linux: update to 4.8.6, add realtime patch

10 files changed, 30937 insertions, 3541 deletions

diff --git a/target/linux/config/Config.in.kernel b/target/linux/config/Config.in.kernel
index 393b1628b..ad0e01819 100644
--- a/target/linux/config/Config.in.kernel
+++ b/target/linux/config/Config.in.kernel
@@ -146,7 +146,8 @@ config ADK_KERNEL_PREEMPT_RTB
 	select ADK_KERNEL_PATCH_REALTIME
 	depends on !ADK_KERNEL_OPROFILE
 	depends on ADK_TARGET_KERNEL_VERSION_4_1 \
-		|| ADK_TARGET_KERNEL_VERSION_4_4
+		|| ADK_TARGET_KERNEL_VERSION_4_4 \
+		|| ADK_TARGET_KERNEL_VERSION_4_8
         help
 	  Preemptible Kernel (Basic RT)
 
@@ -156,7 +157,8 @@ config ADK_KERNEL_PREEMPT_RT_FULL
 	select ADK_KERNEL_PATCH_REALTIME
 	depends on !ADK_KERNEL_OPROFILE
 	depends on ADK_TARGET_KERNEL_VERSION_4_1 \
-		|| ADK_TARGET_KERNEL_VERSION_4_4
+		|| ADK_TARGET_KERNEL_VERSION_4_4 \
+		|| ADK_TARGET_KERNEL_VERSION_4_8
         help
 	  Fully Preemptible Kernel (RealTime)
 	  https://www.kernel.org/pub/linux/kernel/projects/rt/
diff --git a/target/linux/patches/4.1.35/patch-realtime b/target/linux/patches/4.1.35/patch-realtime
index 6ecf019b9..94d6fe355 100644
--- a/target/linux/patches/4.1.35/patch-realtime
+++ b/target/linux/patches/4.1.35/patch-realtime
@@ -1,6 +1,313 @@
-diff -Nur linux-4.1.26.orig/arch/alpha/mm/fault.c linux-4.1.26/arch/alpha/mm/fault.c
---- linux-4.1.26.orig/arch/alpha/mm/fault.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/alpha/mm/fault.c	2016-06-19 15:30:54.915151887 +0200
+diff --git a/Documentation/hwlat_detector.txt b/Documentation/hwlat_detector.txt
+new file mode 100644
+index 000000000000..cb61516483d3
+--- /dev/null
++++ b/Documentation/hwlat_detector.txt
+@@ -0,0 +1,64 @@
++Introduction:
++-------------
++
++The module hwlat_detector is a special purpose kernel module that is used to
++detect large system latencies induced by the behavior of certain underlying
++hardware or firmware, independent of Linux itself. The code was developed
++originally to detect SMIs (System Management Interrupts) on x86 systems,
++however there is nothing x86 specific about this patchset. It was
++originally written for use by the "RT" patch since the Real Time
++kernel is highly latency sensitive.
++
++SMIs are usually not serviced by the Linux kernel, which typically does not
++even know that they are occuring. SMIs are instead are set up by BIOS code
++and are serviced by BIOS code, usually for "critical" events such as
++management of thermal sensors and fans. Sometimes though, SMIs are used for
++other tasks and those tasks can spend an inordinate amount of time in the
++handler (sometimes measured in milliseconds). Obviously this is a problem if
++you are trying to keep event service latencies down in the microsecond range.
++
++The hardware latency detector works by hogging all of the cpus for configurable
++amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter
++for some period, then looking for gaps in the TSC data. Any gap indicates a
++time when the polling was interrupted and since the machine is stopped and
++interrupts turned off the only thing that could do that would be an SMI.
++
++Note that the SMI detector should *NEVER* be used in a production environment.
++It is intended to be run manually to determine if the hardware platform has a
++problem with long system firmware service routines.
++
++Usage:
++------
++
++Loading the module hwlat_detector passing the parameter "enabled=1" (or by
++setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only
++step required to start the hwlat_detector. It is possible to redefine the
++threshold in microseconds (us) above which latency spikes will be taken
++into account (parameter "threshold=").
++
++Example:
++
++	# modprobe hwlat_detector enabled=1 threshold=100
++
++After the module is loaded, it creates a directory named "hwlat_detector" under
++the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary
++to have debugfs mounted, which might be on /sys/debug on your system.
++
++The /debug/hwlat_detector interface contains the following files:
++
++count			- number of latency spikes observed since last reset
++enable			- a global enable/disable toggle (0/1), resets count
++max			- maximum hardware latency actually observed (usecs)
++sample			- a pipe from which to read current raw sample data
++			  in the format <timestamp> <latency observed usecs>
++			  (can be opened O_NONBLOCK for a single sample)
++threshold		- minimum latency value to be considered (usecs)
++width			- time period to sample with CPUs held (usecs)
++			  must be less than the total window size (enforced)
++window			- total period of sampling, width being inside (usecs)
++
++By default we will set width to 500,000 and window to 1,000,000, meaning that
