These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

4 files changed, 146 insertions, 110 deletions

diff --git a/kernel/init/Kconfig b/kernel/init/Kconfig
index a70b5002d..a7c81c091 100644
--- a/kernel/init/Kconfig
+++ b/kernel/init/Kconfig
@@ -435,6 +435,7 @@ config TASKSTATS
 config TASK_DELAY_ACCT
 	bool "Enable per-task delay accounting"
 	depends on TASKSTATS
+	select SCHED_INFO
 	help
 	  Collect information on time spent by a task waiting for system
 	  resources like cpu, synchronous block I/O completion and swapping
@@ -465,13 +466,9 @@ endmenu # "CPU/Task time and stats accounting"
 
 menu "RCU Subsystem"
 
-choice
-	prompt "RCU Implementation"
-	default TREE_RCU
-
 config TREE_RCU
-	bool "Tree-based hierarchical RCU"
-	depends on !PREEMPT && SMP
+	bool
+	default y if !PREEMPT && SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -479,8 +476,8 @@ config TREE_RCU
 	  smaller systems.
 
 config PREEMPT_RCU
-	bool "Preemptible tree-based hierarchical RCU"
-	depends on PREEMPT
+	bool
+	default y if PREEMPT
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -491,15 +488,28 @@ config PREEMPT_RCU
 	  Select this option if you are unsure.
 
 config TINY_RCU
-	bool "UP-only small-memory-footprint RCU"
-	depends on !PREEMPT && !SMP
+	bool
+	default y if !PREEMPT && !SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for UP systems from which real-time response
 	  is not required.  This option greatly reduces the
 	  memory footprint of RCU.
 
-endchoice
+config RCU_EXPERT
+	bool "Make expert-level adjustments to RCU configuration"
+	default y if PREEMPT_RT_FULL
+	help
+	  This option needs to be enabled if you wish to make
+	  expert-level adjustments to RCU configuration.  By default,
+	  no such adjustments can be made, which has the often-beneficial
+	  side-effect of preventing "make oldconfig" from asking you all
+	  sorts of detailed questions about how you would like numerous
+	  obscure RCU options to be set up.
+
+	  Say Y if you need to make expert-level adjustments to RCU.
+
+	  Say N if you are unsure.
 
 config SRCU
 	bool
@@ -509,7 +519,7 @@ config SRCU
 	  sections.
 
 config TASKS_RCU
-	bool "Task_based RCU implementation using voluntary context switch"
+	bool
 	default n
 	select SRCU
 	help
@@ -517,8 +527,6 @@ config TASKS_RCU
 	  only voluntary context switch (not preemption!), idle, and
 	  user-mode execution as quiescent states.
 
-	  If unsure, say N.
-
 config RCU_STALL_COMMON
 	def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
 	help
@@ -530,23 +538,6 @@ config RCU_STALL_COMMON
 config CONTEXT_TRACKING
        bool
 
-config RCU_USER_QS
-	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_CONTEXT_TRACKING && SMP
-	select CONTEXT_TRACKING
-	help
-	  This option sets hooks on kernel / userspace boundaries and
-	  puts RCU in extended quiescent state when the CPU runs in
-	  userspace. It means that when a CPU runs in userspace, it is
-	  excluded from the global RCU state machine and thus doesn't
-	  try to keep the timer tick on for RCU.
-
-	  Unless you want to hack and help the development of the full
-	  dynticks mode, you shouldn't enable this option.  It also
-	  adds unnecessary overhead.
-
-	  If unsure say N
-
 config CONTEXT_TRACKING_FORCE
 	bool "Force context tracking"
 	depends on CONTEXT_TRACKING
@@ -578,7 +569,7 @@ config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
 	range 2 32 if !64BIT
-	depends on TREE_RCU || PREEMPT_RCU
+	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
 	default 64 if 64BIT
 	default 32 if !64BIT
 	help
@@ -596,9 +587,9 @@ config RCU_FANOUT
 
 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 || PREEMPT_RCU
+	range 2 64 if 64BIT
+	range 2 32 if !64BIT
+	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
 	default 16
 	help
 	  This option controls the leaf-level fanout of hierarchical
@@ -621,23 +612,9 @@ config RCU_FANOUT_LEAF
 
 	  Take the default if unsure.
 
