	  the rcu_nocbs= boot parameter.
 
 config RCU_NOCB_CPU_NONE
 	bool "No build_forced no-CBs CPUs"
@@ -691,25 +731,40 @@ config RCU_NOCB_CPU_NONE
 	help
 	  This option does not force any of the CPUs to be no-CBs CPUs.
 	  Only CPUs designated by the rcu_nocbs= boot parameter will be
-	  no-CBs CPUs.
+	  no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU
+	  kthreads whose names begin with "rcuo".  All other CPUs will
+	  invoke their own RCU callbacks in softirq context.
+
+	  Select this option if you want to choose no-CBs CPUs at
+	  boot time, for example, to allow testing of different no-CBs
+	  configurations without having to rebuild the kernel each time.
 
 config RCU_NOCB_CPU_ZERO
 	bool "CPU 0 is a build_forced no-CBs CPU"
 	depends on RCU_NOCB_CPU && !NO_HZ_FULL
 	help
-	  This option forces CPU 0 to be a no-CBs CPU.  Additional CPUs
-	  may be designated as no-CBs CPUs using the rcu_nocbs= boot
-	  parameter will be no-CBs CPUs.
+	  This option forces CPU 0 to be a no-CBs CPU, so that its RCU
+	  callbacks are invoked by a per-CPU kthread whose name begins
+	  with "rcuo".	Additional CPUs may be designated as no-CBs
+	  CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs.
+	  All other CPUs will invoke their own RCU callbacks in softirq
+	  context.
 
 	  Select this if CPU 0 needs to be a no-CBs CPU for real-time
-	  or energy-efficiency reasons.
+	  or energy-efficiency reasons, but the real reason it exists
+	  is to ensure that randconfig testing covers mixed systems.
 
 config RCU_NOCB_CPU_ALL
 	bool "All CPUs are build_forced no-CBs CPUs"
 	depends on RCU_NOCB_CPU
 	help
 	  This option forces all CPUs to be no-CBs CPUs.  The rcu_nocbs=
-	  boot parameter will be ignored.
+	  boot parameter will be ignored.  All CPUs' RCU callbacks will
+	  be executed in the context of per-CPU rcuo kthreads created for
+	  this purpose.  Assuming that the kthreads whose names start with
+	  "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter
+	  on the remaining CPUs, but might decrease memory locality during
+	  RCU-callback invocation, thus potentially degrading throughput.
 
 	  Select this if all CPUs need to be no-CBs CPUs for real-time
 	  or energy-efficiency reasons.
@@ -757,6 +812,9 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
+config GENERIC_SCHED_CLOCK
+	bool
+
 #
 # For architectures that want to enable the support for NUMA-affine scheduler
 # balancing logic:
@@ -876,7 +934,7 @@ config MEMCG
 
 	  Note that setting this option increases fixed memory overhead
 	  associated with each page of memory in the system. By this,
-	  20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
+	  8(16)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
 	  usage tracking struct at boot. Total amount of this is printed out
 	  at boot.
 
@@ -914,7 +972,7 @@ config MEMCG_SWAP_ENABLED
 	  Memory Resource Controller Swap Extension comes with its price in
 	  a bigger memory consumption. General purpose distribution kernels
 	  which want to enable the feature but keep it disabled by default
-	  and let the user enable it by swapaccount boot command line
+	  and let the user enable it by swapaccount=1 boot command line
 	  parameter should have this option unselected.
 	  For those who want to have the feature enabled by default should
 	  select this option (if, for some reason, they need to disable it
@@ -1065,7 +1123,6 @@ config IPC_NS
 
 config USER_NS
 	bool "User namespace"
-	depends on UIDGID_CONVERTED
 	select UIDGID_STRICT_TYPE_CHECKS
 
 	default n
@@ -1099,20 +1156,8 @@ 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
-
-	# Filesystems
-	depends on XFS_FS = 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
@@ -1244,9 +1289,6 @@ config SYSCTL_ARCH_UNALIGN_ALLOW
 	  the unaligned access emulation.
 	  see arch/parisc/kernel/unaligned.c for reference
 
-config HOTPLUG
-	def_bool y
-
 config HAVE_PCSPKR_PLATFORM
 	bool
 
@@ -1558,6 +1600,17 @@ config SLOB
 
 endchoice
 
+config SLUB_CPU_PARTIAL
+	default y
+	depends on SLUB && SMP
+	bool "SLUB per cpu partial cache"
+	help
+	  Per cpu partial caches accellerate objects allocation and freeing
+	  that is local to a processor at the price of more indeterminism
+	  in the latency of the free. On overflow these caches will be cleared
+	  which requires the taking of locks that may cause latency spikes.
+	  Typically one would choose no for a realtime system.
+
 config MMAP_ALLOW_UNINITIALIZED
 	bool "Allow mmapped anonymous memory to be uninitialized"
 	depends on EXPERT && !MMU
@@ -1617,6 +1670,7 @@ config BASE_SMALL
 
 menuconfig MODULES
 	bool "Enable loadable module support"
+	option modules
 	help
 	  Kernel modules are small pieces of compiled code which can
 	  be inserted in the running kernel, rather than being
diff --git a/init/calibrate.c b/init/calibrate.c
index fda0a7b0f06..520702db9ac 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -31,7 +31,7 @@ __setup("lpj=", lpj_setup);
 #define DELAY_CALIBRATION_TICKS			((HZ < 100) ? 1 : (HZ/100))
 #define MAX_DIRECT_CALIBRATION_RETRIES		5
 