++we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we
++observe any latencies that exceed the threshold (initially 100 usecs),
++then we write to a global sample ring buffer of 8K samples, which is
++consumed by reading from the "sample" (pipe) debugfs file interface.
+diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
+index 0e307c94809a..6964d0f80ae7 100644
+--- a/Documentation/sysrq.txt
++++ b/Documentation/sysrq.txt
+@@ -59,10 +59,17 @@ On PowerPC - Press 'ALT - Print Screen (or F13) - <command key>,
+ On other - If you know of the key combos for other architectures, please
+            let me know so I can add them to this section.
+ 
+-On all -  write a character to /proc/sysrq-trigger.  e.g.:
+-
++On all -  write a character to /proc/sysrq-trigger, e.g.:
+ 		echo t > /proc/sysrq-trigger
+ 
++On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g.
++		echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq
++	 Send an ICMP echo request with this pattern plus the particular
++	 SysRq command key. Example:
++		# ping -c1 -s57 -p0102030468
++	 will trigger the SysRq-H (help) command.
++
++
+ *  What are the 'command' keys?
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ 'b'     - Will immediately reboot the system without syncing or unmounting
+diff --git a/Documentation/trace/histograms.txt b/Documentation/trace/histograms.txt
+new file mode 100644
+index 000000000000..6f2aeabf7faa
+--- /dev/null
++++ b/Documentation/trace/histograms.txt
+@@ -0,0 +1,186 @@
++		Using the Linux Kernel Latency Histograms
++
++
++This document gives a short explanation how to enable, configure and use
++latency histograms. Latency histograms are primarily relevant in the
++context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT)
++and are used in the quality management of the Linux real-time
++capabilities.
++
++
++* Purpose of latency histograms
++
++A latency histogram continuously accumulates the frequencies of latency
++data. There are two types of histograms
++- potential sources of latencies
++- effective latencies
++
++
++* Potential sources of latencies
++
++Potential sources of latencies are code segments where interrupts,
++preemption or both are disabled (aka critical sections). To create
++histograms of potential sources of latency, the kernel stores the time
++stamp at the start of a critical section, determines the time elapsed
++when the end of the section is reached, and increments the frequency
++counter of that latency value - irrespective of whether any concurrently
++running process is affected by latency or not.
++- Configuration items (in the Kernel hacking/Tracers submenu)
++  CONFIG_INTERRUPT_OFF_LATENCY
++  CONFIG_PREEMPT_OFF_LATENCY
++
++
++* Effective latencies
++
++Effective latencies are actually occuring during wakeup of a process. To
++determine effective latencies, the kernel stores the time stamp when a
++process is scheduled to be woken up, and determines the duration of the
++wakeup time shortly before control is passed over to this process. Note
++that the apparent latency in user space may be somewhat longer, since the
++process may be interrupted after control is passed over to it but before
++the execution in user space takes place. Simply measuring the interval
++between enqueuing and wakeup may also not appropriate in cases when a
++process is scheduled as a result of a timer expiration. The timer may have
++missed its deadline, e.g. due to disabled interrupts, but this latency
++would not be registered. Therefore, the offsets of missed timers are
++recorded in a separate histogram. If both wakeup latency and missed timer
++offsets are configured and enabled, a third histogram may be enabled that
++records the overall latency as a sum of the timer latency, if any, and the
++wakeup latency. This histogram is called "timerandwakeup".
++- Configuration items (in the Kernel hacking/Tracers submenu)
++  CONFIG_WAKEUP_LATENCY
++  CONFIG_MISSED_TIMER_OFSETS
++
++
++* Usage
++
++The interface to the administration of the latency histograms is located
++in the debugfs file system. To mount it, either enter
++
++mount -t sysfs nodev /sys
++mount -t debugfs nodev /sys/kernel/debug
++
++from shell command line level, or add
++
++nodev	/sys			sysfs	defaults	0 0
++nodev	/sys/kernel/debug	debugfs	defaults	0 0
++
++to the file /etc/fstab. All latency histogram related files are then
++available in the directory /sys/kernel/debug/tracing/latency_hist. A
++particular histogram type is enabled by writing non-zero to the related
++variable in the /sys/kernel/debug/tracing/latency_hist/enable directory.
++Select "preemptirqsoff" for the histograms of potential sources of
++latencies and "wakeup" for histograms of effective latencies etc. The