-config RCU_FANOUT_EXACT
-	bool "Disable tree-based hierarchical RCU auto-balancing"
-	depends on TREE_RCU || PREEMPT_RCU
-	default n
-	help
-	  This option forces use of the exact RCU_FANOUT value specified,
-	  regardless of imbalances in the hierarchy.  This is useful for
-	  testing RCU itself, and might one day be useful on systems with
-	  strong NUMA behavior.
-
-	  Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
-
-	  Say N if unsure.
-
 config RCU_FAST_NO_HZ
 	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on NO_HZ_COMMON && SMP && !PREEMPT_RT_FULL
+	depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL
 	default n
 	help
 	  This option permits CPUs to enter dynticks-idle state even if
@@ -663,7 +640,7 @@ config TREE_RCU_TRACE
 
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
-	depends on RT_MUTEXES && PREEMPT_RCU
+	depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
 	default y if PREEMPT_RT_FULL
 	help
 	  This option boosts the priority of preempted RCU readers that
@@ -680,6 +657,7 @@ config RCU_KTHREAD_PRIO
 	range 0 99 if !RCU_BOOST
 	default 1 if RCU_BOOST
 	default 0 if !RCU_BOOST
+	depends on RCU_EXPERT
 	help
 	  This option specifies the SCHED_FIFO priority value that will be
 	  assigned to the rcuc/n and rcub/n threads and is also the value
@@ -720,6 +698,7 @@ config RCU_BOOST_DELAY
 config RCU_NOCB_CPU
 	bool "Offload RCU callback processing from boot-selected CPUs"
 	depends on TREE_RCU || PREEMPT_RCU
+	depends on RCU_EXPERT || NO_HZ_FULL
 	default n
 	help
 	  Use this option to reduce OS jitter for aggressive HPC or
@@ -834,7 +813,7 @@ config IKCONFIG_PROC
 
 config LOG_BUF_SHIFT
 	int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
-	range 12 21
+	range 12 25
 	default 17
 	depends on PRINTK
 	help
@@ -904,6 +883,16 @@ config ARCH_SUPPORTS_NUMA_BALANCING
 	bool
 
 #
+# For architectures that prefer to flush all TLBs after a number of pages
+# are unmapped instead of sending one IPI per page to flush. The architecture
+# must provide guarantees on what happens if a clean TLB cache entry is
+# written after the unmap. Details are in mm/rmap.c near the check for
+# should_defer_flush. The architecture should also consider if the full flush
+# and the refill costs are offset by the savings of sending fewer IPIs.
+config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	bool
+
+#
 # For architectures that know their GCC __int128 support is sound
 #
 config ARCH_SUPPORTS_INT128
@@ -967,6 +956,22 @@ config CGROUP_FREEZER
 	  Provides a way to freeze and unfreeze all tasks in a
 	  cgroup.
 
+config CGROUP_PIDS
+	bool "PIDs cgroup subsystem"
+	help
+	  Provides enforcement of process number limits in the scope of a
+	  cgroup. Any attempt to fork more processes than is allowed in the
+	  cgroup will fail. PIDs are fundamentally a global resource because it
+	  is fairly trivial to reach PID exhaustion before you reach even a
+	  conservative kmemcg limit. As a result, it is possible to grind a
+	  system to halt without being limited by other cgroup policies. The
+	  PIDs cgroup subsystem is designed to stop this from happening.
+
+	  It should be noted that organisational operations (such as attaching
+	  to a cgroup hierarchy will *not* be blocked by the PIDs subsystem),
+	  since the PIDs limit only affects a process's ability to fork, not to
+	  attach to a cgroup.
+
 config CGROUP_DEVICE
 	bool "Device controller for cgroups"
 	help
@@ -1142,10 +1147,16 @@ config DEBUG_BLK_CGROUP
 	Enable some debugging help. Currently it exports additional stat
 	files in a cgroup which can be useful for debugging.
 