-static unsigned long __cpuinit calibrate_delay_direct(void)
+static unsigned long calibrate_delay_direct(void)
 {
 	unsigned long pre_start, start, post_start;
 	unsigned long pre_end, end, post_end;
@@ -166,7 +166,10 @@ static unsigned long __cpuinit calibrate_delay_direct(void)
 	return 0;
 }
 #else
-static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
+static unsigned long calibrate_delay_direct(void)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -180,7 +183,7 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
  */
 #define LPS_PREC 8
 
-static unsigned long __cpuinit calibrate_delay_converge(void)
+static unsigned long calibrate_delay_converge(void)
 {
 	/* First stage - slowly accelerate to find initial bounds */
 	unsigned long lpj, lpj_base, ticks, loopadd, loopadd_base, chop_limit;
@@ -254,12 +257,12 @@ static DEFINE_PER_CPU(unsigned long, cpu_loops_per_jiffy) = { 0 };
  * Architectures should override this function if a faster calibration
  * method is available.
  */
-unsigned long __attribute__((weak)) __cpuinit calibrate_delay_is_known(void)
+unsigned long __attribute__((weak)) calibrate_delay_is_known(void)
 {
 	return 0;
 }
 
-void __cpuinit calibrate_delay(void)
+void calibrate_delay(void)
 {
 	unsigned long lpj;
 	static bool printed;
diff --git a/init/do_mounts.c b/init/do_mounts.c
index a2b49f2c1bd..a51cddc2ff8 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -26,6 +26,8 @@
 #include <linux/async.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
+#include <linux/ramfs.h>
+#include <linux/shmem_fs.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
@@ -536,7 +538,7 @@ void __init prepare_namespace(void)
 	int is_floppy;
 
 	if (root_delay) {
-		printk(KERN_INFO "Waiting %dsec before mounting root device...\n",
+		printk(KERN_INFO "Waiting %d sec before mounting root device...\n",
 		       root_delay);
 		ssleep(root_delay);
 	}
@@ -588,3 +590,46 @@ out:
 	sys_mount(".", "/", NULL, MS_MOVE, NULL);
 	sys_chroot(".");
 }
+
+static bool is_tmpfs;
+static struct dentry *rootfs_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
+{
+	static unsigned long once;
+	void *fill = ramfs_fill_super;
+
+	if (test_and_set_bit(0, &once))
+		return ERR_PTR(-ENODEV);
+
+	if (IS_ENABLED(CONFIG_TMPFS) && is_tmpfs)
+		fill = shmem_fill_super;
+
+	return mount_nodev(fs_type, flags, data, fill);
+}
+
+static struct file_system_type rootfs_fs_type = {
+	.name		= "rootfs",
+	.mount		= rootfs_mount,
+	.kill_sb	= kill_litter_super,
+};
+
+int __init init_rootfs(void)
+{
+	int err = register_filesystem(&rootfs_fs_type);
+
+	if (err)
+		return err;
+
+	if (IS_ENABLED(CONFIG_TMPFS) && !saved_root_name[0] &&
+		(!root_fs_names || strstr(root_fs_names, "tmpfs"))) {
+		err = shmem_init();
+		is_tmpfs = true;
+	} else {
+		err = init_ramfs_fs();
+	}
+
+	if (err)
+		unregister_filesystem(&rootfs_fs_type);
+
+	return err;
+}
diff --git a/init/main.c b/init/main.c
index 9484f4ba88d..af310afbef2 100644
--- a/init/main.c
+++ b/init/main.c
@@ -74,6 +74,8 @@
 #include <linux/ptrace.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
+#include <linux/sched_clock.h>
+#include <linux/context_tracking.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -542,9 +544,9 @@ asmlinkage void __init start_kernel(void)
 	if (WARN(!irqs_disabled(), "Interrupts were enabled *very* early, fixing it\n"))
 		local_irq_disable();
 	idr_init_cache();
-	perf_event_init();
 	rcu_init();
 	tick_nohz_init();
+	context_tracking_init();
 	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
@@ -555,6 +557,8 @@ asmlinkage void __init start_kernel(void)
 	softirq_init();
 	timekeeping_init();
 	time_init();
+	sched_clock_postinit();
+	perf_event_init();
 	profile_init();
 	call_function_init();
 	WARN(!irqs_disabled(), "Interrupts were enabled early\n");
@@ -655,8 +659,6 @@ static void __init do_ctors(void)
 bool initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
-static char msgbuf[64];
-
 static int __init_or_module do_one_initcall_debug(initcall_t fn)
 {
 	ktime_t calltime, delta, rettime;
@@ -679,6 +681,7 @@ int __init_or_module do_one_initcall(initcall_t fn)
 {
 	int count = preempt_count();
 	int ret;
+	char msgbuf[64];
 
 	if (initcall_debug)
 		ret = do_one_initcall_debug(fn);