++histogram data - one per CPU - are available in the files
++
++/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx
++/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx
++/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx
++/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx
++/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx
++/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx
++/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx
++
++The histograms are reset by writing non-zero to the file "reset" in a
++particular latency directory. To reset all latency data, use
++
++#!/bin/sh
++
++TRACINGDIR=/sys/kernel/debug/tracing
++HISTDIR=$TRACINGDIR/latency_hist
++
++if test -d $HISTDIR
++then
++  cd $HISTDIR
++  for i in `find . | grep /reset$`
++  do
++    echo 1 >$i
++  done
++fi
++
++
++* Data format
++
++Latency data are stored with a resolution of one microsecond. The
++maximum latency is 10,240 microseconds. The data are only valid, if the
++overflow register is empty. Every output line contains the latency in
++microseconds in the first row and the number of samples in the second
++row. To display only lines with a positive latency count, use, for
++example,
++
++grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0
++
++#Minimum latency: 0 microseconds.
++#Average latency: 0 microseconds.
++#Maximum latency: 25 microseconds.
++#Total samples: 3104770694
++#There are 0 samples greater or equal than 10240 microseconds
++#usecs	         samples
++    0	      2984486876
++    1	        49843506
++    2	        58219047
++    3	         5348126
++    4	         2187960
++    5	         3388262
++    6	          959289
++    7	          208294
++    8	           40420
++    9	            4485
++   10	           14918
++   11	           18340
++   12	           25052
++   13	           19455
++   14	            5602
++   15	             969
++   16	              47
++   17	              18
++   18	              14
++   19	               1
++   20	               3
++   21	               2
++   22	               5
++   23	               2
++   25	               1
++
++
++* Wakeup latency of a selected process
++
++To only collect wakeup latency data of a particular process, write the
++PID of the requested process to
++
++/sys/kernel/debug/tracing/latency_hist/wakeup/pid
++
++PIDs are not considered, if this variable is set to 0.
++
++
++* Details of the process with the highest wakeup latency so far
++
++Selected data of the process that suffered from the highest wakeup
++latency that occurred in a particular CPU are available in the file
++
++/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx.
++
++In addition, other relevant system data at the time when the
++latency occurred are given.
++
++The format of the data is (all in one line):
++<PID> <Priority> <Latency> (<Timeroffset>) <Command> \
++<- <PID> <Priority> <Command> <Timestamp>
++
++The value of <Timeroffset> is only relevant in the combined timer
++and wakeup latency recording. In the wakeup recording, it is
++always 0, in the missed_timer_offsets recording, it is the same
++as <Latency>.
++
++When retrospectively searching for the origin of a latency and
++tracing was not enabled, it may be helpful to know the name and
++some basic data of the task that (finally) was switching to the
++late real-tlme task. In addition to the victim's data, also the
++data of the possible culprit are therefore displayed after the
++"<-" symbol.
++
++Finally, the timestamp of the time when the latency occurred
++in <seconds>.<microseconds> after the most recent system boot
++is provided.
++
++These data are also reset when the wakeup histogram is reset.
+diff --git a/arch/Kconfig b/arch/Kconfig
+index a65eafb24997..78d3ed24484a 100644
+--- a/arch/Kconfig
++++ b/arch/Kconfig
+@@ -6,6 +6,7 @@ config OPROFILE
+ 	tristate "OProfile system profiling"
+ 	depends on PROFILING
+ 	depends on HAVE_OPROFILE
++	depends on !PREEMPT_RT_FULL
+ 	select RING_BUFFER
+ 	select RING_BUFFER_ALLOW_SWAP
+ 	help
+@@ -49,6 +50,7 @@ config KPROBES
+ config JUMP_LABEL
+        bool "Optimize very unlikely/likely branches"
+        depends on HAVE_ARCH_JUMP_LABEL
++       depends on (!INTERRUPT_OFF_HIST && !PREEMPT_OFF_HIST && !WAKEUP_LATENCY_HIST && !MISSED_TIMER_OFFSETS_HIST)
+        help
+          This option enables a transparent branch optimization that
+ 	 makes certain almost-always-true or almost-always-false branch
+diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
+index 9d0ac091a52a..4a905bd667e2 100644
+--- a/arch/alpha/mm/fault.c
++++ b/arch/alpha/mm/fault.c
 @@ -23,8 +23,7 @@
  #include <linux/smp.h>
  #include <linux/interrupt.h>
@@ -11,7 +318,7 @@ diff -Nur linux-4.1.26.orig/arch/alpha/mm/fault.c linux-4.1.26/arch/alpha/mm/fau
  
  extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
  
-@@ -107,7 +106,7 @@
+@@ -107,7 +106,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
  
  	/* If we're in an interrupt context, or have no user context,
  	   we must not take the fault.  */
@@ -20,10 +327,11 @@ diff -Nur linux-4.1.26.orig/arch/alpha/mm/fault.c linux-4.1.26/arch/alpha/mm/fau
  		goto no_context;
  
  #ifdef CONFIG_ALPHA_LARGE_VMALLOC
-diff -Nur linux-4.1.26.orig/arch/arc/include/asm/futex.h linux-4.1.26/arch/arc/include/asm/futex.h
---- linux-4.1.26.orig/arch/arc/include/asm/futex.h	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arc/include/asm/futex.h	2016-06-19 15:30:54.915151887 +0200
-@@ -53,7 +53,7 @@
+diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
+index 4dc64ddebece..05b5aaf5b0f9 100644
+--- a/arch/arc/include/asm/futex.h
++++ b/arch/arc/include/asm/futex.h
+@@ -53,7 +53,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
  	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
  		return -EFAULT;
  
@@ -32,7 +340,7 @@ diff -Nur linux-4.1.26.orig/arch/arc/include/asm/futex.h linux-4.1.26/arch/arc/i
  
  	switch (op) {
  	case FUTEX_OP_SET:
-@@ -75,7 +75,7 @@
+@@ -75,7 +75,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
  		ret = -ENOSYS;
  	}
  
@@ -41,7 +349,7 @@ diff -Nur linux-4.1.26.orig/arch/arc/include/asm/futex.h linux-4.1.26/arch/arc/i
  
  	if (!ret) {
  		switch (cmp) {
-@@ -104,7 +104,7 @@
+@@ -104,7 +104,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
  	return ret;
  }
  
@@ -50,7 +358,7 @@ diff -Nur linux-4.1.26.orig/arch/arc/include/asm/futex.h linux-4.1.26/arch/arc/i
   *  Notes:
   *      -Best-Effort: Exchg happens only if compare succeeds.
   *          If compare fails, returns; leaving retry/looping to upper layers
-@@ -121,7 +121,7 @@
+@@ -121,7 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
  	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
  		return -EFAULT;
  
@@ -59,7 +367,7 @@ diff -Nur linux-4.1.26.orig/arch/arc/include/asm/futex.h linux-4.1.26/arch/arc/i
  
  	/* TBD : can use llock/scond */
  	__asm__ __volatile__(
-@@ -142,7 +142,7 @@
+@@ -142,7 +142,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
  	: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
  	: "cc", "memory");
  
@@ -68,10 +376,11 @@ diff -Nur linux-4.1.26.orig/arch/arc/include/asm/futex.h linux-4.1.26/arch/arc/i
  
  	*uval = val;
  	return val;
-diff -Nur linux-4.1.26.orig/arch/arc/mm/fault.c linux-4.1.26/arch/arc/mm/fault.c
---- linux-4.1.26.orig/arch/arc/mm/fault.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arc/mm/fault.c	2016-06-19 15:30:54.915151887 +0200
-@@ -86,7 +86,7 @@
+diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
+index 6a2e006cbcce..d948e4e9d89c 100644
+--- a/arch/arc/mm/fault.c
++++ b/arch/arc/mm/fault.c
+@@ -86,7 +86,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
  	 * If we're in an interrupt or have no user
  	 * context, we must not take the fault..
  	 */
@@ -80,10 +389,32 @@ diff -Nur linux-4.1.26.orig/arch/arc/mm/fault.c linux-4.1.26/arch/arc/mm/fault.c
  		goto no_context;
  
  	if (user_mode(regs))
-diff -Nur linux-4.1.26.orig/arch/arm/include/asm/cmpxchg.h linux-4.1.26/arch/arm/include/asm/cmpxchg.h
---- linux-4.1.26.orig/arch/arm/include/asm/cmpxchg.h	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/include/asm/cmpxchg.h	2016-06-19 15:30:54.919152041 +0200
-@@ -129,6 +129,8 @@
+diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
+index 19f4cc634b0e..e16a259177d4 100644
+--- a/arch/arm/Kconfig
++++ b/arch/arm/Kconfig
+@@ -31,7 +31,7 @@ config ARM
+ 	select HARDIRQS_SW_RESEND
+ 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
+ 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
+-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
++	select HAVE_ARCH_JUMP_LABEL if (!XIP_KERNEL && !PREEMPT_RT_BASE)
+ 	select HAVE_ARCH_KGDB
+ 	select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
+ 	select HAVE_ARCH_TRACEHOOK
+@@ -66,6 +66,7 @@ config ARM
+ 	select HAVE_PERF_EVENTS
+ 	select HAVE_PERF_REGS
+ 	select HAVE_PERF_USER_STACK_DUMP
++	select HAVE_PREEMPT_LAZY
+ 	select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
+ 	select HAVE_REGS_AND_STACK_ACCESS_API
+ 	select HAVE_SYSCALL_TRACEPOINTS
+diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
+index abb2c3769b01..2386e9745ba4 100644
+--- a/arch/arm/include/asm/cmpxchg.h
++++ b/arch/arm/include/asm/cmpxchg.h
+@@ -129,6 +129,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
  