+config CGROUP_WRITEBACK
+	bool
+	depends on MEMCG && BLK_CGROUP
+	default y
+
 endif # CGROUPS
 
 config CHECKPOINT_RESTORE
 	bool "Checkpoint/restore support" if EXPERT
+	select PROC_CHILDREN
 	default n
 	help
 	  Enables additional kernel features in a sake of checkpoint/restore.
@@ -1575,6 +1586,14 @@ config ADVISE_SYSCALLS
 	  applications use these syscalls, you can disable this option to save
 	  space.
 
+config USERFAULTFD
+	bool "Enable userfaultfd() system call"
+	select ANON_INODES
+	depends on MMU
+	help
+	  Enable the userfaultfd() system call that allows to intercept and
+	  handle page faults in userland.
+
 config PCI_QUIRKS
 	default y
 	bool "Enable PCI quirk workarounds" if EXPERT
@@ -1584,6 +1603,18 @@ config PCI_QUIRKS
 	  bugs/quirks. Disable this only if your target machine is
 	  unaffected by PCI quirks.
 
+config MEMBARRIER
+	bool "Enable membarrier() system call" if EXPERT
+	default y
+	help
+	  Enable the membarrier() system call that allows issuing memory
+	  barriers across all running threads, which can be used to distribute
+	  the cost of user-space memory barriers asymmetrically by transforming
+	  pairs of memory barriers into pairs consisting of membarrier() and a
+	  compiler barrier.
+
+	  If unsure, say Y.
+
 config EMBEDDED
 	bool "Embedded system"
 	option allnoconfig_y
@@ -1638,7 +1669,7 @@ config PERF_EVENTS
 config DEBUG_PERF_USE_VMALLOC
 	default n
 	bool "Debug: use vmalloc to back perf mmap() buffers"
-	depends on PERF_EVENTS && DEBUG_KERNEL
+	depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
 	select PERF_USE_VMALLOC
 	help
 	 Use vmalloc memory to back perf mmap() buffers.
@@ -1749,17 +1780,23 @@ config MMAP_ALLOW_UNINITIALIZED
 
 	  See Documentation/nommu-mmap.txt for more information.
 
-config SYSTEM_TRUSTED_KEYRING
-	bool "Provide system-wide ring of trusted keys"
-	depends on KEYS
+config SYSTEM_DATA_VERIFICATION
+	def_bool n
+	select SYSTEM_TRUSTED_KEYRING
+	select KEYS
+	select CRYPTO
+	select ASYMMETRIC_KEY_TYPE
+	select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+	select PUBLIC_KEY_ALGO_RSA
+	select ASN1
+	select OID_REGISTRY
+	select X509_CERTIFICATE_PARSER
+	select PKCS7_MESSAGE_PARSER
 	help
-	  Provide a system keyring to which trusted keys can be added.  Keys in
-	  the keyring are considered to be trusted.  Keys may be added at will
-	  by the kernel from compiled-in data and from hardware key stores, but
-	  userspace may only add extra keys if those keys can be verified by
-	  keys already in the keyring.
-
-	  Keys in this keyring are used by module signature checking.
+	  Provide PKCS#7 message verification using the contents of the system
+	  trusted keyring to provide public keys.  This then can be used for
+	  module verification, kexec image verification and firmware blob
+	  verification.
 
 config PROFILING
 	bool "Profiling support"
@@ -1869,20 +1906,16 @@ config MODULE_SRCVERSION_ALL
 config MODULE_SIG
 	bool "Module signature verification"
 	depends on MODULES
-	select SYSTEM_TRUSTED_KEYRING
-	select KEYS
-	select CRYPTO
-	select ASYMMETRIC_KEY_TYPE
-	select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
-	select PUBLIC_KEY_ALGO_RSA
-	select ASN1
-	select OID_REGISTRY
-	select X509_CERTIFICATE_PARSER
+	select SYSTEM_DATA_VERIFICATION
 	help
 	  Check modules for valid signatures upon load: the signature
 	  is simply appended to the module. For more information see
 	  Documentation/module-signing.txt.
 