  #else	/* min ARCH >= ARMv6 */
  
@@ -92,10 +423,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/cmpxchg.h linux-4.1.26/arch/arm
  extern void __bad_cmpxchg(volatile void *ptr, int size);
  
  /*
-diff -Nur linux-4.1.26.orig/arch/arm/include/asm/futex.h linux-4.1.26/arch/arm/include/asm/futex.h
---- linux-4.1.26.orig/arch/arm/include/asm/futex.h	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/include/asm/futex.h	2016-06-19 15:30:54.919152041 +0200
-@@ -93,6 +93,7 @@
+diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
+index 4e78065a16aa..5eed82809d82 100644
+--- a/arch/arm/include/asm/futex.h
++++ b/arch/arm/include/asm/futex.h
+@@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
  	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
  		return -EFAULT;
  
@@ -103,7 +435,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/futex.h linux-4.1.26/arch/arm/i
  	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
  	"1:	" TUSER(ldr) "	%1, [%4]\n"
  	"	teq	%1, %2\n"
-@@ -104,6 +105,8 @@
+@@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
  	: "cc", "memory");
  
  	*uval = val;
@@ -112,7 +444,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/futex.h linux-4.1.26/arch/arm/i
  	return ret;
  }
  
-@@ -124,7 +127,10 @@
+@@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
  	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
  		return -EFAULT;
  
@@ -124,7 +456,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/futex.h linux-4.1.26/arch/arm/i
  
  	switch (op) {
  	case FUTEX_OP_SET:
-@@ -146,7 +152,10 @@
+@@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
  		ret = -ENOSYS;
  	}
  
@@ -136,9 +468,10 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/futex.h linux-4.1.26/arch/arm/i
  
  	if (!ret) {
  		switch (cmp) {
-diff -Nur linux-4.1.26.orig/arch/arm/include/asm/switch_to.h linux-4.1.26/arch/arm/include/asm/switch_to.h
---- linux-4.1.26.orig/arch/arm/include/asm/switch_to.h	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/include/asm/switch_to.h	2016-06-19 15:30:54.919152041 +0200
+diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
+index c99e259469f7..f3e3d800c407 100644
+--- a/arch/arm/include/asm/switch_to.h
++++ b/arch/arm/include/asm/switch_to.h
 @@ -3,6 +3,13 @@
  
  #include <linux/thread_info.h>
@@ -153,7 +486,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/switch_to.h linux-4.1.26/arch/a
  /*
   * For v7 SMP cores running a preemptible kernel we may be pre-empted
   * during a TLB maintenance operation, so execute an inner-shareable dsb
-@@ -22,6 +29,7 @@
+@@ -22,6 +29,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
  
  #define switch_to(prev,next,last)					\
  do {									\
@@ -161,10 +494,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/switch_to.h linux-4.1.26/arch/a
  	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
  } while (0)
  
-diff -Nur linux-4.1.26.orig/arch/arm/include/asm/thread_info.h linux-4.1.26/arch/arm/include/asm/thread_info.h
---- linux-4.1.26.orig/arch/arm/include/asm/thread_info.h	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/include/asm/thread_info.h	2016-06-19 15:30:54.919152041 +0200
-@@ -50,6 +50,7 @@
+diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
+index bd32eded3e50..b5a616376f60 100644
+--- a/arch/arm/include/asm/thread_info.h
++++ b/arch/arm/include/asm/thread_info.h
+@@ -50,6 +50,7 @@ struct cpu_context_save {
  struct thread_info {
  	unsigned long		flags;		/* low level flags */
  	int			preempt_count;	/* 0 => preemptable, <0 => bug */
@@ -172,7 +506,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/thread_info.h linux-4.1.26/arch
  	mm_segment_t		addr_limit;	/* address limit */
  	struct task_struct	*task;		/* main task structure */
  	__u32			cpu;		/* cpu */
-@@ -147,6 +148,7 @@
+@@ -147,6 +148,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
  #define TIF_SIGPENDING		0
  #define TIF_NEED_RESCHED	1
  #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
@@ -180,7 +514,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/thread_info.h linux-4.1.26/arch
  #define TIF_UPROBE		7
  #define TIF_SYSCALL_TRACE	8
  #define TIF_SYSCALL_AUDIT	9
-@@ -160,6 +162,7 @@
+@@ -160,6 +162,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
  #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
  #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
  #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -188,30 +522,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/include/asm/thread_info.h linux-4.1.26/arch
  #define _TIF_UPROBE		(1 << TIF_UPROBE)
  #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
  #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
-diff -Nur linux-4.1.26.orig/arch/arm/Kconfig linux-4.1.26/arch/arm/Kconfig
---- linux-4.1.26.orig/arch/arm/Kconfig	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/Kconfig	2016-06-19 15:30:54.919152041 +0200
-@@ -31,7 +31,7 @@
- 	select HARDIRQS_SW_RESEND
- 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
- 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
--	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
-+	select HAVE_ARCH_JUMP_LABEL if (!XIP_KERNEL && !PREEMPT_RT_BASE)
- 	select HAVE_ARCH_KGDB
- 	select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
- 	select HAVE_ARCH_TRACEHOOK
-@@ -66,6 +66,7 @@
- 	select HAVE_PERF_EVENTS
- 	select HAVE_PERF_REGS
- 	select HAVE_PERF_USER_STACK_DUMP
-+	select HAVE_PREEMPT_LAZY
- 	select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
- 	select HAVE_REGS_AND_STACK_ACCESS_API
- 	select HAVE_SYSCALL_TRACEPOINTS
-diff -Nur linux-4.1.26.orig/arch/arm/kernel/asm-offsets.c linux-4.1.26/arch/arm/kernel/asm-offsets.c
---- linux-4.1.26.orig/arch/arm/kernel/asm-offsets.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kernel/asm-offsets.c	2016-06-19 15:30:54.919152041 +0200
-@@ -65,6 +65,7 @@
+diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
+index 871b8267d211..4dbe70de7318 100644
+--- a/arch/arm/kernel/asm-offsets.c
++++ b/arch/arm/kernel/asm-offsets.c
+@@ -65,6 +65,7 @@ int main(void)
    BLANK();
    DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
    DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
@@ -219,10 +534,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/asm-offsets.c linux-4.1.26/arch/arm/
    DEFINE(TI_ADDR_LIMIT,		offsetof(struct thread_info, addr_limit));
    DEFINE(TI_TASK,		offsetof(struct thread_info, task));
    DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
-diff -Nur linux-4.1.26.orig/arch/arm/kernel/entry-armv.S linux-4.1.26/arch/arm/kernel/entry-armv.S
---- linux-4.1.26.orig/arch/arm/kernel/entry-armv.S	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kernel/entry-armv.S	2016-06-19 15:30:54.919152041 +0200
-@@ -208,11 +208,18 @@
+diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
+index 570306c49406..797a13d959b7 100644
+--- a/arch/arm/kernel/entry-armv.S
++++ b/arch/arm/kernel/entry-armv.S
+@@ -208,11 +208,18 @@ __irq_svc:
  #ifdef CONFIG_PREEMPT
  	get_thread_info tsk
  	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
@@ -243,19 +559,27 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/entry-armv.S linux-4.1.26/arch/arm/k
  #endif
  
  	svc_exit r5, irq = 1			@ return from exception
-@@ -227,6 +234,8 @@
+@@ -227,8 +234,14 @@ svc_preempt:
  1:	bl	preempt_schedule_irq		@ irq en/disable is done inside
  	ldr	r0, [tsk, #TI_FLAGS]		@ get new tasks TI_FLAGS
  	tst	r0, #_TIF_NEED_RESCHED
 +	bne	1b
 +	tst	r0, #_TIF_NEED_RESCHED_LAZY
  	reteq	r8				@ go again
- 	b	1b
+-	b	1b
++	ldr	r0, [tsk, #TI_PREEMPT_LAZY]	@ get preempt lazy count
++	teq	r0, #0				@ if preempt lazy count != 0
++	beq	1b
++	ret	r8				@ go again
++
  #endif
-diff -Nur linux-4.1.26.orig/arch/arm/kernel/process.c linux-4.1.26/arch/arm/kernel/process.c
---- linux-4.1.26.orig/arch/arm/kernel/process.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kernel/process.c	2016-06-19 15:30:54.919152041 +0200
-@@ -290,6 +290,30 @@
+ 
+ __und_fault:
+diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
+index f192a2a41719..649247ac00e6 100644
+--- a/arch/arm/kernel/process.c
++++ b/arch/arm/kernel/process.c
+@@ -290,6 +290,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
  }
  