+	  Note that this option adds the OpenSSL development packages as a
+	  kernel build dependency so that the signing tool can use its crypto
+	  library.
+
 	  !!!WARNING!!!  If you enable this option, you MUST make sure that the
 	  module DOES NOT get stripped after being signed.  This includes the
 	  debuginfo strip done by some packagers (such as rpmbuild) and
@@ -1951,26 +1984,21 @@ config MODULE_COMPRESS
 	bool "Compress modules on installation"
 	depends on MODULES
 	help
-	  This option compresses the kernel modules when 'make
-	  modules_install' is run.
 
-	  The modules will be compressed either using gzip or xz depend on the
-	  choice made in "Compression algorithm".
+	  Compresses kernel modules when 'make modules_install' is run; gzip or
+	  xz depending on "Compression algorithm" below.
+
+	  module-init-tools MAY support gzip, and kmod MAY support gzip and xz.
 
-	  module-init-tools has support for gzip format while kmod handle gzip
-	  and xz compressed modules.
+	  Out-of-tree kernel modules installed using Kbuild will also be
+	  compressed upon installation.
 
-	  When a kernel module is installed from outside of the main kernel
-	  source and uses the Kbuild system for installing modules then that
-	  kernel module will also be compressed when it is installed.
+	  Note: for modules inside an initrd or initramfs, it's more efficient
+	  to compress the whole initrd or initramfs instead.
 
-	  This option provides little benefit when the modules are to be used inside
-	  an initrd or initramfs, it generally is more efficient to compress the whole
-	  initrd or initramfs instead.
+	  Note: This is fully compatible with signed modules.
 
-	  This is fully compatible with signed modules while the signed module is
-	  compressed. module-init-tools or kmod handles decompression and provide to
-	  other layer the uncompressed but signed payload.
+	  If in doubt, say N.
 
 choice
 	prompt "Compression algorithm"
@@ -1992,6 +2020,10 @@ endchoice
 
 endif # MODULES
 
+config MODULES_TREE_LOOKUP
+	def_bool y
+	depends on PERF_EVENTS || TRACING
+
 config INIT_ALL_POSSIBLE
 	bool
 	help
@@ -2001,13 +2033,6 @@ config INIT_ALL_POSSIBLE
 	  it was better to provide this option than to break all the archs
 	  and have several arch maintainers pursuing me down dark alleys.
 
-config STOP_MACHINE
-	bool
-	default y
-	depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
-	help
-	  Need stop_machine() primitive.
-
 source "block/Kconfig"
 
 config PREEMPT_NOTIFIERS
diff --git a/kernel/init/do_mounts.c b/kernel/init/do_mounts.c
index a95bbdb2a..dea5de95c 100644
--- a/kernel/init/do_mounts.c
+++ b/kernel/init/do_mounts.c
@@ -533,8 +533,13 @@ void __init mount_root(void)
 	}
 #endif
 #ifdef CONFIG_BLOCK
-	create_dev("/dev/root", ROOT_DEV);
-	mount_block_root("/dev/root", root_mountflags);
+	{
+		int err = create_dev("/dev/root", ROOT_DEV);
+
+		if (err < 0)
+			pr_emerg("Failed to create /dev/root: %d\n", err);
+		mount_block_root("/dev/root", root_mountflags);
+	}
 #endif
 }
 
diff --git a/kernel/init/initramfs.c b/kernel/init/initramfs.c
index ad1bd7787..b32ad7d97 100644
--- a/kernel/init/initramfs.c
+++ b/kernel/init/initramfs.c
@@ -526,14 +526,14 @@ extern unsigned long __initramfs_size;
 