  #ifdef CONFIG_MMU
@@ -286,10 +610,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/process.c linux-4.1.26/arch/arm/kern
  #ifdef CONFIG_KUSER_HELPERS
  /*
   * The vectors page is always readable from user space for the
-diff -Nur linux-4.1.26.orig/arch/arm/kernel/signal.c linux-4.1.26/arch/arm/kernel/signal.c
---- linux-4.1.26.orig/arch/arm/kernel/signal.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kernel/signal.c	2016-06-19 15:30:54.919152041 +0200
-@@ -568,7 +568,8 @@
+diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
+index 586eef26203d..25bd12ef0b36 100644
+--- a/arch/arm/kernel/signal.c
++++ b/arch/arm/kernel/signal.c
+@@ -568,7 +568,8 @@ asmlinkage int
  do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
  {
  	do {
@@ -299,10 +624,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/signal.c linux-4.1.26/arch/arm/kerne
  			schedule();
  		} else {
  			if (unlikely(!user_mode(regs)))
-diff -Nur linux-4.1.26.orig/arch/arm/kernel/smp.c linux-4.1.26/arch/arm/kernel/smp.c
---- linux-4.1.26.orig/arch/arm/kernel/smp.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kernel/smp.c	2016-06-19 15:30:54.919152041 +0200
-@@ -213,8 +213,6 @@
+diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
+index f11d82527076..e561aef093c7 100644
+--- a/arch/arm/kernel/smp.c
++++ b/arch/arm/kernel/smp.c
+@@ -213,8 +213,6 @@ int __cpu_disable(void)
  	flush_cache_louis();
  	local_flush_tlb_all();
  
@@ -311,7 +637,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/smp.c linux-4.1.26/arch/arm/kernel/s
  	return 0;
  }
  
-@@ -230,6 +228,9 @@
+@@ -230,6 +228,9 @@ void __cpu_die(unsigned int cpu)
  		pr_err("CPU%u: cpu didn't die\n", cpu);
  		return;
  	}
@@ -321,10 +647,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/smp.c linux-4.1.26/arch/arm/kernel/s
  	pr_notice("CPU%u: shutdown\n", cpu);
  
  	/*
-diff -Nur linux-4.1.26.orig/arch/arm/kernel/unwind.c linux-4.1.26/arch/arm/kernel/unwind.c
---- linux-4.1.26.orig/arch/arm/kernel/unwind.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kernel/unwind.c	2016-06-19 15:30:54.919152041 +0200
-@@ -93,7 +93,7 @@
+diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
+index 0bee233fef9a..314cfb232a63 100644
+--- a/arch/arm/kernel/unwind.c
++++ b/arch/arm/kernel/unwind.c
+@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
  static const struct unwind_idx *__origin_unwind_idx;
  extern const struct unwind_idx __stop_unwind_idx[];
  
@@ -333,7 +660,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/unwind.c linux-4.1.26/arch/arm/kerne
  static LIST_HEAD(unwind_tables);
  
  /* Convert a prel31 symbol to an absolute address */
-@@ -201,7 +201,7 @@
+@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
  		/* module unwind tables */
  		struct unwind_table *table;
  
@@ -342,7 +669,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/unwind.c linux-4.1.26/arch/arm/kerne
  		list_for_each_entry(table, &unwind_tables, list) {
  			if (addr >= table->begin_addr &&
  			    addr < table->end_addr) {
-@@ -213,7 +213,7 @@
+@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
  				break;
  			}
  		}
@@ -351,7 +678,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/unwind.c linux-4.1.26/arch/arm/kerne
  	}
  
  	pr_debug("%s: idx = %p\n", __func__, idx);
-@@ -529,9 +529,9 @@
+@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
  	tab->begin_addr = text_addr;
  	tab->end_addr = text_addr + text_size;
  
@@ -363,7 +690,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/unwind.c linux-4.1.26/arch/arm/kerne
  
  	return tab;
  }
-@@ -543,9 +543,9 @@
+@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_table *tab)
  	if (!tab)
  		return;
  
@@ -375,10 +702,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/kernel/unwind.c linux-4.1.26/arch/arm/kerne
  
  	kfree(tab);
  }
-diff -Nur linux-4.1.26.orig/arch/arm/kvm/arm.c linux-4.1.26/arch/arm/kvm/arm.c
---- linux-4.1.26.orig/arch/arm/kvm/arm.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kvm/arm.c	2016-06-19 15:30:54.919152041 +0200
-@@ -474,9 +474,9 @@
+diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
+index 87b2663a5564..ce5e58d76cf9 100644
+--- a/arch/arm/kvm/arm.c
++++ b/arch/arm/kvm/arm.c
+@@ -473,9 +473,9 @@ bool kvm_arch_intc_initialized(struct kvm *kvm)
  
  static void vcpu_pause(struct kvm_vcpu *vcpu)
  {
@@ -390,10 +718,11 @@ diff -Nur linux-4.1.26.orig/arch/arm/kvm/arm.c linux-4.1.26/arch/arm/kvm/arm.c
  }
  
  static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
-diff -Nur linux-4.1.26.orig/arch/arm/kvm/psci.c linux-4.1.26/arch/arm/kvm/psci.c
---- linux-4.1.26.orig/arch/arm/kvm/psci.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/kvm/psci.c	2016-06-19 15:30:54.919152041 +0200
-@@ -68,7 +68,7 @@
+diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
+index 531e922486b2..e24f0461ea2d 100644
+--- a/arch/arm/kvm/psci.c
++++ b/arch/arm/kvm/psci.c
+@@ -68,7 +68,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
  {
  	struct kvm *kvm = source_vcpu->kvm;
  	struct kvm_vcpu *vcpu = NULL;
@@ -402,7 +731,7 @@ diff -Nur linux-4.1.26.orig/arch/arm/kvm/psci.c linux-4.1.26/arch/arm/kvm/psci.c
  	unsigned long cpu_id;
  	unsigned long context_id;
  	phys_addr_t target_pc;
-@@ -117,7 +117,7 @@
+@@ -117,7 +117,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
  	smp_mb();		/* Make sure the above is visible */
  
  	wq = kvm_arch_vcpu_wq(vcpu);
@@ -411,10 +740,242 @@ diff -Nur linux-4.1.26.orig/arch/arm/kvm/psci.c linux-4.1.26/arch/arm/kvm/psci.c
  
  	return PSCI_RET_SUCCESS;
  }
-diff -Nur linux-4.1.26.orig/arch/arm/mach-exynos/platsmp.c linux-4.1.26/arch/arm/mach-exynos/platsmp.c
---- linux-4.1.26.orig/arch/arm/mach-exynos/platsmp.c	2016-06-07 01:13:11.000000000 +0200
-+++ linux-4.1.26/arch/arm/mach-exynos/platsmp.c	2016-06-19 15:30:54.919152041 +0200
-@@ -231,7 +231,7 @@
+diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
+index eaf58f88ef5d..8d3cb458a99c 100644
+--- a/arch/arm/mach-at91/at91rm9200.c
++++ b/arch/arm/mach-at91/at91rm9200.c
+@@ -13,7 +13,6 @@
+ #include <linux/of_platform.h>
+ 
+ #include <asm/mach/arch.h>
+-#include <asm/system_misc.h>
+ 
+ #include "generic.h"
+ #include "soc.h"
+@@ -34,7 +33,6 @@ static void __init at91rm9200_dt_device_init(void)
+ 
+ 	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
+ 
+-	arm_pm_idle = at91rm9200_idle;
+ 	at91rm9200_pm_init();
+ }
+ 
+diff --git a/arch/arm/mach-at91/at91sam9.c b/arch/arm/mach-at91/at91sam9.c
+index e47a2093a0e7..d2bede665a1b 100644
+--- a/arch/arm/mach-at91/at91sam9.c
++++ b/arch/arm/mach-at91/at91sam9.c
+@@ -62,8 +62,6 @@ static void __init at91sam9_common_init(void)
+ 		soc_dev = soc_device_to_device(soc);
+ 
+ 	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
+-
+-	arm_pm_idle = at91sam9_idle;
+ }
+ 
+ static void __init at91sam9_dt_device_init(void)
+diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h
+index b0fa7dc7286d..28ca57a2060f 100644
+--- a/arch/arm/mach-at91/generic.h
++++ b/arch/arm/mach-at91/generic.h
+@@ -11,27 +11,18 @@
+ #ifndef _AT91_GENERIC_H
+ #define _AT91_GENERIC_H
+ 
+-#include <linux/of.h>
+-#include <linux/reboot.h>
+-
+- /* Map io */
+-extern void __init at91_map_io(void);
+-extern void __init at91_alt_map_io(void);
+-
+-/* idle */
+-extern void at91rm9200_idle(void);
+-extern void at91sam9_idle(void);
+-
+ #ifdef CONFIG_PM
+ extern void __init at91rm9200_pm_init(void);
+ extern void _