 static void __init free_initrd(void)
 {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	unsigned long crashk_start = (unsigned long)__va(crashk_res.start);
 	unsigned long crashk_end   = (unsigned long)__va(crashk_res.end);
 #endif
 	if (do_retain_initrd)
 		goto skip;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	/*
 	 * If the initrd region is overlapped with crashkernel reserved region,
 	 * free only memory that is not part of crashkernel region.
diff --git a/kernel/init/main.c b/kernel/init/main.c
index 0486a8e11..4a76e629c 100644
--- a/kernel/init/main.c
+++ b/kernel/init/main.c
@@ -235,7 +235,8 @@ 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, const char *unused)
+static int __init repair_env_string(char *param, char *val,
+				    const char *unused, void *arg)
 {
 	if (val) {
 		/* param=val or param="val"? */
@@ -252,14 +253,15 @@ static int __init repair_env_string(char *param, char *val, const char *unused)
 }
 
 /* Anything after -- gets handed straight to init. */
-static int __init set_init_arg(char *param, char *val, const char *unused)
+static int __init set_init_arg(char *param, char *val,
+			       const char *unused, void *arg)
 {
 	unsigned int i;
 
 	if (panic_later)
 		return 0;
 
-	repair_env_string(param, val, unused);
+	repair_env_string(param, val, unused, NULL);
 
 	for (i = 0; argv_init[i]; i++) {
 		if (i == MAX_INIT_ARGS) {
@@ -276,9 +278,10 @@ static int __init set_init_arg(char *param, char *val, const char *unused)
  * 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, const char *unused)
+static int __init unknown_bootoption(char *param, char *val,
+				     const char *unused, void *arg)
 {
-	repair_env_string(param, val, unused);
+	repair_env_string(param, val, unused, NULL);
 
 	/* Handle obsolete-style parameters */
 	if (obsolete_checksetup(param))
@@ -410,7 +413,8 @@ static noinline void __init_refok rest_init(void)
 }
 
 /* Check for early params. */
-static int __init do_early_param(char *param, char *val, const char *unused)
+static int __init do_early_param(char *param, char *val,
+				 const char *unused, void *arg)
 {
 	const struct obs_kernel_param *p;
 
@@ -429,7 +433,8 @@ static int __init do_early_param(char *param, char *val, const char *unused)
 
 void __init parse_early_options(char *cmdline)
 {
-	parse_args("early options", cmdline, NULL, 0, 0, 0, do_early_param);
+	parse_args("early options", cmdline, NULL, 0, 0, 0, NULL,
+		   do_early_param);
 }
 
 /* Arch code calls this early on, or if not, just before other parsing. */
@@ -536,10 +541,10 @@ asmlinkage __visible void __init start_kernel(void)
 	after_dashes = parse_args("Booting kernel",
 				  static_command_line, __start___param,
 				  __stop___param - __start___param,
-				  -1, -1, &unknown_bootoption);
+				  -1, -1, NULL, &unknown_bootoption);
 	if (!IS_ERR_OR_NULL(after_dashes))
 		parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
-			   set_init_arg);
+			   NULL, set_init_arg);
 
 	jump_label_init();
 
@@ -652,7 +657,7 @@ asmlinkage __visible void __init start_kernel(void)
 	key_init();
 	security_init();
 	dbg_late_init();
-	vfs_caches_init(totalram_pages);
+	vfs_caches_init();
 	signals_init();
 	/* rootfs populating might need page-writeback */
 	page_writeback_init();
@@ -849,7 +854,7 @@ static void __init do_initcall_level(int level)
 		   initcall_command_line, __start___param,
 		   __stop___param - __start___param,
 		   level, level,
-		   &repair_env_string);
+		   NULL, &repair_env_string);
 
 	for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
 		do_one_initcall(*fn);
@@ -873,7 +878,6 @@ static void __init do_initcalls(void)
 static void __init do_basic_setup(void)
 {
 	cpuset_init_smp();
-	usermodehelper_init();
 	shmem_init();
 	driver_init();
 	init_irq_proc();
@@ -1000,6 +1004,8 @@ static noinline void __init kernel_init_freeable(void)
 	smp_init();
 	sched_init_smp();
 
+	page_alloc_init_late();
+
 	do_basic_setup();
 
 	/* Open the /dev/console on the rootfs, this should never fail */